Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +1 -0
- checkpoint-1026/README.md +202 -0
- checkpoint-1026/adapter_config.json +34 -0
- checkpoint-1026/scheduler.pt +3 -0
- checkpoint-1026/training_args.bin +3 -0
- checkpoint-162/rng_state_0.pth +3 -0
- checkpoint-162/rng_state_1.pth +3 -0
- checkpoint-162/scheduler.pt +3 -0
- checkpoint-162/training_args.bin +3 -0
- checkpoint-216/rng_state_1.pth +3 -0
- checkpoint-270/rng_state_0.pth +3 -0
- checkpoint-270/scheduler.pt +3 -0
- checkpoint-324/merges.txt +0 -0
- checkpoint-324/trainer_state.json +2625 -0
- checkpoint-378/README.md +202 -0
- checkpoint-378/adapter_config.json +34 -0
- checkpoint-378/added_tokens.json +24 -0
- checkpoint-378/merges.txt +0 -0
- checkpoint-378/special_tokens_map.json +31 -0
- checkpoint-378/tokenizer_config.json +209 -0
- checkpoint-378/vocab.json +0 -0
- checkpoint-432/adapter_config.json +34 -0
- checkpoint-432/merges.txt +0 -0
- checkpoint-432/special_tokens_map.json +31 -0
- checkpoint-432/tokenizer_config.json +209 -0
- checkpoint-432/trainer_state.json +3489 -0
- checkpoint-432/vocab.json +0 -0
- checkpoint-486/README.md +202 -0
- checkpoint-486/adapter_config.json +34 -0
- checkpoint-486/added_tokens.json +24 -0
- checkpoint-486/merges.txt +0 -0
- checkpoint-486/special_tokens_map.json +31 -0
- checkpoint-486/tokenizer_config.json +209 -0
- checkpoint-486/trainer_state.json +0 -0
- checkpoint-486/vocab.json +0 -0
- checkpoint-540/README.md +202 -0
- checkpoint-540/adapter_config.json +34 -0
- checkpoint-540/added_tokens.json +24 -0
- checkpoint-540/merges.txt +0 -0
- checkpoint-540/special_tokens_map.json +31 -0
- checkpoint-540/tokenizer_config.json +209 -0
- checkpoint-540/trainer_state.json +0 -0
- checkpoint-540/vocab.json +0 -0
- checkpoint-594/README.md +202 -0
- checkpoint-594/adapter_config.json +34 -0
- checkpoint-594/added_tokens.json +24 -0
- checkpoint-594/merges.txt +0 -0
- checkpoint-594/special_tokens_map.json +31 -0
- checkpoint-594/tokenizer_config.json +209 -0
- checkpoint-594/trainer_state.json +0 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoint-1026/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-1026/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"up_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"o_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-1026/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf1ea04735033bc0224c950468a02fb1269feb4f8c9fa8854561f36195a9e832
|
3 |
+
size 1064
|
checkpoint-1026/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e70cdeaf6550b324dd30ee52fd6fb6259b3a65b6ec342b31522e38e2e66f88d
|
3 |
+
size 5688
|
checkpoint-162/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fff622f7715e6a8ed3f766771c62f005a755f047a2f49688861b07cfb708d70
|
3 |
+
size 14512
|
checkpoint-162/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f7afef3aa9dfeb2c7eba0ed2feddacd0a3f76d96d87a4b96377a3025f8b0e09
|
3 |
+
size 14512
|
checkpoint-162/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3dac1c202cd7a96287d90bf25f318091a9e9fc77f4ad36899fa8e1ae6a903e81
|
3 |
+
size 1064
|
checkpoint-162/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5e70cdeaf6550b324dd30ee52fd6fb6259b3a65b6ec342b31522e38e2e66f88d
|
3 |
+
size 5688
|
checkpoint-216/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da80e0d62556d8a210bb1310d9dd4c2f197962c8ed3b5a9a2d0a8efb3f81c5c4
|
3 |
+
size 14512
|
checkpoint-270/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff9d69a5fb63f7a32c497faaefe01d47695127e90d0f2ec59e41a3d94d941f01
|
3 |
+
size 14512
|
checkpoint-270/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55502e79f33694551e97d2b3fcffbea2fae603e5605d9c887f346ab3ecadf050
|
3 |
+
size 1064
|
checkpoint-324/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-324/trainer_state.json
ADDED
@@ -0,0 +1,2625 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.89908256880734,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 324,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01834862385321101,
|
13 |
+
"grad_norm": 0.04378490149974823,
|
14 |
+
"learning_rate": 4.999989423013716e-05,
|
15 |
+
"loss": 0.6713,
|
16 |
+
"num_input_tokens_seen": 44136,
|
17 |
+
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.03669724770642202,
|
21 |
+
"grad_norm": 0.040646992623806,
|
22 |
+
"learning_rate": 4.999957692144361e-05,
|
23 |
+
"loss": 0.533,
|
24 |
+
"num_input_tokens_seen": 83096,
|
25 |
+
"step": 2
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.05504587155963303,
|
29 |
+
"grad_norm": 0.04658753052353859,
|
30 |
+
"learning_rate": 4.999904807660428e-05,
|
31 |
+
"loss": 0.6048,
|
32 |
+
"num_input_tokens_seen": 122112,
|
33 |
+
"step": 3
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.07339449541284404,
|
37 |
+
"grad_norm": 0.04322144016623497,
|
38 |
+
"learning_rate": 4.999830770009406e-05,
|
39 |
+
"loss": 0.4948,
|
40 |
+
"num_input_tokens_seen": 163064,
|
41 |
+
"step": 4
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.09174311926605505,
|
45 |
+
"grad_norm": 0.06536195427179337,
|
46 |
+
"learning_rate": 4.999735579817769e-05,
|
47 |
+
"loss": 0.6607,
|
48 |
+
"num_input_tokens_seen": 203808,
|
49 |
+
"step": 5
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.11009174311926606,
|
53 |
+
"grad_norm": 0.059904925525188446,
|
54 |
+
"learning_rate": 4.9996192378909786e-05,
|
55 |
+
"loss": 0.5802,
|
56 |
+
"num_input_tokens_seen": 241824,
|
57 |
+
"step": 6
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.12844036697247707,
|
61 |
+
"grad_norm": 0.19818365573883057,
|
62 |
+
"learning_rate": 4.999481745213471e-05,
|
63 |
+
"loss": 0.5148,
|
64 |
+
"num_input_tokens_seen": 287608,
|
65 |
+
"step": 7
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.14678899082568808,
|
69 |
+
"grad_norm": 0.05985472351312637,
|
70 |
+
"learning_rate": 4.9993231029486544e-05,
|
71 |
+
"loss": 0.5714,
|
72 |
+
"num_input_tokens_seen": 325320,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.1651376146788991,
|
77 |
+
"grad_norm": 0.061375778168439865,
|
78 |
+
"learning_rate": 4.999143312438893e-05,
|
79 |
+
"loss": 0.6812,
|
80 |
+
"num_input_tokens_seen": 369848,
|
81 |
+
"step": 9
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.1834862385321101,
|
85 |
+
"grad_norm": 0.06196414306759834,
|
86 |
+
"learning_rate": 4.998942375205502e-05,
|
87 |
+
"loss": 0.5358,
|
88 |
+
"num_input_tokens_seen": 415104,
|
89 |
+
"step": 10
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.2018348623853211,
|
93 |
+
"grad_norm": 0.07861393690109253,
|
94 |
+
"learning_rate": 4.9987202929487275e-05,
|
95 |
+
"loss": 0.6527,
|
96 |
+
"num_input_tokens_seen": 467224,
|
97 |
+
"step": 11
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.22018348623853212,
|
101 |
+
"grad_norm": 0.05596446990966797,
|
102 |
+
"learning_rate": 4.99847706754774e-05,
|
103 |
+
"loss": 0.5354,
|
104 |
+
"num_input_tokens_seen": 502824,
|
105 |
+
"step": 12
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.23853211009174313,
|
109 |
+
"grad_norm": 0.05289844051003456,
|
110 |
+
"learning_rate": 4.998212701060612e-05,
|
111 |
+
"loss": 0.5263,
|
112 |
+
"num_input_tokens_seen": 544744,
|
113 |
+
"step": 13
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.25688073394495414,
|
117 |
+
"grad_norm": 0.04996591433882713,
|
118 |
+
"learning_rate": 4.997927195724303e-05,
|
119 |
+
"loss": 0.5536,
|
120 |
+
"num_input_tokens_seen": 591136,
|
121 |
+
"step": 14
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.27522935779816515,
|
125 |
+
"grad_norm": 0.05822828412055969,
|
126 |
+
"learning_rate": 4.997620553954645e-05,
|
127 |
+
"loss": 0.6106,
|
128 |
+
"num_input_tokens_seen": 629664,
|
129 |
+
"step": 15
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.29357798165137616,
|
133 |
+
"grad_norm": 0.06353770196437836,
|
134 |
+
"learning_rate": 4.997292778346312e-05,
|
135 |
+
"loss": 0.5129,
|
136 |
+
"num_input_tokens_seen": 663392,
|
137 |
+
"step": 16
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.3119266055045872,
|
141 |
+
"grad_norm": 0.07256966829299927,
|
142 |
+
"learning_rate": 4.996943871672807e-05,
|
143 |
+
"loss": 0.6377,
|
144 |
+
"num_input_tokens_seen": 698360,
|
145 |
+
"step": 17
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.3302752293577982,
|
149 |
+
"grad_norm": 0.055458713322877884,
|
150 |
+
"learning_rate": 4.996573836886435e-05,
|
151 |
+
"loss": 0.4083,
|
152 |
+
"num_input_tokens_seen": 737520,
|
153 |
+
"step": 18
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.3486238532110092,
|
157 |
+
"grad_norm": 0.07792335003614426,
|
158 |
+
"learning_rate": 4.9961826771182784e-05,
|
159 |
+
"loss": 0.6086,
|
160 |
+
"num_input_tokens_seen": 768056,
|
161 |
+
"step": 19
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.3669724770642202,
|
165 |
+
"grad_norm": 0.06627275049686432,
|
166 |
+
"learning_rate": 4.995770395678171e-05,
|
167 |
+
"loss": 0.4591,
|
168 |
+
"num_input_tokens_seen": 806256,
|
169 |
+
"step": 20
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.3853211009174312,
|
173 |
+
"grad_norm": 0.05830290913581848,
|
174 |
+
"learning_rate": 4.9953369960546676e-05,
|
175 |
+
"loss": 0.3731,
|
176 |
+
"num_input_tokens_seen": 842336,
|
177 |
+
"step": 21
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.4036697247706422,
|
181 |
+
"grad_norm": 0.07277437299489975,
|
182 |
+
"learning_rate": 4.9948824819150185e-05,
|
183 |
+
"loss": 0.6243,
|
184 |
+
"num_input_tokens_seen": 876672,
|
185 |
+
"step": 22
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.42201834862385323,
|
189 |
+
"grad_norm": 0.07477546483278275,
|
190 |
+
"learning_rate": 4.994406857105136e-05,
|
191 |
+
"loss": 0.5788,
|
192 |
+
"num_input_tokens_seen": 915192,
|
193 |
+
"step": 23
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.44036697247706424,
|
197 |
+
"grad_norm": 0.06912907212972641,
|
198 |
+
"learning_rate": 4.993910125649561e-05,
|
199 |
+
"loss": 0.4753,
|
200 |
+
"num_input_tokens_seen": 951904,
|
201 |
+
"step": 24
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.45871559633027525,
|
205 |
+
"grad_norm": 0.0655476376414299,
|
206 |
+
"learning_rate": 4.993392291751431e-05,
|
207 |
+
"loss": 0.4518,
|
208 |
+
"num_input_tokens_seen": 1001816,
|
209 |
+
"step": 25
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.47706422018348627,
|
213 |
+
"grad_norm": 0.06466512382030487,
|
214 |
+
"learning_rate": 4.992853359792444e-05,
|
215 |
+
"loss": 0.5638,
|
216 |
+
"num_input_tokens_seen": 1053064,
|
217 |
+
"step": 26
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.4954128440366973,
|
221 |
+
"grad_norm": 0.0645688995718956,
|
222 |
+
"learning_rate": 4.99229333433282e-05,
|
223 |
+
"loss": 0.4644,
|
224 |
+
"num_input_tokens_seen": 1086688,
|
225 |
+
"step": 27
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.5137614678899083,
|
229 |
+
"grad_norm": 0.07181251049041748,
|
230 |
+
"learning_rate": 4.9917122201112656e-05,
|
231 |
+
"loss": 0.6191,
|
232 |
+
"num_input_tokens_seen": 1134824,
|
233 |
+
"step": 28
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.5321100917431193,
|
237 |
+
"grad_norm": 0.07322589308023453,
|
238 |
+
"learning_rate": 4.9911100220449293e-05,
|
239 |
+
"loss": 0.6752,
|
240 |
+
"num_input_tokens_seen": 1172072,
|
241 |
+
"step": 29
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.5504587155963303,
|
245 |
+
"grad_norm": 0.06396070122718811,
|
246 |
+
"learning_rate": 4.990486745229364e-05,
|
247 |
+
"loss": 0.3587,
|
248 |
+
"num_input_tokens_seen": 1211096,
|
249 |
+
"step": 30
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.5688073394495413,
|
253 |
+
"grad_norm": 0.07803395390510559,
|
254 |
+
"learning_rate": 4.989842394938482e-05,
|
255 |
+
"loss": 0.459,
|
256 |
+
"num_input_tokens_seen": 1259456,
|
257 |
+
"step": 31
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.5871559633027523,
|
261 |
+
"grad_norm": 0.05974648892879486,
|
262 |
+
"learning_rate": 4.989176976624511e-05,
|
263 |
+
"loss": 0.4148,
|
264 |
+
"num_input_tokens_seen": 1306944,
|
265 |
+
"step": 32
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.6055045871559633,
|
269 |
+
"grad_norm": 0.09784268587827682,
|
270 |
+
"learning_rate": 4.988490495917947e-05,
|
271 |
+
"loss": 0.539,
|
272 |
+
"num_input_tokens_seen": 1353744,
|
273 |
+
"step": 33
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.6238532110091743,
|
277 |
+
"grad_norm": 0.09906516224145889,
|
278 |
+
"learning_rate": 4.987782958627508e-05,
|
279 |
+
"loss": 0.5453,
|
280 |
+
"num_input_tokens_seen": 1394736,
|
281 |
+
"step": 34
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.6422018348623854,
|
285 |
+
"grad_norm": 0.08984062820672989,
|
286 |
+
"learning_rate": 4.987054370740083e-05,
|
287 |
+
"loss": 0.468,
|
288 |
+
"num_input_tokens_seen": 1442048,
|
289 |
+
"step": 35
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.6605504587155964,
|
293 |
+
"grad_norm": 0.08672655373811722,
|
294 |
+
"learning_rate": 4.9863047384206835e-05,
|
295 |
+
"loss": 0.4078,
|
296 |
+
"num_input_tokens_seen": 1478440,
|
297 |
+
"step": 36
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.6788990825688074,
|
301 |
+
"grad_norm": 0.1327345073223114,
|
302 |
+
"learning_rate": 4.9855340680123905e-05,
|
303 |
+
"loss": 0.5299,
|
304 |
+
"num_input_tokens_seen": 1525992,
|
305 |
+
"step": 37
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.6972477064220184,
|
309 |
+
"grad_norm": 0.09178602695465088,
|
310 |
+
"learning_rate": 4.9847423660363e-05,
|
311 |
+
"loss": 0.439,
|
312 |
+
"num_input_tokens_seen": 1555608,
|
313 |
+
"step": 38
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.7155963302752294,
|
317 |
+
"grad_norm": 0.09418320655822754,
|
318 |
+
"learning_rate": 4.983929639191469e-05,
|
319 |
+
"loss": 0.5337,
|
320 |
+
"num_input_tokens_seen": 1597392,
|
321 |
+
"step": 39
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.7339449541284404,
|
325 |
+
"grad_norm": 0.08294719457626343,
|
326 |
+
"learning_rate": 4.983095894354858e-05,
|
327 |
+
"loss": 0.4536,
|
328 |
+
"num_input_tokens_seen": 1649656,
|
329 |
+
"step": 40
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.7522935779816514,
|
333 |
+
"grad_norm": 0.09774205833673477,
|
334 |
+
"learning_rate": 4.982241138581273e-05,
|
335 |
+
"loss": 0.5221,
|
336 |
+
"num_input_tokens_seen": 1695952,
|
337 |
+
"step": 41
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 0.7706422018348624,
|
341 |
+
"grad_norm": 0.09319107979536057,
|
342 |
+
"learning_rate": 4.9813653791033057e-05,
|
343 |
+
"loss": 0.4279,
|
344 |
+
"num_input_tokens_seen": 1737224,
|
345 |
+
"step": 42
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.7889908256880734,
|
349 |
+
"grad_norm": 0.09561405330896378,
|
350 |
+
"learning_rate": 4.980468623331273e-05,
|
351 |
+
"loss": 0.5121,
|
352 |
+
"num_input_tokens_seen": 1772320,
|
353 |
+
"step": 43
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.8073394495412844,
|
357 |
+
"grad_norm": 0.08274025470018387,
|
358 |
+
"learning_rate": 4.979550878853154e-05,
|
359 |
+
"loss": 0.54,
|
360 |
+
"num_input_tokens_seen": 1823888,
|
361 |
+
"step": 44
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.8256880733944955,
|
365 |
+
"grad_norm": 0.08728913217782974,
|
366 |
+
"learning_rate": 4.9786121534345265e-05,
|
367 |
+
"loss": 0.4488,
|
368 |
+
"num_input_tokens_seen": 1872488,
|
369 |
+
"step": 45
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.8440366972477065,
|
373 |
+
"grad_norm": 0.0787016749382019,
|
374 |
+
"learning_rate": 4.9776524550184965e-05,
|
375 |
+
"loss": 0.4353,
|
376 |
+
"num_input_tokens_seen": 1924744,
|
377 |
+
"step": 46
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.8623853211009175,
|
381 |
+
"grad_norm": 0.10952188074588776,
|
382 |
+
"learning_rate": 4.97667179172564e-05,
|
383 |
+
"loss": 0.4784,
|
384 |
+
"num_input_tokens_seen": 1959936,
|
385 |
+
"step": 47
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 0.8807339449541285,
|
389 |
+
"grad_norm": 0.08525826781988144,
|
390 |
+
"learning_rate": 4.975670171853926e-05,
|
391 |
+
"loss": 0.3586,
|
392 |
+
"num_input_tokens_seen": 2003896,
|
393 |
+
"step": 48
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.8990825688073395,
|
397 |
+
"grad_norm": 0.10409987717866898,
|
398 |
+
"learning_rate": 4.9746476038786496e-05,
|
399 |
+
"loss": 0.4451,
|
400 |
+
"num_input_tokens_seen": 2047632,
|
401 |
+
"step": 49
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.9174311926605505,
|
405 |
+
"grad_norm": 0.0782993957400322,
|
406 |
+
"learning_rate": 4.973604096452361e-05,
|
407 |
+
"loss": 0.3591,
|
408 |
+
"num_input_tokens_seen": 2096928,
|
409 |
+
"step": 50
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.9357798165137615,
|
413 |
+
"grad_norm": 0.09829951077699661,
|
414 |
+
"learning_rate": 4.9725396584047925e-05,
|
415 |
+
"loss": 0.3415,
|
416 |
+
"num_input_tokens_seen": 2129536,
|
417 |
+
"step": 51
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.9541284403669725,
|
421 |
+
"grad_norm": 0.10606162995100021,
|
422 |
+
"learning_rate": 4.971454298742779e-05,
|
423 |
+
"loss": 0.3758,
|
424 |
+
"num_input_tokens_seen": 2169144,
|
425 |
+
"step": 52
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.9724770642201835,
|
429 |
+
"grad_norm": 0.09280356764793396,
|
430 |
+
"learning_rate": 4.97034802665019e-05,
|
431 |
+
"loss": 0.485,
|
432 |
+
"num_input_tokens_seen": 2207720,
|
433 |
+
"step": 53
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 0.9908256880733946,
|
437 |
+
"grad_norm": 0.11888203024864197,
|
438 |
+
"learning_rate": 4.9692208514878444e-05,
|
439 |
+
"loss": 0.3469,
|
440 |
+
"num_input_tokens_seen": 2236392,
|
441 |
+
"step": 54
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 1.0,
|
445 |
+
"grad_norm": 0.13222463428974152,
|
446 |
+
"learning_rate": 4.9680727827934354e-05,
|
447 |
+
"loss": 0.4284,
|
448 |
+
"num_input_tokens_seen": 2259088,
|
449 |
+
"step": 55
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 1.018348623853211,
|
453 |
+
"grad_norm": 0.10572745651006699,
|
454 |
+
"learning_rate": 4.966903830281449e-05,
|
455 |
+
"loss": 0.4186,
|
456 |
+
"num_input_tokens_seen": 2298496,
|
457 |
+
"step": 56
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 1.036697247706422,
|
461 |
+
"grad_norm": 0.11462350189685822,
|
462 |
+
"learning_rate": 4.965714003843079e-05,
|
463 |
+
"loss": 0.4696,
|
464 |
+
"num_input_tokens_seen": 2333016,
|
465 |
+
"step": 57
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.0550458715596331,
|
469 |
+
"grad_norm": 0.11215240508317947,
|
470 |
+
"learning_rate": 4.9645033135461494e-05,
|
471 |
+
"loss": 0.3905,
|
472 |
+
"num_input_tokens_seen": 2367992,
|
473 |
+
"step": 58
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 1.073394495412844,
|
477 |
+
"grad_norm": 0.0973561555147171,
|
478 |
+
"learning_rate": 4.963271769635024e-05,
|
479 |
+
"loss": 0.3588,
|
480 |
+
"num_input_tokens_seen": 2415328,
|
481 |
+
"step": 59
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 1.091743119266055,
|
485 |
+
"grad_norm": 0.10240709036588669,
|
486 |
+
"learning_rate": 4.962019382530521e-05,
|
487 |
+
"loss": 0.5532,
|
488 |
+
"num_input_tokens_seen": 2454792,
|
489 |
+
"step": 60
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.110091743119266,
|
493 |
+
"grad_norm": 0.0959337130188942,
|
494 |
+
"learning_rate": 4.9607461628298244e-05,
|
495 |
+
"loss": 0.331,
|
496 |
+
"num_input_tokens_seen": 2503072,
|
497 |
+
"step": 61
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 1.1284403669724772,
|
501 |
+
"grad_norm": 0.10228750854730606,
|
502 |
+
"learning_rate": 4.9594521213063974e-05,
|
503 |
+
"loss": 0.3728,
|
504 |
+
"num_input_tokens_seen": 2546960,
|
505 |
+
"step": 62
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 1.146788990825688,
|
509 |
+
"grad_norm": 0.09403488785028458,
|
510 |
+
"learning_rate": 4.958137268909887e-05,
|
511 |
+
"loss": 0.4695,
|
512 |
+
"num_input_tokens_seen": 2595432,
|
513 |
+
"step": 63
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 1.165137614678899,
|
517 |
+
"grad_norm": 0.11396344751119614,
|
518 |
+
"learning_rate": 4.9568016167660334e-05,
|
519 |
+
"loss": 0.3653,
|
520 |
+
"num_input_tokens_seen": 2633912,
|
521 |
+
"step": 64
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.18348623853211,
|
525 |
+
"grad_norm": 0.09487481415271759,
|
526 |
+
"learning_rate": 4.9554451761765766e-05,
|
527 |
+
"loss": 0.3498,
|
528 |
+
"num_input_tokens_seen": 2680792,
|
529 |
+
"step": 65
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 1.2018348623853212,
|
533 |
+
"grad_norm": 0.1249895691871643,
|
534 |
+
"learning_rate": 4.9540679586191605e-05,
|
535 |
+
"loss": 0.4053,
|
536 |
+
"num_input_tokens_seen": 2716584,
|
537 |
+
"step": 66
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 1.2201834862385321,
|
541 |
+
"grad_norm": 0.12268221378326416,
|
542 |
+
"learning_rate": 4.952669975747232e-05,
|
543 |
+
"loss": 0.4189,
|
544 |
+
"num_input_tokens_seen": 2757088,
|
545 |
+
"step": 67
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 1.238532110091743,
|
549 |
+
"grad_norm": 0.12126032263040543,
|
550 |
+
"learning_rate": 4.951251239389948e-05,
|
551 |
+
"loss": 0.4994,
|
552 |
+
"num_input_tokens_seen": 2795664,
|
553 |
+
"step": 68
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"epoch": 1.2568807339449541,
|
557 |
+
"grad_norm": 0.1069057360291481,
|
558 |
+
"learning_rate": 4.949811761552074e-05,
|
559 |
+
"loss": 0.3275,
|
560 |
+
"num_input_tokens_seen": 2840936,
|
561 |
+
"step": 69
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 1.2752293577981653,
|
565 |
+
"grad_norm": 0.10893313586711884,
|
566 |
+
"learning_rate": 4.948351554413879e-05,
|
567 |
+
"loss": 0.4366,
|
568 |
+
"num_input_tokens_seen": 2886768,
|
569 |
+
"step": 70
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.2935779816513762,
|
573 |
+
"grad_norm": 0.12898756563663483,
|
574 |
+
"learning_rate": 4.9468706303310355e-05,
|
575 |
+
"loss": 0.3916,
|
576 |
+
"num_input_tokens_seen": 2919328,
|
577 |
+
"step": 71
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 1.311926605504587,
|
581 |
+
"grad_norm": 0.12405356019735336,
|
582 |
+
"learning_rate": 4.9453690018345144e-05,
|
583 |
+
"loss": 0.3249,
|
584 |
+
"num_input_tokens_seen": 2966744,
|
585 |
+
"step": 72
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 1.3302752293577982,
|
589 |
+
"grad_norm": 0.13137595355510712,
|
590 |
+
"learning_rate": 4.943846681630479e-05,
|
591 |
+
"loss": 0.3956,
|
592 |
+
"num_input_tokens_seen": 3007248,
|
593 |
+
"step": 73
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 1.3486238532110093,
|
597 |
+
"grad_norm": 0.13920250535011292,
|
598 |
+
"learning_rate": 4.942303682600178e-05,
|
599 |
+
"loss": 0.3956,
|
600 |
+
"num_input_tokens_seen": 3050960,
|
601 |
+
"step": 74
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 1.3669724770642202,
|
605 |
+
"grad_norm": 0.1255589872598648,
|
606 |
+
"learning_rate": 4.940740017799833e-05,
|
607 |
+
"loss": 0.3773,
|
608 |
+
"num_input_tokens_seen": 3088592,
|
609 |
+
"step": 75
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 1.385321100917431,
|
613 |
+
"grad_norm": 0.10222747176885605,
|
614 |
+
"learning_rate": 4.939155700460536e-05,
|
615 |
+
"loss": 0.4,
|
616 |
+
"num_input_tokens_seen": 3153520,
|
617 |
+
"step": 76
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 1.4036697247706422,
|
621 |
+
"grad_norm": 0.13205283880233765,
|
622 |
+
"learning_rate": 4.9375507439881266e-05,
|
623 |
+
"loss": 0.4343,
|
624 |
+
"num_input_tokens_seen": 3199272,
|
625 |
+
"step": 77
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 1.4220183486238533,
|
629 |
+
"grad_norm": 0.11005694419145584,
|
630 |
+
"learning_rate": 4.9359251619630886e-05,
|
631 |
+
"loss": 0.3881,
|
632 |
+
"num_input_tokens_seen": 3247128,
|
633 |
+
"step": 78
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 1.4403669724770642,
|
637 |
+
"grad_norm": 0.14799247682094574,
|
638 |
+
"learning_rate": 4.9342789681404275e-05,
|
639 |
+
"loss": 0.3972,
|
640 |
+
"num_input_tokens_seen": 3294192,
|
641 |
+
"step": 79
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 1.4587155963302751,
|
645 |
+
"grad_norm": 0.1279418021440506,
|
646 |
+
"learning_rate": 4.9326121764495596e-05,
|
647 |
+
"loss": 0.3438,
|
648 |
+
"num_input_tokens_seen": 3329736,
|
649 |
+
"step": 80
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 1.4770642201834863,
|
653 |
+
"grad_norm": 0.11036807298660278,
|
654 |
+
"learning_rate": 4.9309248009941914e-05,
|
655 |
+
"loss": 0.3189,
|
656 |
+
"num_input_tokens_seen": 3371376,
|
657 |
+
"step": 81
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 1.4954128440366974,
|
661 |
+
"grad_norm": 0.11855707317590714,
|
662 |
+
"learning_rate": 4.9292168560522014e-05,
|
663 |
+
"loss": 0.401,
|
664 |
+
"num_input_tokens_seen": 3412368,
|
665 |
+
"step": 82
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 1.5137614678899083,
|
669 |
+
"grad_norm": 0.13195356726646423,
|
670 |
+
"learning_rate": 4.9274883560755156e-05,
|
671 |
+
"loss": 0.4973,
|
672 |
+
"num_input_tokens_seen": 3455000,
|
673 |
+
"step": 83
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 1.5321100917431192,
|
677 |
+
"grad_norm": 0.1462787538766861,
|
678 |
+
"learning_rate": 4.925739315689991e-05,
|
679 |
+
"loss": 0.3768,
|
680 |
+
"num_input_tokens_seen": 3488960,
|
681 |
+
"step": 84
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 1.5504587155963303,
|
685 |
+
"grad_norm": 0.13765974342823029,
|
686 |
+
"learning_rate": 4.92396974969529e-05,
|
687 |
+
"loss": 0.2999,
|
688 |
+
"num_input_tokens_seen": 3521320,
|
689 |
+
"step": 85
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 1.5688073394495414,
|
693 |
+
"grad_norm": 0.15276113152503967,
|
694 |
+
"learning_rate": 4.9221796730647516e-05,
|
695 |
+
"loss": 0.3638,
|
696 |
+
"num_input_tokens_seen": 3559464,
|
697 |
+
"step": 86
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 1.5871559633027523,
|
701 |
+
"grad_norm": 0.1441674381494522,
|
702 |
+
"learning_rate": 4.92036910094527e-05,
|
703 |
+
"loss": 0.3919,
|
704 |
+
"num_input_tokens_seen": 3598080,
|
705 |
+
"step": 87
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 1.6055045871559632,
|
709 |
+
"grad_norm": 0.1780252456665039,
|
710 |
+
"learning_rate": 4.9185380486571595e-05,
|
711 |
+
"loss": 0.3626,
|
712 |
+
"num_input_tokens_seen": 3630064,
|
713 |
+
"step": 88
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 1.6238532110091743,
|
717 |
+
"grad_norm": 0.16947726905345917,
|
718 |
+
"learning_rate": 4.916686531694035e-05,
|
719 |
+
"loss": 0.3439,
|
720 |
+
"num_input_tokens_seen": 3661408,
|
721 |
+
"step": 89
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 1.6422018348623855,
|
725 |
+
"grad_norm": 0.1552971601486206,
|
726 |
+
"learning_rate": 4.914814565722671e-05,
|
727 |
+
"loss": 0.3236,
|
728 |
+
"num_input_tokens_seen": 3695480,
|
729 |
+
"step": 90
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 1.6605504587155964,
|
733 |
+
"grad_norm": 0.14925938844680786,
|
734 |
+
"learning_rate": 4.912922166582874e-05,
|
735 |
+
"loss": 0.4255,
|
736 |
+
"num_input_tokens_seen": 3734560,
|
737 |
+
"step": 91
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 1.6788990825688073,
|
741 |
+
"grad_norm": 0.1332874596118927,
|
742 |
+
"learning_rate": 4.9110093502873476e-05,
|
743 |
+
"loss": 0.3061,
|
744 |
+
"num_input_tokens_seen": 3773112,
|
745 |
+
"step": 92
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 1.6972477064220184,
|
749 |
+
"grad_norm": 0.15471243858337402,
|
750 |
+
"learning_rate": 4.909076133021557e-05,
|
751 |
+
"loss": 0.3275,
|
752 |
+
"num_input_tokens_seen": 3813392,
|
753 |
+
"step": 93
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 1.7155963302752295,
|
757 |
+
"grad_norm": 0.16010524332523346,
|
758 |
+
"learning_rate": 4.907122531143594e-05,
|
759 |
+
"loss": 0.4179,
|
760 |
+
"num_input_tokens_seen": 3856416,
|
761 |
+
"step": 94
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 1.7339449541284404,
|
765 |
+
"grad_norm": 0.13423003256320953,
|
766 |
+
"learning_rate": 4.905148561184033e-05,
|
767 |
+
"loss": 0.3593,
|
768 |
+
"num_input_tokens_seen": 3899472,
|
769 |
+
"step": 95
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 1.7522935779816513,
|
773 |
+
"grad_norm": 0.14900773763656616,
|
774 |
+
"learning_rate": 4.9031542398457974e-05,
|
775 |
+
"loss": 0.5007,
|
776 |
+
"num_input_tokens_seen": 3962976,
|
777 |
+
"step": 96
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 1.7706422018348624,
|
781 |
+
"grad_norm": 0.15728624165058136,
|
782 |
+
"learning_rate": 4.9011395840040144e-05,
|
783 |
+
"loss": 0.3484,
|
784 |
+
"num_input_tokens_seen": 4000696,
|
785 |
+
"step": 97
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 1.7889908256880735,
|
789 |
+
"grad_norm": 0.11092367768287659,
|
790 |
+
"learning_rate": 4.8991046107058735e-05,
|
791 |
+
"loss": 0.2889,
|
792 |
+
"num_input_tokens_seen": 4045256,
|
793 |
+
"step": 98
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 1.8073394495412844,
|
797 |
+
"grad_norm": 0.1289113610982895,
|
798 |
+
"learning_rate": 4.8970493371704826e-05,
|
799 |
+
"loss": 0.2203,
|
800 |
+
"num_input_tokens_seen": 4076800,
|
801 |
+
"step": 99
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 1.8256880733944953,
|
805 |
+
"grad_norm": 0.18886639177799225,
|
806 |
+
"learning_rate": 4.894973780788722e-05,
|
807 |
+
"loss": 0.3966,
|
808 |
+
"num_input_tokens_seen": 4119840,
|
809 |
+
"step": 100
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 1.8440366972477065,
|
813 |
+
"grad_norm": 0.1563039869070053,
|
814 |
+
"learning_rate": 4.892877959123097e-05,
|
815 |
+
"loss": 0.4417,
|
816 |
+
"num_input_tokens_seen": 4165848,
|
817 |
+
"step": 101
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 1.8623853211009176,
|
821 |
+
"grad_norm": 0.16883380711078644,
|
822 |
+
"learning_rate": 4.890761889907589e-05,
|
823 |
+
"loss": 0.4258,
|
824 |
+
"num_input_tokens_seen": 4202824,
|
825 |
+
"step": 102
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 1.8807339449541285,
|
829 |
+
"grad_norm": 0.18241995573043823,
|
830 |
+
"learning_rate": 4.8886255910475054e-05,
|
831 |
+
"loss": 0.3952,
|
832 |
+
"num_input_tokens_seen": 4233888,
|
833 |
+
"step": 103
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 1.8990825688073394,
|
837 |
+
"grad_norm": 0.19913265109062195,
|
838 |
+
"learning_rate": 4.88646908061933e-05,
|
839 |
+
"loss": 0.3241,
|
840 |
+
"num_input_tokens_seen": 4267064,
|
841 |
+
"step": 104
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 1.9174311926605505,
|
845 |
+
"grad_norm": 0.18295545876026154,
|
846 |
+
"learning_rate": 4.884292376870567e-05,
|
847 |
+
"loss": 0.4239,
|
848 |
+
"num_input_tokens_seen": 4312536,
|
849 |
+
"step": 105
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 1.9357798165137616,
|
853 |
+
"grad_norm": 0.16657495498657227,
|
854 |
+
"learning_rate": 4.8820954982195905e-05,
|
855 |
+
"loss": 0.2579,
|
856 |
+
"num_input_tokens_seen": 4356656,
|
857 |
+
"step": 106
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 1.9541284403669725,
|
861 |
+
"grad_norm": 0.18504932522773743,
|
862 |
+
"learning_rate": 4.879878463255483e-05,
|
863 |
+
"loss": 0.44,
|
864 |
+
"num_input_tokens_seen": 4400216,
|
865 |
+
"step": 107
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 1.9724770642201834,
|
869 |
+
"grad_norm": 0.1923118382692337,
|
870 |
+
"learning_rate": 4.877641290737884e-05,
|
871 |
+
"loss": 0.2662,
|
872 |
+
"num_input_tokens_seen": 4436968,
|
873 |
+
"step": 108
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 1.9908256880733946,
|
877 |
+
"grad_norm": 0.19636788964271545,
|
878 |
+
"learning_rate": 4.875383999596828e-05,
|
879 |
+
"loss": 0.4211,
|
880 |
+
"num_input_tokens_seen": 4488232,
|
881 |
+
"step": 109
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 2.0,
|
885 |
+
"grad_norm": 0.3168099820613861,
|
886 |
+
"learning_rate": 4.873106608932585e-05,
|
887 |
+
"loss": 0.2499,
|
888 |
+
"num_input_tokens_seen": 4518176,
|
889 |
+
"step": 110
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 2.018348623853211,
|
893 |
+
"grad_norm": 0.14410308003425598,
|
894 |
+
"learning_rate": 4.8708091380154984e-05,
|
895 |
+
"loss": 0.2722,
|
896 |
+
"num_input_tokens_seen": 4570896,
|
897 |
+
"step": 111
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 2.036697247706422,
|
901 |
+
"grad_norm": 0.17840909957885742,
|
902 |
+
"learning_rate": 4.868491606285823e-05,
|
903 |
+
"loss": 0.2758,
|
904 |
+
"num_input_tokens_seen": 4613576,
|
905 |
+
"step": 112
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 2.055045871559633,
|
909 |
+
"grad_norm": 0.178523987531662,
|
910 |
+
"learning_rate": 4.866154033353561e-05,
|
911 |
+
"loss": 0.3361,
|
912 |
+
"num_input_tokens_seen": 4652896,
|
913 |
+
"step": 113
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 2.073394495412844,
|
917 |
+
"grad_norm": 0.17396725714206696,
|
918 |
+
"learning_rate": 4.8637964389982926e-05,
|
919 |
+
"loss": 0.2667,
|
920 |
+
"num_input_tokens_seen": 4694256,
|
921 |
+
"step": 114
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 2.091743119266055,
|
925 |
+
"grad_norm": 0.19471587240695953,
|
926 |
+
"learning_rate": 4.8614188431690125e-05,
|
927 |
+
"loss": 0.3628,
|
928 |
+
"num_input_tokens_seen": 4747552,
|
929 |
+
"step": 115
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 2.1100917431192663,
|
933 |
+
"grad_norm": 0.1722450852394104,
|
934 |
+
"learning_rate": 4.859021265983959e-05,
|
935 |
+
"loss": 0.3599,
|
936 |
+
"num_input_tokens_seen": 4794080,
|
937 |
+
"step": 116
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 2.128440366972477,
|
941 |
+
"grad_norm": 0.20137006044387817,
|
942 |
+
"learning_rate": 4.856603727730447e-05,
|
943 |
+
"loss": 0.4262,
|
944 |
+
"num_input_tokens_seen": 4847912,
|
945 |
+
"step": 117
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 2.146788990825688,
|
949 |
+
"grad_norm": 0.19395771622657776,
|
950 |
+
"learning_rate": 4.854166248864689e-05,
|
951 |
+
"loss": 0.3118,
|
952 |
+
"num_input_tokens_seen": 4885480,
|
953 |
+
"step": 118
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 2.165137614678899,
|
957 |
+
"grad_norm": 0.209548681974411,
|
958 |
+
"learning_rate": 4.85170885001163e-05,
|
959 |
+
"loss": 0.3725,
|
960 |
+
"num_input_tokens_seen": 4921240,
|
961 |
+
"step": 119
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 2.18348623853211,
|
965 |
+
"grad_norm": 0.18228279054164886,
|
966 |
+
"learning_rate": 4.849231551964771e-05,
|
967 |
+
"loss": 0.3816,
|
968 |
+
"num_input_tokens_seen": 4960224,
|
969 |
+
"step": 120
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 2.2018348623853212,
|
973 |
+
"grad_norm": 0.24349354207515717,
|
974 |
+
"learning_rate": 4.846734375685989e-05,
|
975 |
+
"loss": 0.3383,
|
976 |
+
"num_input_tokens_seen": 4990536,
|
977 |
+
"step": 121
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 2.220183486238532,
|
981 |
+
"grad_norm": 0.17600344121456146,
|
982 |
+
"learning_rate": 4.844217342305363e-05,
|
983 |
+
"loss": 0.3011,
|
984 |
+
"num_input_tokens_seen": 5044296,
|
985 |
+
"step": 122
|
986 |
+
},
|
987 |
+
{
|
988 |
+
"epoch": 2.238532110091743,
|
989 |
+
"grad_norm": 0.18766675889492035,
|
990 |
+
"learning_rate": 4.8416804731209945e-05,
|
991 |
+
"loss": 0.4458,
|
992 |
+
"num_input_tokens_seen": 5088368,
|
993 |
+
"step": 123
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 2.2568807339449544,
|
997 |
+
"grad_norm": 0.17657820880413055,
|
998 |
+
"learning_rate": 4.839123789598829e-05,
|
999 |
+
"loss": 0.2564,
|
1000 |
+
"num_input_tokens_seen": 5133472,
|
1001 |
+
"step": 124
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 2.2752293577981653,
|
1005 |
+
"grad_norm": 0.20606014132499695,
|
1006 |
+
"learning_rate": 4.836547313372471e-05,
|
1007 |
+
"loss": 0.313,
|
1008 |
+
"num_input_tokens_seen": 5167768,
|
1009 |
+
"step": 125
|
1010 |
+
},
|
1011 |
+
{
|
1012 |
+
"epoch": 2.293577981651376,
|
1013 |
+
"grad_norm": 0.23511061072349548,
|
1014 |
+
"learning_rate": 4.8339510662430046e-05,
|
1015 |
+
"loss": 0.2963,
|
1016 |
+
"num_input_tokens_seen": 5209400,
|
1017 |
+
"step": 126
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 2.311926605504587,
|
1021 |
+
"grad_norm": 0.18234293162822723,
|
1022 |
+
"learning_rate": 4.8313350701788054e-05,
|
1023 |
+
"loss": 0.2566,
|
1024 |
+
"num_input_tokens_seen": 5249360,
|
1025 |
+
"step": 127
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 2.330275229357798,
|
1029 |
+
"grad_norm": 0.2223992496728897,
|
1030 |
+
"learning_rate": 4.828699347315356e-05,
|
1031 |
+
"loss": 0.2833,
|
1032 |
+
"num_input_tokens_seen": 5300808,
|
1033 |
+
"step": 128
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 2.3486238532110093,
|
1037 |
+
"grad_norm": 0.23101739585399628,
|
1038 |
+
"learning_rate": 4.826043919955062e-05,
|
1039 |
+
"loss": 0.3099,
|
1040 |
+
"num_input_tokens_seen": 5332960,
|
1041 |
+
"step": 129
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 2.36697247706422,
|
1045 |
+
"grad_norm": 0.26640889048576355,
|
1046 |
+
"learning_rate": 4.823368810567056e-05,
|
1047 |
+
"loss": 0.3238,
|
1048 |
+
"num_input_tokens_seen": 5365008,
|
1049 |
+
"step": 130
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 2.385321100917431,
|
1053 |
+
"grad_norm": 0.2374572902917862,
|
1054 |
+
"learning_rate": 4.820674041787017e-05,
|
1055 |
+
"loss": 0.3153,
|
1056 |
+
"num_input_tokens_seen": 5400184,
|
1057 |
+
"step": 131
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"epoch": 2.4036697247706424,
|
1061 |
+
"grad_norm": 0.22812288999557495,
|
1062 |
+
"learning_rate": 4.817959636416969e-05,
|
1063 |
+
"loss": 0.2997,
|
1064 |
+
"num_input_tokens_seen": 5440320,
|
1065 |
+
"step": 132
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 2.4220183486238533,
|
1069 |
+
"grad_norm": 0.20079149305820465,
|
1070 |
+
"learning_rate": 4.815225617425095e-05,
|
1071 |
+
"loss": 0.2373,
|
1072 |
+
"num_input_tokens_seen": 5480832,
|
1073 |
+
"step": 133
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 2.4403669724770642,
|
1077 |
+
"grad_norm": 0.196709543466568,
|
1078 |
+
"learning_rate": 4.81247200794554e-05,
|
1079 |
+
"loss": 0.2456,
|
1080 |
+
"num_input_tokens_seen": 5526936,
|
1081 |
+
"step": 134
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 2.458715596330275,
|
1085 |
+
"grad_norm": 0.17305873334407806,
|
1086 |
+
"learning_rate": 4.8096988312782174e-05,
|
1087 |
+
"loss": 0.2099,
|
1088 |
+
"num_input_tokens_seen": 5566384,
|
1089 |
+
"step": 135
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 2.477064220183486,
|
1093 |
+
"grad_norm": 3.584635019302368,
|
1094 |
+
"learning_rate": 4.806906110888606e-05,
|
1095 |
+
"loss": 0.3485,
|
1096 |
+
"num_input_tokens_seen": 5629896,
|
1097 |
+
"step": 136
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 2.4954128440366974,
|
1101 |
+
"grad_norm": 0.23481500148773193,
|
1102 |
+
"learning_rate": 4.80409387040756e-05,
|
1103 |
+
"loss": 0.2231,
|
1104 |
+
"num_input_tokens_seen": 5674504,
|
1105 |
+
"step": 137
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 2.5137614678899083,
|
1109 |
+
"grad_norm": 0.27899855375289917,
|
1110 |
+
"learning_rate": 4.8012621336311016e-05,
|
1111 |
+
"loss": 0.4285,
|
1112 |
+
"num_input_tokens_seen": 5714000,
|
1113 |
+
"step": 138
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 2.532110091743119,
|
1117 |
+
"grad_norm": 0.24404938519001007,
|
1118 |
+
"learning_rate": 4.798410924520223e-05,
|
1119 |
+
"loss": 0.3343,
|
1120 |
+
"num_input_tokens_seen": 5756856,
|
1121 |
+
"step": 139
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 2.5504587155963305,
|
1125 |
+
"grad_norm": 0.26869162917137146,
|
1126 |
+
"learning_rate": 4.7955402672006854e-05,
|
1127 |
+
"loss": 0.2497,
|
1128 |
+
"num_input_tokens_seen": 5781192,
|
1129 |
+
"step": 140
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 2.5688073394495414,
|
1133 |
+
"grad_norm": 0.2057972550392151,
|
1134 |
+
"learning_rate": 4.79265018596281e-05,
|
1135 |
+
"loss": 0.2991,
|
1136 |
+
"num_input_tokens_seen": 5824024,
|
1137 |
+
"step": 141
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 2.5871559633027523,
|
1141 |
+
"grad_norm": 0.2184937596321106,
|
1142 |
+
"learning_rate": 4.789740705261278e-05,
|
1143 |
+
"loss": 0.2406,
|
1144 |
+
"num_input_tokens_seen": 5862584,
|
1145 |
+
"step": 142
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 2.6055045871559632,
|
1149 |
+
"grad_norm": 0.23603741824626923,
|
1150 |
+
"learning_rate": 4.786811849714918e-05,
|
1151 |
+
"loss": 0.2722,
|
1152 |
+
"num_input_tokens_seen": 5897344,
|
1153 |
+
"step": 143
|
1154 |
+
},
|
1155 |
+
{
|
1156 |
+
"epoch": 2.623853211009174,
|
1157 |
+
"grad_norm": 0.22983981668949127,
|
1158 |
+
"learning_rate": 4.783863644106502e-05,
|
1159 |
+
"loss": 0.374,
|
1160 |
+
"num_input_tokens_seen": 5931736,
|
1161 |
+
"step": 144
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 2.6422018348623855,
|
1165 |
+
"grad_norm": 0.2825419306755066,
|
1166 |
+
"learning_rate": 4.780896113382536e-05,
|
1167 |
+
"loss": 0.3386,
|
1168 |
+
"num_input_tokens_seen": 5972784,
|
1169 |
+
"step": 145
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 2.6605504587155964,
|
1173 |
+
"grad_norm": 0.4502134621143341,
|
1174 |
+
"learning_rate": 4.777909282653042e-05,
|
1175 |
+
"loss": 0.2289,
|
1176 |
+
"num_input_tokens_seen": 6018968,
|
1177 |
+
"step": 146
|
1178 |
+
},
|
1179 |
+
{
|
1180 |
+
"epoch": 2.6788990825688073,
|
1181 |
+
"grad_norm": 0.2428288459777832,
|
1182 |
+
"learning_rate": 4.7749031771913584e-05,
|
1183 |
+
"loss": 0.4061,
|
1184 |
+
"num_input_tokens_seen": 6062520,
|
1185 |
+
"step": 147
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 2.6972477064220186,
|
1189 |
+
"grad_norm": 0.2685629725456238,
|
1190 |
+
"learning_rate": 4.771877822433911e-05,
|
1191 |
+
"loss": 0.2198,
|
1192 |
+
"num_input_tokens_seen": 6087928,
|
1193 |
+
"step": 148
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 2.7155963302752295,
|
1197 |
+
"grad_norm": 0.24021446704864502,
|
1198 |
+
"learning_rate": 4.7688332439800096e-05,
|
1199 |
+
"loss": 0.34,
|
1200 |
+
"num_input_tokens_seen": 6134792,
|
1201 |
+
"step": 149
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 2.7339449541284404,
|
1205 |
+
"grad_norm": 0.2568534314632416,
|
1206 |
+
"learning_rate": 4.765769467591625e-05,
|
1207 |
+
"loss": 0.3292,
|
1208 |
+
"num_input_tokens_seen": 6183296,
|
1209 |
+
"step": 150
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 2.7522935779816513,
|
1213 |
+
"grad_norm": 0.20823974907398224,
|
1214 |
+
"learning_rate": 4.762686519193175e-05,
|
1215 |
+
"loss": 0.2539,
|
1216 |
+
"num_input_tokens_seen": 6225840,
|
1217 |
+
"step": 151
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 2.770642201834862,
|
1221 |
+
"grad_norm": 0.23333317041397095,
|
1222 |
+
"learning_rate": 4.759584424871302e-05,
|
1223 |
+
"loss": 0.3571,
|
1224 |
+
"num_input_tokens_seen": 6274760,
|
1225 |
+
"step": 152
|
1226 |
+
},
|
1227 |
+
{
|
1228 |
+
"epoch": 2.7889908256880735,
|
1229 |
+
"grad_norm": 0.20232398808002472,
|
1230 |
+
"learning_rate": 4.756463210874652e-05,
|
1231 |
+
"loss": 0.2783,
|
1232 |
+
"num_input_tokens_seen": 6326168,
|
1233 |
+
"step": 153
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 2.8073394495412844,
|
1237 |
+
"grad_norm": 0.3479433059692383,
|
1238 |
+
"learning_rate": 4.7533229036136553e-05,
|
1239 |
+
"loss": 0.2925,
|
1240 |
+
"num_input_tokens_seen": 6360312,
|
1241 |
+
"step": 154
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 2.8256880733944953,
|
1245 |
+
"grad_norm": 0.2659524083137512,
|
1246 |
+
"learning_rate": 4.750163529660303e-05,
|
1247 |
+
"loss": 0.2606,
|
1248 |
+
"num_input_tokens_seen": 6395496,
|
1249 |
+
"step": 155
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 2.8440366972477067,
|
1253 |
+
"grad_norm": 0.24823158979415894,
|
1254 |
+
"learning_rate": 4.7469851157479177e-05,
|
1255 |
+
"loss": 0.3721,
|
1256 |
+
"num_input_tokens_seen": 6437064,
|
1257 |
+
"step": 156
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 2.8623853211009176,
|
1261 |
+
"grad_norm": 0.32034072279930115,
|
1262 |
+
"learning_rate": 4.743787688770932e-05,
|
1263 |
+
"loss": 0.3931,
|
1264 |
+
"num_input_tokens_seen": 6477616,
|
1265 |
+
"step": 157
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 2.8807339449541285,
|
1269 |
+
"grad_norm": 0.23295725882053375,
|
1270 |
+
"learning_rate": 4.740571275784659e-05,
|
1271 |
+
"loss": 0.2201,
|
1272 |
+
"num_input_tokens_seen": 6518680,
|
1273 |
+
"step": 158
|
1274 |
+
},
|
1275 |
+
{
|
1276 |
+
"epoch": 2.8990825688073394,
|
1277 |
+
"grad_norm": 0.2758423984050751,
|
1278 |
+
"learning_rate": 4.737335904005063e-05,
|
1279 |
+
"loss": 0.2579,
|
1280 |
+
"num_input_tokens_seen": 6549768,
|
1281 |
+
"step": 159
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 2.9174311926605503,
|
1285 |
+
"grad_norm": 0.26690953969955444,
|
1286 |
+
"learning_rate": 4.734081600808531e-05,
|
1287 |
+
"loss": 0.2575,
|
1288 |
+
"num_input_tokens_seen": 6581000,
|
1289 |
+
"step": 160
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"epoch": 2.9357798165137616,
|
1293 |
+
"grad_norm": 0.26657482981681824,
|
1294 |
+
"learning_rate": 4.730808393731639e-05,
|
1295 |
+
"loss": 0.2597,
|
1296 |
+
"num_input_tokens_seen": 6612632,
|
1297 |
+
"step": 161
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 2.9541284403669725,
|
1301 |
+
"grad_norm": 0.22647295892238617,
|
1302 |
+
"learning_rate": 4.72751631047092e-05,
|
1303 |
+
"loss": 0.3335,
|
1304 |
+
"num_input_tokens_seen": 6654288,
|
1305 |
+
"step": 162
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 2.9724770642201834,
|
1309 |
+
"grad_norm": 0.2863366901874542,
|
1310 |
+
"learning_rate": 4.72420537888263e-05,
|
1311 |
+
"loss": 0.374,
|
1312 |
+
"num_input_tokens_seen": 6707208,
|
1313 |
+
"step": 163
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 2.9908256880733948,
|
1317 |
+
"grad_norm": 0.2606408894062042,
|
1318 |
+
"learning_rate": 4.7208756269825104e-05,
|
1319 |
+
"loss": 0.3477,
|
1320 |
+
"num_input_tokens_seen": 6748448,
|
1321 |
+
"step": 164
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 3.0,
|
1325 |
+
"grad_norm": 0.440924733877182,
|
1326 |
+
"learning_rate": 4.717527082945554e-05,
|
1327 |
+
"loss": 0.3214,
|
1328 |
+
"num_input_tokens_seen": 6777264,
|
1329 |
+
"step": 165
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 3.018348623853211,
|
1333 |
+
"grad_norm": 0.27583903074264526,
|
1334 |
+
"learning_rate": 4.714159775105765e-05,
|
1335 |
+
"loss": 0.2681,
|
1336 |
+
"num_input_tokens_seen": 6809456,
|
1337 |
+
"step": 166
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 3.036697247706422,
|
1341 |
+
"grad_norm": 0.2995987832546234,
|
1342 |
+
"learning_rate": 4.7107737319559176e-05,
|
1343 |
+
"loss": 0.2633,
|
1344 |
+
"num_input_tokens_seen": 6845768,
|
1345 |
+
"step": 167
|
1346 |
+
},
|
1347 |
+
{
|
1348 |
+
"epoch": 3.055045871559633,
|
1349 |
+
"grad_norm": 0.23999951779842377,
|
1350 |
+
"learning_rate": 4.707368982147318e-05,
|
1351 |
+
"loss": 0.1961,
|
1352 |
+
"num_input_tokens_seen": 6893056,
|
1353 |
+
"step": 168
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 3.073394495412844,
|
1357 |
+
"grad_norm": 0.23356525599956512,
|
1358 |
+
"learning_rate": 4.703945554489558e-05,
|
1359 |
+
"loss": 0.2836,
|
1360 |
+
"num_input_tokens_seen": 6932480,
|
1361 |
+
"step": 169
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 3.091743119266055,
|
1365 |
+
"grad_norm": 0.29919493198394775,
|
1366 |
+
"learning_rate": 4.700503477950278e-05,
|
1367 |
+
"loss": 0.2838,
|
1368 |
+
"num_input_tokens_seen": 6975992,
|
1369 |
+
"step": 170
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 3.1100917431192663,
|
1373 |
+
"grad_norm": 0.3350690007209778,
|
1374 |
+
"learning_rate": 4.697042781654913e-05,
|
1375 |
+
"loss": 0.3489,
|
1376 |
+
"num_input_tokens_seen": 7021840,
|
1377 |
+
"step": 171
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 3.128440366972477,
|
1381 |
+
"grad_norm": 0.2837466895580292,
|
1382 |
+
"learning_rate": 4.693563494886455e-05,
|
1383 |
+
"loss": 0.3797,
|
1384 |
+
"num_input_tokens_seen": 7065192,
|
1385 |
+
"step": 172
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 3.146788990825688,
|
1389 |
+
"grad_norm": 0.24601787328720093,
|
1390 |
+
"learning_rate": 4.6900656470851964e-05,
|
1391 |
+
"loss": 0.2046,
|
1392 |
+
"num_input_tokens_seen": 7114544,
|
1393 |
+
"step": 173
|
1394 |
+
},
|
1395 |
+
{
|
1396 |
+
"epoch": 3.165137614678899,
|
1397 |
+
"grad_norm": 0.32290250062942505,
|
1398 |
+
"learning_rate": 4.6865492678484895e-05,
|
1399 |
+
"loss": 0.2596,
|
1400 |
+
"num_input_tokens_seen": 7152736,
|
1401 |
+
"step": 174
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 3.18348623853211,
|
1405 |
+
"grad_norm": 0.33591920137405396,
|
1406 |
+
"learning_rate": 4.68301438693049e-05,
|
1407 |
+
"loss": 0.3045,
|
1408 |
+
"num_input_tokens_seen": 7207464,
|
1409 |
+
"step": 175
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 3.2018348623853212,
|
1413 |
+
"grad_norm": 0.25471043586730957,
|
1414 |
+
"learning_rate": 4.679461034241906e-05,
|
1415 |
+
"loss": 0.2096,
|
1416 |
+
"num_input_tokens_seen": 7238640,
|
1417 |
+
"step": 176
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 3.220183486238532,
|
1421 |
+
"grad_norm": 0.31238994002342224,
|
1422 |
+
"learning_rate": 4.6758892398497494e-05,
|
1423 |
+
"loss": 0.2226,
|
1424 |
+
"num_input_tokens_seen": 7279112,
|
1425 |
+
"step": 177
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 3.238532110091743,
|
1429 |
+
"grad_norm": 0.35679712891578674,
|
1430 |
+
"learning_rate": 4.672299033977076e-05,
|
1431 |
+
"loss": 0.2403,
|
1432 |
+
"num_input_tokens_seen": 7311632,
|
1433 |
+
"step": 178
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 3.2568807339449544,
|
1437 |
+
"grad_norm": 0.326914519071579,
|
1438 |
+
"learning_rate": 4.6686904470027316e-05,
|
1439 |
+
"loss": 0.2156,
|
1440 |
+
"num_input_tokens_seen": 7344864,
|
1441 |
+
"step": 179
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 3.2752293577981653,
|
1445 |
+
"grad_norm": 0.3293381929397583,
|
1446 |
+
"learning_rate": 4.665063509461097e-05,
|
1447 |
+
"loss": 0.238,
|
1448 |
+
"num_input_tokens_seen": 7389944,
|
1449 |
+
"step": 180
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 3.293577981651376,
|
1453 |
+
"grad_norm": 0.3313307762145996,
|
1454 |
+
"learning_rate": 4.661418252041827e-05,
|
1455 |
+
"loss": 0.2251,
|
1456 |
+
"num_input_tokens_seen": 7423672,
|
1457 |
+
"step": 181
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 3.311926605504587,
|
1461 |
+
"grad_norm": 0.3328595459461212,
|
1462 |
+
"learning_rate": 4.657754705589591e-05,
|
1463 |
+
"loss": 0.2922,
|
1464 |
+
"num_input_tokens_seen": 7459576,
|
1465 |
+
"step": 182
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 3.330275229357798,
|
1469 |
+
"grad_norm": 0.2721710801124573,
|
1470 |
+
"learning_rate": 4.6540729011038146e-05,
|
1471 |
+
"loss": 0.2698,
|
1472 |
+
"num_input_tokens_seen": 7511736,
|
1473 |
+
"step": 183
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 3.3486238532110093,
|
1477 |
+
"grad_norm": 0.2488890290260315,
|
1478 |
+
"learning_rate": 4.650372869738414e-05,
|
1479 |
+
"loss": 0.173,
|
1480 |
+
"num_input_tokens_seen": 7558552,
|
1481 |
+
"step": 184
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 3.36697247706422,
|
1485 |
+
"grad_norm": 0.3800615668296814,
|
1486 |
+
"learning_rate": 4.6466546428015336e-05,
|
1487 |
+
"loss": 0.32,
|
1488 |
+
"num_input_tokens_seen": 7599040,
|
1489 |
+
"step": 185
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 3.385321100917431,
|
1493 |
+
"grad_norm": 0.3377014100551605,
|
1494 |
+
"learning_rate": 4.642918251755281e-05,
|
1495 |
+
"loss": 0.3058,
|
1496 |
+
"num_input_tokens_seen": 7653264,
|
1497 |
+
"step": 186
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 3.4036697247706424,
|
1501 |
+
"grad_norm": 0.25239789485931396,
|
1502 |
+
"learning_rate": 4.639163728215463e-05,
|
1503 |
+
"loss": 0.1896,
|
1504 |
+
"num_input_tokens_seen": 7694272,
|
1505 |
+
"step": 187
|
1506 |
+
},
|
1507 |
+
{
|
1508 |
+
"epoch": 3.4220183486238533,
|
1509 |
+
"grad_norm": 0.34607502818107605,
|
1510 |
+
"learning_rate": 4.6353911039513145e-05,
|
1511 |
+
"loss": 0.2933,
|
1512 |
+
"num_input_tokens_seen": 7730848,
|
1513 |
+
"step": 188
|
1514 |
+
},
|
1515 |
+
{
|
1516 |
+
"epoch": 3.4403669724770642,
|
1517 |
+
"grad_norm": 0.30653324723243713,
|
1518 |
+
"learning_rate": 4.6316004108852305e-05,
|
1519 |
+
"loss": 0.2625,
|
1520 |
+
"num_input_tokens_seen": 7781200,
|
1521 |
+
"step": 189
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 3.458715596330275,
|
1525 |
+
"grad_norm": 0.2943236231803894,
|
1526 |
+
"learning_rate": 4.627791681092499e-05,
|
1527 |
+
"loss": 0.3372,
|
1528 |
+
"num_input_tokens_seen": 7825032,
|
1529 |
+
"step": 190
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 3.477064220183486,
|
1533 |
+
"grad_norm": 0.30080685019493103,
|
1534 |
+
"learning_rate": 4.623964946801027e-05,
|
1535 |
+
"loss": 0.2229,
|
1536 |
+
"num_input_tokens_seen": 7855840,
|
1537 |
+
"step": 191
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 3.4954128440366974,
|
1541 |
+
"grad_norm": 0.3511403799057007,
|
1542 |
+
"learning_rate": 4.620120240391065e-05,
|
1543 |
+
"loss": 0.3967,
|
1544 |
+
"num_input_tokens_seen": 7905928,
|
1545 |
+
"step": 192
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 3.5137614678899083,
|
1549 |
+
"grad_norm": 0.273583322763443,
|
1550 |
+
"learning_rate": 4.61625759439494e-05,
|
1551 |
+
"loss": 0.2254,
|
1552 |
+
"num_input_tokens_seen": 7955992,
|
1553 |
+
"step": 193
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"epoch": 3.532110091743119,
|
1557 |
+
"grad_norm": 0.3457902669906616,
|
1558 |
+
"learning_rate": 4.612377041496776e-05,
|
1559 |
+
"loss": 0.2553,
|
1560 |
+
"num_input_tokens_seen": 7998024,
|
1561 |
+
"step": 194
|
1562 |
+
},
|
1563 |
+
{
|
1564 |
+
"epoch": 3.5504587155963305,
|
1565 |
+
"grad_norm": 0.31968954205513,
|
1566 |
+
"learning_rate": 4.608478614532215e-05,
|
1567 |
+
"loss": 0.2197,
|
1568 |
+
"num_input_tokens_seen": 8055672,
|
1569 |
+
"step": 195
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 3.5688073394495414,
|
1573 |
+
"grad_norm": 0.34753403067588806,
|
1574 |
+
"learning_rate": 4.604562346488144e-05,
|
1575 |
+
"loss": 0.2507,
|
1576 |
+
"num_input_tokens_seen": 8090848,
|
1577 |
+
"step": 196
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 3.5871559633027523,
|
1581 |
+
"grad_norm": 0.3808669149875641,
|
1582 |
+
"learning_rate": 4.6006282705024144e-05,
|
1583 |
+
"loss": 0.2422,
|
1584 |
+
"num_input_tokens_seen": 8136680,
|
1585 |
+
"step": 197
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 3.6055045871559632,
|
1589 |
+
"grad_norm": 0.3004499673843384,
|
1590 |
+
"learning_rate": 4.5966764198635606e-05,
|
1591 |
+
"loss": 0.2107,
|
1592 |
+
"num_input_tokens_seen": 8187472,
|
1593 |
+
"step": 198
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 3.623853211009174,
|
1597 |
+
"grad_norm": 0.30718186497688293,
|
1598 |
+
"learning_rate": 4.592706828010518e-05,
|
1599 |
+
"loss": 0.1854,
|
1600 |
+
"num_input_tokens_seen": 8225216,
|
1601 |
+
"step": 199
|
1602 |
+
},
|
1603 |
+
{
|
1604 |
+
"epoch": 3.6422018348623855,
|
1605 |
+
"grad_norm": 0.23112858831882477,
|
1606 |
+
"learning_rate": 4.588719528532342e-05,
|
1607 |
+
"loss": 0.1687,
|
1608 |
+
"num_input_tokens_seen": 8274456,
|
1609 |
+
"step": 200
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 3.6605504587155964,
|
1613 |
+
"grad_norm": 0.25966888666152954,
|
1614 |
+
"learning_rate": 4.5847145551679206e-05,
|
1615 |
+
"loss": 0.2549,
|
1616 |
+
"num_input_tokens_seen": 8317016,
|
1617 |
+
"step": 201
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 3.6788990825688073,
|
1621 |
+
"grad_norm": 0.25600987672805786,
|
1622 |
+
"learning_rate": 4.580691941805695e-05,
|
1623 |
+
"loss": 0.1602,
|
1624 |
+
"num_input_tokens_seen": 8361856,
|
1625 |
+
"step": 202
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 3.6972477064220186,
|
1629 |
+
"grad_norm": 0.33986184000968933,
|
1630 |
+
"learning_rate": 4.5766517224833637e-05,
|
1631 |
+
"loss": 0.2495,
|
1632 |
+
"num_input_tokens_seen": 8410696,
|
1633 |
+
"step": 203
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 3.7155963302752295,
|
1637 |
+
"grad_norm": 0.36899781227111816,
|
1638 |
+
"learning_rate": 4.572593931387604e-05,
|
1639 |
+
"loss": 0.2012,
|
1640 |
+
"num_input_tokens_seen": 8441872,
|
1641 |
+
"step": 204
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 3.7339449541284404,
|
1645 |
+
"grad_norm": 0.42072632908821106,
|
1646 |
+
"learning_rate": 4.568518602853776e-05,
|
1647 |
+
"loss": 0.2373,
|
1648 |
+
"num_input_tokens_seen": 8482544,
|
1649 |
+
"step": 205
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 3.7522935779816513,
|
1653 |
+
"grad_norm": 0.40593233704566956,
|
1654 |
+
"learning_rate": 4.5644257713656356e-05,
|
1655 |
+
"loss": 0.233,
|
1656 |
+
"num_input_tokens_seen": 8519856,
|
1657 |
+
"step": 206
|
1658 |
+
},
|
1659 |
+
{
|
1660 |
+
"epoch": 3.770642201834862,
|
1661 |
+
"grad_norm": 0.38003161549568176,
|
1662 |
+
"learning_rate": 4.5603154715550386e-05,
|
1663 |
+
"loss": 0.225,
|
1664 |
+
"num_input_tokens_seen": 8551392,
|
1665 |
+
"step": 207
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 3.7889908256880735,
|
1669 |
+
"grad_norm": 0.2564244568347931,
|
1670 |
+
"learning_rate": 4.556187738201656e-05,
|
1671 |
+
"loss": 0.2975,
|
1672 |
+
"num_input_tokens_seen": 8599472,
|
1673 |
+
"step": 208
|
1674 |
+
},
|
1675 |
+
{
|
1676 |
+
"epoch": 3.8073394495412844,
|
1677 |
+
"grad_norm": 0.29023391008377075,
|
1678 |
+
"learning_rate": 4.552042606232668e-05,
|
1679 |
+
"loss": 0.2033,
|
1680 |
+
"num_input_tokens_seen": 8631880,
|
1681 |
+
"step": 209
|
1682 |
+
},
|
1683 |
+
{
|
1684 |
+
"epoch": 3.8256880733944953,
|
1685 |
+
"grad_norm": 0.32886001467704773,
|
1686 |
+
"learning_rate": 4.54788011072248e-05,
|
1687 |
+
"loss": 0.2024,
|
1688 |
+
"num_input_tokens_seen": 8675016,
|
1689 |
+
"step": 210
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 3.8440366972477067,
|
1693 |
+
"grad_norm": 0.36749884486198425,
|
1694 |
+
"learning_rate": 4.5437002868924166e-05,
|
1695 |
+
"loss": 0.2304,
|
1696 |
+
"num_input_tokens_seen": 8713248,
|
1697 |
+
"step": 211
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 3.8623853211009176,
|
1701 |
+
"grad_norm": 0.3055097758769989,
|
1702 |
+
"learning_rate": 4.539503170110431e-05,
|
1703 |
+
"loss": 0.2928,
|
1704 |
+
"num_input_tokens_seen": 8748800,
|
1705 |
+
"step": 212
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 3.8807339449541285,
|
1709 |
+
"grad_norm": 0.38436686992645264,
|
1710 |
+
"learning_rate": 4.535288795890798e-05,
|
1711 |
+
"loss": 0.2214,
|
1712 |
+
"num_input_tokens_seen": 8787832,
|
1713 |
+
"step": 213
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 3.8990825688073394,
|
1717 |
+
"grad_norm": 0.44330883026123047,
|
1718 |
+
"learning_rate": 4.531057199893824e-05,
|
1719 |
+
"loss": 0.2168,
|
1720 |
+
"num_input_tokens_seen": 8819616,
|
1721 |
+
"step": 214
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 3.9174311926605503,
|
1725 |
+
"grad_norm": 0.28318527340888977,
|
1726 |
+
"learning_rate": 4.526808417925531e-05,
|
1727 |
+
"loss": 0.279,
|
1728 |
+
"num_input_tokens_seen": 8860744,
|
1729 |
+
"step": 215
|
1730 |
+
},
|
1731 |
+
{
|
1732 |
+
"epoch": 3.9357798165137616,
|
1733 |
+
"grad_norm": 0.3287319839000702,
|
1734 |
+
"learning_rate": 4.522542485937369e-05,
|
1735 |
+
"loss": 0.2597,
|
1736 |
+
"num_input_tokens_seen": 8906432,
|
1737 |
+
"step": 216
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 3.9541284403669725,
|
1741 |
+
"grad_norm": 0.35815751552581787,
|
1742 |
+
"learning_rate": 4.5182594400259e-05,
|
1743 |
+
"loss": 0.241,
|
1744 |
+
"num_input_tokens_seen": 8955104,
|
1745 |
+
"step": 217
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 3.9724770642201834,
|
1749 |
+
"grad_norm": 0.3299608528614044,
|
1750 |
+
"learning_rate": 4.5139593164324986e-05,
|
1751 |
+
"loss": 0.2157,
|
1752 |
+
"num_input_tokens_seen": 8990200,
|
1753 |
+
"step": 218
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 3.9908256880733948,
|
1757 |
+
"grad_norm": 0.2916093170642853,
|
1758 |
+
"learning_rate": 4.509642151543043e-05,
|
1759 |
+
"loss": 0.2046,
|
1760 |
+
"num_input_tokens_seen": 9020760,
|
1761 |
+
"step": 219
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 4.0,
|
1765 |
+
"grad_norm": 0.40076637268066406,
|
1766 |
+
"learning_rate": 4.50530798188761e-05,
|
1767 |
+
"loss": 0.1714,
|
1768 |
+
"num_input_tokens_seen": 9036352,
|
1769 |
+
"step": 220
|
1770 |
+
},
|
1771 |
+
{
|
1772 |
+
"epoch": 4.018348623853211,
|
1773 |
+
"grad_norm": 0.40515249967575073,
|
1774 |
+
"learning_rate": 4.50095684414016e-05,
|
1775 |
+
"loss": 0.1811,
|
1776 |
+
"num_input_tokens_seen": 9091776,
|
1777 |
+
"step": 221
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 4.036697247706422,
|
1781 |
+
"grad_norm": 0.32984718680381775,
|
1782 |
+
"learning_rate": 4.496588775118232e-05,
|
1783 |
+
"loss": 0.2101,
|
1784 |
+
"num_input_tokens_seen": 9134080,
|
1785 |
+
"step": 222
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 4.055045871559633,
|
1789 |
+
"grad_norm": 0.27288541197776794,
|
1790 |
+
"learning_rate": 4.4922038117826334e-05,
|
1791 |
+
"loss": 0.1444,
|
1792 |
+
"num_input_tokens_seen": 9172720,
|
1793 |
+
"step": 223
|
1794 |
+
},
|
1795 |
+
{
|
1796 |
+
"epoch": 4.073394495412844,
|
1797 |
+
"grad_norm": 0.5168021321296692,
|
1798 |
+
"learning_rate": 4.48780199123712e-05,
|
1799 |
+
"loss": 0.2342,
|
1800 |
+
"num_input_tokens_seen": 9213664,
|
1801 |
+
"step": 224
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 4.091743119266055,
|
1805 |
+
"grad_norm": 0.3986498713493347,
|
1806 |
+
"learning_rate": 4.4833833507280884e-05,
|
1807 |
+
"loss": 0.1676,
|
1808 |
+
"num_input_tokens_seen": 9261768,
|
1809 |
+
"step": 225
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 4.110091743119266,
|
1813 |
+
"grad_norm": 0.4472793936729431,
|
1814 |
+
"learning_rate": 4.478947927644258e-05,
|
1815 |
+
"loss": 0.295,
|
1816 |
+
"num_input_tokens_seen": 9300928,
|
1817 |
+
"step": 226
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 4.128440366972477,
|
1821 |
+
"grad_norm": 0.39240705966949463,
|
1822 |
+
"learning_rate": 4.474495759516358e-05,
|
1823 |
+
"loss": 0.17,
|
1824 |
+
"num_input_tokens_seen": 9329472,
|
1825 |
+
"step": 227
|
1826 |
+
},
|
1827 |
+
{
|
1828 |
+
"epoch": 4.146788990825688,
|
1829 |
+
"grad_norm": 0.354526549577713,
|
1830 |
+
"learning_rate": 4.4700268840168045e-05,
|
1831 |
+
"loss": 0.1759,
|
1832 |
+
"num_input_tokens_seen": 9365640,
|
1833 |
+
"step": 228
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 4.165137614678899,
|
1837 |
+
"grad_norm": 0.3216766119003296,
|
1838 |
+
"learning_rate": 4.4655413389593856e-05,
|
1839 |
+
"loss": 0.1878,
|
1840 |
+
"num_input_tokens_seen": 9410552,
|
1841 |
+
"step": 229
|
1842 |
+
},
|
1843 |
+
{
|
1844 |
+
"epoch": 4.18348623853211,
|
1845 |
+
"grad_norm": 0.30976617336273193,
|
1846 |
+
"learning_rate": 4.4610391622989396e-05,
|
1847 |
+
"loss": 0.1637,
|
1848 |
+
"num_input_tokens_seen": 9452416,
|
1849 |
+
"step": 230
|
1850 |
+
},
|
1851 |
+
{
|
1852 |
+
"epoch": 4.201834862385321,
|
1853 |
+
"grad_norm": 0.385437935590744,
|
1854 |
+
"learning_rate": 4.456520392131035e-05,
|
1855 |
+
"loss": 0.2748,
|
1856 |
+
"num_input_tokens_seen": 9503528,
|
1857 |
+
"step": 231
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 4.220183486238533,
|
1861 |
+
"grad_norm": 0.37948480248451233,
|
1862 |
+
"learning_rate": 4.4519850666916484e-05,
|
1863 |
+
"loss": 0.2635,
|
1864 |
+
"num_input_tokens_seen": 9541592,
|
1865 |
+
"step": 232
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 4.238532110091743,
|
1869 |
+
"grad_norm": 0.36141568422317505,
|
1870 |
+
"learning_rate": 4.447433224356839e-05,
|
1871 |
+
"loss": 0.2027,
|
1872 |
+
"num_input_tokens_seen": 9586064,
|
1873 |
+
"step": 233
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 4.256880733944954,
|
1877 |
+
"grad_norm": 0.4549350440502167,
|
1878 |
+
"learning_rate": 4.442864903642428e-05,
|
1879 |
+
"loss": 0.2107,
|
1880 |
+
"num_input_tokens_seen": 9641688,
|
1881 |
+
"step": 234
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 4.275229357798165,
|
1885 |
+
"grad_norm": 0.3979765474796295,
|
1886 |
+
"learning_rate": 4.438280143203665e-05,
|
1887 |
+
"loss": 0.2879,
|
1888 |
+
"num_input_tokens_seen": 9686240,
|
1889 |
+
"step": 235
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 4.293577981651376,
|
1893 |
+
"grad_norm": 0.35011065006256104,
|
1894 |
+
"learning_rate": 4.43367898183491e-05,
|
1895 |
+
"loss": 0.2594,
|
1896 |
+
"num_input_tokens_seen": 9735632,
|
1897 |
+
"step": 236
|
1898 |
+
},
|
1899 |
+
{
|
1900 |
+
"epoch": 4.3119266055045875,
|
1901 |
+
"grad_norm": 0.3999224007129669,
|
1902 |
+
"learning_rate": 4.4290614584693004e-05,
|
1903 |
+
"loss": 0.1907,
|
1904 |
+
"num_input_tokens_seen": 9766536,
|
1905 |
+
"step": 237
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 4.330275229357798,
|
1909 |
+
"grad_norm": 0.39629611372947693,
|
1910 |
+
"learning_rate": 4.4244276121784195e-05,
|
1911 |
+
"loss": 0.1805,
|
1912 |
+
"num_input_tokens_seen": 9796400,
|
1913 |
+
"step": 238
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 4.348623853211009,
|
1917 |
+
"grad_norm": 0.36784592270851135,
|
1918 |
+
"learning_rate": 4.4197774821719714e-05,
|
1919 |
+
"loss": 0.1824,
|
1920 |
+
"num_input_tokens_seen": 9831992,
|
1921 |
+
"step": 239
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 4.36697247706422,
|
1925 |
+
"grad_norm": 0.3408430516719818,
|
1926 |
+
"learning_rate": 4.415111107797445e-05,
|
1927 |
+
"loss": 0.1721,
|
1928 |
+
"num_input_tokens_seen": 9875640,
|
1929 |
+
"step": 240
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 4.385321100917431,
|
1933 |
+
"grad_norm": 0.3232553005218506,
|
1934 |
+
"learning_rate": 4.410428528539783e-05,
|
1935 |
+
"loss": 0.275,
|
1936 |
+
"num_input_tokens_seen": 9916816,
|
1937 |
+
"step": 241
|
1938 |
+
},
|
1939 |
+
{
|
1940 |
+
"epoch": 4.4036697247706424,
|
1941 |
+
"grad_norm": 0.38150206208229065,
|
1942 |
+
"learning_rate": 4.405729784021046e-05,
|
1943 |
+
"loss": 0.1963,
|
1944 |
+
"num_input_tokens_seen": 9962928,
|
1945 |
+
"step": 242
|
1946 |
+
},
|
1947 |
+
{
|
1948 |
+
"epoch": 4.422018348623853,
|
1949 |
+
"grad_norm": 0.4176963269710541,
|
1950 |
+
"learning_rate": 4.401014914000078e-05,
|
1951 |
+
"loss": 0.1626,
|
1952 |
+
"num_input_tokens_seen": 9997224,
|
1953 |
+
"step": 243
|
1954 |
+
},
|
1955 |
+
{
|
1956 |
+
"epoch": 4.440366972477064,
|
1957 |
+
"grad_norm": 0.38855600357055664,
|
1958 |
+
"learning_rate": 4.396283958372173e-05,
|
1959 |
+
"loss": 0.1733,
|
1960 |
+
"num_input_tokens_seen": 10036248,
|
1961 |
+
"step": 244
|
1962 |
+
},
|
1963 |
+
{
|
1964 |
+
"epoch": 4.458715596330276,
|
1965 |
+
"grad_norm": 0.3860638737678528,
|
1966 |
+
"learning_rate": 4.391536957168733e-05,
|
1967 |
+
"loss": 0.1936,
|
1968 |
+
"num_input_tokens_seen": 10070312,
|
1969 |
+
"step": 245
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 4.477064220183486,
|
1973 |
+
"grad_norm": 0.31510865688323975,
|
1974 |
+
"learning_rate": 4.386773950556931e-05,
|
1975 |
+
"loss": 0.1847,
|
1976 |
+
"num_input_tokens_seen": 10114568,
|
1977 |
+
"step": 246
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 4.495412844036697,
|
1981 |
+
"grad_norm": 0.3280925154685974,
|
1982 |
+
"learning_rate": 4.381994978839371e-05,
|
1983 |
+
"loss": 0.1981,
|
1984 |
+
"num_input_tokens_seen": 10150280,
|
1985 |
+
"step": 247
|
1986 |
+
},
|
1987 |
+
{
|
1988 |
+
"epoch": 4.513761467889909,
|
1989 |
+
"grad_norm": 0.33136090636253357,
|
1990 |
+
"learning_rate": 4.377200082453749e-05,
|
1991 |
+
"loss": 0.1681,
|
1992 |
+
"num_input_tokens_seen": 10194000,
|
1993 |
+
"step": 248
|
1994 |
+
},
|
1995 |
+
{
|
1996 |
+
"epoch": 4.532110091743119,
|
1997 |
+
"grad_norm": 0.43955501914024353,
|
1998 |
+
"learning_rate": 4.372389301972506e-05,
|
1999 |
+
"loss": 0.2111,
|
2000 |
+
"num_input_tokens_seen": 10232264,
|
2001 |
+
"step": 249
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 4.5504587155963305,
|
2005 |
+
"grad_norm": 0.28938886523246765,
|
2006 |
+
"learning_rate": 4.36756267810249e-05,
|
2007 |
+
"loss": 0.2307,
|
2008 |
+
"num_input_tokens_seen": 10271880,
|
2009 |
+
"step": 250
|
2010 |
+
},
|
2011 |
+
{
|
2012 |
+
"epoch": 4.568807339449541,
|
2013 |
+
"grad_norm": 0.37232765555381775,
|
2014 |
+
"learning_rate": 4.36272025168461e-05,
|
2015 |
+
"loss": 0.1609,
|
2016 |
+
"num_input_tokens_seen": 10317720,
|
2017 |
+
"step": 251
|
2018 |
+
},
|
2019 |
+
{
|
2020 |
+
"epoch": 4.587155963302752,
|
2021 |
+
"grad_norm": 0.6248548030853271,
|
2022 |
+
"learning_rate": 4.357862063693486e-05,
|
2023 |
+
"loss": 0.2456,
|
2024 |
+
"num_input_tokens_seen": 10362168,
|
2025 |
+
"step": 252
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 4.605504587155964,
|
2029 |
+
"grad_norm": 0.32828131318092346,
|
2030 |
+
"learning_rate": 4.3529881552371096e-05,
|
2031 |
+
"loss": 0.3159,
|
2032 |
+
"num_input_tokens_seen": 10414312,
|
2033 |
+
"step": 253
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 4.623853211009174,
|
2037 |
+
"grad_norm": 0.4158332049846649,
|
2038 |
+
"learning_rate": 4.34809856755649e-05,
|
2039 |
+
"loss": 0.2194,
|
2040 |
+
"num_input_tokens_seen": 10451800,
|
2041 |
+
"step": 254
|
2042 |
+
},
|
2043 |
+
{
|
2044 |
+
"epoch": 4.6422018348623855,
|
2045 |
+
"grad_norm": 0.3648194670677185,
|
2046 |
+
"learning_rate": 4.34319334202531e-05,
|
2047 |
+
"loss": 0.1846,
|
2048 |
+
"num_input_tokens_seen": 10496224,
|
2049 |
+
"step": 255
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 4.660550458715596,
|
2053 |
+
"grad_norm": 0.36835575103759766,
|
2054 |
+
"learning_rate": 4.3382725201495723e-05,
|
2055 |
+
"loss": 0.1906,
|
2056 |
+
"num_input_tokens_seen": 10536392,
|
2057 |
+
"step": 256
|
2058 |
+
},
|
2059 |
+
{
|
2060 |
+
"epoch": 4.678899082568807,
|
2061 |
+
"grad_norm": 0.3501613140106201,
|
2062 |
+
"learning_rate": 4.333336143567247e-05,
|
2063 |
+
"loss": 0.1793,
|
2064 |
+
"num_input_tokens_seen": 10577640,
|
2065 |
+
"step": 257
|
2066 |
+
},
|
2067 |
+
{
|
2068 |
+
"epoch": 4.697247706422019,
|
2069 |
+
"grad_norm": 0.3431616425514221,
|
2070 |
+
"learning_rate": 4.3283842540479264e-05,
|
2071 |
+
"loss": 0.1576,
|
2072 |
+
"num_input_tokens_seen": 10613376,
|
2073 |
+
"step": 258
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 4.715596330275229,
|
2077 |
+
"grad_norm": 0.3290237784385681,
|
2078 |
+
"learning_rate": 4.3234168934924636e-05,
|
2079 |
+
"loss": 0.1447,
|
2080 |
+
"num_input_tokens_seen": 10647232,
|
2081 |
+
"step": 259
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 4.73394495412844,
|
2085 |
+
"grad_norm": 0.40264153480529785,
|
2086 |
+
"learning_rate": 4.318434103932622e-05,
|
2087 |
+
"loss": 0.1488,
|
2088 |
+
"num_input_tokens_seen": 10696024,
|
2089 |
+
"step": 260
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 4.752293577981652,
|
2093 |
+
"grad_norm": 0.3453703820705414,
|
2094 |
+
"learning_rate": 4.313435927530719e-05,
|
2095 |
+
"loss": 0.1597,
|
2096 |
+
"num_input_tokens_seen": 10730408,
|
2097 |
+
"step": 261
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 4.770642201834862,
|
2101 |
+
"grad_norm": 0.3993653655052185,
|
2102 |
+
"learning_rate": 4.30842240657927e-05,
|
2103 |
+
"loss": 0.2266,
|
2104 |
+
"num_input_tokens_seen": 10764776,
|
2105 |
+
"step": 262
|
2106 |
+
},
|
2107 |
+
{
|
2108 |
+
"epoch": 4.7889908256880735,
|
2109 |
+
"grad_norm": 0.4080798923969269,
|
2110 |
+
"learning_rate": 4.303393583500628e-05,
|
2111 |
+
"loss": 0.1562,
|
2112 |
+
"num_input_tokens_seen": 10792272,
|
2113 |
+
"step": 263
|
2114 |
+
},
|
2115 |
+
{
|
2116 |
+
"epoch": 4.807339449541285,
|
2117 |
+
"grad_norm": 0.3028413951396942,
|
2118 |
+
"learning_rate": 4.2983495008466276e-05,
|
2119 |
+
"loss": 0.1504,
|
2120 |
+
"num_input_tokens_seen": 10825240,
|
2121 |
+
"step": 264
|
2122 |
+
},
|
2123 |
+
{
|
2124 |
+
"epoch": 4.825688073394495,
|
2125 |
+
"grad_norm": 0.3980019688606262,
|
2126 |
+
"learning_rate": 4.293290201298223e-05,
|
2127 |
+
"loss": 0.1648,
|
2128 |
+
"num_input_tokens_seen": 10883592,
|
2129 |
+
"step": 265
|
2130 |
+
},
|
2131 |
+
{
|
2132 |
+
"epoch": 4.844036697247707,
|
2133 |
+
"grad_norm": 0.42035797238349915,
|
2134 |
+
"learning_rate": 4.288215727665129e-05,
|
2135 |
+
"loss": 0.1652,
|
2136 |
+
"num_input_tokens_seen": 10922640,
|
2137 |
+
"step": 266
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 4.862385321100917,
|
2141 |
+
"grad_norm": 0.37766003608703613,
|
2142 |
+
"learning_rate": 4.2831261228854544e-05,
|
2143 |
+
"loss": 0.1817,
|
2144 |
+
"num_input_tokens_seen": 10967288,
|
2145 |
+
"step": 267
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 4.8807339449541285,
|
2149 |
+
"grad_norm": 0.3495088815689087,
|
2150 |
+
"learning_rate": 4.278021430025343e-05,
|
2151 |
+
"loss": 0.2066,
|
2152 |
+
"num_input_tokens_seen": 11011152,
|
2153 |
+
"step": 268
|
2154 |
+
},
|
2155 |
+
{
|
2156 |
+
"epoch": 4.89908256880734,
|
2157 |
+
"grad_norm": 0.34071093797683716,
|
2158 |
+
"learning_rate": 4.272901692278609e-05,
|
2159 |
+
"loss": 0.1522,
|
2160 |
+
"num_input_tokens_seen": 11055608,
|
2161 |
+
"step": 269
|
2162 |
+
},
|
2163 |
+
{
|
2164 |
+
"epoch": 4.91743119266055,
|
2165 |
+
"grad_norm": 0.33437398076057434,
|
2166 |
+
"learning_rate": 4.267766952966369e-05,
|
2167 |
+
"loss": 0.2201,
|
2168 |
+
"num_input_tokens_seen": 11101992,
|
2169 |
+
"step": 270
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 4.935779816513762,
|
2173 |
+
"grad_norm": 0.3340584337711334,
|
2174 |
+
"learning_rate": 4.262617255536676e-05,
|
2175 |
+
"loss": 0.2777,
|
2176 |
+
"num_input_tokens_seen": 11141408,
|
2177 |
+
"step": 271
|
2178 |
+
},
|
2179 |
+
{
|
2180 |
+
"epoch": 4.954128440366972,
|
2181 |
+
"grad_norm": 0.348679780960083,
|
2182 |
+
"learning_rate": 4.257452643564155e-05,
|
2183 |
+
"loss": 0.1857,
|
2184 |
+
"num_input_tokens_seen": 11185344,
|
2185 |
+
"step": 272
|
2186 |
+
},
|
2187 |
+
{
|
2188 |
+
"epoch": 4.972477064220183,
|
2189 |
+
"grad_norm": 0.3691309094429016,
|
2190 |
+
"learning_rate": 4.2522731607496275e-05,
|
2191 |
+
"loss": 0.1653,
|
2192 |
+
"num_input_tokens_seen": 11216160,
|
2193 |
+
"step": 273
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 4.990825688073395,
|
2197 |
+
"grad_norm": 0.4692390561103821,
|
2198 |
+
"learning_rate": 4.24707885091975e-05,
|
2199 |
+
"loss": 0.1761,
|
2200 |
+
"num_input_tokens_seen": 11276200,
|
2201 |
+
"step": 274
|
2202 |
+
},
|
2203 |
+
{
|
2204 |
+
"epoch": 5.0,
|
2205 |
+
"grad_norm": 0.4963766932487488,
|
2206 |
+
"learning_rate": 4.241869758026638e-05,
|
2207 |
+
"loss": 0.1582,
|
2208 |
+
"num_input_tokens_seen": 11295440,
|
2209 |
+
"step": 275
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 5.018348623853211,
|
2213 |
+
"grad_norm": 0.37284544110298157,
|
2214 |
+
"learning_rate": 4.2366459261474933e-05,
|
2215 |
+
"loss": 0.1538,
|
2216 |
+
"num_input_tokens_seen": 11336400,
|
2217 |
+
"step": 276
|
2218 |
+
},
|
2219 |
+
{
|
2220 |
+
"epoch": 5.036697247706422,
|
2221 |
+
"grad_norm": 0.2949577867984772,
|
2222 |
+
"learning_rate": 4.231407399484236e-05,
|
2223 |
+
"loss": 0.1319,
|
2224 |
+
"num_input_tokens_seen": 11374056,
|
2225 |
+
"step": 277
|
2226 |
+
},
|
2227 |
+
{
|
2228 |
+
"epoch": 5.055045871559633,
|
2229 |
+
"grad_norm": 0.32850027084350586,
|
2230 |
+
"learning_rate": 4.226154222363124e-05,
|
2231 |
+
"loss": 0.174,
|
2232 |
+
"num_input_tokens_seen": 11414776,
|
2233 |
+
"step": 278
|
2234 |
+
},
|
2235 |
+
{
|
2236 |
+
"epoch": 5.073394495412844,
|
2237 |
+
"grad_norm": 0.3812579810619354,
|
2238 |
+
"learning_rate": 4.220886439234385e-05,
|
2239 |
+
"loss": 0.1831,
|
2240 |
+
"num_input_tokens_seen": 11465456,
|
2241 |
+
"step": 279
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 5.091743119266055,
|
2245 |
+
"grad_norm": 0.3396337032318115,
|
2246 |
+
"learning_rate": 4.215604094671835e-05,
|
2247 |
+
"loss": 0.1515,
|
2248 |
+
"num_input_tokens_seen": 11500184,
|
2249 |
+
"step": 280
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 5.110091743119266,
|
2253 |
+
"grad_norm": 0.35079169273376465,
|
2254 |
+
"learning_rate": 4.2103072333725e-05,
|
2255 |
+
"loss": 0.1295,
|
2256 |
+
"num_input_tokens_seen": 11537112,
|
2257 |
+
"step": 281
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"epoch": 5.128440366972477,
|
2261 |
+
"grad_norm": 0.3811327815055847,
|
2262 |
+
"learning_rate": 4.2049959001562464e-05,
|
2263 |
+
"loss": 0.1339,
|
2264 |
+
"num_input_tokens_seen": 11579440,
|
2265 |
+
"step": 282
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 5.146788990825688,
|
2269 |
+
"grad_norm": 0.3935602009296417,
|
2270 |
+
"learning_rate": 4.199670139965393e-05,
|
2271 |
+
"loss": 0.1909,
|
2272 |
+
"num_input_tokens_seen": 11643272,
|
2273 |
+
"step": 283
|
2274 |
+
},
|
2275 |
+
{
|
2276 |
+
"epoch": 5.165137614678899,
|
2277 |
+
"grad_norm": 0.3952607810497284,
|
2278 |
+
"learning_rate": 4.194329997864331e-05,
|
2279 |
+
"loss": 0.2334,
|
2280 |
+
"num_input_tokens_seen": 11677528,
|
2281 |
+
"step": 284
|
2282 |
+
},
|
2283 |
+
{
|
2284 |
+
"epoch": 5.18348623853211,
|
2285 |
+
"grad_norm": 0.3687472939491272,
|
2286 |
+
"learning_rate": 4.188975519039151e-05,
|
2287 |
+
"loss": 0.1406,
|
2288 |
+
"num_input_tokens_seen": 11727944,
|
2289 |
+
"step": 285
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 5.201834862385321,
|
2293 |
+
"grad_norm": 0.3518407344818115,
|
2294 |
+
"learning_rate": 4.183606748797251e-05,
|
2295 |
+
"loss": 0.138,
|
2296 |
+
"num_input_tokens_seen": 11779568,
|
2297 |
+
"step": 286
|
2298 |
+
},
|
2299 |
+
{
|
2300 |
+
"epoch": 5.220183486238533,
|
2301 |
+
"grad_norm": 0.4072832763195038,
|
2302 |
+
"learning_rate": 4.1782237325669595e-05,
|
2303 |
+
"loss": 0.159,
|
2304 |
+
"num_input_tokens_seen": 11824600,
|
2305 |
+
"step": 287
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 5.238532110091743,
|
2309 |
+
"grad_norm": 0.386280357837677,
|
2310 |
+
"learning_rate": 4.172826515897146e-05,
|
2311 |
+
"loss": 0.2517,
|
2312 |
+
"num_input_tokens_seen": 11873736,
|
2313 |
+
"step": 288
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 5.256880733944954,
|
2317 |
+
"grad_norm": 0.3576860725879669,
|
2318 |
+
"learning_rate": 4.167415144456841e-05,
|
2319 |
+
"loss": 0.1349,
|
2320 |
+
"num_input_tokens_seen": 11909608,
|
2321 |
+
"step": 289
|
2322 |
+
},
|
2323 |
+
{
|
2324 |
+
"epoch": 5.275229357798165,
|
2325 |
+
"grad_norm": 0.3952435851097107,
|
2326 |
+
"learning_rate": 4.1619896640348445e-05,
|
2327 |
+
"loss": 0.1348,
|
2328 |
+
"num_input_tokens_seen": 11945440,
|
2329 |
+
"step": 290
|
2330 |
+
},
|
2331 |
+
{
|
2332 |
+
"epoch": 5.293577981651376,
|
2333 |
+
"grad_norm": 0.3565181493759155,
|
2334 |
+
"learning_rate": 4.1565501205393445e-05,
|
2335 |
+
"loss": 0.1331,
|
2336 |
+
"num_input_tokens_seen": 11985568,
|
2337 |
+
"step": 291
|
2338 |
+
},
|
2339 |
+
{
|
2340 |
+
"epoch": 5.3119266055045875,
|
2341 |
+
"grad_norm": 0.40558820962905884,
|
2342 |
+
"learning_rate": 4.1510965599975196e-05,
|
2343 |
+
"loss": 0.2337,
|
2344 |
+
"num_input_tokens_seen": 12034320,
|
2345 |
+
"step": 292
|
2346 |
+
},
|
2347 |
+
{
|
2348 |
+
"epoch": 5.330275229357798,
|
2349 |
+
"grad_norm": 0.36426106095314026,
|
2350 |
+
"learning_rate": 4.1456290285551596e-05,
|
2351 |
+
"loss": 0.1299,
|
2352 |
+
"num_input_tokens_seen": 12070184,
|
2353 |
+
"step": 293
|
2354 |
+
},
|
2355 |
+
{
|
2356 |
+
"epoch": 5.348623853211009,
|
2357 |
+
"grad_norm": 0.33881404995918274,
|
2358 |
+
"learning_rate": 4.140147572476268e-05,
|
2359 |
+
"loss": 0.1239,
|
2360 |
+
"num_input_tokens_seen": 12111512,
|
2361 |
+
"step": 294
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 5.36697247706422,
|
2365 |
+
"grad_norm": 0.38019630312919617,
|
2366 |
+
"learning_rate": 4.1346522381426744e-05,
|
2367 |
+
"loss": 0.133,
|
2368 |
+
"num_input_tokens_seen": 12156792,
|
2369 |
+
"step": 295
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 5.385321100917431,
|
2373 |
+
"grad_norm": 0.38179296255111694,
|
2374 |
+
"learning_rate": 4.129143072053638e-05,
|
2375 |
+
"loss": 0.1301,
|
2376 |
+
"num_input_tokens_seen": 12185168,
|
2377 |
+
"step": 296
|
2378 |
+
},
|
2379 |
+
{
|
2380 |
+
"epoch": 5.4036697247706424,
|
2381 |
+
"grad_norm": 0.35054150223731995,
|
2382 |
+
"learning_rate": 4.123620120825459e-05,
|
2383 |
+
"loss": 0.1298,
|
2384 |
+
"num_input_tokens_seen": 12222256,
|
2385 |
+
"step": 297
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"epoch": 5.422018348623853,
|
2389 |
+
"grad_norm": 0.3463946580886841,
|
2390 |
+
"learning_rate": 4.118083431191081e-05,
|
2391 |
+
"loss": 0.2088,
|
2392 |
+
"num_input_tokens_seen": 12257536,
|
2393 |
+
"step": 298
|
2394 |
+
},
|
2395 |
+
{
|
2396 |
+
"epoch": 5.440366972477064,
|
2397 |
+
"grad_norm": 0.42584434151649475,
|
2398 |
+
"learning_rate": 4.112533049999696e-05,
|
2399 |
+
"loss": 0.1062,
|
2400 |
+
"num_input_tokens_seen": 12290576,
|
2401 |
+
"step": 299
|
2402 |
+
},
|
2403 |
+
{
|
2404 |
+
"epoch": 5.458715596330276,
|
2405 |
+
"grad_norm": 0.4341515600681305,
|
2406 |
+
"learning_rate": 4.1069690242163484e-05,
|
2407 |
+
"loss": 0.1989,
|
2408 |
+
"num_input_tokens_seen": 12323416,
|
2409 |
+
"step": 300
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 5.477064220183486,
|
2413 |
+
"grad_norm": 0.4299938380718231,
|
2414 |
+
"learning_rate": 4.101391400921538e-05,
|
2415 |
+
"loss": 0.1243,
|
2416 |
+
"num_input_tokens_seen": 12370264,
|
2417 |
+
"step": 301
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 5.495412844036697,
|
2421 |
+
"grad_norm": 0.4070415198802948,
|
2422 |
+
"learning_rate": 4.095800227310821e-05,
|
2423 |
+
"loss": 0.2281,
|
2424 |
+
"num_input_tokens_seen": 12410568,
|
2425 |
+
"step": 302
|
2426 |
+
},
|
2427 |
+
{
|
2428 |
+
"epoch": 5.513761467889909,
|
2429 |
+
"grad_norm": 0.4446506202220917,
|
2430 |
+
"learning_rate": 4.09019555069441e-05,
|
2431 |
+
"loss": 0.1462,
|
2432 |
+
"num_input_tokens_seen": 12442880,
|
2433 |
+
"step": 303
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 5.532110091743119,
|
2437 |
+
"grad_norm": 0.36110538244247437,
|
2438 |
+
"learning_rate": 4.0845774184967754e-05,
|
2439 |
+
"loss": 0.1497,
|
2440 |
+
"num_input_tokens_seen": 12487016,
|
2441 |
+
"step": 304
|
2442 |
+
},
|
2443 |
+
{
|
2444 |
+
"epoch": 5.5504587155963305,
|
2445 |
+
"grad_norm": 0.42756903171539307,
|
2446 |
+
"learning_rate": 4.078945878256244e-05,
|
2447 |
+
"loss": 0.2082,
|
2448 |
+
"num_input_tokens_seen": 12525072,
|
2449 |
+
"step": 305
|
2450 |
+
},
|
2451 |
+
{
|
2452 |
+
"epoch": 5.568807339449541,
|
2453 |
+
"grad_norm": 0.360649049282074,
|
2454 |
+
"learning_rate": 4.073300977624594e-05,
|
2455 |
+
"loss": 0.1214,
|
2456 |
+
"num_input_tokens_seen": 12555792,
|
2457 |
+
"step": 306
|
2458 |
+
},
|
2459 |
+
{
|
2460 |
+
"epoch": 5.587155963302752,
|
2461 |
+
"grad_norm": 0.3768391013145447,
|
2462 |
+
"learning_rate": 4.067642764366654e-05,
|
2463 |
+
"loss": 0.1278,
|
2464 |
+
"num_input_tokens_seen": 12601616,
|
2465 |
+
"step": 307
|
2466 |
+
},
|
2467 |
+
{
|
2468 |
+
"epoch": 5.605504587155964,
|
2469 |
+
"grad_norm": 0.3882285952568054,
|
2470 |
+
"learning_rate": 4.0619712863599e-05,
|
2471 |
+
"loss": 0.1485,
|
2472 |
+
"num_input_tokens_seen": 12634360,
|
2473 |
+
"step": 308
|
2474 |
+
},
|
2475 |
+
{
|
2476 |
+
"epoch": 5.623853211009174,
|
2477 |
+
"grad_norm": 0.38816162943840027,
|
2478 |
+
"learning_rate": 4.0562865915940496e-05,
|
2479 |
+
"loss": 0.1221,
|
2480 |
+
"num_input_tokens_seen": 12674808,
|
2481 |
+
"step": 309
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 5.6422018348623855,
|
2485 |
+
"grad_norm": 0.41803887486457825,
|
2486 |
+
"learning_rate": 4.05058872817065e-05,
|
2487 |
+
"loss": 0.1388,
|
2488 |
+
"num_input_tokens_seen": 12710864,
|
2489 |
+
"step": 310
|
2490 |
+
},
|
2491 |
+
{
|
2492 |
+
"epoch": 5.660550458715596,
|
2493 |
+
"grad_norm": 0.3802741467952728,
|
2494 |
+
"learning_rate": 4.044877744302683e-05,
|
2495 |
+
"loss": 0.1349,
|
2496 |
+
"num_input_tokens_seen": 12750920,
|
2497 |
+
"step": 311
|
2498 |
+
},
|
2499 |
+
{
|
2500 |
+
"epoch": 5.678899082568807,
|
2501 |
+
"grad_norm": 0.48202404379844666,
|
2502 |
+
"learning_rate": 4.039153688314145e-05,
|
2503 |
+
"loss": 0.1555,
|
2504 |
+
"num_input_tokens_seen": 12789488,
|
2505 |
+
"step": 312
|
2506 |
+
},
|
2507 |
+
{
|
2508 |
+
"epoch": 5.697247706422019,
|
2509 |
+
"grad_norm": 0.3168826103210449,
|
2510 |
+
"learning_rate": 4.0334166086396484e-05,
|
2511 |
+
"loss": 0.1063,
|
2512 |
+
"num_input_tokens_seen": 12831408,
|
2513 |
+
"step": 313
|
2514 |
+
},
|
2515 |
+
{
|
2516 |
+
"epoch": 5.715596330275229,
|
2517 |
+
"grad_norm": 0.43414828181266785,
|
2518 |
+
"learning_rate": 4.0276665538239996e-05,
|
2519 |
+
"loss": 0.127,
|
2520 |
+
"num_input_tokens_seen": 12872584,
|
2521 |
+
"step": 314
|
2522 |
+
},
|
2523 |
+
{
|
2524 |
+
"epoch": 5.73394495412844,
|
2525 |
+
"grad_norm": 0.47761547565460205,
|
2526 |
+
"learning_rate": 4.021903572521802e-05,
|
2527 |
+
"loss": 0.1428,
|
2528 |
+
"num_input_tokens_seen": 12910528,
|
2529 |
+
"step": 315
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 5.752293577981652,
|
2533 |
+
"grad_norm": 0.3542017936706543,
|
2534 |
+
"learning_rate": 4.0161277134970345e-05,
|
2535 |
+
"loss": 0.1279,
|
2536 |
+
"num_input_tokens_seen": 12942800,
|
2537 |
+
"step": 316
|
2538 |
+
},
|
2539 |
+
{
|
2540 |
+
"epoch": 5.770642201834862,
|
2541 |
+
"grad_norm": 0.31866851449012756,
|
2542 |
+
"learning_rate": 4.010339025622641e-05,
|
2543 |
+
"loss": 0.1459,
|
2544 |
+
"num_input_tokens_seen": 12989136,
|
2545 |
+
"step": 317
|
2546 |
+
},
|
2547 |
+
{
|
2548 |
+
"epoch": 5.7889908256880735,
|
2549 |
+
"grad_norm": 0.44918256998062134,
|
2550 |
+
"learning_rate": 4.0045375578801214e-05,
|
2551 |
+
"loss": 0.1429,
|
2552 |
+
"num_input_tokens_seen": 13035472,
|
2553 |
+
"step": 318
|
2554 |
+
},
|
2555 |
+
{
|
2556 |
+
"epoch": 5.807339449541285,
|
2557 |
+
"grad_norm": 0.32426726818084717,
|
2558 |
+
"learning_rate": 3.99872335935911e-05,
|
2559 |
+
"loss": 0.1257,
|
2560 |
+
"num_input_tokens_seen": 13074952,
|
2561 |
+
"step": 319
|
2562 |
+
},
|
2563 |
+
{
|
2564 |
+
"epoch": 5.825688073394495,
|
2565 |
+
"grad_norm": 0.6903991103172302,
|
2566 |
+
"learning_rate": 3.9928964792569655e-05,
|
2567 |
+
"loss": 0.1807,
|
2568 |
+
"num_input_tokens_seen": 13124624,
|
2569 |
+
"step": 320
|
2570 |
+
},
|
2571 |
+
{
|
2572 |
+
"epoch": 5.844036697247707,
|
2573 |
+
"grad_norm": 0.3665274679660797,
|
2574 |
+
"learning_rate": 3.9870569668783536e-05,
|
2575 |
+
"loss": 0.1853,
|
2576 |
+
"num_input_tokens_seen": 13171464,
|
2577 |
+
"step": 321
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"epoch": 5.862385321100917,
|
2581 |
+
"grad_norm": 0.41457998752593994,
|
2582 |
+
"learning_rate": 3.981204871634827e-05,
|
2583 |
+
"loss": 0.214,
|
2584 |
+
"num_input_tokens_seen": 13225240,
|
2585 |
+
"step": 322
|
2586 |
+
},
|
2587 |
+
{
|
2588 |
+
"epoch": 5.8807339449541285,
|
2589 |
+
"grad_norm": 0.4047159254550934,
|
2590 |
+
"learning_rate": 3.9753402430444116e-05,
|
2591 |
+
"loss": 0.1907,
|
2592 |
+
"num_input_tokens_seen": 13275848,
|
2593 |
+
"step": 323
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"epoch": 5.89908256880734,
|
2597 |
+
"grad_norm": 0.4578211307525635,
|
2598 |
+
"learning_rate": 3.969463130731183e-05,
|
2599 |
+
"loss": 0.27,
|
2600 |
+
"num_input_tokens_seen": 13311096,
|
2601 |
+
"step": 324
|
2602 |
+
}
|
2603 |
+
],
|
2604 |
+
"logging_steps": 1.0,
|
2605 |
+
"max_steps": 1080,
|
2606 |
+
"num_input_tokens_seen": 13311096,
|
2607 |
+
"num_train_epochs": 20,
|
2608 |
+
"save_steps": 54,
|
2609 |
+
"stateful_callbacks": {
|
2610 |
+
"TrainerControl": {
|
2611 |
+
"args": {
|
2612 |
+
"should_epoch_stop": false,
|
2613 |
+
"should_evaluate": false,
|
2614 |
+
"should_log": false,
|
2615 |
+
"should_save": true,
|
2616 |
+
"should_training_stop": false
|
2617 |
+
},
|
2618 |
+
"attributes": {}
|
2619 |
+
}
|
2620 |
+
},
|
2621 |
+
"total_flos": 1.1229463256131174e+18,
|
2622 |
+
"train_batch_size": 1,
|
2623 |
+
"trial_name": null,
|
2624 |
+
"trial_params": null
|
2625 |
+
}
|
checkpoint-378/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-378/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"up_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"o_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-378/added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
checkpoint-378/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-378/special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
checkpoint-378/tokenizer_config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 15000,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"padding_side": "right",
|
206 |
+
"split_special_tokens": false,
|
207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
+
"unk_token": null
|
209 |
+
}
|
checkpoint-378/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-432/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"up_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"o_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-432/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-432/special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
checkpoint-432/tokenizer_config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 15000,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"padding_side": "right",
|
206 |
+
"split_special_tokens": false,
|
207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
+
"unk_token": null
|
209 |
+
}
|
checkpoint-432/trainer_state.json
ADDED
@@ -0,0 +1,3489 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.862385321100917,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 432,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01834862385321101,
|
13 |
+
"grad_norm": 0.04378490149974823,
|
14 |
+
"learning_rate": 4.999989423013716e-05,
|
15 |
+
"loss": 0.6713,
|
16 |
+
"num_input_tokens_seen": 44136,
|
17 |
+
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.03669724770642202,
|
21 |
+
"grad_norm": 0.040646992623806,
|
22 |
+
"learning_rate": 4.999957692144361e-05,
|
23 |
+
"loss": 0.533,
|
24 |
+
"num_input_tokens_seen": 83096,
|
25 |
+
"step": 2
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 0.05504587155963303,
|
29 |
+
"grad_norm": 0.04658753052353859,
|
30 |
+
"learning_rate": 4.999904807660428e-05,
|
31 |
+
"loss": 0.6048,
|
32 |
+
"num_input_tokens_seen": 122112,
|
33 |
+
"step": 3
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.07339449541284404,
|
37 |
+
"grad_norm": 0.04322144016623497,
|
38 |
+
"learning_rate": 4.999830770009406e-05,
|
39 |
+
"loss": 0.4948,
|
40 |
+
"num_input_tokens_seen": 163064,
|
41 |
+
"step": 4
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 0.09174311926605505,
|
45 |
+
"grad_norm": 0.06536195427179337,
|
46 |
+
"learning_rate": 4.999735579817769e-05,
|
47 |
+
"loss": 0.6607,
|
48 |
+
"num_input_tokens_seen": 203808,
|
49 |
+
"step": 5
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"epoch": 0.11009174311926606,
|
53 |
+
"grad_norm": 0.059904925525188446,
|
54 |
+
"learning_rate": 4.9996192378909786e-05,
|
55 |
+
"loss": 0.5802,
|
56 |
+
"num_input_tokens_seen": 241824,
|
57 |
+
"step": 6
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.12844036697247707,
|
61 |
+
"grad_norm": 0.19818365573883057,
|
62 |
+
"learning_rate": 4.999481745213471e-05,
|
63 |
+
"loss": 0.5148,
|
64 |
+
"num_input_tokens_seen": 287608,
|
65 |
+
"step": 7
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.14678899082568808,
|
69 |
+
"grad_norm": 0.05985472351312637,
|
70 |
+
"learning_rate": 4.9993231029486544e-05,
|
71 |
+
"loss": 0.5714,
|
72 |
+
"num_input_tokens_seen": 325320,
|
73 |
+
"step": 8
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.1651376146788991,
|
77 |
+
"grad_norm": 0.061375778168439865,
|
78 |
+
"learning_rate": 4.999143312438893e-05,
|
79 |
+
"loss": 0.6812,
|
80 |
+
"num_input_tokens_seen": 369848,
|
81 |
+
"step": 9
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.1834862385321101,
|
85 |
+
"grad_norm": 0.06196414306759834,
|
86 |
+
"learning_rate": 4.998942375205502e-05,
|
87 |
+
"loss": 0.5358,
|
88 |
+
"num_input_tokens_seen": 415104,
|
89 |
+
"step": 10
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.2018348623853211,
|
93 |
+
"grad_norm": 0.07861393690109253,
|
94 |
+
"learning_rate": 4.9987202929487275e-05,
|
95 |
+
"loss": 0.6527,
|
96 |
+
"num_input_tokens_seen": 467224,
|
97 |
+
"step": 11
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.22018348623853212,
|
101 |
+
"grad_norm": 0.05596446990966797,
|
102 |
+
"learning_rate": 4.99847706754774e-05,
|
103 |
+
"loss": 0.5354,
|
104 |
+
"num_input_tokens_seen": 502824,
|
105 |
+
"step": 12
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.23853211009174313,
|
109 |
+
"grad_norm": 0.05289844051003456,
|
110 |
+
"learning_rate": 4.998212701060612e-05,
|
111 |
+
"loss": 0.5263,
|
112 |
+
"num_input_tokens_seen": 544744,
|
113 |
+
"step": 13
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.25688073394495414,
|
117 |
+
"grad_norm": 0.04996591433882713,
|
118 |
+
"learning_rate": 4.997927195724303e-05,
|
119 |
+
"loss": 0.5536,
|
120 |
+
"num_input_tokens_seen": 591136,
|
121 |
+
"step": 14
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.27522935779816515,
|
125 |
+
"grad_norm": 0.05822828412055969,
|
126 |
+
"learning_rate": 4.997620553954645e-05,
|
127 |
+
"loss": 0.6106,
|
128 |
+
"num_input_tokens_seen": 629664,
|
129 |
+
"step": 15
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.29357798165137616,
|
133 |
+
"grad_norm": 0.06353770196437836,
|
134 |
+
"learning_rate": 4.997292778346312e-05,
|
135 |
+
"loss": 0.5129,
|
136 |
+
"num_input_tokens_seen": 663392,
|
137 |
+
"step": 16
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.3119266055045872,
|
141 |
+
"grad_norm": 0.07256966829299927,
|
142 |
+
"learning_rate": 4.996943871672807e-05,
|
143 |
+
"loss": 0.6377,
|
144 |
+
"num_input_tokens_seen": 698360,
|
145 |
+
"step": 17
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.3302752293577982,
|
149 |
+
"grad_norm": 0.055458713322877884,
|
150 |
+
"learning_rate": 4.996573836886435e-05,
|
151 |
+
"loss": 0.4083,
|
152 |
+
"num_input_tokens_seen": 737520,
|
153 |
+
"step": 18
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.3486238532110092,
|
157 |
+
"grad_norm": 0.07792335003614426,
|
158 |
+
"learning_rate": 4.9961826771182784e-05,
|
159 |
+
"loss": 0.6086,
|
160 |
+
"num_input_tokens_seen": 768056,
|
161 |
+
"step": 19
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.3669724770642202,
|
165 |
+
"grad_norm": 0.06627275049686432,
|
166 |
+
"learning_rate": 4.995770395678171e-05,
|
167 |
+
"loss": 0.4591,
|
168 |
+
"num_input_tokens_seen": 806256,
|
169 |
+
"step": 20
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.3853211009174312,
|
173 |
+
"grad_norm": 0.05830290913581848,
|
174 |
+
"learning_rate": 4.9953369960546676e-05,
|
175 |
+
"loss": 0.3731,
|
176 |
+
"num_input_tokens_seen": 842336,
|
177 |
+
"step": 21
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.4036697247706422,
|
181 |
+
"grad_norm": 0.07277437299489975,
|
182 |
+
"learning_rate": 4.9948824819150185e-05,
|
183 |
+
"loss": 0.6243,
|
184 |
+
"num_input_tokens_seen": 876672,
|
185 |
+
"step": 22
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.42201834862385323,
|
189 |
+
"grad_norm": 0.07477546483278275,
|
190 |
+
"learning_rate": 4.994406857105136e-05,
|
191 |
+
"loss": 0.5788,
|
192 |
+
"num_input_tokens_seen": 915192,
|
193 |
+
"step": 23
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.44036697247706424,
|
197 |
+
"grad_norm": 0.06912907212972641,
|
198 |
+
"learning_rate": 4.993910125649561e-05,
|
199 |
+
"loss": 0.4753,
|
200 |
+
"num_input_tokens_seen": 951904,
|
201 |
+
"step": 24
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.45871559633027525,
|
205 |
+
"grad_norm": 0.0655476376414299,
|
206 |
+
"learning_rate": 4.993392291751431e-05,
|
207 |
+
"loss": 0.4518,
|
208 |
+
"num_input_tokens_seen": 1001816,
|
209 |
+
"step": 25
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.47706422018348627,
|
213 |
+
"grad_norm": 0.06466512382030487,
|
214 |
+
"learning_rate": 4.992853359792444e-05,
|
215 |
+
"loss": 0.5638,
|
216 |
+
"num_input_tokens_seen": 1053064,
|
217 |
+
"step": 26
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.4954128440366973,
|
221 |
+
"grad_norm": 0.0645688995718956,
|
222 |
+
"learning_rate": 4.99229333433282e-05,
|
223 |
+
"loss": 0.4644,
|
224 |
+
"num_input_tokens_seen": 1086688,
|
225 |
+
"step": 27
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.5137614678899083,
|
229 |
+
"grad_norm": 0.07181251049041748,
|
230 |
+
"learning_rate": 4.9917122201112656e-05,
|
231 |
+
"loss": 0.6191,
|
232 |
+
"num_input_tokens_seen": 1134824,
|
233 |
+
"step": 28
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.5321100917431193,
|
237 |
+
"grad_norm": 0.07322589308023453,
|
238 |
+
"learning_rate": 4.9911100220449293e-05,
|
239 |
+
"loss": 0.6752,
|
240 |
+
"num_input_tokens_seen": 1172072,
|
241 |
+
"step": 29
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.5504587155963303,
|
245 |
+
"grad_norm": 0.06396070122718811,
|
246 |
+
"learning_rate": 4.990486745229364e-05,
|
247 |
+
"loss": 0.3587,
|
248 |
+
"num_input_tokens_seen": 1211096,
|
249 |
+
"step": 30
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.5688073394495413,
|
253 |
+
"grad_norm": 0.07803395390510559,
|
254 |
+
"learning_rate": 4.989842394938482e-05,
|
255 |
+
"loss": 0.459,
|
256 |
+
"num_input_tokens_seen": 1259456,
|
257 |
+
"step": 31
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.5871559633027523,
|
261 |
+
"grad_norm": 0.05974648892879486,
|
262 |
+
"learning_rate": 4.989176976624511e-05,
|
263 |
+
"loss": 0.4148,
|
264 |
+
"num_input_tokens_seen": 1306944,
|
265 |
+
"step": 32
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.6055045871559633,
|
269 |
+
"grad_norm": 0.09784268587827682,
|
270 |
+
"learning_rate": 4.988490495917947e-05,
|
271 |
+
"loss": 0.539,
|
272 |
+
"num_input_tokens_seen": 1353744,
|
273 |
+
"step": 33
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.6238532110091743,
|
277 |
+
"grad_norm": 0.09906516224145889,
|
278 |
+
"learning_rate": 4.987782958627508e-05,
|
279 |
+
"loss": 0.5453,
|
280 |
+
"num_input_tokens_seen": 1394736,
|
281 |
+
"step": 34
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.6422018348623854,
|
285 |
+
"grad_norm": 0.08984062820672989,
|
286 |
+
"learning_rate": 4.987054370740083e-05,
|
287 |
+
"loss": 0.468,
|
288 |
+
"num_input_tokens_seen": 1442048,
|
289 |
+
"step": 35
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.6605504587155964,
|
293 |
+
"grad_norm": 0.08672655373811722,
|
294 |
+
"learning_rate": 4.9863047384206835e-05,
|
295 |
+
"loss": 0.4078,
|
296 |
+
"num_input_tokens_seen": 1478440,
|
297 |
+
"step": 36
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.6788990825688074,
|
301 |
+
"grad_norm": 0.1327345073223114,
|
302 |
+
"learning_rate": 4.9855340680123905e-05,
|
303 |
+
"loss": 0.5299,
|
304 |
+
"num_input_tokens_seen": 1525992,
|
305 |
+
"step": 37
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 0.6972477064220184,
|
309 |
+
"grad_norm": 0.09178602695465088,
|
310 |
+
"learning_rate": 4.9847423660363e-05,
|
311 |
+
"loss": 0.439,
|
312 |
+
"num_input_tokens_seen": 1555608,
|
313 |
+
"step": 38
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.7155963302752294,
|
317 |
+
"grad_norm": 0.09418320655822754,
|
318 |
+
"learning_rate": 4.983929639191469e-05,
|
319 |
+
"loss": 0.5337,
|
320 |
+
"num_input_tokens_seen": 1597392,
|
321 |
+
"step": 39
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.7339449541284404,
|
325 |
+
"grad_norm": 0.08294719457626343,
|
326 |
+
"learning_rate": 4.983095894354858e-05,
|
327 |
+
"loss": 0.4536,
|
328 |
+
"num_input_tokens_seen": 1649656,
|
329 |
+
"step": 40
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 0.7522935779816514,
|
333 |
+
"grad_norm": 0.09774205833673477,
|
334 |
+
"learning_rate": 4.982241138581273e-05,
|
335 |
+
"loss": 0.5221,
|
336 |
+
"num_input_tokens_seen": 1695952,
|
337 |
+
"step": 41
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 0.7706422018348624,
|
341 |
+
"grad_norm": 0.09319107979536057,
|
342 |
+
"learning_rate": 4.9813653791033057e-05,
|
343 |
+
"loss": 0.4279,
|
344 |
+
"num_input_tokens_seen": 1737224,
|
345 |
+
"step": 42
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.7889908256880734,
|
349 |
+
"grad_norm": 0.09561405330896378,
|
350 |
+
"learning_rate": 4.980468623331273e-05,
|
351 |
+
"loss": 0.5121,
|
352 |
+
"num_input_tokens_seen": 1772320,
|
353 |
+
"step": 43
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.8073394495412844,
|
357 |
+
"grad_norm": 0.08274025470018387,
|
358 |
+
"learning_rate": 4.979550878853154e-05,
|
359 |
+
"loss": 0.54,
|
360 |
+
"num_input_tokens_seen": 1823888,
|
361 |
+
"step": 44
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.8256880733944955,
|
365 |
+
"grad_norm": 0.08728913217782974,
|
366 |
+
"learning_rate": 4.9786121534345265e-05,
|
367 |
+
"loss": 0.4488,
|
368 |
+
"num_input_tokens_seen": 1872488,
|
369 |
+
"step": 45
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.8440366972477065,
|
373 |
+
"grad_norm": 0.0787016749382019,
|
374 |
+
"learning_rate": 4.9776524550184965e-05,
|
375 |
+
"loss": 0.4353,
|
376 |
+
"num_input_tokens_seen": 1924744,
|
377 |
+
"step": 46
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.8623853211009175,
|
381 |
+
"grad_norm": 0.10952188074588776,
|
382 |
+
"learning_rate": 4.97667179172564e-05,
|
383 |
+
"loss": 0.4784,
|
384 |
+
"num_input_tokens_seen": 1959936,
|
385 |
+
"step": 47
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 0.8807339449541285,
|
389 |
+
"grad_norm": 0.08525826781988144,
|
390 |
+
"learning_rate": 4.975670171853926e-05,
|
391 |
+
"loss": 0.3586,
|
392 |
+
"num_input_tokens_seen": 2003896,
|
393 |
+
"step": 48
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.8990825688073395,
|
397 |
+
"grad_norm": 0.10409987717866898,
|
398 |
+
"learning_rate": 4.9746476038786496e-05,
|
399 |
+
"loss": 0.4451,
|
400 |
+
"num_input_tokens_seen": 2047632,
|
401 |
+
"step": 49
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.9174311926605505,
|
405 |
+
"grad_norm": 0.0782993957400322,
|
406 |
+
"learning_rate": 4.973604096452361e-05,
|
407 |
+
"loss": 0.3591,
|
408 |
+
"num_input_tokens_seen": 2096928,
|
409 |
+
"step": 50
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.9357798165137615,
|
413 |
+
"grad_norm": 0.09829951077699661,
|
414 |
+
"learning_rate": 4.9725396584047925e-05,
|
415 |
+
"loss": 0.3415,
|
416 |
+
"num_input_tokens_seen": 2129536,
|
417 |
+
"step": 51
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.9541284403669725,
|
421 |
+
"grad_norm": 0.10606162995100021,
|
422 |
+
"learning_rate": 4.971454298742779e-05,
|
423 |
+
"loss": 0.3758,
|
424 |
+
"num_input_tokens_seen": 2169144,
|
425 |
+
"step": 52
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.9724770642201835,
|
429 |
+
"grad_norm": 0.09280356764793396,
|
430 |
+
"learning_rate": 4.97034802665019e-05,
|
431 |
+
"loss": 0.485,
|
432 |
+
"num_input_tokens_seen": 2207720,
|
433 |
+
"step": 53
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 0.9908256880733946,
|
437 |
+
"grad_norm": 0.11888203024864197,
|
438 |
+
"learning_rate": 4.9692208514878444e-05,
|
439 |
+
"loss": 0.3469,
|
440 |
+
"num_input_tokens_seen": 2236392,
|
441 |
+
"step": 54
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 1.0,
|
445 |
+
"grad_norm": 0.13222463428974152,
|
446 |
+
"learning_rate": 4.9680727827934354e-05,
|
447 |
+
"loss": 0.4284,
|
448 |
+
"num_input_tokens_seen": 2259088,
|
449 |
+
"step": 55
|
450 |
+
},
|
451 |
+
{
|
452 |
+
"epoch": 1.018348623853211,
|
453 |
+
"grad_norm": 0.10572745651006699,
|
454 |
+
"learning_rate": 4.966903830281449e-05,
|
455 |
+
"loss": 0.4186,
|
456 |
+
"num_input_tokens_seen": 2298496,
|
457 |
+
"step": 56
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 1.036697247706422,
|
461 |
+
"grad_norm": 0.11462350189685822,
|
462 |
+
"learning_rate": 4.965714003843079e-05,
|
463 |
+
"loss": 0.4696,
|
464 |
+
"num_input_tokens_seen": 2333016,
|
465 |
+
"step": 57
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.0550458715596331,
|
469 |
+
"grad_norm": 0.11215240508317947,
|
470 |
+
"learning_rate": 4.9645033135461494e-05,
|
471 |
+
"loss": 0.3905,
|
472 |
+
"num_input_tokens_seen": 2367992,
|
473 |
+
"step": 58
|
474 |
+
},
|
475 |
+
{
|
476 |
+
"epoch": 1.073394495412844,
|
477 |
+
"grad_norm": 0.0973561555147171,
|
478 |
+
"learning_rate": 4.963271769635024e-05,
|
479 |
+
"loss": 0.3588,
|
480 |
+
"num_input_tokens_seen": 2415328,
|
481 |
+
"step": 59
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 1.091743119266055,
|
485 |
+
"grad_norm": 0.10240709036588669,
|
486 |
+
"learning_rate": 4.962019382530521e-05,
|
487 |
+
"loss": 0.5532,
|
488 |
+
"num_input_tokens_seen": 2454792,
|
489 |
+
"step": 60
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.110091743119266,
|
493 |
+
"grad_norm": 0.0959337130188942,
|
494 |
+
"learning_rate": 4.9607461628298244e-05,
|
495 |
+
"loss": 0.331,
|
496 |
+
"num_input_tokens_seen": 2503072,
|
497 |
+
"step": 61
|
498 |
+
},
|
499 |
+
{
|
500 |
+
"epoch": 1.1284403669724772,
|
501 |
+
"grad_norm": 0.10228750854730606,
|
502 |
+
"learning_rate": 4.9594521213063974e-05,
|
503 |
+
"loss": 0.3728,
|
504 |
+
"num_input_tokens_seen": 2546960,
|
505 |
+
"step": 62
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 1.146788990825688,
|
509 |
+
"grad_norm": 0.09403488785028458,
|
510 |
+
"learning_rate": 4.958137268909887e-05,
|
511 |
+
"loss": 0.4695,
|
512 |
+
"num_input_tokens_seen": 2595432,
|
513 |
+
"step": 63
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 1.165137614678899,
|
517 |
+
"grad_norm": 0.11396344751119614,
|
518 |
+
"learning_rate": 4.9568016167660334e-05,
|
519 |
+
"loss": 0.3653,
|
520 |
+
"num_input_tokens_seen": 2633912,
|
521 |
+
"step": 64
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 1.18348623853211,
|
525 |
+
"grad_norm": 0.09487481415271759,
|
526 |
+
"learning_rate": 4.9554451761765766e-05,
|
527 |
+
"loss": 0.3498,
|
528 |
+
"num_input_tokens_seen": 2680792,
|
529 |
+
"step": 65
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 1.2018348623853212,
|
533 |
+
"grad_norm": 0.1249895691871643,
|
534 |
+
"learning_rate": 4.9540679586191605e-05,
|
535 |
+
"loss": 0.4053,
|
536 |
+
"num_input_tokens_seen": 2716584,
|
537 |
+
"step": 66
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 1.2201834862385321,
|
541 |
+
"grad_norm": 0.12268221378326416,
|
542 |
+
"learning_rate": 4.952669975747232e-05,
|
543 |
+
"loss": 0.4189,
|
544 |
+
"num_input_tokens_seen": 2757088,
|
545 |
+
"step": 67
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 1.238532110091743,
|
549 |
+
"grad_norm": 0.12126032263040543,
|
550 |
+
"learning_rate": 4.951251239389948e-05,
|
551 |
+
"loss": 0.4994,
|
552 |
+
"num_input_tokens_seen": 2795664,
|
553 |
+
"step": 68
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"epoch": 1.2568807339449541,
|
557 |
+
"grad_norm": 0.1069057360291481,
|
558 |
+
"learning_rate": 4.949811761552074e-05,
|
559 |
+
"loss": 0.3275,
|
560 |
+
"num_input_tokens_seen": 2840936,
|
561 |
+
"step": 69
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 1.2752293577981653,
|
565 |
+
"grad_norm": 0.10893313586711884,
|
566 |
+
"learning_rate": 4.948351554413879e-05,
|
567 |
+
"loss": 0.4366,
|
568 |
+
"num_input_tokens_seen": 2886768,
|
569 |
+
"step": 70
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 1.2935779816513762,
|
573 |
+
"grad_norm": 0.12898756563663483,
|
574 |
+
"learning_rate": 4.9468706303310355e-05,
|
575 |
+
"loss": 0.3916,
|
576 |
+
"num_input_tokens_seen": 2919328,
|
577 |
+
"step": 71
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 1.311926605504587,
|
581 |
+
"grad_norm": 0.12405356019735336,
|
582 |
+
"learning_rate": 4.9453690018345144e-05,
|
583 |
+
"loss": 0.3249,
|
584 |
+
"num_input_tokens_seen": 2966744,
|
585 |
+
"step": 72
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 1.3302752293577982,
|
589 |
+
"grad_norm": 0.13137595355510712,
|
590 |
+
"learning_rate": 4.943846681630479e-05,
|
591 |
+
"loss": 0.3956,
|
592 |
+
"num_input_tokens_seen": 3007248,
|
593 |
+
"step": 73
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 1.3486238532110093,
|
597 |
+
"grad_norm": 0.13920250535011292,
|
598 |
+
"learning_rate": 4.942303682600178e-05,
|
599 |
+
"loss": 0.3956,
|
600 |
+
"num_input_tokens_seen": 3050960,
|
601 |
+
"step": 74
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 1.3669724770642202,
|
605 |
+
"grad_norm": 0.1255589872598648,
|
606 |
+
"learning_rate": 4.940740017799833e-05,
|
607 |
+
"loss": 0.3773,
|
608 |
+
"num_input_tokens_seen": 3088592,
|
609 |
+
"step": 75
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 1.385321100917431,
|
613 |
+
"grad_norm": 0.10222747176885605,
|
614 |
+
"learning_rate": 4.939155700460536e-05,
|
615 |
+
"loss": 0.4,
|
616 |
+
"num_input_tokens_seen": 3153520,
|
617 |
+
"step": 76
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 1.4036697247706422,
|
621 |
+
"grad_norm": 0.13205283880233765,
|
622 |
+
"learning_rate": 4.9375507439881266e-05,
|
623 |
+
"loss": 0.4343,
|
624 |
+
"num_input_tokens_seen": 3199272,
|
625 |
+
"step": 77
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 1.4220183486238533,
|
629 |
+
"grad_norm": 0.11005694419145584,
|
630 |
+
"learning_rate": 4.9359251619630886e-05,
|
631 |
+
"loss": 0.3881,
|
632 |
+
"num_input_tokens_seen": 3247128,
|
633 |
+
"step": 78
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 1.4403669724770642,
|
637 |
+
"grad_norm": 0.14799247682094574,
|
638 |
+
"learning_rate": 4.9342789681404275e-05,
|
639 |
+
"loss": 0.3972,
|
640 |
+
"num_input_tokens_seen": 3294192,
|
641 |
+
"step": 79
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 1.4587155963302751,
|
645 |
+
"grad_norm": 0.1279418021440506,
|
646 |
+
"learning_rate": 4.9326121764495596e-05,
|
647 |
+
"loss": 0.3438,
|
648 |
+
"num_input_tokens_seen": 3329736,
|
649 |
+
"step": 80
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 1.4770642201834863,
|
653 |
+
"grad_norm": 0.11036807298660278,
|
654 |
+
"learning_rate": 4.9309248009941914e-05,
|
655 |
+
"loss": 0.3189,
|
656 |
+
"num_input_tokens_seen": 3371376,
|
657 |
+
"step": 81
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 1.4954128440366974,
|
661 |
+
"grad_norm": 0.11855707317590714,
|
662 |
+
"learning_rate": 4.9292168560522014e-05,
|
663 |
+
"loss": 0.401,
|
664 |
+
"num_input_tokens_seen": 3412368,
|
665 |
+
"step": 82
|
666 |
+
},
|
667 |
+
{
|
668 |
+
"epoch": 1.5137614678899083,
|
669 |
+
"grad_norm": 0.13195356726646423,
|
670 |
+
"learning_rate": 4.9274883560755156e-05,
|
671 |
+
"loss": 0.4973,
|
672 |
+
"num_input_tokens_seen": 3455000,
|
673 |
+
"step": 83
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 1.5321100917431192,
|
677 |
+
"grad_norm": 0.1462787538766861,
|
678 |
+
"learning_rate": 4.925739315689991e-05,
|
679 |
+
"loss": 0.3768,
|
680 |
+
"num_input_tokens_seen": 3488960,
|
681 |
+
"step": 84
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 1.5504587155963303,
|
685 |
+
"grad_norm": 0.13765974342823029,
|
686 |
+
"learning_rate": 4.92396974969529e-05,
|
687 |
+
"loss": 0.2999,
|
688 |
+
"num_input_tokens_seen": 3521320,
|
689 |
+
"step": 85
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 1.5688073394495414,
|
693 |
+
"grad_norm": 0.15276113152503967,
|
694 |
+
"learning_rate": 4.9221796730647516e-05,
|
695 |
+
"loss": 0.3638,
|
696 |
+
"num_input_tokens_seen": 3559464,
|
697 |
+
"step": 86
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 1.5871559633027523,
|
701 |
+
"grad_norm": 0.1441674381494522,
|
702 |
+
"learning_rate": 4.92036910094527e-05,
|
703 |
+
"loss": 0.3919,
|
704 |
+
"num_input_tokens_seen": 3598080,
|
705 |
+
"step": 87
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 1.6055045871559632,
|
709 |
+
"grad_norm": 0.1780252456665039,
|
710 |
+
"learning_rate": 4.9185380486571595e-05,
|
711 |
+
"loss": 0.3626,
|
712 |
+
"num_input_tokens_seen": 3630064,
|
713 |
+
"step": 88
|
714 |
+
},
|
715 |
+
{
|
716 |
+
"epoch": 1.6238532110091743,
|
717 |
+
"grad_norm": 0.16947726905345917,
|
718 |
+
"learning_rate": 4.916686531694035e-05,
|
719 |
+
"loss": 0.3439,
|
720 |
+
"num_input_tokens_seen": 3661408,
|
721 |
+
"step": 89
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 1.6422018348623855,
|
725 |
+
"grad_norm": 0.1552971601486206,
|
726 |
+
"learning_rate": 4.914814565722671e-05,
|
727 |
+
"loss": 0.3236,
|
728 |
+
"num_input_tokens_seen": 3695480,
|
729 |
+
"step": 90
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 1.6605504587155964,
|
733 |
+
"grad_norm": 0.14925938844680786,
|
734 |
+
"learning_rate": 4.912922166582874e-05,
|
735 |
+
"loss": 0.4255,
|
736 |
+
"num_input_tokens_seen": 3734560,
|
737 |
+
"step": 91
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 1.6788990825688073,
|
741 |
+
"grad_norm": 0.1332874596118927,
|
742 |
+
"learning_rate": 4.9110093502873476e-05,
|
743 |
+
"loss": 0.3061,
|
744 |
+
"num_input_tokens_seen": 3773112,
|
745 |
+
"step": 92
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 1.6972477064220184,
|
749 |
+
"grad_norm": 0.15471243858337402,
|
750 |
+
"learning_rate": 4.909076133021557e-05,
|
751 |
+
"loss": 0.3275,
|
752 |
+
"num_input_tokens_seen": 3813392,
|
753 |
+
"step": 93
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 1.7155963302752295,
|
757 |
+
"grad_norm": 0.16010524332523346,
|
758 |
+
"learning_rate": 4.907122531143594e-05,
|
759 |
+
"loss": 0.4179,
|
760 |
+
"num_input_tokens_seen": 3856416,
|
761 |
+
"step": 94
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 1.7339449541284404,
|
765 |
+
"grad_norm": 0.13423003256320953,
|
766 |
+
"learning_rate": 4.905148561184033e-05,
|
767 |
+
"loss": 0.3593,
|
768 |
+
"num_input_tokens_seen": 3899472,
|
769 |
+
"step": 95
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 1.7522935779816513,
|
773 |
+
"grad_norm": 0.14900773763656616,
|
774 |
+
"learning_rate": 4.9031542398457974e-05,
|
775 |
+
"loss": 0.5007,
|
776 |
+
"num_input_tokens_seen": 3962976,
|
777 |
+
"step": 96
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 1.7706422018348624,
|
781 |
+
"grad_norm": 0.15728624165058136,
|
782 |
+
"learning_rate": 4.9011395840040144e-05,
|
783 |
+
"loss": 0.3484,
|
784 |
+
"num_input_tokens_seen": 4000696,
|
785 |
+
"step": 97
|
786 |
+
},
|
787 |
+
{
|
788 |
+
"epoch": 1.7889908256880735,
|
789 |
+
"grad_norm": 0.11092367768287659,
|
790 |
+
"learning_rate": 4.8991046107058735e-05,
|
791 |
+
"loss": 0.2889,
|
792 |
+
"num_input_tokens_seen": 4045256,
|
793 |
+
"step": 98
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 1.8073394495412844,
|
797 |
+
"grad_norm": 0.1289113610982895,
|
798 |
+
"learning_rate": 4.8970493371704826e-05,
|
799 |
+
"loss": 0.2203,
|
800 |
+
"num_input_tokens_seen": 4076800,
|
801 |
+
"step": 99
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 1.8256880733944953,
|
805 |
+
"grad_norm": 0.18886639177799225,
|
806 |
+
"learning_rate": 4.894973780788722e-05,
|
807 |
+
"loss": 0.3966,
|
808 |
+
"num_input_tokens_seen": 4119840,
|
809 |
+
"step": 100
|
810 |
+
},
|
811 |
+
{
|
812 |
+
"epoch": 1.8440366972477065,
|
813 |
+
"grad_norm": 0.1563039869070053,
|
814 |
+
"learning_rate": 4.892877959123097e-05,
|
815 |
+
"loss": 0.4417,
|
816 |
+
"num_input_tokens_seen": 4165848,
|
817 |
+
"step": 101
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 1.8623853211009176,
|
821 |
+
"grad_norm": 0.16883380711078644,
|
822 |
+
"learning_rate": 4.890761889907589e-05,
|
823 |
+
"loss": 0.4258,
|
824 |
+
"num_input_tokens_seen": 4202824,
|
825 |
+
"step": 102
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 1.8807339449541285,
|
829 |
+
"grad_norm": 0.18241995573043823,
|
830 |
+
"learning_rate": 4.8886255910475054e-05,
|
831 |
+
"loss": 0.3952,
|
832 |
+
"num_input_tokens_seen": 4233888,
|
833 |
+
"step": 103
|
834 |
+
},
|
835 |
+
{
|
836 |
+
"epoch": 1.8990825688073394,
|
837 |
+
"grad_norm": 0.19913265109062195,
|
838 |
+
"learning_rate": 4.88646908061933e-05,
|
839 |
+
"loss": 0.3241,
|
840 |
+
"num_input_tokens_seen": 4267064,
|
841 |
+
"step": 104
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 1.9174311926605505,
|
845 |
+
"grad_norm": 0.18295545876026154,
|
846 |
+
"learning_rate": 4.884292376870567e-05,
|
847 |
+
"loss": 0.4239,
|
848 |
+
"num_input_tokens_seen": 4312536,
|
849 |
+
"step": 105
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 1.9357798165137616,
|
853 |
+
"grad_norm": 0.16657495498657227,
|
854 |
+
"learning_rate": 4.8820954982195905e-05,
|
855 |
+
"loss": 0.2579,
|
856 |
+
"num_input_tokens_seen": 4356656,
|
857 |
+
"step": 106
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 1.9541284403669725,
|
861 |
+
"grad_norm": 0.18504932522773743,
|
862 |
+
"learning_rate": 4.879878463255483e-05,
|
863 |
+
"loss": 0.44,
|
864 |
+
"num_input_tokens_seen": 4400216,
|
865 |
+
"step": 107
|
866 |
+
},
|
867 |
+
{
|
868 |
+
"epoch": 1.9724770642201834,
|
869 |
+
"grad_norm": 0.1923118382692337,
|
870 |
+
"learning_rate": 4.877641290737884e-05,
|
871 |
+
"loss": 0.2662,
|
872 |
+
"num_input_tokens_seen": 4436968,
|
873 |
+
"step": 108
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 1.9908256880733946,
|
877 |
+
"grad_norm": 0.19636788964271545,
|
878 |
+
"learning_rate": 4.875383999596828e-05,
|
879 |
+
"loss": 0.4211,
|
880 |
+
"num_input_tokens_seen": 4488232,
|
881 |
+
"step": 109
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 2.0,
|
885 |
+
"grad_norm": 0.3168099820613861,
|
886 |
+
"learning_rate": 4.873106608932585e-05,
|
887 |
+
"loss": 0.2499,
|
888 |
+
"num_input_tokens_seen": 4518176,
|
889 |
+
"step": 110
|
890 |
+
},
|
891 |
+
{
|
892 |
+
"epoch": 2.018348623853211,
|
893 |
+
"grad_norm": 0.14410308003425598,
|
894 |
+
"learning_rate": 4.8708091380154984e-05,
|
895 |
+
"loss": 0.2722,
|
896 |
+
"num_input_tokens_seen": 4570896,
|
897 |
+
"step": 111
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 2.036697247706422,
|
901 |
+
"grad_norm": 0.17840909957885742,
|
902 |
+
"learning_rate": 4.868491606285823e-05,
|
903 |
+
"loss": 0.2758,
|
904 |
+
"num_input_tokens_seen": 4613576,
|
905 |
+
"step": 112
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 2.055045871559633,
|
909 |
+
"grad_norm": 0.178523987531662,
|
910 |
+
"learning_rate": 4.866154033353561e-05,
|
911 |
+
"loss": 0.3361,
|
912 |
+
"num_input_tokens_seen": 4652896,
|
913 |
+
"step": 113
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 2.073394495412844,
|
917 |
+
"grad_norm": 0.17396725714206696,
|
918 |
+
"learning_rate": 4.8637964389982926e-05,
|
919 |
+
"loss": 0.2667,
|
920 |
+
"num_input_tokens_seen": 4694256,
|
921 |
+
"step": 114
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 2.091743119266055,
|
925 |
+
"grad_norm": 0.19471587240695953,
|
926 |
+
"learning_rate": 4.8614188431690125e-05,
|
927 |
+
"loss": 0.3628,
|
928 |
+
"num_input_tokens_seen": 4747552,
|
929 |
+
"step": 115
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 2.1100917431192663,
|
933 |
+
"grad_norm": 0.1722450852394104,
|
934 |
+
"learning_rate": 4.859021265983959e-05,
|
935 |
+
"loss": 0.3599,
|
936 |
+
"num_input_tokens_seen": 4794080,
|
937 |
+
"step": 116
|
938 |
+
},
|
939 |
+
{
|
940 |
+
"epoch": 2.128440366972477,
|
941 |
+
"grad_norm": 0.20137006044387817,
|
942 |
+
"learning_rate": 4.856603727730447e-05,
|
943 |
+
"loss": 0.4262,
|
944 |
+
"num_input_tokens_seen": 4847912,
|
945 |
+
"step": 117
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 2.146788990825688,
|
949 |
+
"grad_norm": 0.19395771622657776,
|
950 |
+
"learning_rate": 4.854166248864689e-05,
|
951 |
+
"loss": 0.3118,
|
952 |
+
"num_input_tokens_seen": 4885480,
|
953 |
+
"step": 118
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 2.165137614678899,
|
957 |
+
"grad_norm": 0.209548681974411,
|
958 |
+
"learning_rate": 4.85170885001163e-05,
|
959 |
+
"loss": 0.3725,
|
960 |
+
"num_input_tokens_seen": 4921240,
|
961 |
+
"step": 119
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 2.18348623853211,
|
965 |
+
"grad_norm": 0.18228279054164886,
|
966 |
+
"learning_rate": 4.849231551964771e-05,
|
967 |
+
"loss": 0.3816,
|
968 |
+
"num_input_tokens_seen": 4960224,
|
969 |
+
"step": 120
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 2.2018348623853212,
|
973 |
+
"grad_norm": 0.24349354207515717,
|
974 |
+
"learning_rate": 4.846734375685989e-05,
|
975 |
+
"loss": 0.3383,
|
976 |
+
"num_input_tokens_seen": 4990536,
|
977 |
+
"step": 121
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 2.220183486238532,
|
981 |
+
"grad_norm": 0.17600344121456146,
|
982 |
+
"learning_rate": 4.844217342305363e-05,
|
983 |
+
"loss": 0.3011,
|
984 |
+
"num_input_tokens_seen": 5044296,
|
985 |
+
"step": 122
|
986 |
+
},
|
987 |
+
{
|
988 |
+
"epoch": 2.238532110091743,
|
989 |
+
"grad_norm": 0.18766675889492035,
|
990 |
+
"learning_rate": 4.8416804731209945e-05,
|
991 |
+
"loss": 0.4458,
|
992 |
+
"num_input_tokens_seen": 5088368,
|
993 |
+
"step": 123
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 2.2568807339449544,
|
997 |
+
"grad_norm": 0.17657820880413055,
|
998 |
+
"learning_rate": 4.839123789598829e-05,
|
999 |
+
"loss": 0.2564,
|
1000 |
+
"num_input_tokens_seen": 5133472,
|
1001 |
+
"step": 124
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 2.2752293577981653,
|
1005 |
+
"grad_norm": 0.20606014132499695,
|
1006 |
+
"learning_rate": 4.836547313372471e-05,
|
1007 |
+
"loss": 0.313,
|
1008 |
+
"num_input_tokens_seen": 5167768,
|
1009 |
+
"step": 125
|
1010 |
+
},
|
1011 |
+
{
|
1012 |
+
"epoch": 2.293577981651376,
|
1013 |
+
"grad_norm": 0.23511061072349548,
|
1014 |
+
"learning_rate": 4.8339510662430046e-05,
|
1015 |
+
"loss": 0.2963,
|
1016 |
+
"num_input_tokens_seen": 5209400,
|
1017 |
+
"step": 126
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 2.311926605504587,
|
1021 |
+
"grad_norm": 0.18234293162822723,
|
1022 |
+
"learning_rate": 4.8313350701788054e-05,
|
1023 |
+
"loss": 0.2566,
|
1024 |
+
"num_input_tokens_seen": 5249360,
|
1025 |
+
"step": 127
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 2.330275229357798,
|
1029 |
+
"grad_norm": 0.2223992496728897,
|
1030 |
+
"learning_rate": 4.828699347315356e-05,
|
1031 |
+
"loss": 0.2833,
|
1032 |
+
"num_input_tokens_seen": 5300808,
|
1033 |
+
"step": 128
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 2.3486238532110093,
|
1037 |
+
"grad_norm": 0.23101739585399628,
|
1038 |
+
"learning_rate": 4.826043919955062e-05,
|
1039 |
+
"loss": 0.3099,
|
1040 |
+
"num_input_tokens_seen": 5332960,
|
1041 |
+
"step": 129
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 2.36697247706422,
|
1045 |
+
"grad_norm": 0.26640889048576355,
|
1046 |
+
"learning_rate": 4.823368810567056e-05,
|
1047 |
+
"loss": 0.3238,
|
1048 |
+
"num_input_tokens_seen": 5365008,
|
1049 |
+
"step": 130
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 2.385321100917431,
|
1053 |
+
"grad_norm": 0.2374572902917862,
|
1054 |
+
"learning_rate": 4.820674041787017e-05,
|
1055 |
+
"loss": 0.3153,
|
1056 |
+
"num_input_tokens_seen": 5400184,
|
1057 |
+
"step": 131
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"epoch": 2.4036697247706424,
|
1061 |
+
"grad_norm": 0.22812288999557495,
|
1062 |
+
"learning_rate": 4.817959636416969e-05,
|
1063 |
+
"loss": 0.2997,
|
1064 |
+
"num_input_tokens_seen": 5440320,
|
1065 |
+
"step": 132
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 2.4220183486238533,
|
1069 |
+
"grad_norm": 0.20079149305820465,
|
1070 |
+
"learning_rate": 4.815225617425095e-05,
|
1071 |
+
"loss": 0.2373,
|
1072 |
+
"num_input_tokens_seen": 5480832,
|
1073 |
+
"step": 133
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 2.4403669724770642,
|
1077 |
+
"grad_norm": 0.196709543466568,
|
1078 |
+
"learning_rate": 4.81247200794554e-05,
|
1079 |
+
"loss": 0.2456,
|
1080 |
+
"num_input_tokens_seen": 5526936,
|
1081 |
+
"step": 134
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 2.458715596330275,
|
1085 |
+
"grad_norm": 0.17305873334407806,
|
1086 |
+
"learning_rate": 4.8096988312782174e-05,
|
1087 |
+
"loss": 0.2099,
|
1088 |
+
"num_input_tokens_seen": 5566384,
|
1089 |
+
"step": 135
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 2.477064220183486,
|
1093 |
+
"grad_norm": 3.584635019302368,
|
1094 |
+
"learning_rate": 4.806906110888606e-05,
|
1095 |
+
"loss": 0.3485,
|
1096 |
+
"num_input_tokens_seen": 5629896,
|
1097 |
+
"step": 136
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 2.4954128440366974,
|
1101 |
+
"grad_norm": 0.23481500148773193,
|
1102 |
+
"learning_rate": 4.80409387040756e-05,
|
1103 |
+
"loss": 0.2231,
|
1104 |
+
"num_input_tokens_seen": 5674504,
|
1105 |
+
"step": 137
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 2.5137614678899083,
|
1109 |
+
"grad_norm": 0.27899855375289917,
|
1110 |
+
"learning_rate": 4.8012621336311016e-05,
|
1111 |
+
"loss": 0.4285,
|
1112 |
+
"num_input_tokens_seen": 5714000,
|
1113 |
+
"step": 138
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 2.532110091743119,
|
1117 |
+
"grad_norm": 0.24404938519001007,
|
1118 |
+
"learning_rate": 4.798410924520223e-05,
|
1119 |
+
"loss": 0.3343,
|
1120 |
+
"num_input_tokens_seen": 5756856,
|
1121 |
+
"step": 139
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 2.5504587155963305,
|
1125 |
+
"grad_norm": 0.26869162917137146,
|
1126 |
+
"learning_rate": 4.7955402672006854e-05,
|
1127 |
+
"loss": 0.2497,
|
1128 |
+
"num_input_tokens_seen": 5781192,
|
1129 |
+
"step": 140
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 2.5688073394495414,
|
1133 |
+
"grad_norm": 0.2057972550392151,
|
1134 |
+
"learning_rate": 4.79265018596281e-05,
|
1135 |
+
"loss": 0.2991,
|
1136 |
+
"num_input_tokens_seen": 5824024,
|
1137 |
+
"step": 141
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 2.5871559633027523,
|
1141 |
+
"grad_norm": 0.2184937596321106,
|
1142 |
+
"learning_rate": 4.789740705261278e-05,
|
1143 |
+
"loss": 0.2406,
|
1144 |
+
"num_input_tokens_seen": 5862584,
|
1145 |
+
"step": 142
|
1146 |
+
},
|
1147 |
+
{
|
1148 |
+
"epoch": 2.6055045871559632,
|
1149 |
+
"grad_norm": 0.23603741824626923,
|
1150 |
+
"learning_rate": 4.786811849714918e-05,
|
1151 |
+
"loss": 0.2722,
|
1152 |
+
"num_input_tokens_seen": 5897344,
|
1153 |
+
"step": 143
|
1154 |
+
},
|
1155 |
+
{
|
1156 |
+
"epoch": 2.623853211009174,
|
1157 |
+
"grad_norm": 0.22983981668949127,
|
1158 |
+
"learning_rate": 4.783863644106502e-05,
|
1159 |
+
"loss": 0.374,
|
1160 |
+
"num_input_tokens_seen": 5931736,
|
1161 |
+
"step": 144
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 2.6422018348623855,
|
1165 |
+
"grad_norm": 0.2825419306755066,
|
1166 |
+
"learning_rate": 4.780896113382536e-05,
|
1167 |
+
"loss": 0.3386,
|
1168 |
+
"num_input_tokens_seen": 5972784,
|
1169 |
+
"step": 145
|
1170 |
+
},
|
1171 |
+
{
|
1172 |
+
"epoch": 2.6605504587155964,
|
1173 |
+
"grad_norm": 0.4502134621143341,
|
1174 |
+
"learning_rate": 4.777909282653042e-05,
|
1175 |
+
"loss": 0.2289,
|
1176 |
+
"num_input_tokens_seen": 6018968,
|
1177 |
+
"step": 146
|
1178 |
+
},
|
1179 |
+
{
|
1180 |
+
"epoch": 2.6788990825688073,
|
1181 |
+
"grad_norm": 0.2428288459777832,
|
1182 |
+
"learning_rate": 4.7749031771913584e-05,
|
1183 |
+
"loss": 0.4061,
|
1184 |
+
"num_input_tokens_seen": 6062520,
|
1185 |
+
"step": 147
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 2.6972477064220186,
|
1189 |
+
"grad_norm": 0.2685629725456238,
|
1190 |
+
"learning_rate": 4.771877822433911e-05,
|
1191 |
+
"loss": 0.2198,
|
1192 |
+
"num_input_tokens_seen": 6087928,
|
1193 |
+
"step": 148
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 2.7155963302752295,
|
1197 |
+
"grad_norm": 0.24021446704864502,
|
1198 |
+
"learning_rate": 4.7688332439800096e-05,
|
1199 |
+
"loss": 0.34,
|
1200 |
+
"num_input_tokens_seen": 6134792,
|
1201 |
+
"step": 149
|
1202 |
+
},
|
1203 |
+
{
|
1204 |
+
"epoch": 2.7339449541284404,
|
1205 |
+
"grad_norm": 0.2568534314632416,
|
1206 |
+
"learning_rate": 4.765769467591625e-05,
|
1207 |
+
"loss": 0.3292,
|
1208 |
+
"num_input_tokens_seen": 6183296,
|
1209 |
+
"step": 150
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 2.7522935779816513,
|
1213 |
+
"grad_norm": 0.20823974907398224,
|
1214 |
+
"learning_rate": 4.762686519193175e-05,
|
1215 |
+
"loss": 0.2539,
|
1216 |
+
"num_input_tokens_seen": 6225840,
|
1217 |
+
"step": 151
|
1218 |
+
},
|
1219 |
+
{
|
1220 |
+
"epoch": 2.770642201834862,
|
1221 |
+
"grad_norm": 0.23333317041397095,
|
1222 |
+
"learning_rate": 4.759584424871302e-05,
|
1223 |
+
"loss": 0.3571,
|
1224 |
+
"num_input_tokens_seen": 6274760,
|
1225 |
+
"step": 152
|
1226 |
+
},
|
1227 |
+
{
|
1228 |
+
"epoch": 2.7889908256880735,
|
1229 |
+
"grad_norm": 0.20232398808002472,
|
1230 |
+
"learning_rate": 4.756463210874652e-05,
|
1231 |
+
"loss": 0.2783,
|
1232 |
+
"num_input_tokens_seen": 6326168,
|
1233 |
+
"step": 153
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 2.8073394495412844,
|
1237 |
+
"grad_norm": 0.3479433059692383,
|
1238 |
+
"learning_rate": 4.7533229036136553e-05,
|
1239 |
+
"loss": 0.2925,
|
1240 |
+
"num_input_tokens_seen": 6360312,
|
1241 |
+
"step": 154
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 2.8256880733944953,
|
1245 |
+
"grad_norm": 0.2659524083137512,
|
1246 |
+
"learning_rate": 4.750163529660303e-05,
|
1247 |
+
"loss": 0.2606,
|
1248 |
+
"num_input_tokens_seen": 6395496,
|
1249 |
+
"step": 155
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 2.8440366972477067,
|
1253 |
+
"grad_norm": 0.24823158979415894,
|
1254 |
+
"learning_rate": 4.7469851157479177e-05,
|
1255 |
+
"loss": 0.3721,
|
1256 |
+
"num_input_tokens_seen": 6437064,
|
1257 |
+
"step": 156
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 2.8623853211009176,
|
1261 |
+
"grad_norm": 0.32034072279930115,
|
1262 |
+
"learning_rate": 4.743787688770932e-05,
|
1263 |
+
"loss": 0.3931,
|
1264 |
+
"num_input_tokens_seen": 6477616,
|
1265 |
+
"step": 157
|
1266 |
+
},
|
1267 |
+
{
|
1268 |
+
"epoch": 2.8807339449541285,
|
1269 |
+
"grad_norm": 0.23295725882053375,
|
1270 |
+
"learning_rate": 4.740571275784659e-05,
|
1271 |
+
"loss": 0.2201,
|
1272 |
+
"num_input_tokens_seen": 6518680,
|
1273 |
+
"step": 158
|
1274 |
+
},
|
1275 |
+
{
|
1276 |
+
"epoch": 2.8990825688073394,
|
1277 |
+
"grad_norm": 0.2758423984050751,
|
1278 |
+
"learning_rate": 4.737335904005063e-05,
|
1279 |
+
"loss": 0.2579,
|
1280 |
+
"num_input_tokens_seen": 6549768,
|
1281 |
+
"step": 159
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 2.9174311926605503,
|
1285 |
+
"grad_norm": 0.26690953969955444,
|
1286 |
+
"learning_rate": 4.734081600808531e-05,
|
1287 |
+
"loss": 0.2575,
|
1288 |
+
"num_input_tokens_seen": 6581000,
|
1289 |
+
"step": 160
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"epoch": 2.9357798165137616,
|
1293 |
+
"grad_norm": 0.26657482981681824,
|
1294 |
+
"learning_rate": 4.730808393731639e-05,
|
1295 |
+
"loss": 0.2597,
|
1296 |
+
"num_input_tokens_seen": 6612632,
|
1297 |
+
"step": 161
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 2.9541284403669725,
|
1301 |
+
"grad_norm": 0.22647295892238617,
|
1302 |
+
"learning_rate": 4.72751631047092e-05,
|
1303 |
+
"loss": 0.3335,
|
1304 |
+
"num_input_tokens_seen": 6654288,
|
1305 |
+
"step": 162
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 2.9724770642201834,
|
1309 |
+
"grad_norm": 0.2863366901874542,
|
1310 |
+
"learning_rate": 4.72420537888263e-05,
|
1311 |
+
"loss": 0.374,
|
1312 |
+
"num_input_tokens_seen": 6707208,
|
1313 |
+
"step": 163
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 2.9908256880733948,
|
1317 |
+
"grad_norm": 0.2606408894062042,
|
1318 |
+
"learning_rate": 4.7208756269825104e-05,
|
1319 |
+
"loss": 0.3477,
|
1320 |
+
"num_input_tokens_seen": 6748448,
|
1321 |
+
"step": 164
|
1322 |
+
},
|
1323 |
+
{
|
1324 |
+
"epoch": 3.0,
|
1325 |
+
"grad_norm": 0.440924733877182,
|
1326 |
+
"learning_rate": 4.717527082945554e-05,
|
1327 |
+
"loss": 0.3214,
|
1328 |
+
"num_input_tokens_seen": 6777264,
|
1329 |
+
"step": 165
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 3.018348623853211,
|
1333 |
+
"grad_norm": 0.27583903074264526,
|
1334 |
+
"learning_rate": 4.714159775105765e-05,
|
1335 |
+
"loss": 0.2681,
|
1336 |
+
"num_input_tokens_seen": 6809456,
|
1337 |
+
"step": 166
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 3.036697247706422,
|
1341 |
+
"grad_norm": 0.2995987832546234,
|
1342 |
+
"learning_rate": 4.7107737319559176e-05,
|
1343 |
+
"loss": 0.2633,
|
1344 |
+
"num_input_tokens_seen": 6845768,
|
1345 |
+
"step": 167
|
1346 |
+
},
|
1347 |
+
{
|
1348 |
+
"epoch": 3.055045871559633,
|
1349 |
+
"grad_norm": 0.23999951779842377,
|
1350 |
+
"learning_rate": 4.707368982147318e-05,
|
1351 |
+
"loss": 0.1961,
|
1352 |
+
"num_input_tokens_seen": 6893056,
|
1353 |
+
"step": 168
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 3.073394495412844,
|
1357 |
+
"grad_norm": 0.23356525599956512,
|
1358 |
+
"learning_rate": 4.703945554489558e-05,
|
1359 |
+
"loss": 0.2836,
|
1360 |
+
"num_input_tokens_seen": 6932480,
|
1361 |
+
"step": 169
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 3.091743119266055,
|
1365 |
+
"grad_norm": 0.29919493198394775,
|
1366 |
+
"learning_rate": 4.700503477950278e-05,
|
1367 |
+
"loss": 0.2838,
|
1368 |
+
"num_input_tokens_seen": 6975992,
|
1369 |
+
"step": 170
|
1370 |
+
},
|
1371 |
+
{
|
1372 |
+
"epoch": 3.1100917431192663,
|
1373 |
+
"grad_norm": 0.3350690007209778,
|
1374 |
+
"learning_rate": 4.697042781654913e-05,
|
1375 |
+
"loss": 0.3489,
|
1376 |
+
"num_input_tokens_seen": 7021840,
|
1377 |
+
"step": 171
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 3.128440366972477,
|
1381 |
+
"grad_norm": 0.2837466895580292,
|
1382 |
+
"learning_rate": 4.693563494886455e-05,
|
1383 |
+
"loss": 0.3797,
|
1384 |
+
"num_input_tokens_seen": 7065192,
|
1385 |
+
"step": 172
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 3.146788990825688,
|
1389 |
+
"grad_norm": 0.24601787328720093,
|
1390 |
+
"learning_rate": 4.6900656470851964e-05,
|
1391 |
+
"loss": 0.2046,
|
1392 |
+
"num_input_tokens_seen": 7114544,
|
1393 |
+
"step": 173
|
1394 |
+
},
|
1395 |
+
{
|
1396 |
+
"epoch": 3.165137614678899,
|
1397 |
+
"grad_norm": 0.32290250062942505,
|
1398 |
+
"learning_rate": 4.6865492678484895e-05,
|
1399 |
+
"loss": 0.2596,
|
1400 |
+
"num_input_tokens_seen": 7152736,
|
1401 |
+
"step": 174
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 3.18348623853211,
|
1405 |
+
"grad_norm": 0.33591920137405396,
|
1406 |
+
"learning_rate": 4.68301438693049e-05,
|
1407 |
+
"loss": 0.3045,
|
1408 |
+
"num_input_tokens_seen": 7207464,
|
1409 |
+
"step": 175
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 3.2018348623853212,
|
1413 |
+
"grad_norm": 0.25471043586730957,
|
1414 |
+
"learning_rate": 4.679461034241906e-05,
|
1415 |
+
"loss": 0.2096,
|
1416 |
+
"num_input_tokens_seen": 7238640,
|
1417 |
+
"step": 176
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 3.220183486238532,
|
1421 |
+
"grad_norm": 0.31238994002342224,
|
1422 |
+
"learning_rate": 4.6758892398497494e-05,
|
1423 |
+
"loss": 0.2226,
|
1424 |
+
"num_input_tokens_seen": 7279112,
|
1425 |
+
"step": 177
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 3.238532110091743,
|
1429 |
+
"grad_norm": 0.35679712891578674,
|
1430 |
+
"learning_rate": 4.672299033977076e-05,
|
1431 |
+
"loss": 0.2403,
|
1432 |
+
"num_input_tokens_seen": 7311632,
|
1433 |
+
"step": 178
|
1434 |
+
},
|
1435 |
+
{
|
1436 |
+
"epoch": 3.2568807339449544,
|
1437 |
+
"grad_norm": 0.326914519071579,
|
1438 |
+
"learning_rate": 4.6686904470027316e-05,
|
1439 |
+
"loss": 0.2156,
|
1440 |
+
"num_input_tokens_seen": 7344864,
|
1441 |
+
"step": 179
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 3.2752293577981653,
|
1445 |
+
"grad_norm": 0.3293381929397583,
|
1446 |
+
"learning_rate": 4.665063509461097e-05,
|
1447 |
+
"loss": 0.238,
|
1448 |
+
"num_input_tokens_seen": 7389944,
|
1449 |
+
"step": 180
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 3.293577981651376,
|
1453 |
+
"grad_norm": 0.3313307762145996,
|
1454 |
+
"learning_rate": 4.661418252041827e-05,
|
1455 |
+
"loss": 0.2251,
|
1456 |
+
"num_input_tokens_seen": 7423672,
|
1457 |
+
"step": 181
|
1458 |
+
},
|
1459 |
+
{
|
1460 |
+
"epoch": 3.311926605504587,
|
1461 |
+
"grad_norm": 0.3328595459461212,
|
1462 |
+
"learning_rate": 4.657754705589591e-05,
|
1463 |
+
"loss": 0.2922,
|
1464 |
+
"num_input_tokens_seen": 7459576,
|
1465 |
+
"step": 182
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 3.330275229357798,
|
1469 |
+
"grad_norm": 0.2721710801124573,
|
1470 |
+
"learning_rate": 4.6540729011038146e-05,
|
1471 |
+
"loss": 0.2698,
|
1472 |
+
"num_input_tokens_seen": 7511736,
|
1473 |
+
"step": 183
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 3.3486238532110093,
|
1477 |
+
"grad_norm": 0.2488890290260315,
|
1478 |
+
"learning_rate": 4.650372869738414e-05,
|
1479 |
+
"loss": 0.173,
|
1480 |
+
"num_input_tokens_seen": 7558552,
|
1481 |
+
"step": 184
|
1482 |
+
},
|
1483 |
+
{
|
1484 |
+
"epoch": 3.36697247706422,
|
1485 |
+
"grad_norm": 0.3800615668296814,
|
1486 |
+
"learning_rate": 4.6466546428015336e-05,
|
1487 |
+
"loss": 0.32,
|
1488 |
+
"num_input_tokens_seen": 7599040,
|
1489 |
+
"step": 185
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 3.385321100917431,
|
1493 |
+
"grad_norm": 0.3377014100551605,
|
1494 |
+
"learning_rate": 4.642918251755281e-05,
|
1495 |
+
"loss": 0.3058,
|
1496 |
+
"num_input_tokens_seen": 7653264,
|
1497 |
+
"step": 186
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 3.4036697247706424,
|
1501 |
+
"grad_norm": 0.25239789485931396,
|
1502 |
+
"learning_rate": 4.639163728215463e-05,
|
1503 |
+
"loss": 0.1896,
|
1504 |
+
"num_input_tokens_seen": 7694272,
|
1505 |
+
"step": 187
|
1506 |
+
},
|
1507 |
+
{
|
1508 |
+
"epoch": 3.4220183486238533,
|
1509 |
+
"grad_norm": 0.34607502818107605,
|
1510 |
+
"learning_rate": 4.6353911039513145e-05,
|
1511 |
+
"loss": 0.2933,
|
1512 |
+
"num_input_tokens_seen": 7730848,
|
1513 |
+
"step": 188
|
1514 |
+
},
|
1515 |
+
{
|
1516 |
+
"epoch": 3.4403669724770642,
|
1517 |
+
"grad_norm": 0.30653324723243713,
|
1518 |
+
"learning_rate": 4.6316004108852305e-05,
|
1519 |
+
"loss": 0.2625,
|
1520 |
+
"num_input_tokens_seen": 7781200,
|
1521 |
+
"step": 189
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 3.458715596330275,
|
1525 |
+
"grad_norm": 0.2943236231803894,
|
1526 |
+
"learning_rate": 4.627791681092499e-05,
|
1527 |
+
"loss": 0.3372,
|
1528 |
+
"num_input_tokens_seen": 7825032,
|
1529 |
+
"step": 190
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 3.477064220183486,
|
1533 |
+
"grad_norm": 0.30080685019493103,
|
1534 |
+
"learning_rate": 4.623964946801027e-05,
|
1535 |
+
"loss": 0.2229,
|
1536 |
+
"num_input_tokens_seen": 7855840,
|
1537 |
+
"step": 191
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 3.4954128440366974,
|
1541 |
+
"grad_norm": 0.3511403799057007,
|
1542 |
+
"learning_rate": 4.620120240391065e-05,
|
1543 |
+
"loss": 0.3967,
|
1544 |
+
"num_input_tokens_seen": 7905928,
|
1545 |
+
"step": 192
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 3.5137614678899083,
|
1549 |
+
"grad_norm": 0.273583322763443,
|
1550 |
+
"learning_rate": 4.61625759439494e-05,
|
1551 |
+
"loss": 0.2254,
|
1552 |
+
"num_input_tokens_seen": 7955992,
|
1553 |
+
"step": 193
|
1554 |
+
},
|
1555 |
+
{
|
1556 |
+
"epoch": 3.532110091743119,
|
1557 |
+
"grad_norm": 0.3457902669906616,
|
1558 |
+
"learning_rate": 4.612377041496776e-05,
|
1559 |
+
"loss": 0.2553,
|
1560 |
+
"num_input_tokens_seen": 7998024,
|
1561 |
+
"step": 194
|
1562 |
+
},
|
1563 |
+
{
|
1564 |
+
"epoch": 3.5504587155963305,
|
1565 |
+
"grad_norm": 0.31968954205513,
|
1566 |
+
"learning_rate": 4.608478614532215e-05,
|
1567 |
+
"loss": 0.2197,
|
1568 |
+
"num_input_tokens_seen": 8055672,
|
1569 |
+
"step": 195
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 3.5688073394495414,
|
1573 |
+
"grad_norm": 0.34753403067588806,
|
1574 |
+
"learning_rate": 4.604562346488144e-05,
|
1575 |
+
"loss": 0.2507,
|
1576 |
+
"num_input_tokens_seen": 8090848,
|
1577 |
+
"step": 196
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 3.5871559633027523,
|
1581 |
+
"grad_norm": 0.3808669149875641,
|
1582 |
+
"learning_rate": 4.6006282705024144e-05,
|
1583 |
+
"loss": 0.2422,
|
1584 |
+
"num_input_tokens_seen": 8136680,
|
1585 |
+
"step": 197
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 3.6055045871559632,
|
1589 |
+
"grad_norm": 0.3004499673843384,
|
1590 |
+
"learning_rate": 4.5966764198635606e-05,
|
1591 |
+
"loss": 0.2107,
|
1592 |
+
"num_input_tokens_seen": 8187472,
|
1593 |
+
"step": 198
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 3.623853211009174,
|
1597 |
+
"grad_norm": 0.30718186497688293,
|
1598 |
+
"learning_rate": 4.592706828010518e-05,
|
1599 |
+
"loss": 0.1854,
|
1600 |
+
"num_input_tokens_seen": 8225216,
|
1601 |
+
"step": 199
|
1602 |
+
},
|
1603 |
+
{
|
1604 |
+
"epoch": 3.6422018348623855,
|
1605 |
+
"grad_norm": 0.23112858831882477,
|
1606 |
+
"learning_rate": 4.588719528532342e-05,
|
1607 |
+
"loss": 0.1687,
|
1608 |
+
"num_input_tokens_seen": 8274456,
|
1609 |
+
"step": 200
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 3.6605504587155964,
|
1613 |
+
"grad_norm": 0.25966888666152954,
|
1614 |
+
"learning_rate": 4.5847145551679206e-05,
|
1615 |
+
"loss": 0.2549,
|
1616 |
+
"num_input_tokens_seen": 8317016,
|
1617 |
+
"step": 201
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 3.6788990825688073,
|
1621 |
+
"grad_norm": 0.25600987672805786,
|
1622 |
+
"learning_rate": 4.580691941805695e-05,
|
1623 |
+
"loss": 0.1602,
|
1624 |
+
"num_input_tokens_seen": 8361856,
|
1625 |
+
"step": 202
|
1626 |
+
},
|
1627 |
+
{
|
1628 |
+
"epoch": 3.6972477064220186,
|
1629 |
+
"grad_norm": 0.33986184000968933,
|
1630 |
+
"learning_rate": 4.5766517224833637e-05,
|
1631 |
+
"loss": 0.2495,
|
1632 |
+
"num_input_tokens_seen": 8410696,
|
1633 |
+
"step": 203
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 3.7155963302752295,
|
1637 |
+
"grad_norm": 0.36899781227111816,
|
1638 |
+
"learning_rate": 4.572593931387604e-05,
|
1639 |
+
"loss": 0.2012,
|
1640 |
+
"num_input_tokens_seen": 8441872,
|
1641 |
+
"step": 204
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 3.7339449541284404,
|
1645 |
+
"grad_norm": 0.42072632908821106,
|
1646 |
+
"learning_rate": 4.568518602853776e-05,
|
1647 |
+
"loss": 0.2373,
|
1648 |
+
"num_input_tokens_seen": 8482544,
|
1649 |
+
"step": 205
|
1650 |
+
},
|
1651 |
+
{
|
1652 |
+
"epoch": 3.7522935779816513,
|
1653 |
+
"grad_norm": 0.40593233704566956,
|
1654 |
+
"learning_rate": 4.5644257713656356e-05,
|
1655 |
+
"loss": 0.233,
|
1656 |
+
"num_input_tokens_seen": 8519856,
|
1657 |
+
"step": 206
|
1658 |
+
},
|
1659 |
+
{
|
1660 |
+
"epoch": 3.770642201834862,
|
1661 |
+
"grad_norm": 0.38003161549568176,
|
1662 |
+
"learning_rate": 4.5603154715550386e-05,
|
1663 |
+
"loss": 0.225,
|
1664 |
+
"num_input_tokens_seen": 8551392,
|
1665 |
+
"step": 207
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 3.7889908256880735,
|
1669 |
+
"grad_norm": 0.2564244568347931,
|
1670 |
+
"learning_rate": 4.556187738201656e-05,
|
1671 |
+
"loss": 0.2975,
|
1672 |
+
"num_input_tokens_seen": 8599472,
|
1673 |
+
"step": 208
|
1674 |
+
},
|
1675 |
+
{
|
1676 |
+
"epoch": 3.8073394495412844,
|
1677 |
+
"grad_norm": 0.29023391008377075,
|
1678 |
+
"learning_rate": 4.552042606232668e-05,
|
1679 |
+
"loss": 0.2033,
|
1680 |
+
"num_input_tokens_seen": 8631880,
|
1681 |
+
"step": 209
|
1682 |
+
},
|
1683 |
+
{
|
1684 |
+
"epoch": 3.8256880733944953,
|
1685 |
+
"grad_norm": 0.32886001467704773,
|
1686 |
+
"learning_rate": 4.54788011072248e-05,
|
1687 |
+
"loss": 0.2024,
|
1688 |
+
"num_input_tokens_seen": 8675016,
|
1689 |
+
"step": 210
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 3.8440366972477067,
|
1693 |
+
"grad_norm": 0.36749884486198425,
|
1694 |
+
"learning_rate": 4.5437002868924166e-05,
|
1695 |
+
"loss": 0.2304,
|
1696 |
+
"num_input_tokens_seen": 8713248,
|
1697 |
+
"step": 211
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 3.8623853211009176,
|
1701 |
+
"grad_norm": 0.3055097758769989,
|
1702 |
+
"learning_rate": 4.539503170110431e-05,
|
1703 |
+
"loss": 0.2928,
|
1704 |
+
"num_input_tokens_seen": 8748800,
|
1705 |
+
"step": 212
|
1706 |
+
},
|
1707 |
+
{
|
1708 |
+
"epoch": 3.8807339449541285,
|
1709 |
+
"grad_norm": 0.38436686992645264,
|
1710 |
+
"learning_rate": 4.535288795890798e-05,
|
1711 |
+
"loss": 0.2214,
|
1712 |
+
"num_input_tokens_seen": 8787832,
|
1713 |
+
"step": 213
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 3.8990825688073394,
|
1717 |
+
"grad_norm": 0.44330883026123047,
|
1718 |
+
"learning_rate": 4.531057199893824e-05,
|
1719 |
+
"loss": 0.2168,
|
1720 |
+
"num_input_tokens_seen": 8819616,
|
1721 |
+
"step": 214
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 3.9174311926605503,
|
1725 |
+
"grad_norm": 0.28318527340888977,
|
1726 |
+
"learning_rate": 4.526808417925531e-05,
|
1727 |
+
"loss": 0.279,
|
1728 |
+
"num_input_tokens_seen": 8860744,
|
1729 |
+
"step": 215
|
1730 |
+
},
|
1731 |
+
{
|
1732 |
+
"epoch": 3.9357798165137616,
|
1733 |
+
"grad_norm": 0.3287319839000702,
|
1734 |
+
"learning_rate": 4.522542485937369e-05,
|
1735 |
+
"loss": 0.2597,
|
1736 |
+
"num_input_tokens_seen": 8906432,
|
1737 |
+
"step": 216
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 3.9541284403669725,
|
1741 |
+
"grad_norm": 0.35815751552581787,
|
1742 |
+
"learning_rate": 4.5182594400259e-05,
|
1743 |
+
"loss": 0.241,
|
1744 |
+
"num_input_tokens_seen": 8955104,
|
1745 |
+
"step": 217
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 3.9724770642201834,
|
1749 |
+
"grad_norm": 0.3299608528614044,
|
1750 |
+
"learning_rate": 4.5139593164324986e-05,
|
1751 |
+
"loss": 0.2157,
|
1752 |
+
"num_input_tokens_seen": 8990200,
|
1753 |
+
"step": 218
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 3.9908256880733948,
|
1757 |
+
"grad_norm": 0.2916093170642853,
|
1758 |
+
"learning_rate": 4.509642151543043e-05,
|
1759 |
+
"loss": 0.2046,
|
1760 |
+
"num_input_tokens_seen": 9020760,
|
1761 |
+
"step": 219
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 4.0,
|
1765 |
+
"grad_norm": 0.40076637268066406,
|
1766 |
+
"learning_rate": 4.50530798188761e-05,
|
1767 |
+
"loss": 0.1714,
|
1768 |
+
"num_input_tokens_seen": 9036352,
|
1769 |
+
"step": 220
|
1770 |
+
},
|
1771 |
+
{
|
1772 |
+
"epoch": 4.018348623853211,
|
1773 |
+
"grad_norm": 0.40515249967575073,
|
1774 |
+
"learning_rate": 4.50095684414016e-05,
|
1775 |
+
"loss": 0.1811,
|
1776 |
+
"num_input_tokens_seen": 9091776,
|
1777 |
+
"step": 221
|
1778 |
+
},
|
1779 |
+
{
|
1780 |
+
"epoch": 4.036697247706422,
|
1781 |
+
"grad_norm": 0.32984718680381775,
|
1782 |
+
"learning_rate": 4.496588775118232e-05,
|
1783 |
+
"loss": 0.2101,
|
1784 |
+
"num_input_tokens_seen": 9134080,
|
1785 |
+
"step": 222
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 4.055045871559633,
|
1789 |
+
"grad_norm": 0.27288541197776794,
|
1790 |
+
"learning_rate": 4.4922038117826334e-05,
|
1791 |
+
"loss": 0.1444,
|
1792 |
+
"num_input_tokens_seen": 9172720,
|
1793 |
+
"step": 223
|
1794 |
+
},
|
1795 |
+
{
|
1796 |
+
"epoch": 4.073394495412844,
|
1797 |
+
"grad_norm": 0.5168021321296692,
|
1798 |
+
"learning_rate": 4.48780199123712e-05,
|
1799 |
+
"loss": 0.2342,
|
1800 |
+
"num_input_tokens_seen": 9213664,
|
1801 |
+
"step": 224
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 4.091743119266055,
|
1805 |
+
"grad_norm": 0.3986498713493347,
|
1806 |
+
"learning_rate": 4.4833833507280884e-05,
|
1807 |
+
"loss": 0.1676,
|
1808 |
+
"num_input_tokens_seen": 9261768,
|
1809 |
+
"step": 225
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 4.110091743119266,
|
1813 |
+
"grad_norm": 0.4472793936729431,
|
1814 |
+
"learning_rate": 4.478947927644258e-05,
|
1815 |
+
"loss": 0.295,
|
1816 |
+
"num_input_tokens_seen": 9300928,
|
1817 |
+
"step": 226
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 4.128440366972477,
|
1821 |
+
"grad_norm": 0.39240705966949463,
|
1822 |
+
"learning_rate": 4.474495759516358e-05,
|
1823 |
+
"loss": 0.17,
|
1824 |
+
"num_input_tokens_seen": 9329472,
|
1825 |
+
"step": 227
|
1826 |
+
},
|
1827 |
+
{
|
1828 |
+
"epoch": 4.146788990825688,
|
1829 |
+
"grad_norm": 0.354526549577713,
|
1830 |
+
"learning_rate": 4.4700268840168045e-05,
|
1831 |
+
"loss": 0.1759,
|
1832 |
+
"num_input_tokens_seen": 9365640,
|
1833 |
+
"step": 228
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 4.165137614678899,
|
1837 |
+
"grad_norm": 0.3216766119003296,
|
1838 |
+
"learning_rate": 4.4655413389593856e-05,
|
1839 |
+
"loss": 0.1878,
|
1840 |
+
"num_input_tokens_seen": 9410552,
|
1841 |
+
"step": 229
|
1842 |
+
},
|
1843 |
+
{
|
1844 |
+
"epoch": 4.18348623853211,
|
1845 |
+
"grad_norm": 0.30976617336273193,
|
1846 |
+
"learning_rate": 4.4610391622989396e-05,
|
1847 |
+
"loss": 0.1637,
|
1848 |
+
"num_input_tokens_seen": 9452416,
|
1849 |
+
"step": 230
|
1850 |
+
},
|
1851 |
+
{
|
1852 |
+
"epoch": 4.201834862385321,
|
1853 |
+
"grad_norm": 0.385437935590744,
|
1854 |
+
"learning_rate": 4.456520392131035e-05,
|
1855 |
+
"loss": 0.2748,
|
1856 |
+
"num_input_tokens_seen": 9503528,
|
1857 |
+
"step": 231
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 4.220183486238533,
|
1861 |
+
"grad_norm": 0.37948480248451233,
|
1862 |
+
"learning_rate": 4.4519850666916484e-05,
|
1863 |
+
"loss": 0.2635,
|
1864 |
+
"num_input_tokens_seen": 9541592,
|
1865 |
+
"step": 232
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 4.238532110091743,
|
1869 |
+
"grad_norm": 0.36141568422317505,
|
1870 |
+
"learning_rate": 4.447433224356839e-05,
|
1871 |
+
"loss": 0.2027,
|
1872 |
+
"num_input_tokens_seen": 9586064,
|
1873 |
+
"step": 233
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 4.256880733944954,
|
1877 |
+
"grad_norm": 0.4549350440502167,
|
1878 |
+
"learning_rate": 4.442864903642428e-05,
|
1879 |
+
"loss": 0.2107,
|
1880 |
+
"num_input_tokens_seen": 9641688,
|
1881 |
+
"step": 234
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 4.275229357798165,
|
1885 |
+
"grad_norm": 0.3979765474796295,
|
1886 |
+
"learning_rate": 4.438280143203665e-05,
|
1887 |
+
"loss": 0.2879,
|
1888 |
+
"num_input_tokens_seen": 9686240,
|
1889 |
+
"step": 235
|
1890 |
+
},
|
1891 |
+
{
|
1892 |
+
"epoch": 4.293577981651376,
|
1893 |
+
"grad_norm": 0.35011065006256104,
|
1894 |
+
"learning_rate": 4.43367898183491e-05,
|
1895 |
+
"loss": 0.2594,
|
1896 |
+
"num_input_tokens_seen": 9735632,
|
1897 |
+
"step": 236
|
1898 |
+
},
|
1899 |
+
{
|
1900 |
+
"epoch": 4.3119266055045875,
|
1901 |
+
"grad_norm": 0.3999224007129669,
|
1902 |
+
"learning_rate": 4.4290614584693004e-05,
|
1903 |
+
"loss": 0.1907,
|
1904 |
+
"num_input_tokens_seen": 9766536,
|
1905 |
+
"step": 237
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 4.330275229357798,
|
1909 |
+
"grad_norm": 0.39629611372947693,
|
1910 |
+
"learning_rate": 4.4244276121784195e-05,
|
1911 |
+
"loss": 0.1805,
|
1912 |
+
"num_input_tokens_seen": 9796400,
|
1913 |
+
"step": 238
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 4.348623853211009,
|
1917 |
+
"grad_norm": 0.36784592270851135,
|
1918 |
+
"learning_rate": 4.4197774821719714e-05,
|
1919 |
+
"loss": 0.1824,
|
1920 |
+
"num_input_tokens_seen": 9831992,
|
1921 |
+
"step": 239
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 4.36697247706422,
|
1925 |
+
"grad_norm": 0.3408430516719818,
|
1926 |
+
"learning_rate": 4.415111107797445e-05,
|
1927 |
+
"loss": 0.1721,
|
1928 |
+
"num_input_tokens_seen": 9875640,
|
1929 |
+
"step": 240
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 4.385321100917431,
|
1933 |
+
"grad_norm": 0.3232553005218506,
|
1934 |
+
"learning_rate": 4.410428528539783e-05,
|
1935 |
+
"loss": 0.275,
|
1936 |
+
"num_input_tokens_seen": 9916816,
|
1937 |
+
"step": 241
|
1938 |
+
},
|
1939 |
+
{
|
1940 |
+
"epoch": 4.4036697247706424,
|
1941 |
+
"grad_norm": 0.38150206208229065,
|
1942 |
+
"learning_rate": 4.405729784021046e-05,
|
1943 |
+
"loss": 0.1963,
|
1944 |
+
"num_input_tokens_seen": 9962928,
|
1945 |
+
"step": 242
|
1946 |
+
},
|
1947 |
+
{
|
1948 |
+
"epoch": 4.422018348623853,
|
1949 |
+
"grad_norm": 0.4176963269710541,
|
1950 |
+
"learning_rate": 4.401014914000078e-05,
|
1951 |
+
"loss": 0.1626,
|
1952 |
+
"num_input_tokens_seen": 9997224,
|
1953 |
+
"step": 243
|
1954 |
+
},
|
1955 |
+
{
|
1956 |
+
"epoch": 4.440366972477064,
|
1957 |
+
"grad_norm": 0.38855600357055664,
|
1958 |
+
"learning_rate": 4.396283958372173e-05,
|
1959 |
+
"loss": 0.1733,
|
1960 |
+
"num_input_tokens_seen": 10036248,
|
1961 |
+
"step": 244
|
1962 |
+
},
|
1963 |
+
{
|
1964 |
+
"epoch": 4.458715596330276,
|
1965 |
+
"grad_norm": 0.3860638737678528,
|
1966 |
+
"learning_rate": 4.391536957168733e-05,
|
1967 |
+
"loss": 0.1936,
|
1968 |
+
"num_input_tokens_seen": 10070312,
|
1969 |
+
"step": 245
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 4.477064220183486,
|
1973 |
+
"grad_norm": 0.31510865688323975,
|
1974 |
+
"learning_rate": 4.386773950556931e-05,
|
1975 |
+
"loss": 0.1847,
|
1976 |
+
"num_input_tokens_seen": 10114568,
|
1977 |
+
"step": 246
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 4.495412844036697,
|
1981 |
+
"grad_norm": 0.3280925154685974,
|
1982 |
+
"learning_rate": 4.381994978839371e-05,
|
1983 |
+
"loss": 0.1981,
|
1984 |
+
"num_input_tokens_seen": 10150280,
|
1985 |
+
"step": 247
|
1986 |
+
},
|
1987 |
+
{
|
1988 |
+
"epoch": 4.513761467889909,
|
1989 |
+
"grad_norm": 0.33136090636253357,
|
1990 |
+
"learning_rate": 4.377200082453749e-05,
|
1991 |
+
"loss": 0.1681,
|
1992 |
+
"num_input_tokens_seen": 10194000,
|
1993 |
+
"step": 248
|
1994 |
+
},
|
1995 |
+
{
|
1996 |
+
"epoch": 4.532110091743119,
|
1997 |
+
"grad_norm": 0.43955501914024353,
|
1998 |
+
"learning_rate": 4.372389301972506e-05,
|
1999 |
+
"loss": 0.2111,
|
2000 |
+
"num_input_tokens_seen": 10232264,
|
2001 |
+
"step": 249
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 4.5504587155963305,
|
2005 |
+
"grad_norm": 0.28938886523246765,
|
2006 |
+
"learning_rate": 4.36756267810249e-05,
|
2007 |
+
"loss": 0.2307,
|
2008 |
+
"num_input_tokens_seen": 10271880,
|
2009 |
+
"step": 250
|
2010 |
+
},
|
2011 |
+
{
|
2012 |
+
"epoch": 4.568807339449541,
|
2013 |
+
"grad_norm": 0.37232765555381775,
|
2014 |
+
"learning_rate": 4.36272025168461e-05,
|
2015 |
+
"loss": 0.1609,
|
2016 |
+
"num_input_tokens_seen": 10317720,
|
2017 |
+
"step": 251
|
2018 |
+
},
|
2019 |
+
{
|
2020 |
+
"epoch": 4.587155963302752,
|
2021 |
+
"grad_norm": 0.6248548030853271,
|
2022 |
+
"learning_rate": 4.357862063693486e-05,
|
2023 |
+
"loss": 0.2456,
|
2024 |
+
"num_input_tokens_seen": 10362168,
|
2025 |
+
"step": 252
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 4.605504587155964,
|
2029 |
+
"grad_norm": 0.32828131318092346,
|
2030 |
+
"learning_rate": 4.3529881552371096e-05,
|
2031 |
+
"loss": 0.3159,
|
2032 |
+
"num_input_tokens_seen": 10414312,
|
2033 |
+
"step": 253
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 4.623853211009174,
|
2037 |
+
"grad_norm": 0.4158332049846649,
|
2038 |
+
"learning_rate": 4.34809856755649e-05,
|
2039 |
+
"loss": 0.2194,
|
2040 |
+
"num_input_tokens_seen": 10451800,
|
2041 |
+
"step": 254
|
2042 |
+
},
|
2043 |
+
{
|
2044 |
+
"epoch": 4.6422018348623855,
|
2045 |
+
"grad_norm": 0.3648194670677185,
|
2046 |
+
"learning_rate": 4.34319334202531e-05,
|
2047 |
+
"loss": 0.1846,
|
2048 |
+
"num_input_tokens_seen": 10496224,
|
2049 |
+
"step": 255
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 4.660550458715596,
|
2053 |
+
"grad_norm": 0.36835575103759766,
|
2054 |
+
"learning_rate": 4.3382725201495723e-05,
|
2055 |
+
"loss": 0.1906,
|
2056 |
+
"num_input_tokens_seen": 10536392,
|
2057 |
+
"step": 256
|
2058 |
+
},
|
2059 |
+
{
|
2060 |
+
"epoch": 4.678899082568807,
|
2061 |
+
"grad_norm": 0.3501613140106201,
|
2062 |
+
"learning_rate": 4.333336143567247e-05,
|
2063 |
+
"loss": 0.1793,
|
2064 |
+
"num_input_tokens_seen": 10577640,
|
2065 |
+
"step": 257
|
2066 |
+
},
|
2067 |
+
{
|
2068 |
+
"epoch": 4.697247706422019,
|
2069 |
+
"grad_norm": 0.3431616425514221,
|
2070 |
+
"learning_rate": 4.3283842540479264e-05,
|
2071 |
+
"loss": 0.1576,
|
2072 |
+
"num_input_tokens_seen": 10613376,
|
2073 |
+
"step": 258
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 4.715596330275229,
|
2077 |
+
"grad_norm": 0.3290237784385681,
|
2078 |
+
"learning_rate": 4.3234168934924636e-05,
|
2079 |
+
"loss": 0.1447,
|
2080 |
+
"num_input_tokens_seen": 10647232,
|
2081 |
+
"step": 259
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 4.73394495412844,
|
2085 |
+
"grad_norm": 0.40264153480529785,
|
2086 |
+
"learning_rate": 4.318434103932622e-05,
|
2087 |
+
"loss": 0.1488,
|
2088 |
+
"num_input_tokens_seen": 10696024,
|
2089 |
+
"step": 260
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 4.752293577981652,
|
2093 |
+
"grad_norm": 0.3453703820705414,
|
2094 |
+
"learning_rate": 4.313435927530719e-05,
|
2095 |
+
"loss": 0.1597,
|
2096 |
+
"num_input_tokens_seen": 10730408,
|
2097 |
+
"step": 261
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 4.770642201834862,
|
2101 |
+
"grad_norm": 0.3993653655052185,
|
2102 |
+
"learning_rate": 4.30842240657927e-05,
|
2103 |
+
"loss": 0.2266,
|
2104 |
+
"num_input_tokens_seen": 10764776,
|
2105 |
+
"step": 262
|
2106 |
+
},
|
2107 |
+
{
|
2108 |
+
"epoch": 4.7889908256880735,
|
2109 |
+
"grad_norm": 0.4080798923969269,
|
2110 |
+
"learning_rate": 4.303393583500628e-05,
|
2111 |
+
"loss": 0.1562,
|
2112 |
+
"num_input_tokens_seen": 10792272,
|
2113 |
+
"step": 263
|
2114 |
+
},
|
2115 |
+
{
|
2116 |
+
"epoch": 4.807339449541285,
|
2117 |
+
"grad_norm": 0.3028413951396942,
|
2118 |
+
"learning_rate": 4.2983495008466276e-05,
|
2119 |
+
"loss": 0.1504,
|
2120 |
+
"num_input_tokens_seen": 10825240,
|
2121 |
+
"step": 264
|
2122 |
+
},
|
2123 |
+
{
|
2124 |
+
"epoch": 4.825688073394495,
|
2125 |
+
"grad_norm": 0.3980019688606262,
|
2126 |
+
"learning_rate": 4.293290201298223e-05,
|
2127 |
+
"loss": 0.1648,
|
2128 |
+
"num_input_tokens_seen": 10883592,
|
2129 |
+
"step": 265
|
2130 |
+
},
|
2131 |
+
{
|
2132 |
+
"epoch": 4.844036697247707,
|
2133 |
+
"grad_norm": 0.42035797238349915,
|
2134 |
+
"learning_rate": 4.288215727665129e-05,
|
2135 |
+
"loss": 0.1652,
|
2136 |
+
"num_input_tokens_seen": 10922640,
|
2137 |
+
"step": 266
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 4.862385321100917,
|
2141 |
+
"grad_norm": 0.37766003608703613,
|
2142 |
+
"learning_rate": 4.2831261228854544e-05,
|
2143 |
+
"loss": 0.1817,
|
2144 |
+
"num_input_tokens_seen": 10967288,
|
2145 |
+
"step": 267
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 4.8807339449541285,
|
2149 |
+
"grad_norm": 0.3495088815689087,
|
2150 |
+
"learning_rate": 4.278021430025343e-05,
|
2151 |
+
"loss": 0.2066,
|
2152 |
+
"num_input_tokens_seen": 11011152,
|
2153 |
+
"step": 268
|
2154 |
+
},
|
2155 |
+
{
|
2156 |
+
"epoch": 4.89908256880734,
|
2157 |
+
"grad_norm": 0.34071093797683716,
|
2158 |
+
"learning_rate": 4.272901692278609e-05,
|
2159 |
+
"loss": 0.1522,
|
2160 |
+
"num_input_tokens_seen": 11055608,
|
2161 |
+
"step": 269
|
2162 |
+
},
|
2163 |
+
{
|
2164 |
+
"epoch": 4.91743119266055,
|
2165 |
+
"grad_norm": 0.33437398076057434,
|
2166 |
+
"learning_rate": 4.267766952966369e-05,
|
2167 |
+
"loss": 0.2201,
|
2168 |
+
"num_input_tokens_seen": 11101992,
|
2169 |
+
"step": 270
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 4.935779816513762,
|
2173 |
+
"grad_norm": 0.3340584337711334,
|
2174 |
+
"learning_rate": 4.262617255536676e-05,
|
2175 |
+
"loss": 0.2777,
|
2176 |
+
"num_input_tokens_seen": 11141408,
|
2177 |
+
"step": 271
|
2178 |
+
},
|
2179 |
+
{
|
2180 |
+
"epoch": 4.954128440366972,
|
2181 |
+
"grad_norm": 0.348679780960083,
|
2182 |
+
"learning_rate": 4.257452643564155e-05,
|
2183 |
+
"loss": 0.1857,
|
2184 |
+
"num_input_tokens_seen": 11185344,
|
2185 |
+
"step": 272
|
2186 |
+
},
|
2187 |
+
{
|
2188 |
+
"epoch": 4.972477064220183,
|
2189 |
+
"grad_norm": 0.3691309094429016,
|
2190 |
+
"learning_rate": 4.2522731607496275e-05,
|
2191 |
+
"loss": 0.1653,
|
2192 |
+
"num_input_tokens_seen": 11216160,
|
2193 |
+
"step": 273
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 4.990825688073395,
|
2197 |
+
"grad_norm": 0.4692390561103821,
|
2198 |
+
"learning_rate": 4.24707885091975e-05,
|
2199 |
+
"loss": 0.1761,
|
2200 |
+
"num_input_tokens_seen": 11276200,
|
2201 |
+
"step": 274
|
2202 |
+
},
|
2203 |
+
{
|
2204 |
+
"epoch": 5.0,
|
2205 |
+
"grad_norm": 0.4963766932487488,
|
2206 |
+
"learning_rate": 4.241869758026638e-05,
|
2207 |
+
"loss": 0.1582,
|
2208 |
+
"num_input_tokens_seen": 11295440,
|
2209 |
+
"step": 275
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 5.018348623853211,
|
2213 |
+
"grad_norm": 0.37284544110298157,
|
2214 |
+
"learning_rate": 4.2366459261474933e-05,
|
2215 |
+
"loss": 0.1538,
|
2216 |
+
"num_input_tokens_seen": 11336400,
|
2217 |
+
"step": 276
|
2218 |
+
},
|
2219 |
+
{
|
2220 |
+
"epoch": 5.036697247706422,
|
2221 |
+
"grad_norm": 0.2949577867984772,
|
2222 |
+
"learning_rate": 4.231407399484236e-05,
|
2223 |
+
"loss": 0.1319,
|
2224 |
+
"num_input_tokens_seen": 11374056,
|
2225 |
+
"step": 277
|
2226 |
+
},
|
2227 |
+
{
|
2228 |
+
"epoch": 5.055045871559633,
|
2229 |
+
"grad_norm": 0.32850027084350586,
|
2230 |
+
"learning_rate": 4.226154222363124e-05,
|
2231 |
+
"loss": 0.174,
|
2232 |
+
"num_input_tokens_seen": 11414776,
|
2233 |
+
"step": 278
|
2234 |
+
},
|
2235 |
+
{
|
2236 |
+
"epoch": 5.073394495412844,
|
2237 |
+
"grad_norm": 0.3812579810619354,
|
2238 |
+
"learning_rate": 4.220886439234385e-05,
|
2239 |
+
"loss": 0.1831,
|
2240 |
+
"num_input_tokens_seen": 11465456,
|
2241 |
+
"step": 279
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 5.091743119266055,
|
2245 |
+
"grad_norm": 0.3396337032318115,
|
2246 |
+
"learning_rate": 4.215604094671835e-05,
|
2247 |
+
"loss": 0.1515,
|
2248 |
+
"num_input_tokens_seen": 11500184,
|
2249 |
+
"step": 280
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 5.110091743119266,
|
2253 |
+
"grad_norm": 0.35079169273376465,
|
2254 |
+
"learning_rate": 4.2103072333725e-05,
|
2255 |
+
"loss": 0.1295,
|
2256 |
+
"num_input_tokens_seen": 11537112,
|
2257 |
+
"step": 281
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"epoch": 5.128440366972477,
|
2261 |
+
"grad_norm": 0.3811327815055847,
|
2262 |
+
"learning_rate": 4.2049959001562464e-05,
|
2263 |
+
"loss": 0.1339,
|
2264 |
+
"num_input_tokens_seen": 11579440,
|
2265 |
+
"step": 282
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 5.146788990825688,
|
2269 |
+
"grad_norm": 0.3935602009296417,
|
2270 |
+
"learning_rate": 4.199670139965393e-05,
|
2271 |
+
"loss": 0.1909,
|
2272 |
+
"num_input_tokens_seen": 11643272,
|
2273 |
+
"step": 283
|
2274 |
+
},
|
2275 |
+
{
|
2276 |
+
"epoch": 5.165137614678899,
|
2277 |
+
"grad_norm": 0.3952607810497284,
|
2278 |
+
"learning_rate": 4.194329997864331e-05,
|
2279 |
+
"loss": 0.2334,
|
2280 |
+
"num_input_tokens_seen": 11677528,
|
2281 |
+
"step": 284
|
2282 |
+
},
|
2283 |
+
{
|
2284 |
+
"epoch": 5.18348623853211,
|
2285 |
+
"grad_norm": 0.3687472939491272,
|
2286 |
+
"learning_rate": 4.188975519039151e-05,
|
2287 |
+
"loss": 0.1406,
|
2288 |
+
"num_input_tokens_seen": 11727944,
|
2289 |
+
"step": 285
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 5.201834862385321,
|
2293 |
+
"grad_norm": 0.3518407344818115,
|
2294 |
+
"learning_rate": 4.183606748797251e-05,
|
2295 |
+
"loss": 0.138,
|
2296 |
+
"num_input_tokens_seen": 11779568,
|
2297 |
+
"step": 286
|
2298 |
+
},
|
2299 |
+
{
|
2300 |
+
"epoch": 5.220183486238533,
|
2301 |
+
"grad_norm": 0.4072832763195038,
|
2302 |
+
"learning_rate": 4.1782237325669595e-05,
|
2303 |
+
"loss": 0.159,
|
2304 |
+
"num_input_tokens_seen": 11824600,
|
2305 |
+
"step": 287
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 5.238532110091743,
|
2309 |
+
"grad_norm": 0.386280357837677,
|
2310 |
+
"learning_rate": 4.172826515897146e-05,
|
2311 |
+
"loss": 0.2517,
|
2312 |
+
"num_input_tokens_seen": 11873736,
|
2313 |
+
"step": 288
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 5.256880733944954,
|
2317 |
+
"grad_norm": 0.3576860725879669,
|
2318 |
+
"learning_rate": 4.167415144456841e-05,
|
2319 |
+
"loss": 0.1349,
|
2320 |
+
"num_input_tokens_seen": 11909608,
|
2321 |
+
"step": 289
|
2322 |
+
},
|
2323 |
+
{
|
2324 |
+
"epoch": 5.275229357798165,
|
2325 |
+
"grad_norm": 0.3952435851097107,
|
2326 |
+
"learning_rate": 4.1619896640348445e-05,
|
2327 |
+
"loss": 0.1348,
|
2328 |
+
"num_input_tokens_seen": 11945440,
|
2329 |
+
"step": 290
|
2330 |
+
},
|
2331 |
+
{
|
2332 |
+
"epoch": 5.293577981651376,
|
2333 |
+
"grad_norm": 0.3565181493759155,
|
2334 |
+
"learning_rate": 4.1565501205393445e-05,
|
2335 |
+
"loss": 0.1331,
|
2336 |
+
"num_input_tokens_seen": 11985568,
|
2337 |
+
"step": 291
|
2338 |
+
},
|
2339 |
+
{
|
2340 |
+
"epoch": 5.3119266055045875,
|
2341 |
+
"grad_norm": 0.40558820962905884,
|
2342 |
+
"learning_rate": 4.1510965599975196e-05,
|
2343 |
+
"loss": 0.2337,
|
2344 |
+
"num_input_tokens_seen": 12034320,
|
2345 |
+
"step": 292
|
2346 |
+
},
|
2347 |
+
{
|
2348 |
+
"epoch": 5.330275229357798,
|
2349 |
+
"grad_norm": 0.36426106095314026,
|
2350 |
+
"learning_rate": 4.1456290285551596e-05,
|
2351 |
+
"loss": 0.1299,
|
2352 |
+
"num_input_tokens_seen": 12070184,
|
2353 |
+
"step": 293
|
2354 |
+
},
|
2355 |
+
{
|
2356 |
+
"epoch": 5.348623853211009,
|
2357 |
+
"grad_norm": 0.33881404995918274,
|
2358 |
+
"learning_rate": 4.140147572476268e-05,
|
2359 |
+
"loss": 0.1239,
|
2360 |
+
"num_input_tokens_seen": 12111512,
|
2361 |
+
"step": 294
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 5.36697247706422,
|
2365 |
+
"grad_norm": 0.38019630312919617,
|
2366 |
+
"learning_rate": 4.1346522381426744e-05,
|
2367 |
+
"loss": 0.133,
|
2368 |
+
"num_input_tokens_seen": 12156792,
|
2369 |
+
"step": 295
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 5.385321100917431,
|
2373 |
+
"grad_norm": 0.38179296255111694,
|
2374 |
+
"learning_rate": 4.129143072053638e-05,
|
2375 |
+
"loss": 0.1301,
|
2376 |
+
"num_input_tokens_seen": 12185168,
|
2377 |
+
"step": 296
|
2378 |
+
},
|
2379 |
+
{
|
2380 |
+
"epoch": 5.4036697247706424,
|
2381 |
+
"grad_norm": 0.35054150223731995,
|
2382 |
+
"learning_rate": 4.123620120825459e-05,
|
2383 |
+
"loss": 0.1298,
|
2384 |
+
"num_input_tokens_seen": 12222256,
|
2385 |
+
"step": 297
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"epoch": 5.422018348623853,
|
2389 |
+
"grad_norm": 0.3463946580886841,
|
2390 |
+
"learning_rate": 4.118083431191081e-05,
|
2391 |
+
"loss": 0.2088,
|
2392 |
+
"num_input_tokens_seen": 12257536,
|
2393 |
+
"step": 298
|
2394 |
+
},
|
2395 |
+
{
|
2396 |
+
"epoch": 5.440366972477064,
|
2397 |
+
"grad_norm": 0.42584434151649475,
|
2398 |
+
"learning_rate": 4.112533049999696e-05,
|
2399 |
+
"loss": 0.1062,
|
2400 |
+
"num_input_tokens_seen": 12290576,
|
2401 |
+
"step": 299
|
2402 |
+
},
|
2403 |
+
{
|
2404 |
+
"epoch": 5.458715596330276,
|
2405 |
+
"grad_norm": 0.4341515600681305,
|
2406 |
+
"learning_rate": 4.1069690242163484e-05,
|
2407 |
+
"loss": 0.1989,
|
2408 |
+
"num_input_tokens_seen": 12323416,
|
2409 |
+
"step": 300
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 5.477064220183486,
|
2413 |
+
"grad_norm": 0.4299938380718231,
|
2414 |
+
"learning_rate": 4.101391400921538e-05,
|
2415 |
+
"loss": 0.1243,
|
2416 |
+
"num_input_tokens_seen": 12370264,
|
2417 |
+
"step": 301
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 5.495412844036697,
|
2421 |
+
"grad_norm": 0.4070415198802948,
|
2422 |
+
"learning_rate": 4.095800227310821e-05,
|
2423 |
+
"loss": 0.2281,
|
2424 |
+
"num_input_tokens_seen": 12410568,
|
2425 |
+
"step": 302
|
2426 |
+
},
|
2427 |
+
{
|
2428 |
+
"epoch": 5.513761467889909,
|
2429 |
+
"grad_norm": 0.4446506202220917,
|
2430 |
+
"learning_rate": 4.09019555069441e-05,
|
2431 |
+
"loss": 0.1462,
|
2432 |
+
"num_input_tokens_seen": 12442880,
|
2433 |
+
"step": 303
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 5.532110091743119,
|
2437 |
+
"grad_norm": 0.36110538244247437,
|
2438 |
+
"learning_rate": 4.0845774184967754e-05,
|
2439 |
+
"loss": 0.1497,
|
2440 |
+
"num_input_tokens_seen": 12487016,
|
2441 |
+
"step": 304
|
2442 |
+
},
|
2443 |
+
{
|
2444 |
+
"epoch": 5.5504587155963305,
|
2445 |
+
"grad_norm": 0.42756903171539307,
|
2446 |
+
"learning_rate": 4.078945878256244e-05,
|
2447 |
+
"loss": 0.2082,
|
2448 |
+
"num_input_tokens_seen": 12525072,
|
2449 |
+
"step": 305
|
2450 |
+
},
|
2451 |
+
{
|
2452 |
+
"epoch": 5.568807339449541,
|
2453 |
+
"grad_norm": 0.360649049282074,
|
2454 |
+
"learning_rate": 4.073300977624594e-05,
|
2455 |
+
"loss": 0.1214,
|
2456 |
+
"num_input_tokens_seen": 12555792,
|
2457 |
+
"step": 306
|
2458 |
+
},
|
2459 |
+
{
|
2460 |
+
"epoch": 5.587155963302752,
|
2461 |
+
"grad_norm": 0.3768391013145447,
|
2462 |
+
"learning_rate": 4.067642764366654e-05,
|
2463 |
+
"loss": 0.1278,
|
2464 |
+
"num_input_tokens_seen": 12601616,
|
2465 |
+
"step": 307
|
2466 |
+
},
|
2467 |
+
{
|
2468 |
+
"epoch": 5.605504587155964,
|
2469 |
+
"grad_norm": 0.3882285952568054,
|
2470 |
+
"learning_rate": 4.0619712863599e-05,
|
2471 |
+
"loss": 0.1485,
|
2472 |
+
"num_input_tokens_seen": 12634360,
|
2473 |
+
"step": 308
|
2474 |
+
},
|
2475 |
+
{
|
2476 |
+
"epoch": 5.623853211009174,
|
2477 |
+
"grad_norm": 0.38816162943840027,
|
2478 |
+
"learning_rate": 4.0562865915940496e-05,
|
2479 |
+
"loss": 0.1221,
|
2480 |
+
"num_input_tokens_seen": 12674808,
|
2481 |
+
"step": 309
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 5.6422018348623855,
|
2485 |
+
"grad_norm": 0.41803887486457825,
|
2486 |
+
"learning_rate": 4.05058872817065e-05,
|
2487 |
+
"loss": 0.1388,
|
2488 |
+
"num_input_tokens_seen": 12710864,
|
2489 |
+
"step": 310
|
2490 |
+
},
|
2491 |
+
{
|
2492 |
+
"epoch": 5.660550458715596,
|
2493 |
+
"grad_norm": 0.3802741467952728,
|
2494 |
+
"learning_rate": 4.044877744302683e-05,
|
2495 |
+
"loss": 0.1349,
|
2496 |
+
"num_input_tokens_seen": 12750920,
|
2497 |
+
"step": 311
|
2498 |
+
},
|
2499 |
+
{
|
2500 |
+
"epoch": 5.678899082568807,
|
2501 |
+
"grad_norm": 0.48202404379844666,
|
2502 |
+
"learning_rate": 4.039153688314145e-05,
|
2503 |
+
"loss": 0.1555,
|
2504 |
+
"num_input_tokens_seen": 12789488,
|
2505 |
+
"step": 312
|
2506 |
+
},
|
2507 |
+
{
|
2508 |
+
"epoch": 5.697247706422019,
|
2509 |
+
"grad_norm": 0.3168826103210449,
|
2510 |
+
"learning_rate": 4.0334166086396484e-05,
|
2511 |
+
"loss": 0.1063,
|
2512 |
+
"num_input_tokens_seen": 12831408,
|
2513 |
+
"step": 313
|
2514 |
+
},
|
2515 |
+
{
|
2516 |
+
"epoch": 5.715596330275229,
|
2517 |
+
"grad_norm": 0.43414828181266785,
|
2518 |
+
"learning_rate": 4.0276665538239996e-05,
|
2519 |
+
"loss": 0.127,
|
2520 |
+
"num_input_tokens_seen": 12872584,
|
2521 |
+
"step": 314
|
2522 |
+
},
|
2523 |
+
{
|
2524 |
+
"epoch": 5.73394495412844,
|
2525 |
+
"grad_norm": 0.47761547565460205,
|
2526 |
+
"learning_rate": 4.021903572521802e-05,
|
2527 |
+
"loss": 0.1428,
|
2528 |
+
"num_input_tokens_seen": 12910528,
|
2529 |
+
"step": 315
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 5.752293577981652,
|
2533 |
+
"grad_norm": 0.3542017936706543,
|
2534 |
+
"learning_rate": 4.0161277134970345e-05,
|
2535 |
+
"loss": 0.1279,
|
2536 |
+
"num_input_tokens_seen": 12942800,
|
2537 |
+
"step": 316
|
2538 |
+
},
|
2539 |
+
{
|
2540 |
+
"epoch": 5.770642201834862,
|
2541 |
+
"grad_norm": 0.31866851449012756,
|
2542 |
+
"learning_rate": 4.010339025622641e-05,
|
2543 |
+
"loss": 0.1459,
|
2544 |
+
"num_input_tokens_seen": 12989136,
|
2545 |
+
"step": 317
|
2546 |
+
},
|
2547 |
+
{
|
2548 |
+
"epoch": 5.7889908256880735,
|
2549 |
+
"grad_norm": 0.44918256998062134,
|
2550 |
+
"learning_rate": 4.0045375578801214e-05,
|
2551 |
+
"loss": 0.1429,
|
2552 |
+
"num_input_tokens_seen": 13035472,
|
2553 |
+
"step": 318
|
2554 |
+
},
|
2555 |
+
{
|
2556 |
+
"epoch": 5.807339449541285,
|
2557 |
+
"grad_norm": 0.32426726818084717,
|
2558 |
+
"learning_rate": 3.99872335935911e-05,
|
2559 |
+
"loss": 0.1257,
|
2560 |
+
"num_input_tokens_seen": 13074952,
|
2561 |
+
"step": 319
|
2562 |
+
},
|
2563 |
+
{
|
2564 |
+
"epoch": 5.825688073394495,
|
2565 |
+
"grad_norm": 0.6903991103172302,
|
2566 |
+
"learning_rate": 3.9928964792569655e-05,
|
2567 |
+
"loss": 0.1807,
|
2568 |
+
"num_input_tokens_seen": 13124624,
|
2569 |
+
"step": 320
|
2570 |
+
},
|
2571 |
+
{
|
2572 |
+
"epoch": 5.844036697247707,
|
2573 |
+
"grad_norm": 0.3665274679660797,
|
2574 |
+
"learning_rate": 3.9870569668783536e-05,
|
2575 |
+
"loss": 0.1853,
|
2576 |
+
"num_input_tokens_seen": 13171464,
|
2577 |
+
"step": 321
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"epoch": 5.862385321100917,
|
2581 |
+
"grad_norm": 0.41457998752593994,
|
2582 |
+
"learning_rate": 3.981204871634827e-05,
|
2583 |
+
"loss": 0.214,
|
2584 |
+
"num_input_tokens_seen": 13225240,
|
2585 |
+
"step": 322
|
2586 |
+
},
|
2587 |
+
{
|
2588 |
+
"epoch": 5.8807339449541285,
|
2589 |
+
"grad_norm": 0.4047159254550934,
|
2590 |
+
"learning_rate": 3.9753402430444116e-05,
|
2591 |
+
"loss": 0.1907,
|
2592 |
+
"num_input_tokens_seen": 13275848,
|
2593 |
+
"step": 323
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"epoch": 5.89908256880734,
|
2597 |
+
"grad_norm": 0.4578211307525635,
|
2598 |
+
"learning_rate": 3.969463130731183e-05,
|
2599 |
+
"loss": 0.27,
|
2600 |
+
"num_input_tokens_seen": 13311096,
|
2601 |
+
"step": 324
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 5.91743119266055,
|
2605 |
+
"grad_norm": 0.42030438780784607,
|
2606 |
+
"learning_rate": 3.963573584424852e-05,
|
2607 |
+
"loss": 0.1775,
|
2608 |
+
"num_input_tokens_seen": 13375064,
|
2609 |
+
"step": 325
|
2610 |
+
},
|
2611 |
+
{
|
2612 |
+
"epoch": 5.935779816513762,
|
2613 |
+
"grad_norm": 0.3531726598739624,
|
2614 |
+
"learning_rate": 3.957671653960337e-05,
|
2615 |
+
"loss": 0.1206,
|
2616 |
+
"num_input_tokens_seen": 13427072,
|
2617 |
+
"step": 326
|
2618 |
+
},
|
2619 |
+
{
|
2620 |
+
"epoch": 5.954128440366972,
|
2621 |
+
"grad_norm": 0.41528916358947754,
|
2622 |
+
"learning_rate": 3.9517573892773494e-05,
|
2623 |
+
"loss": 0.1232,
|
2624 |
+
"num_input_tokens_seen": 13454088,
|
2625 |
+
"step": 327
|
2626 |
+
},
|
2627 |
+
{
|
2628 |
+
"epoch": 5.972477064220183,
|
2629 |
+
"grad_norm": 0.5357607007026672,
|
2630 |
+
"learning_rate": 3.945830840419966e-05,
|
2631 |
+
"loss": 0.1696,
|
2632 |
+
"num_input_tokens_seen": 13486504,
|
2633 |
+
"step": 328
|
2634 |
+
},
|
2635 |
+
{
|
2636 |
+
"epoch": 5.990825688073395,
|
2637 |
+
"grad_norm": 0.32135313749313354,
|
2638 |
+
"learning_rate": 3.9398920575362086e-05,
|
2639 |
+
"loss": 0.1055,
|
2640 |
+
"num_input_tokens_seen": 13523736,
|
2641 |
+
"step": 329
|
2642 |
+
},
|
2643 |
+
{
|
2644 |
+
"epoch": 6.0,
|
2645 |
+
"grad_norm": 0.5267924666404724,
|
2646 |
+
"learning_rate": 3.933941090877615e-05,
|
2647 |
+
"loss": 0.2192,
|
2648 |
+
"num_input_tokens_seen": 13554528,
|
2649 |
+
"step": 330
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 6.018348623853211,
|
2653 |
+
"grad_norm": 0.38375183939933777,
|
2654 |
+
"learning_rate": 3.9279779907988215e-05,
|
2655 |
+
"loss": 0.1318,
|
2656 |
+
"num_input_tokens_seen": 13587424,
|
2657 |
+
"step": 331
|
2658 |
+
},
|
2659 |
+
{
|
2660 |
+
"epoch": 6.036697247706422,
|
2661 |
+
"grad_norm": 0.38274672627449036,
|
2662 |
+
"learning_rate": 3.9220028077571295e-05,
|
2663 |
+
"loss": 0.1136,
|
2664 |
+
"num_input_tokens_seen": 13624376,
|
2665 |
+
"step": 332
|
2666 |
+
},
|
2667 |
+
{
|
2668 |
+
"epoch": 6.055045871559633,
|
2669 |
+
"grad_norm": 0.3571849465370178,
|
2670 |
+
"learning_rate": 3.916015592312082e-05,
|
2671 |
+
"loss": 0.0891,
|
2672 |
+
"num_input_tokens_seen": 13652848,
|
2673 |
+
"step": 333
|
2674 |
+
},
|
2675 |
+
{
|
2676 |
+
"epoch": 6.073394495412844,
|
2677 |
+
"grad_norm": 0.3958500921726227,
|
2678 |
+
"learning_rate": 3.910016395125037e-05,
|
2679 |
+
"loss": 0.1477,
|
2680 |
+
"num_input_tokens_seen": 13719880,
|
2681 |
+
"step": 334
|
2682 |
+
},
|
2683 |
+
{
|
2684 |
+
"epoch": 6.091743119266055,
|
2685 |
+
"grad_norm": 0.3360799551010132,
|
2686 |
+
"learning_rate": 3.9040052669587325e-05,
|
2687 |
+
"loss": 0.0943,
|
2688 |
+
"num_input_tokens_seen": 13764864,
|
2689 |
+
"step": 335
|
2690 |
+
},
|
2691 |
+
{
|
2692 |
+
"epoch": 6.110091743119266,
|
2693 |
+
"grad_norm": 0.4332111179828644,
|
2694 |
+
"learning_rate": 3.897982258676867e-05,
|
2695 |
+
"loss": 0.1039,
|
2696 |
+
"num_input_tokens_seen": 13795048,
|
2697 |
+
"step": 336
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 6.128440366972477,
|
2701 |
+
"grad_norm": 0.4539923071861267,
|
2702 |
+
"learning_rate": 3.891947421243661e-05,
|
2703 |
+
"loss": 0.1294,
|
2704 |
+
"num_input_tokens_seen": 13830064,
|
2705 |
+
"step": 337
|
2706 |
+
},
|
2707 |
+
{
|
2708 |
+
"epoch": 6.146788990825688,
|
2709 |
+
"grad_norm": 0.43116849660873413,
|
2710 |
+
"learning_rate": 3.885900805723429e-05,
|
2711 |
+
"loss": 0.1233,
|
2712 |
+
"num_input_tokens_seen": 13870392,
|
2713 |
+
"step": 338
|
2714 |
+
},
|
2715 |
+
{
|
2716 |
+
"epoch": 6.165137614678899,
|
2717 |
+
"grad_norm": 0.40204253792762756,
|
2718 |
+
"learning_rate": 3.879842463280145e-05,
|
2719 |
+
"loss": 0.1252,
|
2720 |
+
"num_input_tokens_seen": 13913144,
|
2721 |
+
"step": 339
|
2722 |
+
},
|
2723 |
+
{
|
2724 |
+
"epoch": 6.18348623853211,
|
2725 |
+
"grad_norm": 0.4300351142883301,
|
2726 |
+
"learning_rate": 3.873772445177015e-05,
|
2727 |
+
"loss": 0.1191,
|
2728 |
+
"num_input_tokens_seen": 13950384,
|
2729 |
+
"step": 340
|
2730 |
+
},
|
2731 |
+
{
|
2732 |
+
"epoch": 6.201834862385321,
|
2733 |
+
"grad_norm": 0.3162730038166046,
|
2734 |
+
"learning_rate": 3.8676908027760364e-05,
|
2735 |
+
"loss": 0.1028,
|
2736 |
+
"num_input_tokens_seen": 13990464,
|
2737 |
+
"step": 341
|
2738 |
+
},
|
2739 |
+
{
|
2740 |
+
"epoch": 6.220183486238533,
|
2741 |
+
"grad_norm": 0.4316507875919342,
|
2742 |
+
"learning_rate": 3.861597587537568e-05,
|
2743 |
+
"loss": 0.0996,
|
2744 |
+
"num_input_tokens_seen": 14029080,
|
2745 |
+
"step": 342
|
2746 |
+
},
|
2747 |
+
{
|
2748 |
+
"epoch": 6.238532110091743,
|
2749 |
+
"grad_norm": 0.34346097707748413,
|
2750 |
+
"learning_rate": 3.855492851019893e-05,
|
2751 |
+
"loss": 0.172,
|
2752 |
+
"num_input_tokens_seen": 14069824,
|
2753 |
+
"step": 343
|
2754 |
+
},
|
2755 |
+
{
|
2756 |
+
"epoch": 6.256880733944954,
|
2757 |
+
"grad_norm": 0.41037800908088684,
|
2758 |
+
"learning_rate": 3.8493766448787825e-05,
|
2759 |
+
"loss": 0.1244,
|
2760 |
+
"num_input_tokens_seen": 14107616,
|
2761 |
+
"step": 344
|
2762 |
+
},
|
2763 |
+
{
|
2764 |
+
"epoch": 6.275229357798165,
|
2765 |
+
"grad_norm": 0.5019925236701965,
|
2766 |
+
"learning_rate": 3.84324902086706e-05,
|
2767 |
+
"loss": 0.1584,
|
2768 |
+
"num_input_tokens_seen": 14146224,
|
2769 |
+
"step": 345
|
2770 |
+
},
|
2771 |
+
{
|
2772 |
+
"epoch": 6.293577981651376,
|
2773 |
+
"grad_norm": 0.40119829773902893,
|
2774 |
+
"learning_rate": 3.837110030834161e-05,
|
2775 |
+
"loss": 0.1154,
|
2776 |
+
"num_input_tokens_seen": 14183880,
|
2777 |
+
"step": 346
|
2778 |
+
},
|
2779 |
+
{
|
2780 |
+
"epoch": 6.3119266055045875,
|
2781 |
+
"grad_norm": 0.37845325469970703,
|
2782 |
+
"learning_rate": 3.830959726725697e-05,
|
2783 |
+
"loss": 0.098,
|
2784 |
+
"num_input_tokens_seen": 14214632,
|
2785 |
+
"step": 347
|
2786 |
+
},
|
2787 |
+
{
|
2788 |
+
"epoch": 6.330275229357798,
|
2789 |
+
"grad_norm": 0.338489294052124,
|
2790 |
+
"learning_rate": 3.824798160583012e-05,
|
2791 |
+
"loss": 0.2212,
|
2792 |
+
"num_input_tokens_seen": 14263168,
|
2793 |
+
"step": 348
|
2794 |
+
},
|
2795 |
+
{
|
2796 |
+
"epoch": 6.348623853211009,
|
2797 |
+
"grad_norm": 0.4595409631729126,
|
2798 |
+
"learning_rate": 3.81862538454275e-05,
|
2799 |
+
"loss": 0.1423,
|
2800 |
+
"num_input_tokens_seen": 14303680,
|
2801 |
+
"step": 349
|
2802 |
+
},
|
2803 |
+
{
|
2804 |
+
"epoch": 6.36697247706422,
|
2805 |
+
"grad_norm": 0.38874781131744385,
|
2806 |
+
"learning_rate": 3.8124414508364e-05,
|
2807 |
+
"loss": 0.1119,
|
2808 |
+
"num_input_tokens_seen": 14347672,
|
2809 |
+
"step": 350
|
2810 |
+
},
|
2811 |
+
{
|
2812 |
+
"epoch": 6.385321100917431,
|
2813 |
+
"grad_norm": 0.3326081931591034,
|
2814 |
+
"learning_rate": 3.8062464117898724e-05,
|
2815 |
+
"loss": 0.1068,
|
2816 |
+
"num_input_tokens_seen": 14394848,
|
2817 |
+
"step": 351
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 6.4036697247706424,
|
2821 |
+
"grad_norm": 0.40956059098243713,
|
2822 |
+
"learning_rate": 3.8000403198230387e-05,
|
2823 |
+
"loss": 0.1051,
|
2824 |
+
"num_input_tokens_seen": 14438856,
|
2825 |
+
"step": 352
|
2826 |
+
},
|
2827 |
+
{
|
2828 |
+
"epoch": 6.422018348623853,
|
2829 |
+
"grad_norm": 0.353677362203598,
|
2830 |
+
"learning_rate": 3.7938232274493e-05,
|
2831 |
+
"loss": 0.2208,
|
2832 |
+
"num_input_tokens_seen": 14498032,
|
2833 |
+
"step": 353
|
2834 |
+
},
|
2835 |
+
{
|
2836 |
+
"epoch": 6.440366972477064,
|
2837 |
+
"grad_norm": 0.45626017451286316,
|
2838 |
+
"learning_rate": 3.787595187275136e-05,
|
2839 |
+
"loss": 0.1131,
|
2840 |
+
"num_input_tokens_seen": 14534256,
|
2841 |
+
"step": 354
|
2842 |
+
},
|
2843 |
+
{
|
2844 |
+
"epoch": 6.458715596330276,
|
2845 |
+
"grad_norm": 0.4512569308280945,
|
2846 |
+
"learning_rate": 3.781356251999663e-05,
|
2847 |
+
"loss": 0.1207,
|
2848 |
+
"num_input_tokens_seen": 14575016,
|
2849 |
+
"step": 355
|
2850 |
+
},
|
2851 |
+
{
|
2852 |
+
"epoch": 6.477064220183486,
|
2853 |
+
"grad_norm": 0.3183128237724304,
|
2854 |
+
"learning_rate": 3.775106474414188e-05,
|
2855 |
+
"loss": 0.0887,
|
2856 |
+
"num_input_tokens_seen": 14627272,
|
2857 |
+
"step": 356
|
2858 |
+
},
|
2859 |
+
{
|
2860 |
+
"epoch": 6.495412844036697,
|
2861 |
+
"grad_norm": 0.36176785826683044,
|
2862 |
+
"learning_rate": 3.7688459074017606e-05,
|
2863 |
+
"loss": 0.1022,
|
2864 |
+
"num_input_tokens_seen": 14658696,
|
2865 |
+
"step": 357
|
2866 |
+
},
|
2867 |
+
{
|
2868 |
+
"epoch": 6.513761467889909,
|
2869 |
+
"grad_norm": 0.362131804227829,
|
2870 |
+
"learning_rate": 3.762574603936725e-05,
|
2871 |
+
"loss": 0.1582,
|
2872 |
+
"num_input_tokens_seen": 14702208,
|
2873 |
+
"step": 358
|
2874 |
+
},
|
2875 |
+
{
|
2876 |
+
"epoch": 6.532110091743119,
|
2877 |
+
"grad_norm": 0.27560174465179443,
|
2878 |
+
"learning_rate": 3.756292617084275e-05,
|
2879 |
+
"loss": 0.0855,
|
2880 |
+
"num_input_tokens_seen": 14757376,
|
2881 |
+
"step": 359
|
2882 |
+
},
|
2883 |
+
{
|
2884 |
+
"epoch": 6.5504587155963305,
|
2885 |
+
"grad_norm": 0.4014551043510437,
|
2886 |
+
"learning_rate": 3.7500000000000003e-05,
|
2887 |
+
"loss": 0.1923,
|
2888 |
+
"num_input_tokens_seen": 14796592,
|
2889 |
+
"step": 360
|
2890 |
+
},
|
2891 |
+
{
|
2892 |
+
"epoch": 6.568807339449541,
|
2893 |
+
"grad_norm": 0.38982701301574707,
|
2894 |
+
"learning_rate": 3.7436968059294414e-05,
|
2895 |
+
"loss": 0.1125,
|
2896 |
+
"num_input_tokens_seen": 14834656,
|
2897 |
+
"step": 361
|
2898 |
+
},
|
2899 |
+
{
|
2900 |
+
"epoch": 6.587155963302752,
|
2901 |
+
"grad_norm": 0.3973703384399414,
|
2902 |
+
"learning_rate": 3.7373830882076354e-05,
|
2903 |
+
"loss": 0.1947,
|
2904 |
+
"num_input_tokens_seen": 14869528,
|
2905 |
+
"step": 362
|
2906 |
+
},
|
2907 |
+
{
|
2908 |
+
"epoch": 6.605504587155964,
|
2909 |
+
"grad_norm": 0.43253588676452637,
|
2910 |
+
"learning_rate": 3.731058900258668e-05,
|
2911 |
+
"loss": 0.1173,
|
2912 |
+
"num_input_tokens_seen": 14909720,
|
2913 |
+
"step": 363
|
2914 |
+
},
|
2915 |
+
{
|
2916 |
+
"epoch": 6.623853211009174,
|
2917 |
+
"grad_norm": 0.4936161935329437,
|
2918 |
+
"learning_rate": 3.7247242955952175e-05,
|
2919 |
+
"loss": 0.1523,
|
2920 |
+
"num_input_tokens_seen": 14952704,
|
2921 |
+
"step": 364
|
2922 |
+
},
|
2923 |
+
{
|
2924 |
+
"epoch": 6.6422018348623855,
|
2925 |
+
"grad_norm": 0.43221941590309143,
|
2926 |
+
"learning_rate": 3.718379327818106e-05,
|
2927 |
+
"loss": 0.1313,
|
2928 |
+
"num_input_tokens_seen": 14989640,
|
2929 |
+
"step": 365
|
2930 |
+
},
|
2931 |
+
{
|
2932 |
+
"epoch": 6.660550458715596,
|
2933 |
+
"grad_norm": 0.3976401686668396,
|
2934 |
+
"learning_rate": 3.712024050615843e-05,
|
2935 |
+
"loss": 0.0985,
|
2936 |
+
"num_input_tokens_seen": 15028200,
|
2937 |
+
"step": 366
|
2938 |
+
},
|
2939 |
+
{
|
2940 |
+
"epoch": 6.678899082568807,
|
2941 |
+
"grad_norm": 0.3843483030796051,
|
2942 |
+
"learning_rate": 3.705658517764172e-05,
|
2943 |
+
"loss": 0.1905,
|
2944 |
+
"num_input_tokens_seen": 15075960,
|
2945 |
+
"step": 367
|
2946 |
+
},
|
2947 |
+
{
|
2948 |
+
"epoch": 6.697247706422019,
|
2949 |
+
"grad_norm": 0.45637550950050354,
|
2950 |
+
"learning_rate": 3.699282783125616e-05,
|
2951 |
+
"loss": 0.1166,
|
2952 |
+
"num_input_tokens_seen": 15113096,
|
2953 |
+
"step": 368
|
2954 |
+
},
|
2955 |
+
{
|
2956 |
+
"epoch": 6.715596330275229,
|
2957 |
+
"grad_norm": 0.3767227232456207,
|
2958 |
+
"learning_rate": 3.692896900649021e-05,
|
2959 |
+
"loss": 0.138,
|
2960 |
+
"num_input_tokens_seen": 15162432,
|
2961 |
+
"step": 369
|
2962 |
+
},
|
2963 |
+
{
|
2964 |
+
"epoch": 6.73394495412844,
|
2965 |
+
"grad_norm": 0.3972814977169037,
|
2966 |
+
"learning_rate": 3.686500924369101e-05,
|
2967 |
+
"loss": 0.1612,
|
2968 |
+
"num_input_tokens_seen": 15203656,
|
2969 |
+
"step": 370
|
2970 |
+
},
|
2971 |
+
{
|
2972 |
+
"epoch": 6.752293577981652,
|
2973 |
+
"grad_norm": 0.39401331543922424,
|
2974 |
+
"learning_rate": 3.680094908405978e-05,
|
2975 |
+
"loss": 0.1131,
|
2976 |
+
"num_input_tokens_seen": 15251056,
|
2977 |
+
"step": 371
|
2978 |
+
},
|
2979 |
+
{
|
2980 |
+
"epoch": 6.770642201834862,
|
2981 |
+
"grad_norm": 0.5119125247001648,
|
2982 |
+
"learning_rate": 3.673678906964727e-05,
|
2983 |
+
"loss": 0.1264,
|
2984 |
+
"num_input_tokens_seen": 15283552,
|
2985 |
+
"step": 372
|
2986 |
+
},
|
2987 |
+
{
|
2988 |
+
"epoch": 6.7889908256880735,
|
2989 |
+
"grad_norm": 0.38780996203422546,
|
2990 |
+
"learning_rate": 3.6672529743349146e-05,
|
2991 |
+
"loss": 0.1167,
|
2992 |
+
"num_input_tokens_seen": 15338944,
|
2993 |
+
"step": 373
|
2994 |
+
},
|
2995 |
+
{
|
2996 |
+
"epoch": 6.807339449541285,
|
2997 |
+
"grad_norm": 0.45605945587158203,
|
2998 |
+
"learning_rate": 3.660817164890143e-05,
|
2999 |
+
"loss": 0.131,
|
3000 |
+
"num_input_tokens_seen": 15369936,
|
3001 |
+
"step": 374
|
3002 |
+
},
|
3003 |
+
{
|
3004 |
+
"epoch": 6.825688073394495,
|
3005 |
+
"grad_norm": 0.4043484926223755,
|
3006 |
+
"learning_rate": 3.654371533087586e-05,
|
3007 |
+
"loss": 0.095,
|
3008 |
+
"num_input_tokens_seen": 15411576,
|
3009 |
+
"step": 375
|
3010 |
+
},
|
3011 |
+
{
|
3012 |
+
"epoch": 6.844036697247707,
|
3013 |
+
"grad_norm": 0.38716065883636475,
|
3014 |
+
"learning_rate": 3.6479161334675296e-05,
|
3015 |
+
"loss": 0.0937,
|
3016 |
+
"num_input_tokens_seen": 15457520,
|
3017 |
+
"step": 376
|
3018 |
+
},
|
3019 |
+
{
|
3020 |
+
"epoch": 6.862385321100917,
|
3021 |
+
"grad_norm": 0.38785362243652344,
|
3022 |
+
"learning_rate": 3.641451020652914e-05,
|
3023 |
+
"loss": 0.1017,
|
3024 |
+
"num_input_tokens_seen": 15485536,
|
3025 |
+
"step": 377
|
3026 |
+
},
|
3027 |
+
{
|
3028 |
+
"epoch": 6.8807339449541285,
|
3029 |
+
"grad_norm": 0.3736408054828644,
|
3030 |
+
"learning_rate": 3.634976249348867e-05,
|
3031 |
+
"loss": 0.1075,
|
3032 |
+
"num_input_tokens_seen": 15526704,
|
3033 |
+
"step": 378
|
3034 |
+
},
|
3035 |
+
{
|
3036 |
+
"epoch": 6.89908256880734,
|
3037 |
+
"grad_norm": 0.5013216733932495,
|
3038 |
+
"learning_rate": 3.6284918743422425e-05,
|
3039 |
+
"loss": 0.132,
|
3040 |
+
"num_input_tokens_seen": 15567344,
|
3041 |
+
"step": 379
|
3042 |
+
},
|
3043 |
+
{
|
3044 |
+
"epoch": 6.91743119266055,
|
3045 |
+
"grad_norm": 0.5258253216743469,
|
3046 |
+
"learning_rate": 3.621997950501156e-05,
|
3047 |
+
"loss": 0.1435,
|
3048 |
+
"num_input_tokens_seen": 15608408,
|
3049 |
+
"step": 380
|
3050 |
+
},
|
3051 |
+
{
|
3052 |
+
"epoch": 6.935779816513762,
|
3053 |
+
"grad_norm": 0.3486093282699585,
|
3054 |
+
"learning_rate": 3.615494532774522e-05,
|
3055 |
+
"loss": 0.0958,
|
3056 |
+
"num_input_tokens_seen": 15667496,
|
3057 |
+
"step": 381
|
3058 |
+
},
|
3059 |
+
{
|
3060 |
+
"epoch": 6.954128440366972,
|
3061 |
+
"grad_norm": 0.39199239015579224,
|
3062 |
+
"learning_rate": 3.6089816761915906e-05,
|
3063 |
+
"loss": 0.1465,
|
3064 |
+
"num_input_tokens_seen": 15715496,
|
3065 |
+
"step": 382
|
3066 |
+
},
|
3067 |
+
{
|
3068 |
+
"epoch": 6.972477064220183,
|
3069 |
+
"grad_norm": 0.3722994923591614,
|
3070 |
+
"learning_rate": 3.602459435861475e-05,
|
3071 |
+
"loss": 0.1111,
|
3072 |
+
"num_input_tokens_seen": 15755688,
|
3073 |
+
"step": 383
|
3074 |
+
},
|
3075 |
+
{
|
3076 |
+
"epoch": 6.990825688073395,
|
3077 |
+
"grad_norm": 0.41041186451911926,
|
3078 |
+
"learning_rate": 3.5959278669726935e-05,
|
3079 |
+
"loss": 0.1084,
|
3080 |
+
"num_input_tokens_seen": 15798304,
|
3081 |
+
"step": 384
|
3082 |
+
},
|
3083 |
+
{
|
3084 |
+
"epoch": 7.0,
|
3085 |
+
"grad_norm": 0.6807722449302673,
|
3086 |
+
"learning_rate": 3.589387024792699e-05,
|
3087 |
+
"loss": 0.1234,
|
3088 |
+
"num_input_tokens_seen": 15813616,
|
3089 |
+
"step": 385
|
3090 |
+
},
|
3091 |
+
{
|
3092 |
+
"epoch": 7.018348623853211,
|
3093 |
+
"grad_norm": 0.3617340922355652,
|
3094 |
+
"learning_rate": 3.582836964667408e-05,
|
3095 |
+
"loss": 0.1167,
|
3096 |
+
"num_input_tokens_seen": 15855256,
|
3097 |
+
"step": 386
|
3098 |
+
},
|
3099 |
+
{
|
3100 |
+
"epoch": 7.036697247706422,
|
3101 |
+
"grad_norm": 0.36471137404441833,
|
3102 |
+
"learning_rate": 3.576277742020738e-05,
|
3103 |
+
"loss": 0.0829,
|
3104 |
+
"num_input_tokens_seen": 15887512,
|
3105 |
+
"step": 387
|
3106 |
+
},
|
3107 |
+
{
|
3108 |
+
"epoch": 7.055045871559633,
|
3109 |
+
"grad_norm": 0.8828345537185669,
|
3110 |
+
"learning_rate": 3.569709412354136e-05,
|
3111 |
+
"loss": 0.1213,
|
3112 |
+
"num_input_tokens_seen": 15934400,
|
3113 |
+
"step": 388
|
3114 |
+
},
|
3115 |
+
{
|
3116 |
+
"epoch": 7.073394495412844,
|
3117 |
+
"grad_norm": 0.4129248261451721,
|
3118 |
+
"learning_rate": 3.563132031246108e-05,
|
3119 |
+
"loss": 0.0914,
|
3120 |
+
"num_input_tokens_seen": 15969904,
|
3121 |
+
"step": 389
|
3122 |
+
},
|
3123 |
+
{
|
3124 |
+
"epoch": 7.091743119266055,
|
3125 |
+
"grad_norm": 0.38659873604774475,
|
3126 |
+
"learning_rate": 3.556545654351749e-05,
|
3127 |
+
"loss": 0.09,
|
3128 |
+
"num_input_tokens_seen": 16010760,
|
3129 |
+
"step": 390
|
3130 |
+
},
|
3131 |
+
{
|
3132 |
+
"epoch": 7.110091743119266,
|
3133 |
+
"grad_norm": 0.46532171964645386,
|
3134 |
+
"learning_rate": 3.549950337402274e-05,
|
3135 |
+
"loss": 0.0832,
|
3136 |
+
"num_input_tokens_seen": 16059680,
|
3137 |
+
"step": 391
|
3138 |
+
},
|
3139 |
+
{
|
3140 |
+
"epoch": 7.128440366972477,
|
3141 |
+
"grad_norm": 0.3775540888309479,
|
3142 |
+
"learning_rate": 3.543346136204545e-05,
|
3143 |
+
"loss": 0.079,
|
3144 |
+
"num_input_tokens_seen": 16095992,
|
3145 |
+
"step": 392
|
3146 |
+
},
|
3147 |
+
{
|
3148 |
+
"epoch": 7.146788990825688,
|
3149 |
+
"grad_norm": 0.5437320470809937,
|
3150 |
+
"learning_rate": 3.536733106640598e-05,
|
3151 |
+
"loss": 0.1,
|
3152 |
+
"num_input_tokens_seen": 16135568,
|
3153 |
+
"step": 393
|
3154 |
+
},
|
3155 |
+
{
|
3156 |
+
"epoch": 7.165137614678899,
|
3157 |
+
"grad_norm": 0.3908531963825226,
|
3158 |
+
"learning_rate": 3.5301113046671714e-05,
|
3159 |
+
"loss": 0.0962,
|
3160 |
+
"num_input_tokens_seen": 16165016,
|
3161 |
+
"step": 394
|
3162 |
+
},
|
3163 |
+
{
|
3164 |
+
"epoch": 7.18348623853211,
|
3165 |
+
"grad_norm": 0.40789636969566345,
|
3166 |
+
"learning_rate": 3.523480786315231e-05,
|
3167 |
+
"loss": 0.0923,
|
3168 |
+
"num_input_tokens_seen": 16208344,
|
3169 |
+
"step": 395
|
3170 |
+
},
|
3171 |
+
{
|
3172 |
+
"epoch": 7.201834862385321,
|
3173 |
+
"grad_norm": 0.4682011902332306,
|
3174 |
+
"learning_rate": 3.516841607689501e-05,
|
3175 |
+
"loss": 0.101,
|
3176 |
+
"num_input_tokens_seen": 16244312,
|
3177 |
+
"step": 396
|
3178 |
+
},
|
3179 |
+
{
|
3180 |
+
"epoch": 7.220183486238533,
|
3181 |
+
"grad_norm": 0.5206179618835449,
|
3182 |
+
"learning_rate": 3.5101938249679794e-05,
|
3183 |
+
"loss": 0.1124,
|
3184 |
+
"num_input_tokens_seen": 16283848,
|
3185 |
+
"step": 397
|
3186 |
+
},
|
3187 |
+
{
|
3188 |
+
"epoch": 7.238532110091743,
|
3189 |
+
"grad_norm": 0.5803564786911011,
|
3190 |
+
"learning_rate": 3.503537494401473e-05,
|
3191 |
+
"loss": 0.1054,
|
3192 |
+
"num_input_tokens_seen": 16336288,
|
3193 |
+
"step": 398
|
3194 |
+
},
|
3195 |
+
{
|
3196 |
+
"epoch": 7.256880733944954,
|
3197 |
+
"grad_norm": 0.44892576336860657,
|
3198 |
+
"learning_rate": 3.496872672313116e-05,
|
3199 |
+
"loss": 0.1781,
|
3200 |
+
"num_input_tokens_seen": 16375448,
|
3201 |
+
"step": 399
|
3202 |
+
},
|
3203 |
+
{
|
3204 |
+
"epoch": 7.275229357798165,
|
3205 |
+
"grad_norm": 0.42554035782814026,
|
3206 |
+
"learning_rate": 3.490199415097892e-05,
|
3207 |
+
"loss": 0.0935,
|
3208 |
+
"num_input_tokens_seen": 16412608,
|
3209 |
+
"step": 400
|
3210 |
+
},
|
3211 |
+
{
|
3212 |
+
"epoch": 7.293577981651376,
|
3213 |
+
"grad_norm": 0.3525730073451996,
|
3214 |
+
"learning_rate": 3.483517779222163e-05,
|
3215 |
+
"loss": 0.0944,
|
3216 |
+
"num_input_tokens_seen": 16455904,
|
3217 |
+
"step": 401
|
3218 |
+
},
|
3219 |
+
{
|
3220 |
+
"epoch": 7.3119266055045875,
|
3221 |
+
"grad_norm": 0.3382134735584259,
|
3222 |
+
"learning_rate": 3.476827821223184e-05,
|
3223 |
+
"loss": 0.0878,
|
3224 |
+
"num_input_tokens_seen": 16496824,
|
3225 |
+
"step": 402
|
3226 |
+
},
|
3227 |
+
{
|
3228 |
+
"epoch": 7.330275229357798,
|
3229 |
+
"grad_norm": 0.38020089268684387,
|
3230 |
+
"learning_rate": 3.4701295977086324e-05,
|
3231 |
+
"loss": 0.0911,
|
3232 |
+
"num_input_tokens_seen": 16529344,
|
3233 |
+
"step": 403
|
3234 |
+
},
|
3235 |
+
{
|
3236 |
+
"epoch": 7.348623853211009,
|
3237 |
+
"grad_norm": 0.44909772276878357,
|
3238 |
+
"learning_rate": 3.463423165356121e-05,
|
3239 |
+
"loss": 0.1047,
|
3240 |
+
"num_input_tokens_seen": 16563664,
|
3241 |
+
"step": 404
|
3242 |
+
},
|
3243 |
+
{
|
3244 |
+
"epoch": 7.36697247706422,
|
3245 |
+
"grad_norm": 0.3612752854824066,
|
3246 |
+
"learning_rate": 3.456708580912725e-05,
|
3247 |
+
"loss": 0.1228,
|
3248 |
+
"num_input_tokens_seen": 16607272,
|
3249 |
+
"step": 405
|
3250 |
+
},
|
3251 |
+
{
|
3252 |
+
"epoch": 7.385321100917431,
|
3253 |
+
"grad_norm": 0.5135468244552612,
|
3254 |
+
"learning_rate": 3.449985901194498e-05,
|
3255 |
+
"loss": 0.1801,
|
3256 |
+
"num_input_tokens_seen": 16646040,
|
3257 |
+
"step": 406
|
3258 |
+
},
|
3259 |
+
{
|
3260 |
+
"epoch": 7.4036697247706424,
|
3261 |
+
"grad_norm": 0.33949241042137146,
|
3262 |
+
"learning_rate": 3.443255183085993e-05,
|
3263 |
+
"loss": 0.0883,
|
3264 |
+
"num_input_tokens_seen": 16693544,
|
3265 |
+
"step": 407
|
3266 |
+
},
|
3267 |
+
{
|
3268 |
+
"epoch": 7.422018348623853,
|
3269 |
+
"grad_norm": 0.3560762405395508,
|
3270 |
+
"learning_rate": 3.436516483539781e-05,
|
3271 |
+
"loss": 0.083,
|
3272 |
+
"num_input_tokens_seen": 16742128,
|
3273 |
+
"step": 408
|
3274 |
+
},
|
3275 |
+
{
|
3276 |
+
"epoch": 7.440366972477064,
|
3277 |
+
"grad_norm": 0.32824087142944336,
|
3278 |
+
"learning_rate": 3.4297698595759664e-05,
|
3279 |
+
"loss": 0.1247,
|
3280 |
+
"num_input_tokens_seen": 16792000,
|
3281 |
+
"step": 409
|
3282 |
+
},
|
3283 |
+
{
|
3284 |
+
"epoch": 7.458715596330276,
|
3285 |
+
"grad_norm": 0.44831863045692444,
|
3286 |
+
"learning_rate": 3.423015368281711e-05,
|
3287 |
+
"loss": 0.0948,
|
3288 |
+
"num_input_tokens_seen": 16824312,
|
3289 |
+
"step": 410
|
3290 |
+
},
|
3291 |
+
{
|
3292 |
+
"epoch": 7.477064220183486,
|
3293 |
+
"grad_norm": 0.4942893981933594,
|
3294 |
+
"learning_rate": 3.4162530668107434e-05,
|
3295 |
+
"loss": 0.0993,
|
3296 |
+
"num_input_tokens_seen": 16856344,
|
3297 |
+
"step": 411
|
3298 |
+
},
|
3299 |
+
{
|
3300 |
+
"epoch": 7.495412844036697,
|
3301 |
+
"grad_norm": 0.3783268332481384,
|
3302 |
+
"learning_rate": 3.409483012382879e-05,
|
3303 |
+
"loss": 0.1273,
|
3304 |
+
"num_input_tokens_seen": 16898256,
|
3305 |
+
"step": 412
|
3306 |
+
},
|
3307 |
+
{
|
3308 |
+
"epoch": 7.513761467889909,
|
3309 |
+
"grad_norm": 0.5532792210578918,
|
3310 |
+
"learning_rate": 3.402705262283537e-05,
|
3311 |
+
"loss": 0.1171,
|
3312 |
+
"num_input_tokens_seen": 16939304,
|
3313 |
+
"step": 413
|
3314 |
+
},
|
3315 |
+
{
|
3316 |
+
"epoch": 7.532110091743119,
|
3317 |
+
"grad_norm": 0.3667624592781067,
|
3318 |
+
"learning_rate": 3.39591987386325e-05,
|
3319 |
+
"loss": 0.1753,
|
3320 |
+
"num_input_tokens_seen": 16978632,
|
3321 |
+
"step": 414
|
3322 |
+
},
|
3323 |
+
{
|
3324 |
+
"epoch": 7.5504587155963305,
|
3325 |
+
"grad_norm": 0.42965346574783325,
|
3326 |
+
"learning_rate": 3.389126904537192e-05,
|
3327 |
+
"loss": 0.1567,
|
3328 |
+
"num_input_tokens_seen": 17016552,
|
3329 |
+
"step": 415
|
3330 |
+
},
|
3331 |
+
{
|
3332 |
+
"epoch": 7.568807339449541,
|
3333 |
+
"grad_norm": 0.41699931025505066,
|
3334 |
+
"learning_rate": 3.382326411784672e-05,
|
3335 |
+
"loss": 0.0941,
|
3336 |
+
"num_input_tokens_seen": 17067688,
|
3337 |
+
"step": 416
|
3338 |
+
},
|
3339 |
+
{
|
3340 |
+
"epoch": 7.587155963302752,
|
3341 |
+
"grad_norm": 0.3647185266017914,
|
3342 |
+
"learning_rate": 3.375518453148669e-05,
|
3343 |
+
"loss": 0.0961,
|
3344 |
+
"num_input_tokens_seen": 17126008,
|
3345 |
+
"step": 417
|
3346 |
+
},
|
3347 |
+
{
|
3348 |
+
"epoch": 7.605504587155964,
|
3349 |
+
"grad_norm": 0.5344395041465759,
|
3350 |
+
"learning_rate": 3.3687030862353286e-05,
|
3351 |
+
"loss": 0.1974,
|
3352 |
+
"num_input_tokens_seen": 17165800,
|
3353 |
+
"step": 418
|
3354 |
+
},
|
3355 |
+
{
|
3356 |
+
"epoch": 7.623853211009174,
|
3357 |
+
"grad_norm": 0.38556504249572754,
|
3358 |
+
"learning_rate": 3.361880368713486e-05,
|
3359 |
+
"loss": 0.094,
|
3360 |
+
"num_input_tokens_seen": 17199832,
|
3361 |
+
"step": 419
|
3362 |
+
},
|
3363 |
+
{
|
3364 |
+
"epoch": 7.6422018348623855,
|
3365 |
+
"grad_norm": 0.3512709438800812,
|
3366 |
+
"learning_rate": 3.355050358314172e-05,
|
3367 |
+
"loss": 0.0717,
|
3368 |
+
"num_input_tokens_seen": 17237952,
|
3369 |
+
"step": 420
|
3370 |
+
},
|
3371 |
+
{
|
3372 |
+
"epoch": 7.660550458715596,
|
3373 |
+
"grad_norm": 0.35488539934158325,
|
3374 |
+
"learning_rate": 3.348213112830128e-05,
|
3375 |
+
"loss": 0.0943,
|
3376 |
+
"num_input_tokens_seen": 17278384,
|
3377 |
+
"step": 421
|
3378 |
+
},
|
3379 |
+
{
|
3380 |
+
"epoch": 7.678899082568807,
|
3381 |
+
"grad_norm": 0.4220011234283447,
|
3382 |
+
"learning_rate": 3.3413686901153165e-05,
|
3383 |
+
"loss": 0.0814,
|
3384 |
+
"num_input_tokens_seen": 17309544,
|
3385 |
+
"step": 422
|
3386 |
+
},
|
3387 |
+
{
|
3388 |
+
"epoch": 7.697247706422019,
|
3389 |
+
"grad_norm": 0.42773446440696716,
|
3390 |
+
"learning_rate": 3.3345171480844275e-05,
|
3391 |
+
"loss": 0.1192,
|
3392 |
+
"num_input_tokens_seen": 17344896,
|
3393 |
+
"step": 423
|
3394 |
+
},
|
3395 |
+
{
|
3396 |
+
"epoch": 7.715596330275229,
|
3397 |
+
"grad_norm": 0.30265432596206665,
|
3398 |
+
"learning_rate": 3.327658544712395e-05,
|
3399 |
+
"loss": 0.104,
|
3400 |
+
"num_input_tokens_seen": 17413176,
|
3401 |
+
"step": 424
|
3402 |
+
},
|
3403 |
+
{
|
3404 |
+
"epoch": 7.73394495412844,
|
3405 |
+
"grad_norm": 0.38354116678237915,
|
3406 |
+
"learning_rate": 3.3207929380339034e-05,
|
3407 |
+
"loss": 0.0965,
|
3408 |
+
"num_input_tokens_seen": 17450416,
|
3409 |
+
"step": 425
|
3410 |
+
},
|
3411 |
+
{
|
3412 |
+
"epoch": 7.752293577981652,
|
3413 |
+
"grad_norm": 0.33634060621261597,
|
3414 |
+
"learning_rate": 3.313920386142892e-05,
|
3415 |
+
"loss": 0.0775,
|
3416 |
+
"num_input_tokens_seen": 17491256,
|
3417 |
+
"step": 426
|
3418 |
+
},
|
3419 |
+
{
|
3420 |
+
"epoch": 7.770642201834862,
|
3421 |
+
"grad_norm": 0.4931448698043823,
|
3422 |
+
"learning_rate": 3.3070409471920726e-05,
|
3423 |
+
"loss": 0.1651,
|
3424 |
+
"num_input_tokens_seen": 17521600,
|
3425 |
+
"step": 427
|
3426 |
+
},
|
3427 |
+
{
|
3428 |
+
"epoch": 7.7889908256880735,
|
3429 |
+
"grad_norm": 0.4020994007587433,
|
3430 |
+
"learning_rate": 3.3001546793924285e-05,
|
3431 |
+
"loss": 0.1071,
|
3432 |
+
"num_input_tokens_seen": 17564288,
|
3433 |
+
"step": 428
|
3434 |
+
},
|
3435 |
+
{
|
3436 |
+
"epoch": 7.807339449541285,
|
3437 |
+
"grad_norm": 0.47053155303001404,
|
3438 |
+
"learning_rate": 3.293261641012731e-05,
|
3439 |
+
"loss": 0.0987,
|
3440 |
+
"num_input_tokens_seen": 17604304,
|
3441 |
+
"step": 429
|
3442 |
+
},
|
3443 |
+
{
|
3444 |
+
"epoch": 7.825688073394495,
|
3445 |
+
"grad_norm": 0.6638731956481934,
|
3446 |
+
"learning_rate": 3.2863618903790346e-05,
|
3447 |
+
"loss": 0.1743,
|
3448 |
+
"num_input_tokens_seen": 17641384,
|
3449 |
+
"step": 430
|
3450 |
+
},
|
3451 |
+
{
|
3452 |
+
"epoch": 7.844036697247707,
|
3453 |
+
"grad_norm": 0.4213615357875824,
|
3454 |
+
"learning_rate": 3.279455485874195e-05,
|
3455 |
+
"loss": 0.0854,
|
3456 |
+
"num_input_tokens_seen": 17680560,
|
3457 |
+
"step": 431
|
3458 |
+
},
|
3459 |
+
{
|
3460 |
+
"epoch": 7.862385321100917,
|
3461 |
+
"grad_norm": 0.47264209389686584,
|
3462 |
+
"learning_rate": 3.272542485937369e-05,
|
3463 |
+
"loss": 0.0949,
|
3464 |
+
"num_input_tokens_seen": 17715312,
|
3465 |
+
"step": 432
|
3466 |
+
}
|
3467 |
+
],
|
3468 |
+
"logging_steps": 1.0,
|
3469 |
+
"max_steps": 1080,
|
3470 |
+
"num_input_tokens_seen": 17715312,
|
3471 |
+
"num_train_epochs": 20,
|
3472 |
+
"save_steps": 54,
|
3473 |
+
"stateful_callbacks": {
|
3474 |
+
"TrainerControl": {
|
3475 |
+
"args": {
|
3476 |
+
"should_epoch_stop": false,
|
3477 |
+
"should_evaluate": false,
|
3478 |
+
"should_log": false,
|
3479 |
+
"should_save": true,
|
3480 |
+
"should_training_stop": false
|
3481 |
+
},
|
3482 |
+
"attributes": {}
|
3483 |
+
}
|
3484 |
+
},
|
3485 |
+
"total_flos": 1.4944933548665078e+18,
|
3486 |
+
"train_batch_size": 1,
|
3487 |
+
"trial_name": null,
|
3488 |
+
"trial_params": null
|
3489 |
+
}
|
checkpoint-432/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-486/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-486/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"up_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"o_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-486/added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
checkpoint-486/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-486/special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
checkpoint-486/tokenizer_config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 15000,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"padding_side": "right",
|
206 |
+
"split_special_tokens": false,
|
207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
+
"unk_token": null
|
209 |
+
}
|
checkpoint-486/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-486/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-540/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-540/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"up_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"o_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-540/added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
checkpoint-540/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-540/special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
checkpoint-540/tokenizer_config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 15000,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"padding_side": "right",
|
206 |
+
"split_special_tokens": false,
|
207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
+
"unk_token": null
|
209 |
+
}
|
checkpoint-540/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-540/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-594/README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Qwen/Qwen2.5-Coder-14B-Instruct
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
200 |
+
### Framework versions
|
201 |
+
|
202 |
+
- PEFT 0.12.0
|
checkpoint-594/adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2.5-Coder-14B-Instruct",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj",
|
25 |
+
"up_proj",
|
26 |
+
"gate_proj",
|
27 |
+
"o_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
checkpoint-594/added_tokens.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</tool_call>": 151658,
|
3 |
+
"<tool_call>": 151657,
|
4 |
+
"<|box_end|>": 151649,
|
5 |
+
"<|box_start|>": 151648,
|
6 |
+
"<|endoftext|>": 151643,
|
7 |
+
"<|file_sep|>": 151664,
|
8 |
+
"<|fim_middle|>": 151660,
|
9 |
+
"<|fim_pad|>": 151662,
|
10 |
+
"<|fim_prefix|>": 151659,
|
11 |
+
"<|fim_suffix|>": 151661,
|
12 |
+
"<|im_end|>": 151645,
|
13 |
+
"<|im_start|>": 151644,
|
14 |
+
"<|image_pad|>": 151655,
|
15 |
+
"<|object_ref_end|>": 151647,
|
16 |
+
"<|object_ref_start|>": 151646,
|
17 |
+
"<|quad_end|>": 151651,
|
18 |
+
"<|quad_start|>": 151650,
|
19 |
+
"<|repo_name|>": 151663,
|
20 |
+
"<|video_pad|>": 151656,
|
21 |
+
"<|vision_end|>": 151653,
|
22 |
+
"<|vision_pad|>": 151654,
|
23 |
+
"<|vision_start|>": 151652
|
24 |
+
}
|
checkpoint-594/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-594/special_tokens_map.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>",
|
5 |
+
"<|object_ref_start|>",
|
6 |
+
"<|object_ref_end|>",
|
7 |
+
"<|box_start|>",
|
8 |
+
"<|box_end|>",
|
9 |
+
"<|quad_start|>",
|
10 |
+
"<|quad_end|>",
|
11 |
+
"<|vision_start|>",
|
12 |
+
"<|vision_end|>",
|
13 |
+
"<|vision_pad|>",
|
14 |
+
"<|image_pad|>",
|
15 |
+
"<|video_pad|>"
|
16 |
+
],
|
17 |
+
"eos_token": {
|
18 |
+
"content": "<|im_end|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": {
|
25 |
+
"content": "<|endoftext|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
}
|
31 |
+
}
|
checkpoint-594/tokenizer_config.json
ADDED
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"151643": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"151644": {
|
14 |
+
"content": "<|im_start|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"151645": {
|
22 |
+
"content": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"151646": {
|
30 |
+
"content": "<|object_ref_start|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"151647": {
|
38 |
+
"content": "<|object_ref_end|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"151648": {
|
46 |
+
"content": "<|box_start|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"151649": {
|
54 |
+
"content": "<|box_end|>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"151650": {
|
62 |
+
"content": "<|quad_start|>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"151651": {
|
70 |
+
"content": "<|quad_end|>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"151652": {
|
78 |
+
"content": "<|vision_start|>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"151653": {
|
86 |
+
"content": "<|vision_end|>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"151654": {
|
94 |
+
"content": "<|vision_pad|>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"151655": {
|
102 |
+
"content": "<|image_pad|>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"151656": {
|
110 |
+
"content": "<|video_pad|>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"151657": {
|
118 |
+
"content": "<tool_call>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": false
|
124 |
+
},
|
125 |
+
"151658": {
|
126 |
+
"content": "</tool_call>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": false
|
132 |
+
},
|
133 |
+
"151659": {
|
134 |
+
"content": "<|fim_prefix|>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": false
|
140 |
+
},
|
141 |
+
"151660": {
|
142 |
+
"content": "<|fim_middle|>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": false
|
148 |
+
},
|
149 |
+
"151661": {
|
150 |
+
"content": "<|fim_suffix|>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": false
|
156 |
+
},
|
157 |
+
"151662": {
|
158 |
+
"content": "<|fim_pad|>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": false
|
164 |
+
},
|
165 |
+
"151663": {
|
166 |
+
"content": "<|repo_name|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": false
|
172 |
+
},
|
173 |
+
"151664": {
|
174 |
+
"content": "<|file_sep|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": false
|
180 |
+
}
|
181 |
+
},
|
182 |
+
"additional_special_tokens": [
|
183 |
+
"<|im_start|>",
|
184 |
+
"<|im_end|>",
|
185 |
+
"<|object_ref_start|>",
|
186 |
+
"<|object_ref_end|>",
|
187 |
+
"<|box_start|>",
|
188 |
+
"<|box_end|>",
|
189 |
+
"<|quad_start|>",
|
190 |
+
"<|quad_end|>",
|
191 |
+
"<|vision_start|>",
|
192 |
+
"<|vision_end|>",
|
193 |
+
"<|vision_pad|>",
|
194 |
+
"<|image_pad|>",
|
195 |
+
"<|video_pad|>"
|
196 |
+
],
|
197 |
+
"bos_token": null,
|
198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
199 |
+
"clean_up_tokenization_spaces": false,
|
200 |
+
"eos_token": "<|im_end|>",
|
201 |
+
"errors": "replace",
|
202 |
+
"extra_special_tokens": {},
|
203 |
+
"model_max_length": 15000,
|
204 |
+
"pad_token": "<|endoftext|>",
|
205 |
+
"padding_side": "right",
|
206 |
+
"split_special_tokens": false,
|
207 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
208 |
+
"unk_token": null
|
209 |
+
}
|
checkpoint-594/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|