Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +202 -0
- adapter_config.json +42 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2066 -0
- trainer_state.json +2156 -0
- training_args.bin +3 -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
|
README.md
ADDED
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: unsloth/Llama-3.2-3B
|
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 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": {
|
4 |
+
"base_model_class": "LlamaForCausalLM",
|
5 |
+
"parent_library": "transformers.models.llama.modeling_llama"
|
6 |
+
},
|
7 |
+
"base_model_name_or_path": "unsloth/Llama-3.2-3B",
|
8 |
+
"bias": "none",
|
9 |
+
"corda_config": null,
|
10 |
+
"eva_config": null,
|
11 |
+
"exclude_modules": null,
|
12 |
+
"fan_in_fan_out": false,
|
13 |
+
"inference_mode": true,
|
14 |
+
"init_lora_weights": true,
|
15 |
+
"layer_replication": null,
|
16 |
+
"layers_pattern": null,
|
17 |
+
"layers_to_transform": null,
|
18 |
+
"loftq_config": {},
|
19 |
+
"lora_alpha": 256,
|
20 |
+
"lora_bias": false,
|
21 |
+
"lora_dropout": 0,
|
22 |
+
"megatron_config": null,
|
23 |
+
"megatron_core": "megatron.core",
|
24 |
+
"modules_to_save": null,
|
25 |
+
"peft_type": "LORA",
|
26 |
+
"r": 128,
|
27 |
+
"rank_pattern": {},
|
28 |
+
"revision": null,
|
29 |
+
"target_modules": [
|
30 |
+
"down_proj",
|
31 |
+
"v_proj",
|
32 |
+
"k_proj",
|
33 |
+
"gate_proj",
|
34 |
+
"o_proj",
|
35 |
+
"q_proj",
|
36 |
+
"up_proj"
|
37 |
+
],
|
38 |
+
"task_type": null,
|
39 |
+
"trainable_token_indices": null,
|
40 |
+
"use_dora": false,
|
41 |
+
"use_rslora": false
|
42 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34495706de78a9eca641e1e3dba4dd1ef89f2604e07b2a17d370902f678e132f
|
3 |
+
size 778096664
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7d894c9d6019d0f12f02b899e8bbaf897f038b7c20c60903eb099c8bcfe00c3
|
3 |
+
size 1556417578
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6a9147b74de75d00b4c314484d5c71acbe4e6bc6a03d709554a1e7b3cd79ad6
|
3 |
+
size 14512
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51b78008f920edbd8236ed78f60e5d0853641a618ce77f8199ae253bc543aca7
|
3 |
+
size 14512
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76790dd068dfa178787330a98c8d5aa0e9385ed1f9d12bfa9e7de9e96949c796
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|end_of_text|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|finetune_right_pad_id|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
3 |
+
size 17209920
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2066 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"128000": {
|
5 |
+
"content": "<|begin_of_text|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"128001": {
|
13 |
+
"content": "<|end_of_text|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"128002": {
|
21 |
+
"content": "<|reserved_special_token_0|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"128003": {
|
29 |
+
"content": "<|reserved_special_token_1|>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"128004": {
|
37 |
+
"content": "<|finetune_right_pad_id|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"128005": {
|
45 |
+
"content": "<|reserved_special_token_2|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"128006": {
|
53 |
+
"content": "<|start_header_id|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"128007": {
|
61 |
+
"content": "<|end_header_id|>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"128008": {
|
69 |
+
"content": "<|eom_id|>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"128009": {
|
77 |
+
"content": "<|eot_id|>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"128010": {
|
85 |
+
"content": "<|python_tag|>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"128011": {
|
93 |
+
"content": "<|reserved_special_token_3|>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"128012": {
|
101 |
+
"content": "<|reserved_special_token_4|>",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"128013": {
|
109 |
+
"content": "<|reserved_special_token_5|>",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"128014": {
|
117 |
+
"content": "<|reserved_special_token_6|>",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"128015": {
|
125 |
+
"content": "<|reserved_special_token_7|>",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"128016": {
|
133 |
+
"content": "<|reserved_special_token_8|>",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"128017": {
|
141 |
+
"content": "<|reserved_special_token_9|>",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"128018": {
|
149 |
+
"content": "<|reserved_special_token_10|>",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"128019": {
|
157 |
+
"content": "<|reserved_special_token_11|>",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"128020": {
|
165 |
+
"content": "<|reserved_special_token_12|>",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"128021": {
|
173 |
+
"content": "<|reserved_special_token_13|>",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"128022": {
|
181 |
+
"content": "<|reserved_special_token_14|>",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"128023": {
|
189 |
+
"content": "<|reserved_special_token_15|>",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"128024": {
|
197 |
+
"content": "<|reserved_special_token_16|>",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"128025": {
|
205 |
+
"content": "<|reserved_special_token_17|>",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"128026": {
|
213 |
+
"content": "<|reserved_special_token_18|>",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"128027": {
|
221 |
+
"content": "<|reserved_special_token_19|>",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"128028": {
|
229 |
+
"content": "<|reserved_special_token_20|>",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"128029": {
|
237 |
+
"content": "<|reserved_special_token_21|>",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"128030": {
|
245 |
+
"content": "<|reserved_special_token_22|>",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"128031": {
|
253 |
+
"content": "<|reserved_special_token_23|>",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"128032": {
|
261 |
+
"content": "<|reserved_special_token_24|>",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
},
|
268 |
+
"128033": {
|
269 |
+
"content": "<|reserved_special_token_25|>",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
"128034": {
|
277 |
+
"content": "<|reserved_special_token_26|>",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": true
|
283 |
+
},
|
284 |
+
"128035": {
|
285 |
+
"content": "<|reserved_special_token_27|>",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": true
|
291 |
+
},
|
292 |
+
"128036": {
|
293 |
+
"content": "<|reserved_special_token_28|>",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": true
|
299 |
+
},
|
300 |
+
"128037": {
|
301 |
+
"content": "<|reserved_special_token_29|>",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": true
|
307 |
+
},
|
308 |
+
"128038": {
|
309 |
+
"content": "<|reserved_special_token_30|>",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": true
|
315 |
+
},
|
316 |
+
"128039": {
|
317 |
+
"content": "<|reserved_special_token_31|>",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
+
},
|
324 |
+
"128040": {
|
325 |
+
"content": "<|reserved_special_token_32|>",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": true
|
331 |
+
},
|
332 |
+
"128041": {
|
333 |
+
"content": "<|reserved_special_token_33|>",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": true
|
339 |
+
},
|
340 |
+
"128042": {
|
341 |
+
"content": "<|reserved_special_token_34|>",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": true
|
347 |
+
},
|
348 |
+
"128043": {
|
349 |
+
"content": "<|reserved_special_token_35|>",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": false,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": true
|
355 |
+
},
|
356 |
+
"128044": {
|
357 |
+
"content": "<|reserved_special_token_36|>",
|
358 |
+
"lstrip": false,
|
359 |
+
"normalized": false,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": true
|
363 |
+
},
|
364 |
+
"128045": {
|
365 |
+
"content": "<|reserved_special_token_37|>",
|
366 |
+
"lstrip": false,
|
367 |
+
"normalized": false,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": true
|
371 |
+
},
|
372 |
+
"128046": {
|
373 |
+
"content": "<|reserved_special_token_38|>",
|
374 |
+
"lstrip": false,
|
375 |
+
"normalized": false,
|
376 |
+
"rstrip": false,
|
377 |
+
"single_word": false,
|
378 |
+
"special": true
|
379 |
+
},
|
380 |
+
"128047": {
|
381 |
+
"content": "<|reserved_special_token_39|>",
|
382 |
+
"lstrip": false,
|
383 |
+
"normalized": false,
|
384 |
+
"rstrip": false,
|
385 |
+
"single_word": false,
|
386 |
+
"special": true
|
387 |
+
},
|
388 |
+
"128048": {
|
389 |
+
"content": "<|reserved_special_token_40|>",
|
390 |
+
"lstrip": false,
|
391 |
+
"normalized": false,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false,
|
394 |
+
"special": true
|
395 |
+
},
|
396 |
+
"128049": {
|
397 |
+
"content": "<|reserved_special_token_41|>",
|
398 |
+
"lstrip": false,
|
399 |
+
"normalized": false,
|
400 |
+
"rstrip": false,
|
401 |
+
"single_word": false,
|
402 |
+
"special": true
|
403 |
+
},
|
404 |
+
"128050": {
|
405 |
+
"content": "<|reserved_special_token_42|>",
|
406 |
+
"lstrip": false,
|
407 |
+
"normalized": false,
|
408 |
+
"rstrip": false,
|
409 |
+
"single_word": false,
|
410 |
+
"special": true
|
411 |
+
},
|
412 |
+
"128051": {
|
413 |
+
"content": "<|reserved_special_token_43|>",
|
414 |
+
"lstrip": false,
|
415 |
+
"normalized": false,
|
416 |
+
"rstrip": false,
|
417 |
+
"single_word": false,
|
418 |
+
"special": true
|
419 |
+
},
|
420 |
+
"128052": {
|
421 |
+
"content": "<|reserved_special_token_44|>",
|
422 |
+
"lstrip": false,
|
423 |
+
"normalized": false,
|
424 |
+
"rstrip": false,
|
425 |
+
"single_word": false,
|
426 |
+
"special": true
|
427 |
+
},
|
428 |
+
"128053": {
|
429 |
+
"content": "<|reserved_special_token_45|>",
|
430 |
+
"lstrip": false,
|
431 |
+
"normalized": false,
|
432 |
+
"rstrip": false,
|
433 |
+
"single_word": false,
|
434 |
+
"special": true
|
435 |
+
},
|
436 |
+
"128054": {
|
437 |
+
"content": "<|reserved_special_token_46|>",
|
438 |
+
"lstrip": false,
|
439 |
+
"normalized": false,
|
440 |
+
"rstrip": false,
|
441 |
+
"single_word": false,
|
442 |
+
"special": true
|
443 |
+
},
|
444 |
+
"128055": {
|
445 |
+
"content": "<|reserved_special_token_47|>",
|
446 |
+
"lstrip": false,
|
447 |
+
"normalized": false,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false,
|
450 |
+
"special": true
|
451 |
+
},
|
452 |
+
"128056": {
|
453 |
+
"content": "<|reserved_special_token_48|>",
|
454 |
+
"lstrip": false,
|
455 |
+
"normalized": false,
|
456 |
+
"rstrip": false,
|
457 |
+
"single_word": false,
|
458 |
+
"special": true
|
459 |
+
},
|
460 |
+
"128057": {
|
461 |
+
"content": "<|reserved_special_token_49|>",
|
462 |
+
"lstrip": false,
|
463 |
+
"normalized": false,
|
464 |
+
"rstrip": false,
|
465 |
+
"single_word": false,
|
466 |
+
"special": true
|
467 |
+
},
|
468 |
+
"128058": {
|
469 |
+
"content": "<|reserved_special_token_50|>",
|
470 |
+
"lstrip": false,
|
471 |
+
"normalized": false,
|
472 |
+
"rstrip": false,
|
473 |
+
"single_word": false,
|
474 |
+
"special": true
|
475 |
+
},
|
476 |
+
"128059": {
|
477 |
+
"content": "<|reserved_special_token_51|>",
|
478 |
+
"lstrip": false,
|
479 |
+
"normalized": false,
|
480 |
+
"rstrip": false,
|
481 |
+
"single_word": false,
|
482 |
+
"special": true
|
483 |
+
},
|
484 |
+
"128060": {
|
485 |
+
"content": "<|reserved_special_token_52|>",
|
486 |
+
"lstrip": false,
|
487 |
+
"normalized": false,
|
488 |
+
"rstrip": false,
|
489 |
+
"single_word": false,
|
490 |
+
"special": true
|
491 |
+
},
|
492 |
+
"128061": {
|
493 |
+
"content": "<|reserved_special_token_53|>",
|
494 |
+
"lstrip": false,
|
495 |
+
"normalized": false,
|
496 |
+
"rstrip": false,
|
497 |
+
"single_word": false,
|
498 |
+
"special": true
|
499 |
+
},
|
500 |
+
"128062": {
|
501 |
+
"content": "<|reserved_special_token_54|>",
|
502 |
+
"lstrip": false,
|
503 |
+
"normalized": false,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false,
|
506 |
+
"special": true
|
507 |
+
},
|
508 |
+
"128063": {
|
509 |
+
"content": "<|reserved_special_token_55|>",
|
510 |
+
"lstrip": false,
|
511 |
+
"normalized": false,
|
512 |
+
"rstrip": false,
|
513 |
+
"single_word": false,
|
514 |
+
"special": true
|
515 |
+
},
|
516 |
+
"128064": {
|
517 |
+
"content": "<|reserved_special_token_56|>",
|
518 |
+
"lstrip": false,
|
519 |
+
"normalized": false,
|
520 |
+
"rstrip": false,
|
521 |
+
"single_word": false,
|
522 |
+
"special": true
|
523 |
+
},
|
524 |
+
"128065": {
|
525 |
+
"content": "<|reserved_special_token_57|>",
|
526 |
+
"lstrip": false,
|
527 |
+
"normalized": false,
|
528 |
+
"rstrip": false,
|
529 |
+
"single_word": false,
|
530 |
+
"special": true
|
531 |
+
},
|
532 |
+
"128066": {
|
533 |
+
"content": "<|reserved_special_token_58|>",
|
534 |
+
"lstrip": false,
|
535 |
+
"normalized": false,
|
536 |
+
"rstrip": false,
|
537 |
+
"single_word": false,
|
538 |
+
"special": true
|
539 |
+
},
|
540 |
+
"128067": {
|
541 |
+
"content": "<|reserved_special_token_59|>",
|
542 |
+
"lstrip": false,
|
543 |
+
"normalized": false,
|
544 |
+
"rstrip": false,
|
545 |
+
"single_word": false,
|
546 |
+
"special": true
|
547 |
+
},
|
548 |
+
"128068": {
|
549 |
+
"content": "<|reserved_special_token_60|>",
|
550 |
+
"lstrip": false,
|
551 |
+
"normalized": false,
|
552 |
+
"rstrip": false,
|
553 |
+
"single_word": false,
|
554 |
+
"special": true
|
555 |
+
},
|
556 |
+
"128069": {
|
557 |
+
"content": "<|reserved_special_token_61|>",
|
558 |
+
"lstrip": false,
|
559 |
+
"normalized": false,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false,
|
562 |
+
"special": true
|
563 |
+
},
|
564 |
+
"128070": {
|
565 |
+
"content": "<|reserved_special_token_62|>",
|
566 |
+
"lstrip": false,
|
567 |
+
"normalized": false,
|
568 |
+
"rstrip": false,
|
569 |
+
"single_word": false,
|
570 |
+
"special": true
|
571 |
+
},
|
572 |
+
"128071": {
|
573 |
+
"content": "<|reserved_special_token_63|>",
|
574 |
+
"lstrip": false,
|
575 |
+
"normalized": false,
|
576 |
+
"rstrip": false,
|
577 |
+
"single_word": false,
|
578 |
+
"special": true
|
579 |
+
},
|
580 |
+
"128072": {
|
581 |
+
"content": "<|reserved_special_token_64|>",
|
582 |
+
"lstrip": false,
|
583 |
+
"normalized": false,
|
584 |
+
"rstrip": false,
|
585 |
+
"single_word": false,
|
586 |
+
"special": true
|
587 |
+
},
|
588 |
+
"128073": {
|
589 |
+
"content": "<|reserved_special_token_65|>",
|
590 |
+
"lstrip": false,
|
591 |
+
"normalized": false,
|
592 |
+
"rstrip": false,
|
593 |
+
"single_word": false,
|
594 |
+
"special": true
|
595 |
+
},
|
596 |
+
"128074": {
|
597 |
+
"content": "<|reserved_special_token_66|>",
|
598 |
+
"lstrip": false,
|
599 |
+
"normalized": false,
|
600 |
+
"rstrip": false,
|
601 |
+
"single_word": false,
|
602 |
+
"special": true
|
603 |
+
},
|
604 |
+
"128075": {
|
605 |
+
"content": "<|reserved_special_token_67|>",
|
606 |
+
"lstrip": false,
|
607 |
+
"normalized": false,
|
608 |
+
"rstrip": false,
|
609 |
+
"single_word": false,
|
610 |
+
"special": true
|
611 |
+
},
|
612 |
+
"128076": {
|
613 |
+
"content": "<|reserved_special_token_68|>",
|
614 |
+
"lstrip": false,
|
615 |
+
"normalized": false,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false,
|
618 |
+
"special": true
|
619 |
+
},
|
620 |
+
"128077": {
|
621 |
+
"content": "<|reserved_special_token_69|>",
|
622 |
+
"lstrip": false,
|
623 |
+
"normalized": false,
|
624 |
+
"rstrip": false,
|
625 |
+
"single_word": false,
|
626 |
+
"special": true
|
627 |
+
},
|
628 |
+
"128078": {
|
629 |
+
"content": "<|reserved_special_token_70|>",
|
630 |
+
"lstrip": false,
|
631 |
+
"normalized": false,
|
632 |
+
"rstrip": false,
|
633 |
+
"single_word": false,
|
634 |
+
"special": true
|
635 |
+
},
|
636 |
+
"128079": {
|
637 |
+
"content": "<|reserved_special_token_71|>",
|
638 |
+
"lstrip": false,
|
639 |
+
"normalized": false,
|
640 |
+
"rstrip": false,
|
641 |
+
"single_word": false,
|
642 |
+
"special": true
|
643 |
+
},
|
644 |
+
"128080": {
|
645 |
+
"content": "<|reserved_special_token_72|>",
|
646 |
+
"lstrip": false,
|
647 |
+
"normalized": false,
|
648 |
+
"rstrip": false,
|
649 |
+
"single_word": false,
|
650 |
+
"special": true
|
651 |
+
},
|
652 |
+
"128081": {
|
653 |
+
"content": "<|reserved_special_token_73|>",
|
654 |
+
"lstrip": false,
|
655 |
+
"normalized": false,
|
656 |
+
"rstrip": false,
|
657 |
+
"single_word": false,
|
658 |
+
"special": true
|
659 |
+
},
|
660 |
+
"128082": {
|
661 |
+
"content": "<|reserved_special_token_74|>",
|
662 |
+
"lstrip": false,
|
663 |
+
"normalized": false,
|
664 |
+
"rstrip": false,
|
665 |
+
"single_word": false,
|
666 |
+
"special": true
|
667 |
+
},
|
668 |
+
"128083": {
|
669 |
+
"content": "<|reserved_special_token_75|>",
|
670 |
+
"lstrip": false,
|
671 |
+
"normalized": false,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false,
|
674 |
+
"special": true
|
675 |
+
},
|
676 |
+
"128084": {
|
677 |
+
"content": "<|reserved_special_token_76|>",
|
678 |
+
"lstrip": false,
|
679 |
+
"normalized": false,
|
680 |
+
"rstrip": false,
|
681 |
+
"single_word": false,
|
682 |
+
"special": true
|
683 |
+
},
|
684 |
+
"128085": {
|
685 |
+
"content": "<|reserved_special_token_77|>",
|
686 |
+
"lstrip": false,
|
687 |
+
"normalized": false,
|
688 |
+
"rstrip": false,
|
689 |
+
"single_word": false,
|
690 |
+
"special": true
|
691 |
+
},
|
692 |
+
"128086": {
|
693 |
+
"content": "<|reserved_special_token_78|>",
|
694 |
+
"lstrip": false,
|
695 |
+
"normalized": false,
|
696 |
+
"rstrip": false,
|
697 |
+
"single_word": false,
|
698 |
+
"special": true
|
699 |
+
},
|
700 |
+
"128087": {
|
701 |
+
"content": "<|reserved_special_token_79|>",
|
702 |
+
"lstrip": false,
|
703 |
+
"normalized": false,
|
704 |
+
"rstrip": false,
|
705 |
+
"single_word": false,
|
706 |
+
"special": true
|
707 |
+
},
|
708 |
+
"128088": {
|
709 |
+
"content": "<|reserved_special_token_80|>",
|
710 |
+
"lstrip": false,
|
711 |
+
"normalized": false,
|
712 |
+
"rstrip": false,
|
713 |
+
"single_word": false,
|
714 |
+
"special": true
|
715 |
+
},
|
716 |
+
"128089": {
|
717 |
+
"content": "<|reserved_special_token_81|>",
|
718 |
+
"lstrip": false,
|
719 |
+
"normalized": false,
|
720 |
+
"rstrip": false,
|
721 |
+
"single_word": false,
|
722 |
+
"special": true
|
723 |
+
},
|
724 |
+
"128090": {
|
725 |
+
"content": "<|reserved_special_token_82|>",
|
726 |
+
"lstrip": false,
|
727 |
+
"normalized": false,
|
728 |
+
"rstrip": false,
|
729 |
+
"single_word": false,
|
730 |
+
"special": true
|
731 |
+
},
|
732 |
+
"128091": {
|
733 |
+
"content": "<|reserved_special_token_83|>",
|
734 |
+
"lstrip": false,
|
735 |
+
"normalized": false,
|
736 |
+
"rstrip": false,
|
737 |
+
"single_word": false,
|
738 |
+
"special": true
|
739 |
+
},
|
740 |
+
"128092": {
|
741 |
+
"content": "<|reserved_special_token_84|>",
|
742 |
+
"lstrip": false,
|
743 |
+
"normalized": false,
|
744 |
+
"rstrip": false,
|
745 |
+
"single_word": false,
|
746 |
+
"special": true
|
747 |
+
},
|
748 |
+
"128093": {
|
749 |
+
"content": "<|reserved_special_token_85|>",
|
750 |
+
"lstrip": false,
|
751 |
+
"normalized": false,
|
752 |
+
"rstrip": false,
|
753 |
+
"single_word": false,
|
754 |
+
"special": true
|
755 |
+
},
|
756 |
+
"128094": {
|
757 |
+
"content": "<|reserved_special_token_86|>",
|
758 |
+
"lstrip": false,
|
759 |
+
"normalized": false,
|
760 |
+
"rstrip": false,
|
761 |
+
"single_word": false,
|
762 |
+
"special": true
|
763 |
+
},
|
764 |
+
"128095": {
|
765 |
+
"content": "<|reserved_special_token_87|>",
|
766 |
+
"lstrip": false,
|
767 |
+
"normalized": false,
|
768 |
+
"rstrip": false,
|
769 |
+
"single_word": false,
|
770 |
+
"special": true
|
771 |
+
},
|
772 |
+
"128096": {
|
773 |
+
"content": "<|reserved_special_token_88|>",
|
774 |
+
"lstrip": false,
|
775 |
+
"normalized": false,
|
776 |
+
"rstrip": false,
|
777 |
+
"single_word": false,
|
778 |
+
"special": true
|
779 |
+
},
|
780 |
+
"128097": {
|
781 |
+
"content": "<|reserved_special_token_89|>",
|
782 |
+
"lstrip": false,
|
783 |
+
"normalized": false,
|
784 |
+
"rstrip": false,
|
785 |
+
"single_word": false,
|
786 |
+
"special": true
|
787 |
+
},
|
788 |
+
"128098": {
|
789 |
+
"content": "<|reserved_special_token_90|>",
|
790 |
+
"lstrip": false,
|
791 |
+
"normalized": false,
|
792 |
+
"rstrip": false,
|
793 |
+
"single_word": false,
|
794 |
+
"special": true
|
795 |
+
},
|
796 |
+
"128099": {
|
797 |
+
"content": "<|reserved_special_token_91|>",
|
798 |
+
"lstrip": false,
|
799 |
+
"normalized": false,
|
800 |
+
"rstrip": false,
|
801 |
+
"single_word": false,
|
802 |
+
"special": true
|
803 |
+
},
|
804 |
+
"128100": {
|
805 |
+
"content": "<|reserved_special_token_92|>",
|
806 |
+
"lstrip": false,
|
807 |
+
"normalized": false,
|
808 |
+
"rstrip": false,
|
809 |
+
"single_word": false,
|
810 |
+
"special": true
|
811 |
+
},
|
812 |
+
"128101": {
|
813 |
+
"content": "<|reserved_special_token_93|>",
|
814 |
+
"lstrip": false,
|
815 |
+
"normalized": false,
|
816 |
+
"rstrip": false,
|
817 |
+
"single_word": false,
|
818 |
+
"special": true
|
819 |
+
},
|
820 |
+
"128102": {
|
821 |
+
"content": "<|reserved_special_token_94|>",
|
822 |
+
"lstrip": false,
|
823 |
+
"normalized": false,
|
824 |
+
"rstrip": false,
|
825 |
+
"single_word": false,
|
826 |
+
"special": true
|
827 |
+
},
|
828 |
+
"128103": {
|
829 |
+
"content": "<|reserved_special_token_95|>",
|
830 |
+
"lstrip": false,
|
831 |
+
"normalized": false,
|
832 |
+
"rstrip": false,
|
833 |
+
"single_word": false,
|
834 |
+
"special": true
|
835 |
+
},
|
836 |
+
"128104": {
|
837 |
+
"content": "<|reserved_special_token_96|>",
|
838 |
+
"lstrip": false,
|
839 |
+
"normalized": false,
|
840 |
+
"rstrip": false,
|
841 |
+
"single_word": false,
|
842 |
+
"special": true
|
843 |
+
},
|
844 |
+
"128105": {
|
845 |
+
"content": "<|reserved_special_token_97|>",
|
846 |
+
"lstrip": false,
|
847 |
+
"normalized": false,
|
848 |
+
"rstrip": false,
|
849 |
+
"single_word": false,
|
850 |
+
"special": true
|
851 |
+
},
|
852 |
+
"128106": {
|
853 |
+
"content": "<|reserved_special_token_98|>",
|
854 |
+
"lstrip": false,
|
855 |
+
"normalized": false,
|
856 |
+
"rstrip": false,
|
857 |
+
"single_word": false,
|
858 |
+
"special": true
|
859 |
+
},
|
860 |
+
"128107": {
|
861 |
+
"content": "<|reserved_special_token_99|>",
|
862 |
+
"lstrip": false,
|
863 |
+
"normalized": false,
|
864 |
+
"rstrip": false,
|
865 |
+
"single_word": false,
|
866 |
+
"special": true
|
867 |
+
},
|
868 |
+
"128108": {
|
869 |
+
"content": "<|reserved_special_token_100|>",
|
870 |
+
"lstrip": false,
|
871 |
+
"normalized": false,
|
872 |
+
"rstrip": false,
|
873 |
+
"single_word": false,
|
874 |
+
"special": true
|
875 |
+
},
|
876 |
+
"128109": {
|
877 |
+
"content": "<|reserved_special_token_101|>",
|
878 |
+
"lstrip": false,
|
879 |
+
"normalized": false,
|
880 |
+
"rstrip": false,
|
881 |
+
"single_word": false,
|
882 |
+
"special": true
|
883 |
+
},
|
884 |
+
"128110": {
|
885 |
+
"content": "<|reserved_special_token_102|>",
|
886 |
+
"lstrip": false,
|
887 |
+
"normalized": false,
|
888 |
+
"rstrip": false,
|
889 |
+
"single_word": false,
|
890 |
+
"special": true
|
891 |
+
},
|
892 |
+
"128111": {
|
893 |
+
"content": "<|reserved_special_token_103|>",
|
894 |
+
"lstrip": false,
|
895 |
+
"normalized": false,
|
896 |
+
"rstrip": false,
|
897 |
+
"single_word": false,
|
898 |
+
"special": true
|
899 |
+
},
|
900 |
+
"128112": {
|
901 |
+
"content": "<|reserved_special_token_104|>",
|
902 |
+
"lstrip": false,
|
903 |
+
"normalized": false,
|
904 |
+
"rstrip": false,
|
905 |
+
"single_word": false,
|
906 |
+
"special": true
|
907 |
+
},
|
908 |
+
"128113": {
|
909 |
+
"content": "<|reserved_special_token_105|>",
|
910 |
+
"lstrip": false,
|
911 |
+
"normalized": false,
|
912 |
+
"rstrip": false,
|
913 |
+
"single_word": false,
|
914 |
+
"special": true
|
915 |
+
},
|
916 |
+
"128114": {
|
917 |
+
"content": "<|reserved_special_token_106|>",
|
918 |
+
"lstrip": false,
|
919 |
+
"normalized": false,
|
920 |
+
"rstrip": false,
|
921 |
+
"single_word": false,
|
922 |
+
"special": true
|
923 |
+
},
|
924 |
+
"128115": {
|
925 |
+
"content": "<|reserved_special_token_107|>",
|
926 |
+
"lstrip": false,
|
927 |
+
"normalized": false,
|
928 |
+
"rstrip": false,
|
929 |
+
"single_word": false,
|
930 |
+
"special": true
|
931 |
+
},
|
932 |
+
"128116": {
|
933 |
+
"content": "<|reserved_special_token_108|>",
|
934 |
+
"lstrip": false,
|
935 |
+
"normalized": false,
|
936 |
+
"rstrip": false,
|
937 |
+
"single_word": false,
|
938 |
+
"special": true
|
939 |
+
},
|
940 |
+
"128117": {
|
941 |
+
"content": "<|reserved_special_token_109|>",
|
942 |
+
"lstrip": false,
|
943 |
+
"normalized": false,
|
944 |
+
"rstrip": false,
|
945 |
+
"single_word": false,
|
946 |
+
"special": true
|
947 |
+
},
|
948 |
+
"128118": {
|
949 |
+
"content": "<|reserved_special_token_110|>",
|
950 |
+
"lstrip": false,
|
951 |
+
"normalized": false,
|
952 |
+
"rstrip": false,
|
953 |
+
"single_word": false,
|
954 |
+
"special": true
|
955 |
+
},
|
956 |
+
"128119": {
|
957 |
+
"content": "<|reserved_special_token_111|>",
|
958 |
+
"lstrip": false,
|
959 |
+
"normalized": false,
|
960 |
+
"rstrip": false,
|
961 |
+
"single_word": false,
|
962 |
+
"special": true
|
963 |
+
},
|
964 |
+
"128120": {
|
965 |
+
"content": "<|reserved_special_token_112|>",
|
966 |
+
"lstrip": false,
|
967 |
+
"normalized": false,
|
968 |
+
"rstrip": false,
|
969 |
+
"single_word": false,
|
970 |
+
"special": true
|
971 |
+
},
|
972 |
+
"128121": {
|
973 |
+
"content": "<|reserved_special_token_113|>",
|
974 |
+
"lstrip": false,
|
975 |
+
"normalized": false,
|
976 |
+
"rstrip": false,
|
977 |
+
"single_word": false,
|
978 |
+
"special": true
|
979 |
+
},
|
980 |
+
"128122": {
|
981 |
+
"content": "<|reserved_special_token_114|>",
|
982 |
+
"lstrip": false,
|
983 |
+
"normalized": false,
|
984 |
+
"rstrip": false,
|
985 |
+
"single_word": false,
|
986 |
+
"special": true
|
987 |
+
},
|
988 |
+
"128123": {
|
989 |
+
"content": "<|reserved_special_token_115|>",
|
990 |
+
"lstrip": false,
|
991 |
+
"normalized": false,
|
992 |
+
"rstrip": false,
|
993 |
+
"single_word": false,
|
994 |
+
"special": true
|
995 |
+
},
|
996 |
+
"128124": {
|
997 |
+
"content": "<|reserved_special_token_116|>",
|
998 |
+
"lstrip": false,
|
999 |
+
"normalized": false,
|
1000 |
+
"rstrip": false,
|
1001 |
+
"single_word": false,
|
1002 |
+
"special": true
|
1003 |
+
},
|
1004 |
+
"128125": {
|
1005 |
+
"content": "<|reserved_special_token_117|>",
|
1006 |
+
"lstrip": false,
|
1007 |
+
"normalized": false,
|
1008 |
+
"rstrip": false,
|
1009 |
+
"single_word": false,
|
1010 |
+
"special": true
|
1011 |
+
},
|
1012 |
+
"128126": {
|
1013 |
+
"content": "<|reserved_special_token_118|>",
|
1014 |
+
"lstrip": false,
|
1015 |
+
"normalized": false,
|
1016 |
+
"rstrip": false,
|
1017 |
+
"single_word": false,
|
1018 |
+
"special": true
|
1019 |
+
},
|
1020 |
+
"128127": {
|
1021 |
+
"content": "<|reserved_special_token_119|>",
|
1022 |
+
"lstrip": false,
|
1023 |
+
"normalized": false,
|
1024 |
+
"rstrip": false,
|
1025 |
+
"single_word": false,
|
1026 |
+
"special": true
|
1027 |
+
},
|
1028 |
+
"128128": {
|
1029 |
+
"content": "<|reserved_special_token_120|>",
|
1030 |
+
"lstrip": false,
|
1031 |
+
"normalized": false,
|
1032 |
+
"rstrip": false,
|
1033 |
+
"single_word": false,
|
1034 |
+
"special": true
|
1035 |
+
},
|
1036 |
+
"128129": {
|
1037 |
+
"content": "<|reserved_special_token_121|>",
|
1038 |
+
"lstrip": false,
|
1039 |
+
"normalized": false,
|
1040 |
+
"rstrip": false,
|
1041 |
+
"single_word": false,
|
1042 |
+
"special": true
|
1043 |
+
},
|
1044 |
+
"128130": {
|
1045 |
+
"content": "<|reserved_special_token_122|>",
|
1046 |
+
"lstrip": false,
|
1047 |
+
"normalized": false,
|
1048 |
+
"rstrip": false,
|
1049 |
+
"single_word": false,
|
1050 |
+
"special": true
|
1051 |
+
},
|
1052 |
+
"128131": {
|
1053 |
+
"content": "<|reserved_special_token_123|>",
|
1054 |
+
"lstrip": false,
|
1055 |
+
"normalized": false,
|
1056 |
+
"rstrip": false,
|
1057 |
+
"single_word": false,
|
1058 |
+
"special": true
|
1059 |
+
},
|
1060 |
+
"128132": {
|
1061 |
+
"content": "<|reserved_special_token_124|>",
|
1062 |
+
"lstrip": false,
|
1063 |
+
"normalized": false,
|
1064 |
+
"rstrip": false,
|
1065 |
+
"single_word": false,
|
1066 |
+
"special": true
|
1067 |
+
},
|
1068 |
+
"128133": {
|
1069 |
+
"content": "<|reserved_special_token_125|>",
|
1070 |
+
"lstrip": false,
|
1071 |
+
"normalized": false,
|
1072 |
+
"rstrip": false,
|
1073 |
+
"single_word": false,
|
1074 |
+
"special": true
|
1075 |
+
},
|
1076 |
+
"128134": {
|
1077 |
+
"content": "<|reserved_special_token_126|>",
|
1078 |
+
"lstrip": false,
|
1079 |
+
"normalized": false,
|
1080 |
+
"rstrip": false,
|
1081 |
+
"single_word": false,
|
1082 |
+
"special": true
|
1083 |
+
},
|
1084 |
+
"128135": {
|
1085 |
+
"content": "<|reserved_special_token_127|>",
|
1086 |
+
"lstrip": false,
|
1087 |
+
"normalized": false,
|
1088 |
+
"rstrip": false,
|
1089 |
+
"single_word": false,
|
1090 |
+
"special": true
|
1091 |
+
},
|
1092 |
+
"128136": {
|
1093 |
+
"content": "<|reserved_special_token_128|>",
|
1094 |
+
"lstrip": false,
|
1095 |
+
"normalized": false,
|
1096 |
+
"rstrip": false,
|
1097 |
+
"single_word": false,
|
1098 |
+
"special": true
|
1099 |
+
},
|
1100 |
+
"128137": {
|
1101 |
+
"content": "<|reserved_special_token_129|>",
|
1102 |
+
"lstrip": false,
|
1103 |
+
"normalized": false,
|
1104 |
+
"rstrip": false,
|
1105 |
+
"single_word": false,
|
1106 |
+
"special": true
|
1107 |
+
},
|
1108 |
+
"128138": {
|
1109 |
+
"content": "<|reserved_special_token_130|>",
|
1110 |
+
"lstrip": false,
|
1111 |
+
"normalized": false,
|
1112 |
+
"rstrip": false,
|
1113 |
+
"single_word": false,
|
1114 |
+
"special": true
|
1115 |
+
},
|
1116 |
+
"128139": {
|
1117 |
+
"content": "<|reserved_special_token_131|>",
|
1118 |
+
"lstrip": false,
|
1119 |
+
"normalized": false,
|
1120 |
+
"rstrip": false,
|
1121 |
+
"single_word": false,
|
1122 |
+
"special": true
|
1123 |
+
},
|
1124 |
+
"128140": {
|
1125 |
+
"content": "<|reserved_special_token_132|>",
|
1126 |
+
"lstrip": false,
|
1127 |
+
"normalized": false,
|
1128 |
+
"rstrip": false,
|
1129 |
+
"single_word": false,
|
1130 |
+
"special": true
|
1131 |
+
},
|
1132 |
+
"128141": {
|
1133 |
+
"content": "<|reserved_special_token_133|>",
|
1134 |
+
"lstrip": false,
|
1135 |
+
"normalized": false,
|
1136 |
+
"rstrip": false,
|
1137 |
+
"single_word": false,
|
1138 |
+
"special": true
|
1139 |
+
},
|
1140 |
+
"128142": {
|
1141 |
+
"content": "<|reserved_special_token_134|>",
|
1142 |
+
"lstrip": false,
|
1143 |
+
"normalized": false,
|
1144 |
+
"rstrip": false,
|
1145 |
+
"single_word": false,
|
1146 |
+
"special": true
|
1147 |
+
},
|
1148 |
+
"128143": {
|
1149 |
+
"content": "<|reserved_special_token_135|>",
|
1150 |
+
"lstrip": false,
|
1151 |
+
"normalized": false,
|
1152 |
+
"rstrip": false,
|
1153 |
+
"single_word": false,
|
1154 |
+
"special": true
|
1155 |
+
},
|
1156 |
+
"128144": {
|
1157 |
+
"content": "<|reserved_special_token_136|>",
|
1158 |
+
"lstrip": false,
|
1159 |
+
"normalized": false,
|
1160 |
+
"rstrip": false,
|
1161 |
+
"single_word": false,
|
1162 |
+
"special": true
|
1163 |
+
},
|
1164 |
+
"128145": {
|
1165 |
+
"content": "<|reserved_special_token_137|>",
|
1166 |
+
"lstrip": false,
|
1167 |
+
"normalized": false,
|
1168 |
+
"rstrip": false,
|
1169 |
+
"single_word": false,
|
1170 |
+
"special": true
|
1171 |
+
},
|
1172 |
+
"128146": {
|
1173 |
+
"content": "<|reserved_special_token_138|>",
|
1174 |
+
"lstrip": false,
|
1175 |
+
"normalized": false,
|
1176 |
+
"rstrip": false,
|
1177 |
+
"single_word": false,
|
1178 |
+
"special": true
|
1179 |
+
},
|
1180 |
+
"128147": {
|
1181 |
+
"content": "<|reserved_special_token_139|>",
|
1182 |
+
"lstrip": false,
|
1183 |
+
"normalized": false,
|
1184 |
+
"rstrip": false,
|
1185 |
+
"single_word": false,
|
1186 |
+
"special": true
|
1187 |
+
},
|
1188 |
+
"128148": {
|
1189 |
+
"content": "<|reserved_special_token_140|>",
|
1190 |
+
"lstrip": false,
|
1191 |
+
"normalized": false,
|
1192 |
+
"rstrip": false,
|
1193 |
+
"single_word": false,
|
1194 |
+
"special": true
|
1195 |
+
},
|
1196 |
+
"128149": {
|
1197 |
+
"content": "<|reserved_special_token_141|>",
|
1198 |
+
"lstrip": false,
|
1199 |
+
"normalized": false,
|
1200 |
+
"rstrip": false,
|
1201 |
+
"single_word": false,
|
1202 |
+
"special": true
|
1203 |
+
},
|
1204 |
+
"128150": {
|
1205 |
+
"content": "<|reserved_special_token_142|>",
|
1206 |
+
"lstrip": false,
|
1207 |
+
"normalized": false,
|
1208 |
+
"rstrip": false,
|
1209 |
+
"single_word": false,
|
1210 |
+
"special": true
|
1211 |
+
},
|
1212 |
+
"128151": {
|
1213 |
+
"content": "<|reserved_special_token_143|>",
|
1214 |
+
"lstrip": false,
|
1215 |
+
"normalized": false,
|
1216 |
+
"rstrip": false,
|
1217 |
+
"single_word": false,
|
1218 |
+
"special": true
|
1219 |
+
},
|
1220 |
+
"128152": {
|
1221 |
+
"content": "<|reserved_special_token_144|>",
|
1222 |
+
"lstrip": false,
|
1223 |
+
"normalized": false,
|
1224 |
+
"rstrip": false,
|
1225 |
+
"single_word": false,
|
1226 |
+
"special": true
|
1227 |
+
},
|
1228 |
+
"128153": {
|
1229 |
+
"content": "<|reserved_special_token_145|>",
|
1230 |
+
"lstrip": false,
|
1231 |
+
"normalized": false,
|
1232 |
+
"rstrip": false,
|
1233 |
+
"single_word": false,
|
1234 |
+
"special": true
|
1235 |
+
},
|
1236 |
+
"128154": {
|
1237 |
+
"content": "<|reserved_special_token_146|>",
|
1238 |
+
"lstrip": false,
|
1239 |
+
"normalized": false,
|
1240 |
+
"rstrip": false,
|
1241 |
+
"single_word": false,
|
1242 |
+
"special": true
|
1243 |
+
},
|
1244 |
+
"128155": {
|
1245 |
+
"content": "<|reserved_special_token_147|>",
|
1246 |
+
"lstrip": false,
|
1247 |
+
"normalized": false,
|
1248 |
+
"rstrip": false,
|
1249 |
+
"single_word": false,
|
1250 |
+
"special": true
|
1251 |
+
},
|
1252 |
+
"128156": {
|
1253 |
+
"content": "<|reserved_special_token_148|>",
|
1254 |
+
"lstrip": false,
|
1255 |
+
"normalized": false,
|
1256 |
+
"rstrip": false,
|
1257 |
+
"single_word": false,
|
1258 |
+
"special": true
|
1259 |
+
},
|
1260 |
+
"128157": {
|
1261 |
+
"content": "<|reserved_special_token_149|>",
|
1262 |
+
"lstrip": false,
|
1263 |
+
"normalized": false,
|
1264 |
+
"rstrip": false,
|
1265 |
+
"single_word": false,
|
1266 |
+
"special": true
|
1267 |
+
},
|
1268 |
+
"128158": {
|
1269 |
+
"content": "<|reserved_special_token_150|>",
|
1270 |
+
"lstrip": false,
|
1271 |
+
"normalized": false,
|
1272 |
+
"rstrip": false,
|
1273 |
+
"single_word": false,
|
1274 |
+
"special": true
|
1275 |
+
},
|
1276 |
+
"128159": {
|
1277 |
+
"content": "<|reserved_special_token_151|>",
|
1278 |
+
"lstrip": false,
|
1279 |
+
"normalized": false,
|
1280 |
+
"rstrip": false,
|
1281 |
+
"single_word": false,
|
1282 |
+
"special": true
|
1283 |
+
},
|
1284 |
+
"128160": {
|
1285 |
+
"content": "<|reserved_special_token_152|>",
|
1286 |
+
"lstrip": false,
|
1287 |
+
"normalized": false,
|
1288 |
+
"rstrip": false,
|
1289 |
+
"single_word": false,
|
1290 |
+
"special": true
|
1291 |
+
},
|
1292 |
+
"128161": {
|
1293 |
+
"content": "<|reserved_special_token_153|>",
|
1294 |
+
"lstrip": false,
|
1295 |
+
"normalized": false,
|
1296 |
+
"rstrip": false,
|
1297 |
+
"single_word": false,
|
1298 |
+
"special": true
|
1299 |
+
},
|
1300 |
+
"128162": {
|
1301 |
+
"content": "<|reserved_special_token_154|>",
|
1302 |
+
"lstrip": false,
|
1303 |
+
"normalized": false,
|
1304 |
+
"rstrip": false,
|
1305 |
+
"single_word": false,
|
1306 |
+
"special": true
|
1307 |
+
},
|
1308 |
+
"128163": {
|
1309 |
+
"content": "<|reserved_special_token_155|>",
|
1310 |
+
"lstrip": false,
|
1311 |
+
"normalized": false,
|
1312 |
+
"rstrip": false,
|
1313 |
+
"single_word": false,
|
1314 |
+
"special": true
|
1315 |
+
},
|
1316 |
+
"128164": {
|
1317 |
+
"content": "<|reserved_special_token_156|>",
|
1318 |
+
"lstrip": false,
|
1319 |
+
"normalized": false,
|
1320 |
+
"rstrip": false,
|
1321 |
+
"single_word": false,
|
1322 |
+
"special": true
|
1323 |
+
},
|
1324 |
+
"128165": {
|
1325 |
+
"content": "<|reserved_special_token_157|>",
|
1326 |
+
"lstrip": false,
|
1327 |
+
"normalized": false,
|
1328 |
+
"rstrip": false,
|
1329 |
+
"single_word": false,
|
1330 |
+
"special": true
|
1331 |
+
},
|
1332 |
+
"128166": {
|
1333 |
+
"content": "<|reserved_special_token_158|>",
|
1334 |
+
"lstrip": false,
|
1335 |
+
"normalized": false,
|
1336 |
+
"rstrip": false,
|
1337 |
+
"single_word": false,
|
1338 |
+
"special": true
|
1339 |
+
},
|
1340 |
+
"128167": {
|
1341 |
+
"content": "<|reserved_special_token_159|>",
|
1342 |
+
"lstrip": false,
|
1343 |
+
"normalized": false,
|
1344 |
+
"rstrip": false,
|
1345 |
+
"single_word": false,
|
1346 |
+
"special": true
|
1347 |
+
},
|
1348 |
+
"128168": {
|
1349 |
+
"content": "<|reserved_special_token_160|>",
|
1350 |
+
"lstrip": false,
|
1351 |
+
"normalized": false,
|
1352 |
+
"rstrip": false,
|
1353 |
+
"single_word": false,
|
1354 |
+
"special": true
|
1355 |
+
},
|
1356 |
+
"128169": {
|
1357 |
+
"content": "<|reserved_special_token_161|>",
|
1358 |
+
"lstrip": false,
|
1359 |
+
"normalized": false,
|
1360 |
+
"rstrip": false,
|
1361 |
+
"single_word": false,
|
1362 |
+
"special": true
|
1363 |
+
},
|
1364 |
+
"128170": {
|
1365 |
+
"content": "<|reserved_special_token_162|>",
|
1366 |
+
"lstrip": false,
|
1367 |
+
"normalized": false,
|
1368 |
+
"rstrip": false,
|
1369 |
+
"single_word": false,
|
1370 |
+
"special": true
|
1371 |
+
},
|
1372 |
+
"128171": {
|
1373 |
+
"content": "<|reserved_special_token_163|>",
|
1374 |
+
"lstrip": false,
|
1375 |
+
"normalized": false,
|
1376 |
+
"rstrip": false,
|
1377 |
+
"single_word": false,
|
1378 |
+
"special": true
|
1379 |
+
},
|
1380 |
+
"128172": {
|
1381 |
+
"content": "<|reserved_special_token_164|>",
|
1382 |
+
"lstrip": false,
|
1383 |
+
"normalized": false,
|
1384 |
+
"rstrip": false,
|
1385 |
+
"single_word": false,
|
1386 |
+
"special": true
|
1387 |
+
},
|
1388 |
+
"128173": {
|
1389 |
+
"content": "<|reserved_special_token_165|>",
|
1390 |
+
"lstrip": false,
|
1391 |
+
"normalized": false,
|
1392 |
+
"rstrip": false,
|
1393 |
+
"single_word": false,
|
1394 |
+
"special": true
|
1395 |
+
},
|
1396 |
+
"128174": {
|
1397 |
+
"content": "<|reserved_special_token_166|>",
|
1398 |
+
"lstrip": false,
|
1399 |
+
"normalized": false,
|
1400 |
+
"rstrip": false,
|
1401 |
+
"single_word": false,
|
1402 |
+
"special": true
|
1403 |
+
},
|
1404 |
+
"128175": {
|
1405 |
+
"content": "<|reserved_special_token_167|>",
|
1406 |
+
"lstrip": false,
|
1407 |
+
"normalized": false,
|
1408 |
+
"rstrip": false,
|
1409 |
+
"single_word": false,
|
1410 |
+
"special": true
|
1411 |
+
},
|
1412 |
+
"128176": {
|
1413 |
+
"content": "<|reserved_special_token_168|>",
|
1414 |
+
"lstrip": false,
|
1415 |
+
"normalized": false,
|
1416 |
+
"rstrip": false,
|
1417 |
+
"single_word": false,
|
1418 |
+
"special": true
|
1419 |
+
},
|
1420 |
+
"128177": {
|
1421 |
+
"content": "<|reserved_special_token_169|>",
|
1422 |
+
"lstrip": false,
|
1423 |
+
"normalized": false,
|
1424 |
+
"rstrip": false,
|
1425 |
+
"single_word": false,
|
1426 |
+
"special": true
|
1427 |
+
},
|
1428 |
+
"128178": {
|
1429 |
+
"content": "<|reserved_special_token_170|>",
|
1430 |
+
"lstrip": false,
|
1431 |
+
"normalized": false,
|
1432 |
+
"rstrip": false,
|
1433 |
+
"single_word": false,
|
1434 |
+
"special": true
|
1435 |
+
},
|
1436 |
+
"128179": {
|
1437 |
+
"content": "<|reserved_special_token_171|>",
|
1438 |
+
"lstrip": false,
|
1439 |
+
"normalized": false,
|
1440 |
+
"rstrip": false,
|
1441 |
+
"single_word": false,
|
1442 |
+
"special": true
|
1443 |
+
},
|
1444 |
+
"128180": {
|
1445 |
+
"content": "<|reserved_special_token_172|>",
|
1446 |
+
"lstrip": false,
|
1447 |
+
"normalized": false,
|
1448 |
+
"rstrip": false,
|
1449 |
+
"single_word": false,
|
1450 |
+
"special": true
|
1451 |
+
},
|
1452 |
+
"128181": {
|
1453 |
+
"content": "<|reserved_special_token_173|>",
|
1454 |
+
"lstrip": false,
|
1455 |
+
"normalized": false,
|
1456 |
+
"rstrip": false,
|
1457 |
+
"single_word": false,
|
1458 |
+
"special": true
|
1459 |
+
},
|
1460 |
+
"128182": {
|
1461 |
+
"content": "<|reserved_special_token_174|>",
|
1462 |
+
"lstrip": false,
|
1463 |
+
"normalized": false,
|
1464 |
+
"rstrip": false,
|
1465 |
+
"single_word": false,
|
1466 |
+
"special": true
|
1467 |
+
},
|
1468 |
+
"128183": {
|
1469 |
+
"content": "<|reserved_special_token_175|>",
|
1470 |
+
"lstrip": false,
|
1471 |
+
"normalized": false,
|
1472 |
+
"rstrip": false,
|
1473 |
+
"single_word": false,
|
1474 |
+
"special": true
|
1475 |
+
},
|
1476 |
+
"128184": {
|
1477 |
+
"content": "<|reserved_special_token_176|>",
|
1478 |
+
"lstrip": false,
|
1479 |
+
"normalized": false,
|
1480 |
+
"rstrip": false,
|
1481 |
+
"single_word": false,
|
1482 |
+
"special": true
|
1483 |
+
},
|
1484 |
+
"128185": {
|
1485 |
+
"content": "<|reserved_special_token_177|>",
|
1486 |
+
"lstrip": false,
|
1487 |
+
"normalized": false,
|
1488 |
+
"rstrip": false,
|
1489 |
+
"single_word": false,
|
1490 |
+
"special": true
|
1491 |
+
},
|
1492 |
+
"128186": {
|
1493 |
+
"content": "<|reserved_special_token_178|>",
|
1494 |
+
"lstrip": false,
|
1495 |
+
"normalized": false,
|
1496 |
+
"rstrip": false,
|
1497 |
+
"single_word": false,
|
1498 |
+
"special": true
|
1499 |
+
},
|
1500 |
+
"128187": {
|
1501 |
+
"content": "<|reserved_special_token_179|>",
|
1502 |
+
"lstrip": false,
|
1503 |
+
"normalized": false,
|
1504 |
+
"rstrip": false,
|
1505 |
+
"single_word": false,
|
1506 |
+
"special": true
|
1507 |
+
},
|
1508 |
+
"128188": {
|
1509 |
+
"content": "<|reserved_special_token_180|>",
|
1510 |
+
"lstrip": false,
|
1511 |
+
"normalized": false,
|
1512 |
+
"rstrip": false,
|
1513 |
+
"single_word": false,
|
1514 |
+
"special": true
|
1515 |
+
},
|
1516 |
+
"128189": {
|
1517 |
+
"content": "<|reserved_special_token_181|>",
|
1518 |
+
"lstrip": false,
|
1519 |
+
"normalized": false,
|
1520 |
+
"rstrip": false,
|
1521 |
+
"single_word": false,
|
1522 |
+
"special": true
|
1523 |
+
},
|
1524 |
+
"128190": {
|
1525 |
+
"content": "<|reserved_special_token_182|>",
|
1526 |
+
"lstrip": false,
|
1527 |
+
"normalized": false,
|
1528 |
+
"rstrip": false,
|
1529 |
+
"single_word": false,
|
1530 |
+
"special": true
|
1531 |
+
},
|
1532 |
+
"128191": {
|
1533 |
+
"content": "<|reserved_special_token_183|>",
|
1534 |
+
"lstrip": false,
|
1535 |
+
"normalized": false,
|
1536 |
+
"rstrip": false,
|
1537 |
+
"single_word": false,
|
1538 |
+
"special": true
|
1539 |
+
},
|
1540 |
+
"128192": {
|
1541 |
+
"content": "<|reserved_special_token_184|>",
|
1542 |
+
"lstrip": false,
|
1543 |
+
"normalized": false,
|
1544 |
+
"rstrip": false,
|
1545 |
+
"single_word": false,
|
1546 |
+
"special": true
|
1547 |
+
},
|
1548 |
+
"128193": {
|
1549 |
+
"content": "<|reserved_special_token_185|>",
|
1550 |
+
"lstrip": false,
|
1551 |
+
"normalized": false,
|
1552 |
+
"rstrip": false,
|
1553 |
+
"single_word": false,
|
1554 |
+
"special": true
|
1555 |
+
},
|
1556 |
+
"128194": {
|
1557 |
+
"content": "<|reserved_special_token_186|>",
|
1558 |
+
"lstrip": false,
|
1559 |
+
"normalized": false,
|
1560 |
+
"rstrip": false,
|
1561 |
+
"single_word": false,
|
1562 |
+
"special": true
|
1563 |
+
},
|
1564 |
+
"128195": {
|
1565 |
+
"content": "<|reserved_special_token_187|>",
|
1566 |
+
"lstrip": false,
|
1567 |
+
"normalized": false,
|
1568 |
+
"rstrip": false,
|
1569 |
+
"single_word": false,
|
1570 |
+
"special": true
|
1571 |
+
},
|
1572 |
+
"128196": {
|
1573 |
+
"content": "<|reserved_special_token_188|>",
|
1574 |
+
"lstrip": false,
|
1575 |
+
"normalized": false,
|
1576 |
+
"rstrip": false,
|
1577 |
+
"single_word": false,
|
1578 |
+
"special": true
|
1579 |
+
},
|
1580 |
+
"128197": {
|
1581 |
+
"content": "<|reserved_special_token_189|>",
|
1582 |
+
"lstrip": false,
|
1583 |
+
"normalized": false,
|
1584 |
+
"rstrip": false,
|
1585 |
+
"single_word": false,
|
1586 |
+
"special": true
|
1587 |
+
},
|
1588 |
+
"128198": {
|
1589 |
+
"content": "<|reserved_special_token_190|>",
|
1590 |
+
"lstrip": false,
|
1591 |
+
"normalized": false,
|
1592 |
+
"rstrip": false,
|
1593 |
+
"single_word": false,
|
1594 |
+
"special": true
|
1595 |
+
},
|
1596 |
+
"128199": {
|
1597 |
+
"content": "<|reserved_special_token_191|>",
|
1598 |
+
"lstrip": false,
|
1599 |
+
"normalized": false,
|
1600 |
+
"rstrip": false,
|
1601 |
+
"single_word": false,
|
1602 |
+
"special": true
|
1603 |
+
},
|
1604 |
+
"128200": {
|
1605 |
+
"content": "<|reserved_special_token_192|>",
|
1606 |
+
"lstrip": false,
|
1607 |
+
"normalized": false,
|
1608 |
+
"rstrip": false,
|
1609 |
+
"single_word": false,
|
1610 |
+
"special": true
|
1611 |
+
},
|
1612 |
+
"128201": {
|
1613 |
+
"content": "<|reserved_special_token_193|>",
|
1614 |
+
"lstrip": false,
|
1615 |
+
"normalized": false,
|
1616 |
+
"rstrip": false,
|
1617 |
+
"single_word": false,
|
1618 |
+
"special": true
|
1619 |
+
},
|
1620 |
+
"128202": {
|
1621 |
+
"content": "<|reserved_special_token_194|>",
|
1622 |
+
"lstrip": false,
|
1623 |
+
"normalized": false,
|
1624 |
+
"rstrip": false,
|
1625 |
+
"single_word": false,
|
1626 |
+
"special": true
|
1627 |
+
},
|
1628 |
+
"128203": {
|
1629 |
+
"content": "<|reserved_special_token_195|>",
|
1630 |
+
"lstrip": false,
|
1631 |
+
"normalized": false,
|
1632 |
+
"rstrip": false,
|
1633 |
+
"single_word": false,
|
1634 |
+
"special": true
|
1635 |
+
},
|
1636 |
+
"128204": {
|
1637 |
+
"content": "<|reserved_special_token_196|>",
|
1638 |
+
"lstrip": false,
|
1639 |
+
"normalized": false,
|
1640 |
+
"rstrip": false,
|
1641 |
+
"single_word": false,
|
1642 |
+
"special": true
|
1643 |
+
},
|
1644 |
+
"128205": {
|
1645 |
+
"content": "<|reserved_special_token_197|>",
|
1646 |
+
"lstrip": false,
|
1647 |
+
"normalized": false,
|
1648 |
+
"rstrip": false,
|
1649 |
+
"single_word": false,
|
1650 |
+
"special": true
|
1651 |
+
},
|
1652 |
+
"128206": {
|
1653 |
+
"content": "<|reserved_special_token_198|>",
|
1654 |
+
"lstrip": false,
|
1655 |
+
"normalized": false,
|
1656 |
+
"rstrip": false,
|
1657 |
+
"single_word": false,
|
1658 |
+
"special": true
|
1659 |
+
},
|
1660 |
+
"128207": {
|
1661 |
+
"content": "<|reserved_special_token_199|>",
|
1662 |
+
"lstrip": false,
|
1663 |
+
"normalized": false,
|
1664 |
+
"rstrip": false,
|
1665 |
+
"single_word": false,
|
1666 |
+
"special": true
|
1667 |
+
},
|
1668 |
+
"128208": {
|
1669 |
+
"content": "<|reserved_special_token_200|>",
|
1670 |
+
"lstrip": false,
|
1671 |
+
"normalized": false,
|
1672 |
+
"rstrip": false,
|
1673 |
+
"single_word": false,
|
1674 |
+
"special": true
|
1675 |
+
},
|
1676 |
+
"128209": {
|
1677 |
+
"content": "<|reserved_special_token_201|>",
|
1678 |
+
"lstrip": false,
|
1679 |
+
"normalized": false,
|
1680 |
+
"rstrip": false,
|
1681 |
+
"single_word": false,
|
1682 |
+
"special": true
|
1683 |
+
},
|
1684 |
+
"128210": {
|
1685 |
+
"content": "<|reserved_special_token_202|>",
|
1686 |
+
"lstrip": false,
|
1687 |
+
"normalized": false,
|
1688 |
+
"rstrip": false,
|
1689 |
+
"single_word": false,
|
1690 |
+
"special": true
|
1691 |
+
},
|
1692 |
+
"128211": {
|
1693 |
+
"content": "<|reserved_special_token_203|>",
|
1694 |
+
"lstrip": false,
|
1695 |
+
"normalized": false,
|
1696 |
+
"rstrip": false,
|
1697 |
+
"single_word": false,
|
1698 |
+
"special": true
|
1699 |
+
},
|
1700 |
+
"128212": {
|
1701 |
+
"content": "<|reserved_special_token_204|>",
|
1702 |
+
"lstrip": false,
|
1703 |
+
"normalized": false,
|
1704 |
+
"rstrip": false,
|
1705 |
+
"single_word": false,
|
1706 |
+
"special": true
|
1707 |
+
},
|
1708 |
+
"128213": {
|
1709 |
+
"content": "<|reserved_special_token_205|>",
|
1710 |
+
"lstrip": false,
|
1711 |
+
"normalized": false,
|
1712 |
+
"rstrip": false,
|
1713 |
+
"single_word": false,
|
1714 |
+
"special": true
|
1715 |
+
},
|
1716 |
+
"128214": {
|
1717 |
+
"content": "<|reserved_special_token_206|>",
|
1718 |
+
"lstrip": false,
|
1719 |
+
"normalized": false,
|
1720 |
+
"rstrip": false,
|
1721 |
+
"single_word": false,
|
1722 |
+
"special": true
|
1723 |
+
},
|
1724 |
+
"128215": {
|
1725 |
+
"content": "<|reserved_special_token_207|>",
|
1726 |
+
"lstrip": false,
|
1727 |
+
"normalized": false,
|
1728 |
+
"rstrip": false,
|
1729 |
+
"single_word": false,
|
1730 |
+
"special": true
|
1731 |
+
},
|
1732 |
+
"128216": {
|
1733 |
+
"content": "<|reserved_special_token_208|>",
|
1734 |
+
"lstrip": false,
|
1735 |
+
"normalized": false,
|
1736 |
+
"rstrip": false,
|
1737 |
+
"single_word": false,
|
1738 |
+
"special": true
|
1739 |
+
},
|
1740 |
+
"128217": {
|
1741 |
+
"content": "<|reserved_special_token_209|>",
|
1742 |
+
"lstrip": false,
|
1743 |
+
"normalized": false,
|
1744 |
+
"rstrip": false,
|
1745 |
+
"single_word": false,
|
1746 |
+
"special": true
|
1747 |
+
},
|
1748 |
+
"128218": {
|
1749 |
+
"content": "<|reserved_special_token_210|>",
|
1750 |
+
"lstrip": false,
|
1751 |
+
"normalized": false,
|
1752 |
+
"rstrip": false,
|
1753 |
+
"single_word": false,
|
1754 |
+
"special": true
|
1755 |
+
},
|
1756 |
+
"128219": {
|
1757 |
+
"content": "<|reserved_special_token_211|>",
|
1758 |
+
"lstrip": false,
|
1759 |
+
"normalized": false,
|
1760 |
+
"rstrip": false,
|
1761 |
+
"single_word": false,
|
1762 |
+
"special": true
|
1763 |
+
},
|
1764 |
+
"128220": {
|
1765 |
+
"content": "<|reserved_special_token_212|>",
|
1766 |
+
"lstrip": false,
|
1767 |
+
"normalized": false,
|
1768 |
+
"rstrip": false,
|
1769 |
+
"single_word": false,
|
1770 |
+
"special": true
|
1771 |
+
},
|
1772 |
+
"128221": {
|
1773 |
+
"content": "<|reserved_special_token_213|>",
|
1774 |
+
"lstrip": false,
|
1775 |
+
"normalized": false,
|
1776 |
+
"rstrip": false,
|
1777 |
+
"single_word": false,
|
1778 |
+
"special": true
|
1779 |
+
},
|
1780 |
+
"128222": {
|
1781 |
+
"content": "<|reserved_special_token_214|>",
|
1782 |
+
"lstrip": false,
|
1783 |
+
"normalized": false,
|
1784 |
+
"rstrip": false,
|
1785 |
+
"single_word": false,
|
1786 |
+
"special": true
|
1787 |
+
},
|
1788 |
+
"128223": {
|
1789 |
+
"content": "<|reserved_special_token_215|>",
|
1790 |
+
"lstrip": false,
|
1791 |
+
"normalized": false,
|
1792 |
+
"rstrip": false,
|
1793 |
+
"single_word": false,
|
1794 |
+
"special": true
|
1795 |
+
},
|
1796 |
+
"128224": {
|
1797 |
+
"content": "<|reserved_special_token_216|>",
|
1798 |
+
"lstrip": false,
|
1799 |
+
"normalized": false,
|
1800 |
+
"rstrip": false,
|
1801 |
+
"single_word": false,
|
1802 |
+
"special": true
|
1803 |
+
},
|
1804 |
+
"128225": {
|
1805 |
+
"content": "<|reserved_special_token_217|>",
|
1806 |
+
"lstrip": false,
|
1807 |
+
"normalized": false,
|
1808 |
+
"rstrip": false,
|
1809 |
+
"single_word": false,
|
1810 |
+
"special": true
|
1811 |
+
},
|
1812 |
+
"128226": {
|
1813 |
+
"content": "<|reserved_special_token_218|>",
|
1814 |
+
"lstrip": false,
|
1815 |
+
"normalized": false,
|
1816 |
+
"rstrip": false,
|
1817 |
+
"single_word": false,
|
1818 |
+
"special": true
|
1819 |
+
},
|
1820 |
+
"128227": {
|
1821 |
+
"content": "<|reserved_special_token_219|>",
|
1822 |
+
"lstrip": false,
|
1823 |
+
"normalized": false,
|
1824 |
+
"rstrip": false,
|
1825 |
+
"single_word": false,
|
1826 |
+
"special": true
|
1827 |
+
},
|
1828 |
+
"128228": {
|
1829 |
+
"content": "<|reserved_special_token_220|>",
|
1830 |
+
"lstrip": false,
|
1831 |
+
"normalized": false,
|
1832 |
+
"rstrip": false,
|
1833 |
+
"single_word": false,
|
1834 |
+
"special": true
|
1835 |
+
},
|
1836 |
+
"128229": {
|
1837 |
+
"content": "<|reserved_special_token_221|>",
|
1838 |
+
"lstrip": false,
|
1839 |
+
"normalized": false,
|
1840 |
+
"rstrip": false,
|
1841 |
+
"single_word": false,
|
1842 |
+
"special": true
|
1843 |
+
},
|
1844 |
+
"128230": {
|
1845 |
+
"content": "<|reserved_special_token_222|>",
|
1846 |
+
"lstrip": false,
|
1847 |
+
"normalized": false,
|
1848 |
+
"rstrip": false,
|
1849 |
+
"single_word": false,
|
1850 |
+
"special": true
|
1851 |
+
},
|
1852 |
+
"128231": {
|
1853 |
+
"content": "<|reserved_special_token_223|>",
|
1854 |
+
"lstrip": false,
|
1855 |
+
"normalized": false,
|
1856 |
+
"rstrip": false,
|
1857 |
+
"single_word": false,
|
1858 |
+
"special": true
|
1859 |
+
},
|
1860 |
+
"128232": {
|
1861 |
+
"content": "<|reserved_special_token_224|>",
|
1862 |
+
"lstrip": false,
|
1863 |
+
"normalized": false,
|
1864 |
+
"rstrip": false,
|
1865 |
+
"single_word": false,
|
1866 |
+
"special": true
|
1867 |
+
},
|
1868 |
+
"128233": {
|
1869 |
+
"content": "<|reserved_special_token_225|>",
|
1870 |
+
"lstrip": false,
|
1871 |
+
"normalized": false,
|
1872 |
+
"rstrip": false,
|
1873 |
+
"single_word": false,
|
1874 |
+
"special": true
|
1875 |
+
},
|
1876 |
+
"128234": {
|
1877 |
+
"content": "<|reserved_special_token_226|>",
|
1878 |
+
"lstrip": false,
|
1879 |
+
"normalized": false,
|
1880 |
+
"rstrip": false,
|
1881 |
+
"single_word": false,
|
1882 |
+
"special": true
|
1883 |
+
},
|
1884 |
+
"128235": {
|
1885 |
+
"content": "<|reserved_special_token_227|>",
|
1886 |
+
"lstrip": false,
|
1887 |
+
"normalized": false,
|
1888 |
+
"rstrip": false,
|
1889 |
+
"single_word": false,
|
1890 |
+
"special": true
|
1891 |
+
},
|
1892 |
+
"128236": {
|
1893 |
+
"content": "<|reserved_special_token_228|>",
|
1894 |
+
"lstrip": false,
|
1895 |
+
"normalized": false,
|
1896 |
+
"rstrip": false,
|
1897 |
+
"single_word": false,
|
1898 |
+
"special": true
|
1899 |
+
},
|
1900 |
+
"128237": {
|
1901 |
+
"content": "<|reserved_special_token_229|>",
|
1902 |
+
"lstrip": false,
|
1903 |
+
"normalized": false,
|
1904 |
+
"rstrip": false,
|
1905 |
+
"single_word": false,
|
1906 |
+
"special": true
|
1907 |
+
},
|
1908 |
+
"128238": {
|
1909 |
+
"content": "<|reserved_special_token_230|>",
|
1910 |
+
"lstrip": false,
|
1911 |
+
"normalized": false,
|
1912 |
+
"rstrip": false,
|
1913 |
+
"single_word": false,
|
1914 |
+
"special": true
|
1915 |
+
},
|
1916 |
+
"128239": {
|
1917 |
+
"content": "<|reserved_special_token_231|>",
|
1918 |
+
"lstrip": false,
|
1919 |
+
"normalized": false,
|
1920 |
+
"rstrip": false,
|
1921 |
+
"single_word": false,
|
1922 |
+
"special": true
|
1923 |
+
},
|
1924 |
+
"128240": {
|
1925 |
+
"content": "<|reserved_special_token_232|>",
|
1926 |
+
"lstrip": false,
|
1927 |
+
"normalized": false,
|
1928 |
+
"rstrip": false,
|
1929 |
+
"single_word": false,
|
1930 |
+
"special": true
|
1931 |
+
},
|
1932 |
+
"128241": {
|
1933 |
+
"content": "<|reserved_special_token_233|>",
|
1934 |
+
"lstrip": false,
|
1935 |
+
"normalized": false,
|
1936 |
+
"rstrip": false,
|
1937 |
+
"single_word": false,
|
1938 |
+
"special": true
|
1939 |
+
},
|
1940 |
+
"128242": {
|
1941 |
+
"content": "<|reserved_special_token_234|>",
|
1942 |
+
"lstrip": false,
|
1943 |
+
"normalized": false,
|
1944 |
+
"rstrip": false,
|
1945 |
+
"single_word": false,
|
1946 |
+
"special": true
|
1947 |
+
},
|
1948 |
+
"128243": {
|
1949 |
+
"content": "<|reserved_special_token_235|>",
|
1950 |
+
"lstrip": false,
|
1951 |
+
"normalized": false,
|
1952 |
+
"rstrip": false,
|
1953 |
+
"single_word": false,
|
1954 |
+
"special": true
|
1955 |
+
},
|
1956 |
+
"128244": {
|
1957 |
+
"content": "<|reserved_special_token_236|>",
|
1958 |
+
"lstrip": false,
|
1959 |
+
"normalized": false,
|
1960 |
+
"rstrip": false,
|
1961 |
+
"single_word": false,
|
1962 |
+
"special": true
|
1963 |
+
},
|
1964 |
+
"128245": {
|
1965 |
+
"content": "<|reserved_special_token_237|>",
|
1966 |
+
"lstrip": false,
|
1967 |
+
"normalized": false,
|
1968 |
+
"rstrip": false,
|
1969 |
+
"single_word": false,
|
1970 |
+
"special": true
|
1971 |
+
},
|
1972 |
+
"128246": {
|
1973 |
+
"content": "<|reserved_special_token_238|>",
|
1974 |
+
"lstrip": false,
|
1975 |
+
"normalized": false,
|
1976 |
+
"rstrip": false,
|
1977 |
+
"single_word": false,
|
1978 |
+
"special": true
|
1979 |
+
},
|
1980 |
+
"128247": {
|
1981 |
+
"content": "<|reserved_special_token_239|>",
|
1982 |
+
"lstrip": false,
|
1983 |
+
"normalized": false,
|
1984 |
+
"rstrip": false,
|
1985 |
+
"single_word": false,
|
1986 |
+
"special": true
|
1987 |
+
},
|
1988 |
+
"128248": {
|
1989 |
+
"content": "<|reserved_special_token_240|>",
|
1990 |
+
"lstrip": false,
|
1991 |
+
"normalized": false,
|
1992 |
+
"rstrip": false,
|
1993 |
+
"single_word": false,
|
1994 |
+
"special": true
|
1995 |
+
},
|
1996 |
+
"128249": {
|
1997 |
+
"content": "<|reserved_special_token_241|>",
|
1998 |
+
"lstrip": false,
|
1999 |
+
"normalized": false,
|
2000 |
+
"rstrip": false,
|
2001 |
+
"single_word": false,
|
2002 |
+
"special": true
|
2003 |
+
},
|
2004 |
+
"128250": {
|
2005 |
+
"content": "<|reserved_special_token_242|>",
|
2006 |
+
"lstrip": false,
|
2007 |
+
"normalized": false,
|
2008 |
+
"rstrip": false,
|
2009 |
+
"single_word": false,
|
2010 |
+
"special": true
|
2011 |
+
},
|
2012 |
+
"128251": {
|
2013 |
+
"content": "<|reserved_special_token_243|>",
|
2014 |
+
"lstrip": false,
|
2015 |
+
"normalized": false,
|
2016 |
+
"rstrip": false,
|
2017 |
+
"single_word": false,
|
2018 |
+
"special": true
|
2019 |
+
},
|
2020 |
+
"128252": {
|
2021 |
+
"content": "<|reserved_special_token_244|>",
|
2022 |
+
"lstrip": false,
|
2023 |
+
"normalized": false,
|
2024 |
+
"rstrip": false,
|
2025 |
+
"single_word": false,
|
2026 |
+
"special": true
|
2027 |
+
},
|
2028 |
+
"128253": {
|
2029 |
+
"content": "<|reserved_special_token_245|>",
|
2030 |
+
"lstrip": false,
|
2031 |
+
"normalized": false,
|
2032 |
+
"rstrip": false,
|
2033 |
+
"single_word": false,
|
2034 |
+
"special": true
|
2035 |
+
},
|
2036 |
+
"128254": {
|
2037 |
+
"content": "<|reserved_special_token_246|>",
|
2038 |
+
"lstrip": false,
|
2039 |
+
"normalized": false,
|
2040 |
+
"rstrip": false,
|
2041 |
+
"single_word": false,
|
2042 |
+
"special": true
|
2043 |
+
},
|
2044 |
+
"128255": {
|
2045 |
+
"content": "<|reserved_special_token_247|>",
|
2046 |
+
"lstrip": false,
|
2047 |
+
"normalized": false,
|
2048 |
+
"rstrip": false,
|
2049 |
+
"single_word": false,
|
2050 |
+
"special": true
|
2051 |
+
}
|
2052 |
+
},
|
2053 |
+
"bos_token": "<|begin_of_text|>",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|end_of_text|>",
|
2056 |
+
"extra_special_tokens": {},
|
2057 |
+
"model_input_names": [
|
2058 |
+
"input_ids",
|
2059 |
+
"attention_mask"
|
2060 |
+
],
|
2061 |
+
"model_max_length": 131072,
|
2062 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
2063 |
+
"padding_side": "left",
|
2064 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
2065 |
+
"unk_token": null
|
2066 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": null,
|
3 |
+
"best_metric": null,
|
4 |
+
"best_model_checkpoint": null,
|
5 |
+
"epoch": 0.8616937691959715,
|
6 |
+
"eval_steps": 1005,
|
7 |
+
"global_step": 9048,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.0038094331087355064,
|
14 |
+
"grad_norm": 1.1105036735534668,
|
15 |
+
"learning_rate": 1.2714024683199598e-06,
|
16 |
+
"loss": 1.9169,
|
17 |
+
"mean_token_accuracy": 0.5754982324317097,
|
18 |
+
"num_tokens": 213515.0,
|
19 |
+
"step": 40
|
20 |
+
},
|
21 |
+
{
|
22 |
+
"epoch": 0.007618866217471013,
|
23 |
+
"grad_norm": 0.8602012991905212,
|
24 |
+
"learning_rate": 2.575404999930175e-06,
|
25 |
+
"loss": 1.7612,
|
26 |
+
"mean_token_accuracy": 0.5973538164049387,
|
27 |
+
"num_tokens": 428291.0,
|
28 |
+
"step": 80
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 0.01142829932620652,
|
32 |
+
"grad_norm": 0.7212763428688049,
|
33 |
+
"learning_rate": 3.87940753154039e-06,
|
34 |
+
"loss": 1.7641,
|
35 |
+
"mean_token_accuracy": 0.6031968526542186,
|
36 |
+
"num_tokens": 649316.0,
|
37 |
+
"step": 120
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.015237732434942025,
|
41 |
+
"grad_norm": 0.9749614000320435,
|
42 |
+
"learning_rate": 5.183410063150605e-06,
|
43 |
+
"loss": 1.5732,
|
44 |
+
"mean_token_accuracy": 0.6395209338515997,
|
45 |
+
"num_tokens": 867038.0,
|
46 |
+
"step": 160
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.01904716554367753,
|
50 |
+
"grad_norm": 0.8746033310890198,
|
51 |
+
"learning_rate": 6.48741259476082e-06,
|
52 |
+
"loss": 1.5567,
|
53 |
+
"mean_token_accuracy": 0.6250597681850195,
|
54 |
+
"num_tokens": 1084477.0,
|
55 |
+
"step": 200
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 0.02285659865241304,
|
59 |
+
"grad_norm": 0.6283444762229919,
|
60 |
+
"learning_rate": 7.791415126371035e-06,
|
61 |
+
"loss": 1.4563,
|
62 |
+
"mean_token_accuracy": 0.6498559027910232,
|
63 |
+
"num_tokens": 1304254.0,
|
64 |
+
"step": 240
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 0.026666031761148543,
|
68 |
+
"grad_norm": 0.8473705053329468,
|
69 |
+
"learning_rate": 9.09541765798125e-06,
|
70 |
+
"loss": 1.5125,
|
71 |
+
"mean_token_accuracy": 0.640368782542646,
|
72 |
+
"num_tokens": 1518177.0,
|
73 |
+
"step": 280
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.03047546486988405,
|
77 |
+
"grad_norm": 0.8421404361724854,
|
78 |
+
"learning_rate": 1.0399420189591466e-05,
|
79 |
+
"loss": 1.43,
|
80 |
+
"mean_token_accuracy": 0.6589812656864524,
|
81 |
+
"num_tokens": 1745573.0,
|
82 |
+
"step": 320
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.034284897978619555,
|
86 |
+
"grad_norm": 0.7308921813964844,
|
87 |
+
"learning_rate": 1.1703422721201682e-05,
|
88 |
+
"loss": 1.3957,
|
89 |
+
"mean_token_accuracy": 0.6596783269196749,
|
90 |
+
"num_tokens": 1970323.0,
|
91 |
+
"step": 360
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.03809433108735506,
|
95 |
+
"grad_norm": 1.024109125137329,
|
96 |
+
"learning_rate": 1.3007425252811896e-05,
|
97 |
+
"loss": 1.2906,
|
98 |
+
"mean_token_accuracy": 0.6734623985365034,
|
99 |
+
"num_tokens": 2209851.0,
|
100 |
+
"step": 400
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.04190376419609057,
|
104 |
+
"grad_norm": 0.8211472034454346,
|
105 |
+
"learning_rate": 1.4311427784422112e-05,
|
106 |
+
"loss": 1.4547,
|
107 |
+
"mean_token_accuracy": 0.65384187027812,
|
108 |
+
"num_tokens": 2419422.0,
|
109 |
+
"step": 440
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.04571319730482608,
|
113 |
+
"grad_norm": 0.9193497896194458,
|
114 |
+
"learning_rate": 1.5615430316032328e-05,
|
115 |
+
"loss": 1.3763,
|
116 |
+
"mean_token_accuracy": 0.6668608419597148,
|
117 |
+
"num_tokens": 2650647.0,
|
118 |
+
"step": 480
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.04952263041356158,
|
122 |
+
"grad_norm": 0.9686090350151062,
|
123 |
+
"learning_rate": 1.6919432847642544e-05,
|
124 |
+
"loss": 1.3092,
|
125 |
+
"mean_token_accuracy": 0.6819563843309879,
|
126 |
+
"num_tokens": 2895742.0,
|
127 |
+
"step": 520
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 0.053332063522297087,
|
131 |
+
"grad_norm": 0.6123139262199402,
|
132 |
+
"learning_rate": 1.8223435379252756e-05,
|
133 |
+
"loss": 1.3106,
|
134 |
+
"mean_token_accuracy": 0.6761070437729358,
|
135 |
+
"num_tokens": 3131131.0,
|
136 |
+
"step": 560
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.057141496631032594,
|
140 |
+
"grad_norm": 0.8315911293029785,
|
141 |
+
"learning_rate": 1.952743791086297e-05,
|
142 |
+
"loss": 1.295,
|
143 |
+
"mean_token_accuracy": 0.6829990902915597,
|
144 |
+
"num_tokens": 3358554.0,
|
145 |
+
"step": 600
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 0.0609509297397681,
|
149 |
+
"grad_norm": 0.6099031567573547,
|
150 |
+
"learning_rate": 2.0831440442473187e-05,
|
151 |
+
"loss": 1.315,
|
152 |
+
"mean_token_accuracy": 0.6704990575090051,
|
153 |
+
"num_tokens": 3584968.0,
|
154 |
+
"step": 640
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.0647603628485036,
|
158 |
+
"grad_norm": 0.8671184778213501,
|
159 |
+
"learning_rate": 2.2135442974083403e-05,
|
160 |
+
"loss": 1.4007,
|
161 |
+
"mean_token_accuracy": 0.6610645942389966,
|
162 |
+
"num_tokens": 3789884.0,
|
163 |
+
"step": 680
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.06856979595723911,
|
167 |
+
"grad_norm": 0.8112688064575195,
|
168 |
+
"learning_rate": 2.3439445505693616e-05,
|
169 |
+
"loss": 1.3192,
|
170 |
+
"mean_token_accuracy": 0.6786379875615239,
|
171 |
+
"num_tokens": 4010228.0,
|
172 |
+
"step": 720
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.07237922906597462,
|
176 |
+
"grad_norm": 0.7991048097610474,
|
177 |
+
"learning_rate": 2.474344803730383e-05,
|
178 |
+
"loss": 1.357,
|
179 |
+
"mean_token_accuracy": 0.6695337913930416,
|
180 |
+
"num_tokens": 4240601.0,
|
181 |
+
"step": 760
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.07618866217471013,
|
185 |
+
"grad_norm": 0.6952106356620789,
|
186 |
+
"learning_rate": 2.6047450568914047e-05,
|
187 |
+
"loss": 1.3805,
|
188 |
+
"mean_token_accuracy": 0.666619416512549,
|
189 |
+
"num_tokens": 4457613.0,
|
190 |
+
"step": 800
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 0.07999809528344563,
|
194 |
+
"grad_norm": 0.5898691415786743,
|
195 |
+
"learning_rate": 2.7351453100524263e-05,
|
196 |
+
"loss": 1.3645,
|
197 |
+
"mean_token_accuracy": 0.6681723784655332,
|
198 |
+
"num_tokens": 4675575.0,
|
199 |
+
"step": 840
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.08380752839218114,
|
203 |
+
"grad_norm": 0.8592577576637268,
|
204 |
+
"learning_rate": 2.865545563213448e-05,
|
205 |
+
"loss": 1.3007,
|
206 |
+
"mean_token_accuracy": 0.6759131707251071,
|
207 |
+
"num_tokens": 4914793.0,
|
208 |
+
"step": 880
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 0.08761696150091665,
|
212 |
+
"grad_norm": 0.47871366143226624,
|
213 |
+
"learning_rate": 2.9959458163744694e-05,
|
214 |
+
"loss": 1.3316,
|
215 |
+
"mean_token_accuracy": 0.6775730215013027,
|
216 |
+
"num_tokens": 5145053.0,
|
217 |
+
"step": 920
|
218 |
+
},
|
219 |
+
{
|
220 |
+
"epoch": 0.09142639460965216,
|
221 |
+
"grad_norm": 0.6131187081336975,
|
222 |
+
"learning_rate": 3.126346069535491e-05,
|
223 |
+
"loss": 1.3631,
|
224 |
+
"mean_token_accuracy": 0.6744197152554989,
|
225 |
+
"num_tokens": 5353224.0,
|
226 |
+
"step": 960
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.09523582771838766,
|
230 |
+
"grad_norm": 0.6329927444458008,
|
231 |
+
"learning_rate": 3.256746322696512e-05,
|
232 |
+
"loss": 1.3321,
|
233 |
+
"mean_token_accuracy": 0.677939809858799,
|
234 |
+
"num_tokens": 5574886.0,
|
235 |
+
"step": 1000
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.0957120068569796,
|
239 |
+
"eval_mean_token_accuracy": 0.6180267786704393,
|
240 |
+
"eval_num_tokens": 5598115.0,
|
241 |
+
"eval_test_loss": 1.8654624223709106,
|
242 |
+
"eval_test_runtime": 94.5921,
|
243 |
+
"eval_test_samples_per_second": 21.048,
|
244 |
+
"eval_test_steps_per_second": 10.529,
|
245 |
+
"step": 1005
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.09904526082712316,
|
249 |
+
"grad_norm": 0.5825843214988708,
|
250 |
+
"learning_rate": 3.387146575857534e-05,
|
251 |
+
"loss": 1.3293,
|
252 |
+
"mean_token_accuracy": 0.6768566837534309,
|
253 |
+
"num_tokens": 5800189.0,
|
254 |
+
"step": 1040
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.10285469393585867,
|
258 |
+
"grad_norm": 0.47114425897598267,
|
259 |
+
"learning_rate": 3.5175468290185554e-05,
|
260 |
+
"loss": 1.273,
|
261 |
+
"mean_token_accuracy": 0.6856468811631202,
|
262 |
+
"num_tokens": 6035590.0,
|
263 |
+
"step": 1080
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.10666412704459417,
|
267 |
+
"grad_norm": 0.6536944508552551,
|
268 |
+
"learning_rate": 3.647947082179577e-05,
|
269 |
+
"loss": 1.2521,
|
270 |
+
"mean_token_accuracy": 0.6856056058779358,
|
271 |
+
"num_tokens": 6271507.0,
|
272 |
+
"step": 1120
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 0.11047356015332968,
|
276 |
+
"grad_norm": 0.49625030159950256,
|
277 |
+
"learning_rate": 3.7783473353405986e-05,
|
278 |
+
"loss": 1.3219,
|
279 |
+
"mean_token_accuracy": 0.6740474671125412,
|
280 |
+
"num_tokens": 6485242.0,
|
281 |
+
"step": 1160
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 0.11428299326206519,
|
285 |
+
"grad_norm": 0.4760020971298218,
|
286 |
+
"learning_rate": 3.90874758850162e-05,
|
287 |
+
"loss": 1.3866,
|
288 |
+
"mean_token_accuracy": 0.666905522160232,
|
289 |
+
"num_tokens": 6694201.0,
|
290 |
+
"step": 1200
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.1180924263708007,
|
294 |
+
"grad_norm": 0.6702063083648682,
|
295 |
+
"learning_rate": 4.039147841662642e-05,
|
296 |
+
"loss": 1.3396,
|
297 |
+
"mean_token_accuracy": 0.673108272999525,
|
298 |
+
"num_tokens": 6920931.0,
|
299 |
+
"step": 1240
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.1219018594795362,
|
303 |
+
"grad_norm": 0.5828559398651123,
|
304 |
+
"learning_rate": 4.169548094823663e-05,
|
305 |
+
"loss": 1.2849,
|
306 |
+
"mean_token_accuracy": 0.6773701002821326,
|
307 |
+
"num_tokens": 7147355.0,
|
308 |
+
"step": 1280
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.1257112925882717,
|
312 |
+
"grad_norm": 0.558748185634613,
|
313 |
+
"learning_rate": 4.299948347984684e-05,
|
314 |
+
"loss": 1.3391,
|
315 |
+
"mean_token_accuracy": 0.6739463916048407,
|
316 |
+
"num_tokens": 7365364.0,
|
317 |
+
"step": 1320
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.1295207256970072,
|
321 |
+
"grad_norm": 0.5812460780143738,
|
322 |
+
"learning_rate": 4.430348601145706e-05,
|
323 |
+
"loss": 1.3572,
|
324 |
+
"mean_token_accuracy": 0.6651050833985209,
|
325 |
+
"num_tokens": 7575079.0,
|
326 |
+
"step": 1360
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 0.13333015880574273,
|
330 |
+
"grad_norm": 0.7141745686531067,
|
331 |
+
"learning_rate": 4.5607488543067274e-05,
|
332 |
+
"loss": 1.2944,
|
333 |
+
"mean_token_accuracy": 0.681589861959219,
|
334 |
+
"num_tokens": 7804608.0,
|
335 |
+
"step": 1400
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.13713959191447822,
|
339 |
+
"grad_norm": 0.5530197024345398,
|
340 |
+
"learning_rate": 4.691149107467749e-05,
|
341 |
+
"loss": 1.3375,
|
342 |
+
"mean_token_accuracy": 0.6718398928642273,
|
343 |
+
"num_tokens": 8017882.0,
|
344 |
+
"step": 1440
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 0.14094902502321374,
|
348 |
+
"grad_norm": 0.48236706852912903,
|
349 |
+
"learning_rate": 4.8215493606287705e-05,
|
350 |
+
"loss": 1.335,
|
351 |
+
"mean_token_accuracy": 0.6747591784223914,
|
352 |
+
"num_tokens": 8238637.0,
|
353 |
+
"step": 1480
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.14475845813194924,
|
357 |
+
"grad_norm": 0.5896688103675842,
|
358 |
+
"learning_rate": 4.919348145872209e-05,
|
359 |
+
"loss": 1.359,
|
360 |
+
"mean_token_accuracy": 0.6685425175353885,
|
361 |
+
"num_tokens": 8448265.0,
|
362 |
+
"step": 1520
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.14856789124068476,
|
366 |
+
"grad_norm": 0.6068539619445801,
|
367 |
+
"learning_rate": 4.9193144349007555e-05,
|
368 |
+
"loss": 1.3475,
|
369 |
+
"mean_token_accuracy": 0.6698486657813192,
|
370 |
+
"num_tokens": 8663046.0,
|
371 |
+
"step": 1560
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 0.15237732434942025,
|
375 |
+
"grad_norm": 0.4848249852657318,
|
376 |
+
"learning_rate": 4.91923577659781e-05,
|
377 |
+
"loss": 1.3355,
|
378 |
+
"mean_token_accuracy": 0.6719444127753377,
|
379 |
+
"num_tokens": 8882966.0,
|
380 |
+
"step": 1600
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.15618675745815574,
|
384 |
+
"grad_norm": 0.5089111924171448,
|
385 |
+
"learning_rate": 4.9191121724764224e-05,
|
386 |
+
"loss": 1.3455,
|
387 |
+
"mean_token_accuracy": 0.6727668078616261,
|
388 |
+
"num_tokens": 9099039.0,
|
389 |
+
"step": 1640
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 0.15999619056689127,
|
393 |
+
"grad_norm": 0.5716065168380737,
|
394 |
+
"learning_rate": 4.9189436249142116e-05,
|
395 |
+
"loss": 1.3555,
|
396 |
+
"mean_token_accuracy": 0.6711426375433802,
|
397 |
+
"num_tokens": 9320395.0,
|
398 |
+
"step": 1680
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.16380562367562676,
|
402 |
+
"grad_norm": 0.7265896797180176,
|
403 |
+
"learning_rate": 4.918730137153316e-05,
|
404 |
+
"loss": 1.3418,
|
405 |
+
"mean_token_accuracy": 0.6719378443434835,
|
406 |
+
"num_tokens": 9535056.0,
|
407 |
+
"step": 1720
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 0.16761505678436228,
|
411 |
+
"grad_norm": 0.6088116765022278,
|
412 |
+
"learning_rate": 4.9184717133003326e-05,
|
413 |
+
"loss": 1.306,
|
414 |
+
"mean_token_accuracy": 0.6769841868430376,
|
415 |
+
"num_tokens": 9753473.0,
|
416 |
+
"step": 1760
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.17142448989309778,
|
420 |
+
"grad_norm": 0.3883936405181885,
|
421 |
+
"learning_rate": 4.918168358326239e-05,
|
422 |
+
"loss": 1.2348,
|
423 |
+
"mean_token_accuracy": 0.6958686344325542,
|
424 |
+
"num_tokens": 9977829.0,
|
425 |
+
"step": 1800
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 0.1752339230018333,
|
429 |
+
"grad_norm": 0.5694851279258728,
|
430 |
+
"learning_rate": 4.917820078066296e-05,
|
431 |
+
"loss": 1.3571,
|
432 |
+
"mean_token_accuracy": 0.6749148614704609,
|
433 |
+
"num_tokens": 10202796.0,
|
434 |
+
"step": 1840
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.1790433561105688,
|
438 |
+
"grad_norm": 0.4964405298233032,
|
439 |
+
"learning_rate": 4.9174268792199355e-05,
|
440 |
+
"loss": 1.292,
|
441 |
+
"mean_token_accuracy": 0.682447912171483,
|
442 |
+
"num_tokens": 10446726.0,
|
443 |
+
"step": 1880
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.1828527892193043,
|
447 |
+
"grad_norm": 0.585851788520813,
|
448 |
+
"learning_rate": 4.916988769350633e-05,
|
449 |
+
"loss": 1.3271,
|
450 |
+
"mean_token_accuracy": 0.6706608653068542,
|
451 |
+
"num_tokens": 10675299.0,
|
452 |
+
"step": 1920
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 0.1866622223280398,
|
456 |
+
"grad_norm": 0.4936956763267517,
|
457 |
+
"learning_rate": 4.91650575688576e-05,
|
458 |
+
"loss": 1.3212,
|
459 |
+
"mean_token_accuracy": 0.6725098427385092,
|
460 |
+
"num_tokens": 10908277.0,
|
461 |
+
"step": 1960
|
462 |
+
},
|
463 |
+
{
|
464 |
+
"epoch": 0.19047165543677533,
|
465 |
+
"grad_norm": 0.4473949670791626,
|
466 |
+
"learning_rate": 4.9159778511164254e-05,
|
467 |
+
"loss": 1.2485,
|
468 |
+
"mean_token_accuracy": 0.6835329543799162,
|
469 |
+
"num_tokens": 11138801.0,
|
470 |
+
"step": 2000
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.1914240137139592,
|
474 |
+
"eval_mean_token_accuracy": 0.6230506894878115,
|
475 |
+
"eval_num_tokens": 11194791.0,
|
476 |
+
"eval_test_loss": 1.832930564880371,
|
477 |
+
"eval_test_runtime": 95.4667,
|
478 |
+
"eval_test_samples_per_second": 20.855,
|
479 |
+
"eval_test_steps_per_second": 10.433,
|
480 |
+
"step": 2010
|
481 |
+
},
|
482 |
+
{
|
483 |
+
"epoch": 0.19428108854551082,
|
484 |
+
"grad_norm": 0.5689784288406372,
|
485 |
+
"learning_rate": 4.915405062197292e-05,
|
486 |
+
"loss": 1.2842,
|
487 |
+
"mean_token_accuracy": 0.6809853713959455,
|
488 |
+
"num_tokens": 11368252.0,
|
489 |
+
"step": 2040
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.19809052165424632,
|
493 |
+
"grad_norm": 0.5339015126228333,
|
494 |
+
"learning_rate": 4.914787401146385e-05,
|
495 |
+
"loss": 1.3224,
|
496 |
+
"mean_token_accuracy": 0.67562406193465,
|
497 |
+
"num_tokens": 11590368.0,
|
498 |
+
"step": 2080
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 0.20189995476298184,
|
502 |
+
"grad_norm": 0.6560924053192139,
|
503 |
+
"learning_rate": 4.91412487984488e-05,
|
504 |
+
"loss": 1.3732,
|
505 |
+
"mean_token_accuracy": 0.6702003039419651,
|
506 |
+
"num_tokens": 11798414.0,
|
507 |
+
"step": 2120
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.20570938787171733,
|
511 |
+
"grad_norm": 0.5972558259963989,
|
512 |
+
"learning_rate": 4.91341751103687e-05,
|
513 |
+
"loss": 1.2983,
|
514 |
+
"mean_token_accuracy": 0.6805376719683409,
|
515 |
+
"num_tokens": 12013463.0,
|
516 |
+
"step": 2160
|
517 |
+
},
|
518 |
+
{
|
519 |
+
"epoch": 0.20951882098045285,
|
520 |
+
"grad_norm": 0.4506518542766571,
|
521 |
+
"learning_rate": 4.912665308329125e-05,
|
522 |
+
"loss": 1.2653,
|
523 |
+
"mean_token_accuracy": 0.6877350242808461,
|
524 |
+
"num_tokens": 12236318.0,
|
525 |
+
"step": 2200
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.21332825408918835,
|
529 |
+
"grad_norm": 0.5365843772888184,
|
530 |
+
"learning_rate": 4.91186828619083e-05,
|
531 |
+
"loss": 1.3285,
|
532 |
+
"mean_token_accuracy": 0.6712553380057216,
|
533 |
+
"num_tokens": 12458126.0,
|
534 |
+
"step": 2240
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.21713768719792387,
|
538 |
+
"grad_norm": 0.4755626916885376,
|
539 |
+
"learning_rate": 4.9110264599533055e-05,
|
540 |
+
"loss": 1.3315,
|
541 |
+
"mean_token_accuracy": 0.6608016982674598,
|
542 |
+
"num_tokens": 12678890.0,
|
543 |
+
"step": 2280
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.22094712030665936,
|
547 |
+
"grad_norm": 0.43261516094207764,
|
548 |
+
"learning_rate": 4.9101398458097093e-05,
|
549 |
+
"loss": 1.3166,
|
550 |
+
"mean_token_accuracy": 0.6768794044852257,
|
551 |
+
"num_tokens": 12900305.0,
|
552 |
+
"step": 2320
|
553 |
+
},
|
554 |
+
{
|
555 |
+
"epoch": 0.22475655341539488,
|
556 |
+
"grad_norm": 0.5397626161575317,
|
557 |
+
"learning_rate": 4.9092084608147315e-05,
|
558 |
+
"loss": 1.3296,
|
559 |
+
"mean_token_accuracy": 0.6792715717107057,
|
560 |
+
"num_tokens": 13109419.0,
|
561 |
+
"step": 2360
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.22856598652413038,
|
565 |
+
"grad_norm": 0.4163241386413574,
|
566 |
+
"learning_rate": 4.908232322884261e-05,
|
567 |
+
"loss": 1.2938,
|
568 |
+
"mean_token_accuracy": 0.6871387459337711,
|
569 |
+
"num_tokens": 13335797.0,
|
570 |
+
"step": 2400
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.23237541963286587,
|
574 |
+
"grad_norm": 0.7546857595443726,
|
575 |
+
"learning_rate": 4.907211450795045e-05,
|
576 |
+
"loss": 1.2872,
|
577 |
+
"mean_token_accuracy": 0.6850869571790099,
|
578 |
+
"num_tokens": 13565988.0,
|
579 |
+
"step": 2440
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.2361848527416014,
|
583 |
+
"grad_norm": 0.6345241069793701,
|
584 |
+
"learning_rate": 4.906145864184325e-05,
|
585 |
+
"loss": 1.3234,
|
586 |
+
"mean_token_accuracy": 0.6739947069436312,
|
587 |
+
"num_tokens": 13779004.0,
|
588 |
+
"step": 2480
|
589 |
+
},
|
590 |
+
{
|
591 |
+
"epoch": 0.23999428585033689,
|
592 |
+
"grad_norm": 0.5710681080818176,
|
593 |
+
"learning_rate": 4.905035583549459e-05,
|
594 |
+
"loss": 1.3,
|
595 |
+
"mean_token_accuracy": 0.6780852235853672,
|
596 |
+
"num_tokens": 14005597.0,
|
597 |
+
"step": 2520
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.2438037189590724,
|
601 |
+
"grad_norm": 0.5527021288871765,
|
602 |
+
"learning_rate": 4.903880630247529e-05,
|
603 |
+
"loss": 1.3019,
|
604 |
+
"mean_token_accuracy": 0.6793860571458936,
|
605 |
+
"num_tokens": 14235179.0,
|
606 |
+
"step": 2560
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 0.2476131520678079,
|
610 |
+
"grad_norm": 0.4566735327243805,
|
611 |
+
"learning_rate": 4.902681026494929e-05,
|
612 |
+
"loss": 1.2927,
|
613 |
+
"mean_token_accuracy": 0.6824004529044032,
|
614 |
+
"num_tokens": 14464950.0,
|
615 |
+
"step": 2600
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.2514225851765434,
|
619 |
+
"grad_norm": 0.5023188591003418,
|
620 |
+
"learning_rate": 4.901436795366938e-05,
|
621 |
+
"loss": 1.2996,
|
622 |
+
"mean_token_accuracy": 0.6823519911617041,
|
623 |
+
"num_tokens": 14686771.0,
|
624 |
+
"step": 2640
|
625 |
+
},
|
626 |
+
{
|
627 |
+
"epoch": 0.2552320182852789,
|
628 |
+
"grad_norm": 0.6048426628112793,
|
629 |
+
"learning_rate": 4.900147960797276e-05,
|
630 |
+
"loss": 1.3523,
|
631 |
+
"mean_token_accuracy": 0.6745322810485959,
|
632 |
+
"num_tokens": 14896388.0,
|
633 |
+
"step": 2680
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.2590414513940144,
|
637 |
+
"grad_norm": 0.5594220757484436,
|
638 |
+
"learning_rate": 4.898814547577645e-05,
|
639 |
+
"loss": 1.2733,
|
640 |
+
"mean_token_accuracy": 0.685325993783772,
|
641 |
+
"num_tokens": 15115431.0,
|
642 |
+
"step": 2720
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.26285088450274996,
|
646 |
+
"grad_norm": 0.5266786813735962,
|
647 |
+
"learning_rate": 4.89743658135725e-05,
|
648 |
+
"loss": 1.378,
|
649 |
+
"mean_token_accuracy": 0.661252242513001,
|
650 |
+
"num_tokens": 15318046.0,
|
651 |
+
"step": 2760
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.26666031761148545,
|
655 |
+
"grad_norm": 0.33945998549461365,
|
656 |
+
"learning_rate": 4.896014088642304e-05,
|
657 |
+
"loss": 1.2849,
|
658 |
+
"mean_token_accuracy": 0.68093207962811,
|
659 |
+
"num_tokens": 15546171.0,
|
660 |
+
"step": 2800
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.27046975072022095,
|
664 |
+
"grad_norm": 0.38815465569496155,
|
665 |
+
"learning_rate": 4.8945470967955234e-05,
|
666 |
+
"loss": 1.3622,
|
667 |
+
"mean_token_accuracy": 0.6677591029554606,
|
668 |
+
"num_tokens": 15763709.0,
|
669 |
+
"step": 2840
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.27427918382895644,
|
673 |
+
"grad_norm": 0.5876178741455078,
|
674 |
+
"learning_rate": 4.8930356340355986e-05,
|
675 |
+
"loss": 1.2209,
|
676 |
+
"mean_token_accuracy": 0.7016260443255306,
|
677 |
+
"num_tokens": 15994580.0,
|
678 |
+
"step": 2880
|
679 |
+
},
|
680 |
+
{
|
681 |
+
"epoch": 0.27808861693769193,
|
682 |
+
"grad_norm": 0.6305630207061768,
|
683 |
+
"learning_rate": 4.8914797294366514e-05,
|
684 |
+
"loss": 1.3553,
|
685 |
+
"mean_token_accuracy": 0.6636421175673604,
|
686 |
+
"num_tokens": 16208325.0,
|
687 |
+
"step": 2920
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.2818980500464275,
|
691 |
+
"grad_norm": 0.47434547543525696,
|
692 |
+
"learning_rate": 4.889879412927675e-05,
|
693 |
+
"loss": 1.3085,
|
694 |
+
"mean_token_accuracy": 0.6797755250707269,
|
695 |
+
"num_tokens": 16428418.0,
|
696 |
+
"step": 2960
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.285707483155163,
|
700 |
+
"grad_norm": 0.5395858883857727,
|
701 |
+
"learning_rate": 4.888234715291958e-05,
|
702 |
+
"loss": 1.2705,
|
703 |
+
"mean_token_accuracy": 0.6883305061608553,
|
704 |
+
"num_tokens": 16658226.0,
|
705 |
+
"step": 3000
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.2871360205709388,
|
709 |
+
"eval_mean_token_accuracy": 0.6258668910906496,
|
710 |
+
"eval_num_tokens": 16745761.0,
|
711 |
+
"eval_test_loss": 1.8088411092758179,
|
712 |
+
"eval_test_runtime": 94.958,
|
713 |
+
"eval_test_samples_per_second": 20.967,
|
714 |
+
"eval_test_steps_per_second": 10.489,
|
715 |
+
"step": 3015
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 0.28951691626389847,
|
719 |
+
"grad_norm": 0.5518168210983276,
|
720 |
+
"learning_rate": 4.8865456681664965e-05,
|
721 |
+
"loss": 1.2997,
|
722 |
+
"mean_token_accuracy": 0.6776028882712126,
|
723 |
+
"num_tokens": 16876039.0,
|
724 |
+
"step": 3040
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.29332634937263397,
|
728 |
+
"grad_norm": 0.6039868593215942,
|
729 |
+
"learning_rate": 4.88481230404138e-05,
|
730 |
+
"loss": 1.2621,
|
731 |
+
"mean_token_accuracy": 0.6928930662572383,
|
732 |
+
"num_tokens": 17104229.0,
|
733 |
+
"step": 3080
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.2971357824813695,
|
737 |
+
"grad_norm": 0.5715156197547913,
|
738 |
+
"learning_rate": 4.883034656259167e-05,
|
739 |
+
"loss": 1.3461,
|
740 |
+
"mean_token_accuracy": 0.6714908115565776,
|
741 |
+
"num_tokens": 17312134.0,
|
742 |
+
"step": 3120
|
743 |
+
},
|
744 |
+
{
|
745 |
+
"epoch": 0.300945215590105,
|
746 |
+
"grad_norm": 0.5405182838439941,
|
747 |
+
"learning_rate": 4.8812127590142505e-05,
|
748 |
+
"loss": 1.2837,
|
749 |
+
"mean_token_accuracy": 0.6896362887695432,
|
750 |
+
"num_tokens": 17550198.0,
|
751 |
+
"step": 3160
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.3047546486988405,
|
755 |
+
"grad_norm": 0.5504481792449951,
|
756 |
+
"learning_rate": 4.8793466473521904e-05,
|
757 |
+
"loss": 1.2181,
|
758 |
+
"mean_token_accuracy": 0.6988515704870224,
|
759 |
+
"num_tokens": 17778838.0,
|
760 |
+
"step": 3200
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 0.308564081807576,
|
764 |
+
"grad_norm": 0.621837317943573,
|
765 |
+
"learning_rate": 4.877436357169048e-05,
|
766 |
+
"loss": 1.3323,
|
767 |
+
"mean_token_accuracy": 0.6710341470316052,
|
768 |
+
"num_tokens": 17985533.0,
|
769 |
+
"step": 3240
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 0.3123735149163115,
|
773 |
+
"grad_norm": 0.6566672325134277,
|
774 |
+
"learning_rate": 4.8754819252106876e-05,
|
775 |
+
"loss": 1.2744,
|
776 |
+
"mean_token_accuracy": 0.683073416352272,
|
777 |
+
"num_tokens": 18208416.0,
|
778 |
+
"step": 3280
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 0.31618294802504704,
|
782 |
+
"grad_norm": 0.5615633130073547,
|
783 |
+
"learning_rate": 4.873483389072076e-05,
|
784 |
+
"loss": 1.315,
|
785 |
+
"mean_token_accuracy": 0.684354678913951,
|
786 |
+
"num_tokens": 18426223.0,
|
787 |
+
"step": 3320
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.31999238113378253,
|
791 |
+
"grad_norm": 0.4581094980239868,
|
792 |
+
"learning_rate": 4.871440787196558e-05,
|
793 |
+
"loss": 1.3269,
|
794 |
+
"mean_token_accuracy": 0.6761635078117252,
|
795 |
+
"num_tokens": 18635703.0,
|
796 |
+
"step": 3360
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 0.323801814242518,
|
800 |
+
"grad_norm": 0.5478665232658386,
|
801 |
+
"learning_rate": 4.8693541588751144e-05,
|
802 |
+
"loss": 1.2554,
|
803 |
+
"mean_token_accuracy": 0.688594707287848,
|
804 |
+
"num_tokens": 18859074.0,
|
805 |
+
"step": 3400
|
806 |
+
},
|
807 |
+
{
|
808 |
+
"epoch": 0.3276112473512535,
|
809 |
+
"grad_norm": 0.39972299337387085,
|
810 |
+
"learning_rate": 4.867223544245607e-05,
|
811 |
+
"loss": 1.2497,
|
812 |
+
"mean_token_accuracy": 0.6876592069864274,
|
813 |
+
"num_tokens": 19084486.0,
|
814 |
+
"step": 3440
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.33142068045998907,
|
818 |
+
"grad_norm": 0.6696220636367798,
|
819 |
+
"learning_rate": 4.865048984292009e-05,
|
820 |
+
"loss": 1.2776,
|
821 |
+
"mean_token_accuracy": 0.6786478063091635,
|
822 |
+
"num_tokens": 19305228.0,
|
823 |
+
"step": 3480
|
824 |
+
},
|
825 |
+
{
|
826 |
+
"epoch": 0.33523011356872456,
|
827 |
+
"grad_norm": 0.5517823100090027,
|
828 |
+
"learning_rate": 4.8628305208436137e-05,
|
829 |
+
"loss": 1.2922,
|
830 |
+
"mean_token_accuracy": 0.6886478485539556,
|
831 |
+
"num_tokens": 19538363.0,
|
832 |
+
"step": 3520
|
833 |
+
},
|
834 |
+
{
|
835 |
+
"epoch": 0.33903954667746006,
|
836 |
+
"grad_norm": 0.44766560196876526,
|
837 |
+
"learning_rate": 4.860568196574232e-05,
|
838 |
+
"loss": 1.2851,
|
839 |
+
"mean_token_accuracy": 0.6843299470841885,
|
840 |
+
"num_tokens": 19774720.0,
|
841 |
+
"step": 3560
|
842 |
+
},
|
843 |
+
{
|
844 |
+
"epoch": 0.34284897978619555,
|
845 |
+
"grad_norm": 0.38793668150901794,
|
846 |
+
"learning_rate": 4.858262055001371e-05,
|
847 |
+
"loss": 1.3057,
|
848 |
+
"mean_token_accuracy": 0.6804726634174585,
|
849 |
+
"num_tokens": 19998879.0,
|
850 |
+
"step": 3600
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.3466584128949311,
|
854 |
+
"grad_norm": 0.45702189207077026,
|
855 |
+
"learning_rate": 4.8559121404853944e-05,
|
856 |
+
"loss": 1.1826,
|
857 |
+
"mean_token_accuracy": 0.7049577981233597,
|
858 |
+
"num_tokens": 20243495.0,
|
859 |
+
"step": 3640
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 0.3504678460036666,
|
863 |
+
"grad_norm": 0.5189054608345032,
|
864 |
+
"learning_rate": 4.853518498228674e-05,
|
865 |
+
"loss": 1.2659,
|
866 |
+
"mean_token_accuracy": 0.6826557310298085,
|
867 |
+
"num_tokens": 20462476.0,
|
868 |
+
"step": 3680
|
869 |
+
},
|
870 |
+
{
|
871 |
+
"epoch": 0.3542772791124021,
|
872 |
+
"grad_norm": 0.4221845269203186,
|
873 |
+
"learning_rate": 4.851081174274715e-05,
|
874 |
+
"loss": 1.3576,
|
875 |
+
"mean_token_accuracy": 0.6631780494004488,
|
876 |
+
"num_tokens": 20679798.0,
|
877 |
+
"step": 3720
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.3580867122211376,
|
881 |
+
"grad_norm": 0.4048372209072113,
|
882 |
+
"learning_rate": 4.8486002155072754e-05,
|
883 |
+
"loss": 1.2332,
|
884 |
+
"mean_token_accuracy": 0.7002108607441186,
|
885 |
+
"num_tokens": 20913935.0,
|
886 |
+
"step": 3760
|
887 |
+
},
|
888 |
+
{
|
889 |
+
"epoch": 0.3618961453298731,
|
890 |
+
"grad_norm": 0.5621294379234314,
|
891 |
+
"learning_rate": 4.8460756696494594e-05,
|
892 |
+
"loss": 1.2625,
|
893 |
+
"mean_token_accuracy": 0.6872183892875909,
|
894 |
+
"num_tokens": 21138524.0,
|
895 |
+
"step": 3800
|
896 |
+
},
|
897 |
+
{
|
898 |
+
"epoch": 0.3657055784386086,
|
899 |
+
"grad_norm": 0.5211415886878967,
|
900 |
+
"learning_rate": 4.843507585262804e-05,
|
901 |
+
"loss": 1.2533,
|
902 |
+
"mean_token_accuracy": 0.6849848669022321,
|
903 |
+
"num_tokens": 21373326.0,
|
904 |
+
"step": 3840
|
905 |
+
},
|
906 |
+
{
|
907 |
+
"epoch": 0.3695150115473441,
|
908 |
+
"grad_norm": 0.551052987575531,
|
909 |
+
"learning_rate": 4.8408960117463386e-05,
|
910 |
+
"loss": 1.304,
|
911 |
+
"mean_token_accuracy": 0.6765170315280556,
|
912 |
+
"num_tokens": 21590656.0,
|
913 |
+
"step": 3880
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.3733244446560796,
|
917 |
+
"grad_norm": 0.5423365831375122,
|
918 |
+
"learning_rate": 4.838240999335643e-05,
|
919 |
+
"loss": 1.3441,
|
920 |
+
"mean_token_accuracy": 0.6701787773519754,
|
921 |
+
"num_tokens": 21795838.0,
|
922 |
+
"step": 3920
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.3771338777648151,
|
926 |
+
"grad_norm": 0.46691930294036865,
|
927 |
+
"learning_rate": 4.835542599101873e-05,
|
928 |
+
"loss": 1.3163,
|
929 |
+
"mean_token_accuracy": 0.6742871653288602,
|
930 |
+
"num_tokens": 22007062.0,
|
931 |
+
"step": 3960
|
932 |
+
},
|
933 |
+
{
|
934 |
+
"epoch": 0.38094331087355066,
|
935 |
+
"grad_norm": 0.6379289627075195,
|
936 |
+
"learning_rate": 4.8328008629507863e-05,
|
937 |
+
"loss": 1.3094,
|
938 |
+
"mean_token_accuracy": 0.6776679191738367,
|
939 |
+
"num_tokens": 22232306.0,
|
940 |
+
"step": 4000
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.3828480274279184,
|
944 |
+
"eval_mean_token_accuracy": 0.6281169285496555,
|
945 |
+
"eval_num_tokens": 22348477.0,
|
946 |
+
"eval_test_loss": 1.793502926826477,
|
947 |
+
"eval_test_runtime": 95.0461,
|
948 |
+
"eval_test_samples_per_second": 20.948,
|
949 |
+
"eval_test_steps_per_second": 10.479,
|
950 |
+
"step": 4020
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 0.38475274398228615,
|
954 |
+
"grad_norm": 0.6131725311279297,
|
955 |
+
"learning_rate": 4.830015843621735e-05,
|
956 |
+
"loss": 1.2705,
|
957 |
+
"mean_token_accuracy": 0.6874665239825845,
|
958 |
+
"num_tokens": 22461894.0,
|
959 |
+
"step": 4040
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 0.38856217709102164,
|
963 |
+
"grad_norm": 0.4669947326183319,
|
964 |
+
"learning_rate": 4.8271875946866574e-05,
|
965 |
+
"loss": 1.3255,
|
966 |
+
"mean_token_accuracy": 0.6841361073777079,
|
967 |
+
"num_tokens": 22684394.0,
|
968 |
+
"step": 4080
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.39237161019975714,
|
972 |
+
"grad_norm": 0.42204299569129944,
|
973 |
+
"learning_rate": 4.824316170549047e-05,
|
974 |
+
"loss": 1.2425,
|
975 |
+
"mean_token_accuracy": 0.6886863965541125,
|
976 |
+
"num_tokens": 22918777.0,
|
977 |
+
"step": 4120
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 0.39618104330849263,
|
981 |
+
"grad_norm": 0.5980663895606995,
|
982 |
+
"learning_rate": 4.821401626442903e-05,
|
983 |
+
"loss": 1.2868,
|
984 |
+
"mean_token_accuracy": 0.6745259683579207,
|
985 |
+
"num_tokens": 23139486.0,
|
986 |
+
"step": 4160
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.3999904764172282,
|
990 |
+
"grad_norm": 0.46430954337120056,
|
991 |
+
"learning_rate": 4.8184440184316695e-05,
|
992 |
+
"loss": 1.228,
|
993 |
+
"mean_token_accuracy": 0.6927272006869316,
|
994 |
+
"num_tokens": 23372563.0,
|
995 |
+
"step": 4200
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 0.4037999095259637,
|
999 |
+
"grad_norm": 0.5982958078384399,
|
1000 |
+
"learning_rate": 4.815443403407159e-05,
|
1001 |
+
"loss": 1.2377,
|
1002 |
+
"mean_token_accuracy": 0.687408297508955,
|
1003 |
+
"num_tokens": 23601002.0,
|
1004 |
+
"step": 4240
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.40760934263469917,
|
1008 |
+
"grad_norm": 0.5242788195610046,
|
1009 |
+
"learning_rate": 4.812399839088453e-05,
|
1010 |
+
"loss": 1.2926,
|
1011 |
+
"mean_token_accuracy": 0.6808499401435256,
|
1012 |
+
"num_tokens": 23814142.0,
|
1013 |
+
"step": 4280
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 0.41141877574343466,
|
1017 |
+
"grad_norm": 0.44663509726524353,
|
1018 |
+
"learning_rate": 4.809313384020799e-05,
|
1019 |
+
"loss": 1.2768,
|
1020 |
+
"mean_token_accuracy": 0.6787567920982838,
|
1021 |
+
"num_tokens": 24034008.0,
|
1022 |
+
"step": 4320
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 0.4152282088521702,
|
1026 |
+
"grad_norm": 0.571322500705719,
|
1027 |
+
"learning_rate": 4.806184097574478e-05,
|
1028 |
+
"loss": 1.299,
|
1029 |
+
"mean_token_accuracy": 0.6753746373578906,
|
1030 |
+
"num_tokens": 24241179.0,
|
1031 |
+
"step": 4360
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.4190376419609057,
|
1035 |
+
"grad_norm": 0.6444421410560608,
|
1036 |
+
"learning_rate": 4.8030120399436636e-05,
|
1037 |
+
"loss": 1.2922,
|
1038 |
+
"mean_token_accuracy": 0.6790545796975493,
|
1039 |
+
"num_tokens": 24463001.0,
|
1040 |
+
"step": 4400
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 0.4228470750696412,
|
1044 |
+
"grad_norm": 0.5884628891944885,
|
1045 |
+
"learning_rate": 4.799797272145267e-05,
|
1046 |
+
"loss": 1.3354,
|
1047 |
+
"mean_token_accuracy": 0.6655034508556128,
|
1048 |
+
"num_tokens": 24672669.0,
|
1049 |
+
"step": 4440
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 0.4266565081783767,
|
1053 |
+
"grad_norm": 0.6725838780403137,
|
1054 |
+
"learning_rate": 4.796539856017762e-05,
|
1055 |
+
"loss": 1.2866,
|
1056 |
+
"mean_token_accuracy": 0.6829743100330233,
|
1057 |
+
"num_tokens": 24895076.0,
|
1058 |
+
"step": 4480
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.4304659412871122,
|
1062 |
+
"grad_norm": 0.5089847445487976,
|
1063 |
+
"learning_rate": 4.7932398542199935e-05,
|
1064 |
+
"loss": 1.3312,
|
1065 |
+
"mean_token_accuracy": 0.6777703372761608,
|
1066 |
+
"num_tokens": 25105078.0,
|
1067 |
+
"step": 4520
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 0.43427537439584774,
|
1071 |
+
"grad_norm": 0.6170702576637268,
|
1072 |
+
"learning_rate": 4.7898973302299746e-05,
|
1073 |
+
"loss": 1.2308,
|
1074 |
+
"mean_token_accuracy": 0.6913123942911625,
|
1075 |
+
"num_tokens": 25330411.0,
|
1076 |
+
"step": 4560
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 0.43808480750458323,
|
1080 |
+
"grad_norm": 0.47749921679496765,
|
1081 |
+
"learning_rate": 4.786512348343664e-05,
|
1082 |
+
"loss": 1.2394,
|
1083 |
+
"mean_token_accuracy": 0.6930743562057614,
|
1084 |
+
"num_tokens": 25558075.0,
|
1085 |
+
"step": 4600
|
1086 |
+
},
|
1087 |
+
{
|
1088 |
+
"epoch": 0.4418942406133187,
|
1089 |
+
"grad_norm": 0.5179374814033508,
|
1090 |
+
"learning_rate": 4.783084973673732e-05,
|
1091 |
+
"loss": 1.3121,
|
1092 |
+
"mean_token_accuracy": 0.6737616384401918,
|
1093 |
+
"num_tokens": 25787633.0,
|
1094 |
+
"step": 4640
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 0.4457036737220542,
|
1098 |
+
"grad_norm": 0.4957481920719147,
|
1099 |
+
"learning_rate": 4.7796152721483024e-05,
|
1100 |
+
"loss": 1.2679,
|
1101 |
+
"mean_token_accuracy": 0.6782409870997071,
|
1102 |
+
"num_tokens": 26010384.0,
|
1103 |
+
"step": 4680
|
1104 |
+
},
|
1105 |
+
{
|
1106 |
+
"epoch": 0.44951310683078977,
|
1107 |
+
"grad_norm": 0.46905845403671265,
|
1108 |
+
"learning_rate": 4.776103310509691e-05,
|
1109 |
+
"loss": 1.3583,
|
1110 |
+
"mean_token_accuracy": 0.6669555108994245,
|
1111 |
+
"num_tokens": 26220009.0,
|
1112 |
+
"step": 4720
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 0.45332253993952526,
|
1116 |
+
"grad_norm": 0.6176592707633972,
|
1117 |
+
"learning_rate": 4.7725491563131164e-05,
|
1118 |
+
"loss": 1.3376,
|
1119 |
+
"mean_token_accuracy": 0.6773041613399983,
|
1120 |
+
"num_tokens": 26437068.0,
|
1121 |
+
"step": 4760
|
1122 |
+
},
|
1123 |
+
{
|
1124 |
+
"epoch": 0.45713197304826075,
|
1125 |
+
"grad_norm": 0.641156017780304,
|
1126 |
+
"learning_rate": 4.7689528779254057e-05,
|
1127 |
+
"loss": 1.338,
|
1128 |
+
"mean_token_accuracy": 0.6686659481376409,
|
1129 |
+
"num_tokens": 26646369.0,
|
1130 |
+
"step": 4800
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.46094140615699625,
|
1134 |
+
"grad_norm": 0.5560479760169983,
|
1135 |
+
"learning_rate": 4.7653145445236725e-05,
|
1136 |
+
"loss": 1.3156,
|
1137 |
+
"mean_token_accuracy": 0.6741218714043498,
|
1138 |
+
"num_tokens": 26872767.0,
|
1139 |
+
"step": 4840
|
1140 |
+
},
|
1141 |
+
{
|
1142 |
+
"epoch": 0.46475083926573174,
|
1143 |
+
"grad_norm": 0.6000213027000427,
|
1144 |
+
"learning_rate": 4.761634226093993e-05,
|
1145 |
+
"loss": 1.2637,
|
1146 |
+
"mean_token_accuracy": 0.6870461646467447,
|
1147 |
+
"num_tokens": 27092463.0,
|
1148 |
+
"step": 4880
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 0.4685602723744673,
|
1152 |
+
"grad_norm": 0.3717496693134308,
|
1153 |
+
"learning_rate": 4.757911993430057e-05,
|
1154 |
+
"loss": 1.3356,
|
1155 |
+
"mean_token_accuracy": 0.6666051434352994,
|
1156 |
+
"num_tokens": 27314300.0,
|
1157 |
+
"step": 4920
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 0.4723697054832028,
|
1161 |
+
"grad_norm": 0.839055061340332,
|
1162 |
+
"learning_rate": 4.754147918131804e-05,
|
1163 |
+
"loss": 1.2933,
|
1164 |
+
"mean_token_accuracy": 0.6818767448887229,
|
1165 |
+
"num_tokens": 27534317.0,
|
1166 |
+
"step": 4960
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 0.4761791385919383,
|
1170 |
+
"grad_norm": 0.5968820452690125,
|
1171 |
+
"learning_rate": 4.7503420726040496e-05,
|
1172 |
+
"loss": 1.3218,
|
1173 |
+
"mean_token_accuracy": 0.6756005242466927,
|
1174 |
+
"num_tokens": 27744710.0,
|
1175 |
+
"step": 5000
|
1176 |
+
},
|
1177 |
+
{
|
1178 |
+
"epoch": 0.47856003428489796,
|
1179 |
+
"eval_mean_token_accuracy": 0.6309991637506638,
|
1180 |
+
"eval_num_tokens": 27879664.0,
|
1181 |
+
"eval_test_loss": 1.7806874513626099,
|
1182 |
+
"eval_test_runtime": 94.8719,
|
1183 |
+
"eval_test_samples_per_second": 20.986,
|
1184 |
+
"eval_test_steps_per_second": 10.498,
|
1185 |
+
"step": 5025
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.47998857170067377,
|
1189 |
+
"grad_norm": 0.555782675743103,
|
1190 |
+
"learning_rate": 4.74649453005509e-05,
|
1191 |
+
"loss": 1.2746,
|
1192 |
+
"mean_token_accuracy": 0.684971004165709,
|
1193 |
+
"num_tokens": 27964540.0,
|
1194 |
+
"step": 5040
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.4837980048094093,
|
1198 |
+
"grad_norm": 0.5832619071006775,
|
1199 |
+
"learning_rate": 4.742605364495298e-05,
|
1200 |
+
"loss": 1.2391,
|
1201 |
+
"mean_token_accuracy": 0.691305941529572,
|
1202 |
+
"num_tokens": 28195211.0,
|
1203 |
+
"step": 5080
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.4876074379181448,
|
1207 |
+
"grad_norm": 0.4528619349002838,
|
1208 |
+
"learning_rate": 4.738674650735692e-05,
|
1209 |
+
"loss": 1.2295,
|
1210 |
+
"mean_token_accuracy": 0.683625971712172,
|
1211 |
+
"num_tokens": 28427726.0,
|
1212 |
+
"step": 5120
|
1213 |
+
},
|
1214 |
+
{
|
1215 |
+
"epoch": 0.4914168710268803,
|
1216 |
+
"grad_norm": 0.8959270119667053,
|
1217 |
+
"learning_rate": 4.734702464386503e-05,
|
1218 |
+
"loss": 1.3764,
|
1219 |
+
"mean_token_accuracy": 0.6636357877403498,
|
1220 |
+
"num_tokens": 28631998.0,
|
1221 |
+
"step": 5160
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.4952263041356158,
|
1225 |
+
"grad_norm": 0.43296220898628235,
|
1226 |
+
"learning_rate": 4.73068888185572e-05,
|
1227 |
+
"loss": 1.2929,
|
1228 |
+
"mean_token_accuracy": 0.6792870191857219,
|
1229 |
+
"num_tokens": 28846791.0,
|
1230 |
+
"step": 5200
|
1231 |
+
},
|
1232 |
+
{
|
1233 |
+
"epoch": 0.49903573724435135,
|
1234 |
+
"grad_norm": 0.722977340221405,
|
1235 |
+
"learning_rate": 4.726633980347616e-05,
|
1236 |
+
"loss": 1.3176,
|
1237 |
+
"mean_token_accuracy": 0.6724835351109505,
|
1238 |
+
"num_tokens": 29054506.0,
|
1239 |
+
"step": 5240
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.5028451703530868,
|
1243 |
+
"grad_norm": 0.41740506887435913,
|
1244 |
+
"learning_rate": 4.722537837861267e-05,
|
1245 |
+
"loss": 1.2455,
|
1246 |
+
"mean_token_accuracy": 0.688827583193779,
|
1247 |
+
"num_tokens": 29270620.0,
|
1248 |
+
"step": 5280
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 0.5066546034618223,
|
1252 |
+
"grad_norm": 0.38050729036331177,
|
1253 |
+
"learning_rate": 4.718400533189051e-05,
|
1254 |
+
"loss": 1.2743,
|
1255 |
+
"mean_token_accuracy": 0.6829100279137492,
|
1256 |
+
"num_tokens": 29490565.0,
|
1257 |
+
"step": 5320
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.5104640365705578,
|
1261 |
+
"grad_norm": 0.5724825263023376,
|
1262 |
+
"learning_rate": 4.7142221459151294e-05,
|
1263 |
+
"loss": 1.2773,
|
1264 |
+
"mean_token_accuracy": 0.6881643293425441,
|
1265 |
+
"num_tokens": 29704265.0,
|
1266 |
+
"step": 5360
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"epoch": 0.5142734696792933,
|
1270 |
+
"grad_norm": 0.6543896198272705,
|
1271 |
+
"learning_rate": 4.7100027564139196e-05,
|
1272 |
+
"loss": 1.3307,
|
1273 |
+
"mean_token_accuracy": 0.6777999725192785,
|
1274 |
+
"num_tokens": 29924515.0,
|
1275 |
+
"step": 5400
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 0.5180829027880288,
|
1279 |
+
"grad_norm": 0.43163400888442993,
|
1280 |
+
"learning_rate": 4.705742445848548e-05,
|
1281 |
+
"loss": 1.2653,
|
1282 |
+
"mean_token_accuracy": 0.682813161984086,
|
1283 |
+
"num_tokens": 30148026.0,
|
1284 |
+
"step": 5440
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.5218923358967643,
|
1288 |
+
"grad_norm": 0.47830525040626526,
|
1289 |
+
"learning_rate": 4.7014412961692864e-05,
|
1290 |
+
"loss": 1.1955,
|
1291 |
+
"mean_token_accuracy": 0.7004892747849226,
|
1292 |
+
"num_tokens": 30372129.0,
|
1293 |
+
"step": 5480
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 0.5257017690054999,
|
1297 |
+
"grad_norm": 0.5903618931770325,
|
1298 |
+
"learning_rate": 4.697099390111981e-05,
|
1299 |
+
"loss": 1.2973,
|
1300 |
+
"mean_token_accuracy": 0.6818130781874061,
|
1301 |
+
"num_tokens": 30596623.0,
|
1302 |
+
"step": 5520
|
1303 |
+
},
|
1304 |
+
{
|
1305 |
+
"epoch": 0.5295112021142354,
|
1306 |
+
"grad_norm": 0.43726322054862976,
|
1307 |
+
"learning_rate": 4.6927168111964555e-05,
|
1308 |
+
"loss": 1.2095,
|
1309 |
+
"mean_token_accuracy": 0.696308933570981,
|
1310 |
+
"num_tokens": 30834116.0,
|
1311 |
+
"step": 5560
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.5333206352229709,
|
1315 |
+
"grad_norm": 0.7869614958763123,
|
1316 |
+
"learning_rate": 4.6882936437249056e-05,
|
1317 |
+
"loss": 1.2275,
|
1318 |
+
"mean_token_accuracy": 0.6923372825607658,
|
1319 |
+
"num_tokens": 31066239.0,
|
1320 |
+
"step": 5600
|
1321 |
+
},
|
1322 |
+
{
|
1323 |
+
"epoch": 0.5371300683317064,
|
1324 |
+
"grad_norm": 0.4349427819252014,
|
1325 |
+
"learning_rate": 4.6838299727802786e-05,
|
1326 |
+
"loss": 1.2973,
|
1327 |
+
"mean_token_accuracy": 0.688424677029252,
|
1328 |
+
"num_tokens": 31302823.0,
|
1329 |
+
"step": 5640
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.5409395014404419,
|
1333 |
+
"grad_norm": 0.5851991772651672,
|
1334 |
+
"learning_rate": 4.67932588422464e-05,
|
1335 |
+
"loss": 1.237,
|
1336 |
+
"mean_token_accuracy": 0.6886244036257267,
|
1337 |
+
"num_tokens": 31530684.0,
|
1338 |
+
"step": 5680
|
1339 |
+
},
|
1340 |
+
{
|
1341 |
+
"epoch": 0.5447489345491774,
|
1342 |
+
"grad_norm": 0.6614839434623718,
|
1343 |
+
"learning_rate": 4.6747814646975134e-05,
|
1344 |
+
"loss": 1.3017,
|
1345 |
+
"mean_token_accuracy": 0.6840987723320723,
|
1346 |
+
"num_tokens": 31741759.0,
|
1347 |
+
"step": 5720
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.5485583676579129,
|
1351 |
+
"grad_norm": 0.4596734642982483,
|
1352 |
+
"learning_rate": 4.670196801614224e-05,
|
1353 |
+
"loss": 1.1938,
|
1354 |
+
"mean_token_accuracy": 0.7047518376260996,
|
1355 |
+
"num_tokens": 31987926.0,
|
1356 |
+
"step": 5760
|
1357 |
+
},
|
1358 |
+
{
|
1359 |
+
"epoch": 0.5523678007666484,
|
1360 |
+
"grad_norm": 0.5416800379753113,
|
1361 |
+
"learning_rate": 4.665571983164207e-05,
|
1362 |
+
"loss": 1.2874,
|
1363 |
+
"mean_token_accuracy": 0.6859219571575522,
|
1364 |
+
"num_tokens": 32213674.0,
|
1365 |
+
"step": 5800
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 0.5561772338753839,
|
1369 |
+
"grad_norm": 0.4644794464111328,
|
1370 |
+
"learning_rate": 4.660907098309319e-05,
|
1371 |
+
"loss": 1.2893,
|
1372 |
+
"mean_token_accuracy": 0.6782131699845195,
|
1373 |
+
"num_tokens": 32429679.0,
|
1374 |
+
"step": 5840
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 0.5599866669841195,
|
1378 |
+
"grad_norm": 0.5027694702148438,
|
1379 |
+
"learning_rate": 4.6562022367821244e-05,
|
1380 |
+
"loss": 1.2955,
|
1381 |
+
"mean_token_accuracy": 0.6798365904018283,
|
1382 |
+
"num_tokens": 32646061.0,
|
1383 |
+
"step": 5880
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.563796100092855,
|
1387 |
+
"grad_norm": 0.5148358345031738,
|
1388 |
+
"learning_rate": 4.651457489084167e-05,
|
1389 |
+
"loss": 1.2533,
|
1390 |
+
"mean_token_accuracy": 0.684299885481596,
|
1391 |
+
"num_tokens": 32867990.0,
|
1392 |
+
"step": 5920
|
1393 |
+
},
|
1394 |
+
{
|
1395 |
+
"epoch": 0.5676055332015905,
|
1396 |
+
"grad_norm": 0.4006965756416321,
|
1397 |
+
"learning_rate": 4.646672946484232e-05,
|
1398 |
+
"loss": 1.2246,
|
1399 |
+
"mean_token_accuracy": 0.6978412168100476,
|
1400 |
+
"num_tokens": 33100846.0,
|
1401 |
+
"step": 5960
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 0.571414966310326,
|
1405 |
+
"grad_norm": 0.5946612358093262,
|
1406 |
+
"learning_rate": 4.641848701016592e-05,
|
1407 |
+
"loss": 1.3112,
|
1408 |
+
"mean_token_accuracy": 0.682670296356082,
|
1409 |
+
"num_tokens": 33316830.0,
|
1410 |
+
"step": 6000
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.5742720411418776,
|
1414 |
+
"eval_mean_token_accuracy": 0.6325134164597614,
|
1415 |
+
"eval_num_tokens": 33490786.0,
|
1416 |
+
"eval_test_loss": 1.7651844024658203,
|
1417 |
+
"eval_test_runtime": 95.3517,
|
1418 |
+
"eval_test_samples_per_second": 20.881,
|
1419 |
+
"eval_test_steps_per_second": 10.446,
|
1420 |
+
"step": 6030
|
1421 |
+
},
|
1422 |
+
{
|
1423 |
+
"epoch": 0.5752243994190614,
|
1424 |
+
"grad_norm": 0.5004485249519348,
|
1425 |
+
"learning_rate": 4.636984845479229e-05,
|
1426 |
+
"loss": 1.3189,
|
1427 |
+
"mean_token_accuracy": 0.6787041410803795,
|
1428 |
+
"num_tokens": 33547057.0,
|
1429 |
+
"step": 6040
|
1430 |
+
},
|
1431 |
+
{
|
1432 |
+
"epoch": 0.5790338325277969,
|
1433 |
+
"grad_norm": 0.6013615727424622,
|
1434 |
+
"learning_rate": 4.6320814734320574e-05,
|
1435 |
+
"loss": 1.2999,
|
1436 |
+
"mean_token_accuracy": 0.6829198809340596,
|
1437 |
+
"num_tokens": 33751128.0,
|
1438 |
+
"step": 6080
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 0.5828432656365324,
|
1442 |
+
"grad_norm": 0.46301329135894775,
|
1443 |
+
"learning_rate": 4.627138679195122e-05,
|
1444 |
+
"loss": 1.2979,
|
1445 |
+
"mean_token_accuracy": 0.6834639564156533,
|
1446 |
+
"num_tokens": 33958374.0,
|
1447 |
+
"step": 6120
|
1448 |
+
},
|
1449 |
+
{
|
1450 |
+
"epoch": 0.5866526987452679,
|
1451 |
+
"grad_norm": 0.5537028908729553,
|
1452 |
+
"learning_rate": 4.622156557846782e-05,
|
1453 |
+
"loss": 1.2919,
|
1454 |
+
"mean_token_accuracy": 0.6853473074734211,
|
1455 |
+
"num_tokens": 34173776.0,
|
1456 |
+
"step": 6160
|
1457 |
+
},
|
1458 |
+
{
|
1459 |
+
"epoch": 0.5904621318540034,
|
1460 |
+
"grad_norm": 0.5172299146652222,
|
1461 |
+
"learning_rate": 4.617135205221882e-05,
|
1462 |
+
"loss": 1.2535,
|
1463 |
+
"mean_token_accuracy": 0.6891471687704325,
|
1464 |
+
"num_tokens": 34402012.0,
|
1465 |
+
"step": 6200
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 0.594271564962739,
|
1469 |
+
"grad_norm": 0.45443201065063477,
|
1470 |
+
"learning_rate": 4.6120747179099115e-05,
|
1471 |
+
"loss": 1.3631,
|
1472 |
+
"mean_token_accuracy": 0.6746680632233619,
|
1473 |
+
"num_tokens": 34619563.0,
|
1474 |
+
"step": 6240
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 0.5980809980714745,
|
1478 |
+
"grad_norm": 0.5318917632102966,
|
1479 |
+
"learning_rate": 4.606975193253145e-05,
|
1480 |
+
"loss": 1.2875,
|
1481 |
+
"mean_token_accuracy": 0.6842667568475008,
|
1482 |
+
"num_tokens": 34842995.0,
|
1483 |
+
"step": 6280
|
1484 |
+
},
|
1485 |
+
{
|
1486 |
+
"epoch": 0.60189043118021,
|
1487 |
+
"grad_norm": 0.41732507944107056,
|
1488 |
+
"learning_rate": 4.6018367293447696e-05,
|
1489 |
+
"loss": 1.2011,
|
1490 |
+
"mean_token_accuracy": 0.6991326250135899,
|
1491 |
+
"num_tokens": 35074476.0,
|
1492 |
+
"step": 6320
|
1493 |
+
},
|
1494 |
+
{
|
1495 |
+
"epoch": 0.6056998642889455,
|
1496 |
+
"grad_norm": 0.4196927845478058,
|
1497 |
+
"learning_rate": 4.5966594250269964e-05,
|
1498 |
+
"loss": 1.3135,
|
1499 |
+
"mean_token_accuracy": 0.6805538948625326,
|
1500 |
+
"num_tokens": 35296363.0,
|
1501 |
+
"step": 6360
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 0.609509297397681,
|
1505 |
+
"grad_norm": 0.42691197991371155,
|
1506 |
+
"learning_rate": 4.5914433798891605e-05,
|
1507 |
+
"loss": 1.246,
|
1508 |
+
"mean_token_accuracy": 0.6876704445108771,
|
1509 |
+
"num_tokens": 35523754.0,
|
1510 |
+
"step": 6400
|
1511 |
+
},
|
1512 |
+
{
|
1513 |
+
"epoch": 0.6133187305064165,
|
1514 |
+
"grad_norm": 0.3611372113227844,
|
1515 |
+
"learning_rate": 4.5861886942658106e-05,
|
1516 |
+
"loss": 1.2269,
|
1517 |
+
"mean_token_accuracy": 0.6875138944014907,
|
1518 |
+
"num_tokens": 35758849.0,
|
1519 |
+
"step": 6440
|
1520 |
+
},
|
1521 |
+
{
|
1522 |
+
"epoch": 0.617128163615152,
|
1523 |
+
"grad_norm": 0.7133765816688538,
|
1524 |
+
"learning_rate": 4.580895469234769e-05,
|
1525 |
+
"loss": 1.2242,
|
1526 |
+
"mean_token_accuracy": 0.6886107694357634,
|
1527 |
+
"num_tokens": 35988842.0,
|
1528 |
+
"step": 6480
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 0.6209375967238875,
|
1532 |
+
"grad_norm": 0.44684138894081116,
|
1533 |
+
"learning_rate": 4.575563806615196e-05,
|
1534 |
+
"loss": 1.2675,
|
1535 |
+
"mean_token_accuracy": 0.6812176534906029,
|
1536 |
+
"num_tokens": 36201602.0,
|
1537 |
+
"step": 6520
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 0.624747029832623,
|
1541 |
+
"grad_norm": 0.5846595168113708,
|
1542 |
+
"learning_rate": 4.5701938089656256e-05,
|
1543 |
+
"loss": 1.2703,
|
1544 |
+
"mean_token_accuracy": 0.6853839591145515,
|
1545 |
+
"num_tokens": 36403261.0,
|
1546 |
+
"step": 6560
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 0.6285564629413586,
|
1550 |
+
"grad_norm": 0.3759899437427521,
|
1551 |
+
"learning_rate": 4.5647855795819943e-05,
|
1552 |
+
"loss": 1.3111,
|
1553 |
+
"mean_token_accuracy": 0.6767927626147866,
|
1554 |
+
"num_tokens": 36619797.0,
|
1555 |
+
"step": 6600
|
1556 |
+
},
|
1557 |
+
{
|
1558 |
+
"epoch": 0.6323658960500941,
|
1559 |
+
"grad_norm": 0.6737694144248962,
|
1560 |
+
"learning_rate": 4.5593392224956576e-05,
|
1561 |
+
"loss": 1.3165,
|
1562 |
+
"mean_token_accuracy": 0.6752157468348742,
|
1563 |
+
"num_tokens": 36828768.0,
|
1564 |
+
"step": 6640
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 0.6361753291588296,
|
1568 |
+
"grad_norm": 0.5695846676826477,
|
1569 |
+
"learning_rate": 4.5538548424713835e-05,
|
1570 |
+
"loss": 1.2397,
|
1571 |
+
"mean_token_accuracy": 0.6919887445867061,
|
1572 |
+
"num_tokens": 37053251.0,
|
1573 |
+
"step": 6680
|
1574 |
+
},
|
1575 |
+
{
|
1576 |
+
"epoch": 0.6399847622675651,
|
1577 |
+
"grad_norm": 0.5237749218940735,
|
1578 |
+
"learning_rate": 4.5483325450053406e-05,
|
1579 |
+
"loss": 1.2553,
|
1580 |
+
"mean_token_accuracy": 0.6820298057049513,
|
1581 |
+
"num_tokens": 37268972.0,
|
1582 |
+
"step": 6720
|
1583 |
+
},
|
1584 |
+
{
|
1585 |
+
"epoch": 0.6437941953763006,
|
1586 |
+
"grad_norm": 0.6554339528083801,
|
1587 |
+
"learning_rate": 4.5427724363230683e-05,
|
1588 |
+
"loss": 1.2682,
|
1589 |
+
"mean_token_accuracy": 0.6873216938227416,
|
1590 |
+
"num_tokens": 37492541.0,
|
1591 |
+
"step": 6760
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 0.647603628485036,
|
1595 |
+
"grad_norm": 0.5178593397140503,
|
1596 |
+
"learning_rate": 4.537174623377432e-05,
|
1597 |
+
"loss": 1.2537,
|
1598 |
+
"mean_token_accuracy": 0.6826527412980795,
|
1599 |
+
"num_tokens": 37705009.0,
|
1600 |
+
"step": 6800
|
1601 |
+
},
|
1602 |
+
{
|
1603 |
+
"epoch": 0.6514130615937715,
|
1604 |
+
"grad_norm": 0.4857373833656311,
|
1605 |
+
"learning_rate": 4.53153921384657e-05,
|
1606 |
+
"loss": 1.3497,
|
1607 |
+
"mean_token_accuracy": 0.6726470049470663,
|
1608 |
+
"num_tokens": 37915354.0,
|
1609 |
+
"step": 6840
|
1610 |
+
},
|
1611 |
+
{
|
1612 |
+
"epoch": 0.655222494702507,
|
1613 |
+
"grad_norm": 0.48057419061660767,
|
1614 |
+
"learning_rate": 4.5258663161318136e-05,
|
1615 |
+
"loss": 1.2267,
|
1616 |
+
"mean_token_accuracy": 0.6866666225716471,
|
1617 |
+
"num_tokens": 38146196.0,
|
1618 |
+
"step": 6880
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 0.6590319278112425,
|
1622 |
+
"grad_norm": 0.5138698220252991,
|
1623 |
+
"learning_rate": 4.5201560393556134e-05,
|
1624 |
+
"loss": 1.2439,
|
1625 |
+
"mean_token_accuracy": 0.6901180801913143,
|
1626 |
+
"num_tokens": 38373540.0,
|
1627 |
+
"step": 6920
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 0.6628413609199781,
|
1631 |
+
"grad_norm": 0.47547754645347595,
|
1632 |
+
"learning_rate": 4.5144084933594303e-05,
|
1633 |
+
"loss": 1.2706,
|
1634 |
+
"mean_token_accuracy": 0.6800282135605812,
|
1635 |
+
"num_tokens": 38589036.0,
|
1636 |
+
"step": 6960
|
1637 |
+
},
|
1638 |
+
{
|
1639 |
+
"epoch": 0.6666507940287136,
|
1640 |
+
"grad_norm": 0.6765561103820801,
|
1641 |
+
"learning_rate": 4.508623788701628e-05,
|
1642 |
+
"loss": 1.2929,
|
1643 |
+
"mean_token_accuracy": 0.6894892951473593,
|
1644 |
+
"num_tokens": 38802771.0,
|
1645 |
+
"step": 7000
|
1646 |
+
},
|
1647 |
+
{
|
1648 |
+
"epoch": 0.6699840479988571,
|
1649 |
+
"eval_mean_token_accuracy": 0.6329328228970129,
|
1650 |
+
"eval_num_tokens": 38980983.0,
|
1651 |
+
"eval_test_loss": 1.7534339427947998,
|
1652 |
+
"eval_test_runtime": 95.0805,
|
1653 |
+
"eval_test_samples_per_second": 20.94,
|
1654 |
+
"eval_test_steps_per_second": 10.475,
|
1655 |
+
"step": 7035
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 0.6704602271374491,
|
1659 |
+
"grad_norm": 0.40170061588287354,
|
1660 |
+
"learning_rate": 4.502802036655346e-05,
|
1661 |
+
"loss": 1.3205,
|
1662 |
+
"mean_token_accuracy": 0.675545847415924,
|
1663 |
+
"num_tokens": 39011417.0,
|
1664 |
+
"step": 7040
|
1665 |
+
},
|
1666 |
+
{
|
1667 |
+
"epoch": 0.6742696602461846,
|
1668 |
+
"grad_norm": 0.49673372507095337,
|
1669 |
+
"learning_rate": 4.4969433492063564e-05,
|
1670 |
+
"loss": 1.256,
|
1671 |
+
"mean_token_accuracy": 0.6876663960516453,
|
1672 |
+
"num_tokens": 39231629.0,
|
1673 |
+
"step": 7080
|
1674 |
+
},
|
1675 |
+
{
|
1676 |
+
"epoch": 0.6780790933549201,
|
1677 |
+
"grad_norm": 0.45921561121940613,
|
1678 |
+
"learning_rate": 4.491047839050912e-05,
|
1679 |
+
"loss": 1.2542,
|
1680 |
+
"mean_token_accuracy": 0.6906937116757035,
|
1681 |
+
"num_tokens": 39457882.0,
|
1682 |
+
"step": 7120
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 0.6818885264636556,
|
1686 |
+
"grad_norm": 0.49605095386505127,
|
1687 |
+
"learning_rate": 4.4851156195935785e-05,
|
1688 |
+
"loss": 1.3266,
|
1689 |
+
"mean_token_accuracy": 0.673082504235208,
|
1690 |
+
"num_tokens": 39675712.0,
|
1691 |
+
"step": 7160
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 0.6856979595723911,
|
1695 |
+
"grad_norm": 0.5613274574279785,
|
1696 |
+
"learning_rate": 4.479146804945053e-05,
|
1697 |
+
"loss": 1.3061,
|
1698 |
+
"mean_token_accuracy": 0.6837763454765081,
|
1699 |
+
"num_tokens": 39892449.0,
|
1700 |
+
"step": 7200
|
1701 |
+
},
|
1702 |
+
{
|
1703 |
+
"epoch": 0.6895073926811266,
|
1704 |
+
"grad_norm": 0.40411025285720825,
|
1705 |
+
"learning_rate": 4.473141509919966e-05,
|
1706 |
+
"loss": 1.2459,
|
1707 |
+
"mean_token_accuracy": 0.6935942692682147,
|
1708 |
+
"num_tokens": 40122187.0,
|
1709 |
+
"step": 7240
|
1710 |
+
},
|
1711 |
+
{
|
1712 |
+
"epoch": 0.6933168257898622,
|
1713 |
+
"grad_norm": 0.66608726978302,
|
1714 |
+
"learning_rate": 4.4670998500346795e-05,
|
1715 |
+
"loss": 1.263,
|
1716 |
+
"mean_token_accuracy": 0.6886698173359036,
|
1717 |
+
"num_tokens": 40339718.0,
|
1718 |
+
"step": 7280
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 0.6971262588985977,
|
1722 |
+
"grad_norm": 0.5249150395393372,
|
1723 |
+
"learning_rate": 4.461021941505057e-05,
|
1724 |
+
"loss": 1.2077,
|
1725 |
+
"mean_token_accuracy": 0.6970062265172601,
|
1726 |
+
"num_tokens": 40568071.0,
|
1727 |
+
"step": 7320
|
1728 |
+
},
|
1729 |
+
{
|
1730 |
+
"epoch": 0.7009356920073332,
|
1731 |
+
"grad_norm": 0.5321863293647766,
|
1732 |
+
"learning_rate": 4.454907901244236e-05,
|
1733 |
+
"loss": 1.2908,
|
1734 |
+
"mean_token_accuracy": 0.6871679758653044,
|
1735 |
+
"num_tokens": 40781022.0,
|
1736 |
+
"step": 7360
|
1737 |
+
},
|
1738 |
+
{
|
1739 |
+
"epoch": 0.7047451251160687,
|
1740 |
+
"grad_norm": 0.5298981666564941,
|
1741 |
+
"learning_rate": 4.44875784686037e-05,
|
1742 |
+
"loss": 1.2256,
|
1743 |
+
"mean_token_accuracy": 0.6957620535045862,
|
1744 |
+
"num_tokens": 41015922.0,
|
1745 |
+
"step": 7400
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 0.7085545582248042,
|
1749 |
+
"grad_norm": 0.6805555820465088,
|
1750 |
+
"learning_rate": 4.442571896654375e-05,
|
1751 |
+
"loss": 1.2059,
|
1752 |
+
"mean_token_accuracy": 0.6951308185234666,
|
1753 |
+
"num_tokens": 41247452.0,
|
1754 |
+
"step": 7440
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 0.7123639913335397,
|
1758 |
+
"grad_norm": 0.3826749622821808,
|
1759 |
+
"learning_rate": 4.4363501696176494e-05,
|
1760 |
+
"loss": 1.2866,
|
1761 |
+
"mean_token_accuracy": 0.6792947178706527,
|
1762 |
+
"num_tokens": 41470415.0,
|
1763 |
+
"step": 7480
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 0.7161734244422752,
|
1767 |
+
"grad_norm": 0.5363141298294067,
|
1768 |
+
"learning_rate": 4.4300927854297856e-05,
|
1769 |
+
"loss": 1.2691,
|
1770 |
+
"mean_token_accuracy": 0.682473830319941,
|
1771 |
+
"num_tokens": 41701000.0,
|
1772 |
+
"step": 7520
|
1773 |
+
},
|
1774 |
+
{
|
1775 |
+
"epoch": 0.7199828575510107,
|
1776 |
+
"grad_norm": 0.5626250505447388,
|
1777 |
+
"learning_rate": 4.423799864456266e-05,
|
1778 |
+
"loss": 1.3133,
|
1779 |
+
"mean_token_accuracy": 0.6788626465946436,
|
1780 |
+
"num_tokens": 41915333.0,
|
1781 |
+
"step": 7560
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 0.7237922906597462,
|
1785 |
+
"grad_norm": 0.6899204850196838,
|
1786 |
+
"learning_rate": 4.417471527746152e-05,
|
1787 |
+
"loss": 1.365,
|
1788 |
+
"mean_token_accuracy": 0.6754604885354638,
|
1789 |
+
"num_tokens": 42139999.0,
|
1790 |
+
"step": 7600
|
1791 |
+
},
|
1792 |
+
{
|
1793 |
+
"epoch": 0.7276017237684818,
|
1794 |
+
"grad_norm": 0.5523748993873596,
|
1795 |
+
"learning_rate": 4.411107897029755e-05,
|
1796 |
+
"loss": 1.2776,
|
1797 |
+
"mean_token_accuracy": 0.6912444988265634,
|
1798 |
+
"num_tokens": 42367874.0,
|
1799 |
+
"step": 7640
|
1800 |
+
},
|
1801 |
+
{
|
1802 |
+
"epoch": 0.7314111568772173,
|
1803 |
+
"grad_norm": 0.5411382913589478,
|
1804 |
+
"learning_rate": 4.404709094716289e-05,
|
1805 |
+
"loss": 1.2326,
|
1806 |
+
"mean_token_accuracy": 0.6946828311309219,
|
1807 |
+
"num_tokens": 42594804.0,
|
1808 |
+
"step": 7680
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 0.7352205899859527,
|
1812 |
+
"grad_norm": 0.6533775329589844,
|
1813 |
+
"learning_rate": 4.398275243891522e-05,
|
1814 |
+
"loss": 1.2828,
|
1815 |
+
"mean_token_accuracy": 0.6842706995084882,
|
1816 |
+
"num_tokens": 42814558.0,
|
1817 |
+
"step": 7720
|
1818 |
+
},
|
1819 |
+
{
|
1820 |
+
"epoch": 0.7390300230946882,
|
1821 |
+
"grad_norm": 0.3408315181732178,
|
1822 |
+
"learning_rate": 4.391806468315408e-05,
|
1823 |
+
"loss": 1.2614,
|
1824 |
+
"mean_token_accuracy": 0.690892388857901,
|
1825 |
+
"num_tokens": 43040642.0,
|
1826 |
+
"step": 7760
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 0.7428394562034237,
|
1830 |
+
"grad_norm": 0.4586963355541229,
|
1831 |
+
"learning_rate": 4.385302892419702e-05,
|
1832 |
+
"loss": 1.2984,
|
1833 |
+
"mean_token_accuracy": 0.6800136685371398,
|
1834 |
+
"num_tokens": 43259728.0,
|
1835 |
+
"step": 7800
|
1836 |
+
},
|
1837 |
+
{
|
1838 |
+
"epoch": 0.7466488893121592,
|
1839 |
+
"grad_norm": 0.6477558016777039,
|
1840 |
+
"learning_rate": 4.37876464130557e-05,
|
1841 |
+
"loss": 1.3249,
|
1842 |
+
"mean_token_accuracy": 0.6777775203809142,
|
1843 |
+
"num_tokens": 43467264.0,
|
1844 |
+
"step": 7840
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 0.7504583224208947,
|
1848 |
+
"grad_norm": 0.4374445080757141,
|
1849 |
+
"learning_rate": 4.3721918407411845e-05,
|
1850 |
+
"loss": 1.2729,
|
1851 |
+
"mean_token_accuracy": 0.689405850879848,
|
1852 |
+
"num_tokens": 43679068.0,
|
1853 |
+
"step": 7880
|
1854 |
+
},
|
1855 |
+
{
|
1856 |
+
"epoch": 0.7542677555296302,
|
1857 |
+
"grad_norm": 0.5325660109519958,
|
1858 |
+
"learning_rate": 4.3655846171592994e-05,
|
1859 |
+
"loss": 1.2863,
|
1860 |
+
"mean_token_accuracy": 0.6884377462789416,
|
1861 |
+
"num_tokens": 43899283.0,
|
1862 |
+
"step": 7920
|
1863 |
+
},
|
1864 |
+
{
|
1865 |
+
"epoch": 0.7580771886383657,
|
1866 |
+
"grad_norm": 0.7073720097541809,
|
1867 |
+
"learning_rate": 4.358943097654823e-05,
|
1868 |
+
"loss": 1.245,
|
1869 |
+
"mean_token_accuracy": 0.6904063617810607,
|
1870 |
+
"num_tokens": 44113559.0,
|
1871 |
+
"step": 7960
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 0.7618866217471013,
|
1875 |
+
"grad_norm": 0.44697853922843933,
|
1876 |
+
"learning_rate": 4.3522674099823705e-05,
|
1877 |
+
"loss": 1.2699,
|
1878 |
+
"mean_token_accuracy": 0.6843698143959045,
|
1879 |
+
"num_tokens": 44334374.0,
|
1880 |
+
"step": 8000
|
1881 |
+
},
|
1882 |
+
{
|
1883 |
+
"epoch": 0.7656960548558368,
|
1884 |
+
"grad_norm": 0.4306088984012604,
|
1885 |
+
"learning_rate": 4.345557682553807e-05,
|
1886 |
+
"loss": 1.2319,
|
1887 |
+
"step": 8040
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 0.7656960548558368,
|
1891 |
+
"eval_mean_token_accuracy": 0.6363147346070971,
|
1892 |
+
"eval_num_tokens": 44575460.0,
|
1893 |
+
"eval_test_loss": 1.7359126806259155,
|
1894 |
+
"eval_test_runtime": 95.9212,
|
1895 |
+
"eval_test_samples_per_second": 20.757,
|
1896 |
+
"eval_test_steps_per_second": 10.384,
|
1897 |
+
"step": 8040
|
1898 |
+
},
|
1899 |
+
{
|
1900 |
+
"epoch": 0.7695054879645723,
|
1901 |
+
"grad_norm": 0.6170753836631775,
|
1902 |
+
"learning_rate": 4.3388140444357795e-05,
|
1903 |
+
"loss": 1.2328,
|
1904 |
+
"mean_token_accuracy": 0.6931531462818384,
|
1905 |
+
"num_tokens": 44806038.0,
|
1906 |
+
"step": 8080
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 0.7733149210733078,
|
1910 |
+
"grad_norm": 0.7038352489471436,
|
1911 |
+
"learning_rate": 4.332036625347232e-05,
|
1912 |
+
"loss": 1.2929,
|
1913 |
+
"mean_token_accuracy": 0.6844880169257521,
|
1914 |
+
"num_tokens": 45016584.0,
|
1915 |
+
"step": 8120
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 0.7771243541820433,
|
1919 |
+
"grad_norm": 0.4224265515804291,
|
1920 |
+
"learning_rate": 4.325225555656911e-05,
|
1921 |
+
"loss": 1.2634,
|
1922 |
+
"mean_token_accuracy": 0.6930087611079216,
|
1923 |
+
"num_tokens": 45246046.0,
|
1924 |
+
"step": 8160
|
1925 |
+
},
|
1926 |
+
{
|
1927 |
+
"epoch": 0.7809337872907788,
|
1928 |
+
"grad_norm": 0.46587294340133667,
|
1929 |
+
"learning_rate": 4.3183809663808556e-05,
|
1930 |
+
"loss": 1.2605,
|
1931 |
+
"mean_token_accuracy": 0.687124558724463,
|
1932 |
+
"num_tokens": 45464284.0,
|
1933 |
+
"step": 8200
|
1934 |
+
},
|
1935 |
+
{
|
1936 |
+
"epoch": 0.7847432203995143,
|
1937 |
+
"grad_norm": 0.5252248644828796,
|
1938 |
+
"learning_rate": 4.311502989179882e-05,
|
1939 |
+
"loss": 1.2728,
|
1940 |
+
"mean_token_accuracy": 0.6883155029267073,
|
1941 |
+
"num_tokens": 45684249.0,
|
1942 |
+
"step": 8240
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 0.7885526535082498,
|
1946 |
+
"grad_norm": 0.4695100486278534,
|
1947 |
+
"learning_rate": 4.304591756357046e-05,
|
1948 |
+
"loss": 1.27,
|
1949 |
+
"mean_token_accuracy": 0.6879516759887337,
|
1950 |
+
"num_tokens": 45919177.0,
|
1951 |
+
"step": 8280
|
1952 |
+
},
|
1953 |
+
{
|
1954 |
+
"epoch": 0.7923620866169853,
|
1955 |
+
"grad_norm": 0.46411824226379395,
|
1956 |
+
"learning_rate": 4.297647400855103e-05,
|
1957 |
+
"loss": 1.3028,
|
1958 |
+
"mean_token_accuracy": 0.683055117353797,
|
1959 |
+
"num_tokens": 46131789.0,
|
1960 |
+
"step": 8320
|
1961 |
+
},
|
1962 |
+
{
|
1963 |
+
"epoch": 0.7961715197257209,
|
1964 |
+
"grad_norm": 0.7392385601997375,
|
1965 |
+
"learning_rate": 4.290670056253944e-05,
|
1966 |
+
"loss": 1.173,
|
1967 |
+
"mean_token_accuracy": 0.6985200975090265,
|
1968 |
+
"num_tokens": 46348383.0,
|
1969 |
+
"step": 8360
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 0.7999809528344564,
|
1973 |
+
"grad_norm": 0.5996558666229248,
|
1974 |
+
"learning_rate": 4.283659856768036e-05,
|
1975 |
+
"loss": 1.1934,
|
1976 |
+
"mean_token_accuracy": 0.6913962122052908,
|
1977 |
+
"num_tokens": 46572321.0,
|
1978 |
+
"step": 8400
|
1979 |
+
},
|
1980 |
+
{
|
1981 |
+
"epoch": 0.8037903859431919,
|
1982 |
+
"grad_norm": 0.6277273297309875,
|
1983 |
+
"learning_rate": 4.276616937243828e-05,
|
1984 |
+
"loss": 1.2401,
|
1985 |
+
"mean_token_accuracy": 0.6883677888661623,
|
1986 |
+
"num_tokens": 46798263.0,
|
1987 |
+
"step": 8440
|
1988 |
+
},
|
1989 |
+
{
|
1990 |
+
"epoch": 0.8075998190519273,
|
1991 |
+
"grad_norm": 0.7397225499153137,
|
1992 |
+
"learning_rate": 4.2695414331571673e-05,
|
1993 |
+
"loss": 1.3177,
|
1994 |
+
"mean_token_accuracy": 0.6755096849054099,
|
1995 |
+
"num_tokens": 47017444.0,
|
1996 |
+
"step": 8480
|
1997 |
+
},
|
1998 |
+
{
|
1999 |
+
"epoch": 0.8114092521606628,
|
2000 |
+
"grad_norm": 0.650918185710907,
|
2001 |
+
"learning_rate": 4.2624334806106894e-05,
|
2002 |
+
"loss": 1.3164,
|
2003 |
+
"mean_token_accuracy": 0.6786608980968595,
|
2004 |
+
"num_tokens": 47230158.0,
|
2005 |
+
"step": 8520
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 0.8152186852693983,
|
2009 |
+
"grad_norm": 0.6894013285636902,
|
2010 |
+
"learning_rate": 4.255293216331197e-05,
|
2011 |
+
"loss": 1.2527,
|
2012 |
+
"mean_token_accuracy": 0.6907643361017108,
|
2013 |
+
"num_tokens": 47453276.0,
|
2014 |
+
"step": 8560
|
2015 |
+
},
|
2016 |
+
{
|
2017 |
+
"epoch": 0.8190281183781338,
|
2018 |
+
"grad_norm": 0.6085829138755798,
|
2019 |
+
"learning_rate": 4.2481207776670396e-05,
|
2020 |
+
"loss": 1.2798,
|
2021 |
+
"mean_token_accuracy": 0.6841305760666728,
|
2022 |
+
"num_tokens": 47662402.0,
|
2023 |
+
"step": 8600
|
2024 |
+
},
|
2025 |
+
{
|
2026 |
+
"epoch": 0.8228375514868693,
|
2027 |
+
"grad_norm": 0.47271421551704407,
|
2028 |
+
"learning_rate": 4.24091630258546e-05,
|
2029 |
+
"loss": 1.2038,
|
2030 |
+
"mean_token_accuracy": 0.6984878290444613,
|
2031 |
+
"num_tokens": 47889095.0,
|
2032 |
+
"step": 8640
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 0.8266469845956048,
|
2036 |
+
"grad_norm": 0.6806793212890625,
|
2037 |
+
"learning_rate": 4.2336799296699454e-05,
|
2038 |
+
"loss": 1.1881,
|
2039 |
+
"mean_token_accuracy": 0.7019338620826602,
|
2040 |
+
"num_tokens": 48117494.0,
|
2041 |
+
"step": 8680
|
2042 |
+
},
|
2043 |
+
{
|
2044 |
+
"epoch": 0.8304564177043404,
|
2045 |
+
"grad_norm": 0.5494069457054138,
|
2046 |
+
"learning_rate": 4.2264117981175665e-05,
|
2047 |
+
"loss": 1.2331,
|
2048 |
+
"mean_token_accuracy": 0.6901240289211273,
|
2049 |
+
"num_tokens": 48340935.0,
|
2050 |
+
"step": 8720
|
2051 |
+
},
|
2052 |
+
{
|
2053 |
+
"epoch": 0.8342658508130759,
|
2054 |
+
"grad_norm": 0.6391497254371643,
|
2055 |
+
"learning_rate": 4.21911204773629e-05,
|
2056 |
+
"loss": 1.2149,
|
2057 |
+
"mean_token_accuracy": 0.6961538307368755,
|
2058 |
+
"num_tokens": 48573668.0,
|
2059 |
+
"step": 8760
|
2060 |
+
},
|
2061 |
+
{
|
2062 |
+
"epoch": 0.8380752839218114,
|
2063 |
+
"grad_norm": 0.3758852481842041,
|
2064 |
+
"learning_rate": 4.211780818942297e-05,
|
2065 |
+
"loss": 1.251,
|
2066 |
+
"mean_token_accuracy": 0.6919752093032002,
|
2067 |
+
"num_tokens": 48795852.0,
|
2068 |
+
"step": 8800
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 0.8418847170305469,
|
2072 |
+
"grad_norm": 0.5446637868881226,
|
2073 |
+
"learning_rate": 4.2044182527572795e-05,
|
2074 |
+
"loss": 1.3,
|
2075 |
+
"mean_token_accuracy": 0.6852457968518137,
|
2076 |
+
"num_tokens": 49032650.0,
|
2077 |
+
"step": 8840
|
2078 |
+
},
|
2079 |
+
{
|
2080 |
+
"epoch": 0.8456941501392824,
|
2081 |
+
"grad_norm": 0.3522646427154541,
|
2082 |
+
"learning_rate": 4.197024490805727e-05,
|
2083 |
+
"loss": 1.2702,
|
2084 |
+
"mean_token_accuracy": 0.6935782097280025,
|
2085 |
+
"num_tokens": 49250248.0,
|
2086 |
+
"step": 8880
|
2087 |
+
},
|
2088 |
+
{
|
2089 |
+
"epoch": 0.8495035832480179,
|
2090 |
+
"grad_norm": 0.652208149433136,
|
2091 |
+
"learning_rate": 4.189599675312204e-05,
|
2092 |
+
"loss": 1.2844,
|
2093 |
+
"mean_token_accuracy": 0.6847639823332429,
|
2094 |
+
"num_tokens": 49476266.0,
|
2095 |
+
"step": 8920
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 0.8533130163567534,
|
2099 |
+
"grad_norm": 0.41794517636299133,
|
2100 |
+
"learning_rate": 4.182143949098612e-05,
|
2101 |
+
"loss": 1.2659,
|
2102 |
+
"mean_token_accuracy": 0.6905384896323085,
|
2103 |
+
"num_tokens": 49700173.0,
|
2104 |
+
"step": 8960
|
2105 |
+
},
|
2106 |
+
{
|
2107 |
+
"epoch": 0.8571224494654889,
|
2108 |
+
"grad_norm": 0.532646656036377,
|
2109 |
+
"learning_rate": 4.1746574555814455e-05,
|
2110 |
+
"loss": 1.282,
|
2111 |
+
"mean_token_accuracy": 0.6890167951583862,
|
2112 |
+
"num_tokens": 49930863.0,
|
2113 |
+
"step": 9000
|
2114 |
+
},
|
2115 |
+
{
|
2116 |
+
"epoch": 0.8609318825742244,
|
2117 |
+
"grad_norm": 0.5750353932380676,
|
2118 |
+
"learning_rate": 4.1671403387690284e-05,
|
2119 |
+
"loss": 1.1884,
|
2120 |
+
"mean_token_accuracy": 0.7017395876348018,
|
2121 |
+
"num_tokens": 50166067.0,
|
2122 |
+
"step": 9040
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"epoch": 0.8614080617128164,
|
2126 |
+
"eval_mean_token_accuracy": 0.6381066715621565,
|
2127 |
+
"eval_num_tokens": 50195310.0,
|
2128 |
+
"eval_test_loss": 1.723710060119629,
|
2129 |
+
"eval_test_runtime": 96.0763,
|
2130 |
+
"eval_test_samples_per_second": 20.723,
|
2131 |
+
"eval_test_steps_per_second": 10.367,
|
2132 |
+
"step": 9045
|
2133 |
+
}
|
2134 |
+
],
|
2135 |
+
"logging_steps": 40,
|
2136 |
+
"max_steps": 30161,
|
2137 |
+
"num_input_tokens_seen": 0,
|
2138 |
+
"num_train_epochs": 3,
|
2139 |
+
"save_steps": 3016,
|
2140 |
+
"stateful_callbacks": {
|
2141 |
+
"TrainerControl": {
|
2142 |
+
"args": {
|
2143 |
+
"should_epoch_stop": false,
|
2144 |
+
"should_evaluate": false,
|
2145 |
+
"should_log": false,
|
2146 |
+
"should_save": true,
|
2147 |
+
"should_training_stop": false
|
2148 |
+
},
|
2149 |
+
"attributes": {}
|
2150 |
+
}
|
2151 |
+
},
|
2152 |
+
"total_flos": 2.1928985580997181e+18,
|
2153 |
+
"train_batch_size": 4,
|
2154 |
+
"trial_name": null,
|
2155 |
+
"trial_params": null
|
2156 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6631e4a00699be75f40e1e3aac60f70d18a41fe948e5cea1bfaa64791e3965d
|
3 |
+
size 6008
|