Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +202 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2063 -0
- trainer_state.json +3533 -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-3.2-1B-bnb-4bit
|
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 0.13.2
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "unsloth/Llama-3.2-1B-bnb-4bit",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 16,
|
14 |
+
"lora_dropout": 0,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"up_proj",
|
25 |
+
"down_proj",
|
26 |
+
"o_proj",
|
27 |
+
"v_proj",
|
28 |
+
"k_proj",
|
29 |
+
"gate_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7709735974ef3cdf9dd207c1180f0bd023918d5942a731d305c24b2365b162c0
|
3 |
+
size 45118424
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a017741c4e54346586fe32ff058dbec8b154b0b4ebe652698ebbdcd565ec8126
|
3 |
+
size 23159546
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f078a27a793c86328ba28a6dfba5a1eb5bbedcd6e09d2fec0ba4b6f518c41808
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f1a8a35855af4d20caa744dad2214733db37e988a833eae9f149a88a2f88be9
|
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 +1,2063 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|finetune_right_pad_id|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_2|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|eom_id|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|python_tag|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_3|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_4|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_5|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_6|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_7|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_8|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_9|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_10|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_11|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_12|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_13|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_14|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_15|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_16|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_17|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_18|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_19|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_20|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_21|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_22|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_23|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_24|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_25|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_26|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_27|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_28|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_29|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_30|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_31|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_32|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_33|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_34|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_35|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_36|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_37|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_38|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_39|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_40|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_41|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_42|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_43|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_44|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_45|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_46|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_47|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_48|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_49|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_50|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_51|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_52|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_53|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_54|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_55|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_56|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_57|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_58|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_59|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_60|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_61|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_62|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_63|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_64|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_65|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_66|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_67|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_68|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_69|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_70|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_71|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_72|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_73|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_74|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_75|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_76|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_77|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_78|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_79|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_80|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_81|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_82|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_83|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_84|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_85|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_86|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_87|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_88|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_89|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_90|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_91|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_92|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_93|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_94|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_95|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_96|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_97|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_98|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_99|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_100|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_101|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_102|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_103|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_104|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_105|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_106|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_107|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_108|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_109|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_110|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_111|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_112|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_113|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_114|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_115|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_116|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_117|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_118|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_119|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_120|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_121|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_122|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_123|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_124|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_125|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_126|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_127|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_128|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_129|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_130|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_131|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_132|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_133|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_134|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_135|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_136|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_137|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_138|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_139|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_140|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_141|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_142|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_143|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_144|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_145|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_146|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_147|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_148|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_149|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_150|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_151|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_152|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_153|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_154|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_155|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_156|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_157|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_158|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_159|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_160|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_161|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_162|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_163|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_164|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_165|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_166|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_167|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_168|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_169|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_170|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_171|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_172|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_173|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_174|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_175|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_176|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_177|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_178|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_179|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_180|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_181|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_182|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_183|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_184|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_185|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_186|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_187|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_188|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_189|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_190|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_191|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_192|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_193|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_194|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_195|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_196|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_197|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_198|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_199|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_200|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_201|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_202|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_203|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_204|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_205|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_206|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_207|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_208|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_209|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_210|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_211|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_212|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_213|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_214|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_215|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_216|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_217|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_218|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_219|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_220|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_221|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_222|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_223|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_224|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_225|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_226|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_227|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_228|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_229|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_230|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_231|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_232|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_233|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_234|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_235|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_236|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_237|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_238|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_239|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_240|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_241|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"clean_up_tokenization_spaces": true,
|
2054 |
+
"eos_token": "<|end_of_text|>",
|
2055 |
+
"model_input_names": [
|
2056 |
+
"input_ids",
|
2057 |
+
"attention_mask"
|
2058 |
+
],
|
2059 |
+
"model_max_length": 131072,
|
2060 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
2061 |
+
"padding_side": "left",
|
2062 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3533 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.463215258855586,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.010899182561307902,
|
13 |
+
"grad_norm": 6.173911094665527,
|
14 |
+
"learning_rate": 4e-05,
|
15 |
+
"loss": 14.7136,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.021798365122615803,
|
20 |
+
"grad_norm": 6.3364973068237305,
|
21 |
+
"learning_rate": 8e-05,
|
22 |
+
"loss": 14.8041,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0326975476839237,
|
27 |
+
"grad_norm": 6.231718063354492,
|
28 |
+
"learning_rate": 0.00012,
|
29 |
+
"loss": 14.7035,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.043596730245231606,
|
34 |
+
"grad_norm": 6.516734600067139,
|
35 |
+
"learning_rate": 0.00016,
|
36 |
+
"loss": 14.6141,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.05449591280653951,
|
41 |
+
"grad_norm": NaN,
|
42 |
+
"learning_rate": 0.00016,
|
43 |
+
"loss": 14.4407,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0653950953678474,
|
48 |
+
"grad_norm": 7.817420482635498,
|
49 |
+
"learning_rate": 0.0002,
|
50 |
+
"loss": 14.5375,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.07629427792915532,
|
55 |
+
"grad_norm": 9.571914672851562,
|
56 |
+
"learning_rate": 0.0001995959595959596,
|
57 |
+
"loss": 14.3553,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.08719346049046321,
|
62 |
+
"grad_norm": 11.314117431640625,
|
63 |
+
"learning_rate": 0.0001991919191919192,
|
64 |
+
"loss": 14.1913,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.09809264305177112,
|
69 |
+
"grad_norm": 12.428942680358887,
|
70 |
+
"learning_rate": 0.00019878787878787878,
|
71 |
+
"loss": 14.0594,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.10899182561307902,
|
76 |
+
"grad_norm": 13.171401977539062,
|
77 |
+
"learning_rate": 0.00019838383838383837,
|
78 |
+
"loss": 13.8783,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.11989100817438691,
|
83 |
+
"grad_norm": 14.13656997680664,
|
84 |
+
"learning_rate": 0.000197979797979798,
|
85 |
+
"loss": 13.7696,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.1307901907356948,
|
90 |
+
"grad_norm": 14.418411254882812,
|
91 |
+
"learning_rate": 0.0001975757575757576,
|
92 |
+
"loss": 13.6174,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.14168937329700274,
|
97 |
+
"grad_norm": 14.280936241149902,
|
98 |
+
"learning_rate": 0.0001971717171717172,
|
99 |
+
"loss": 13.4457,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.15258855585831063,
|
104 |
+
"grad_norm": 15.03721809387207,
|
105 |
+
"learning_rate": 0.00019676767676767677,
|
106 |
+
"loss": 13.3558,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.16348773841961853,
|
111 |
+
"grad_norm": 15.251821517944336,
|
112 |
+
"learning_rate": 0.00019636363636363636,
|
113 |
+
"loss": 13.2064,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.17438692098092642,
|
118 |
+
"grad_norm": 15.709274291992188,
|
119 |
+
"learning_rate": 0.00019595959595959596,
|
120 |
+
"loss": 13.0549,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.18528610354223432,
|
125 |
+
"grad_norm": 15.98558521270752,
|
126 |
+
"learning_rate": 0.00019555555555555556,
|
127 |
+
"loss": 12.8944,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.19618528610354224,
|
132 |
+
"grad_norm": 16.447908401489258,
|
133 |
+
"learning_rate": 0.00019515151515151516,
|
134 |
+
"loss": 12.8388,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.20708446866485014,
|
139 |
+
"grad_norm": 17.313697814941406,
|
140 |
+
"learning_rate": 0.00019474747474747476,
|
141 |
+
"loss": 12.6693,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.21798365122615804,
|
146 |
+
"grad_norm": 18.5076961517334,
|
147 |
+
"learning_rate": 0.00019434343434343435,
|
148 |
+
"loss": 12.5437,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.22888283378746593,
|
153 |
+
"grad_norm": 18.852705001831055,
|
154 |
+
"learning_rate": 0.00019393939393939395,
|
155 |
+
"loss": 12.3889,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.23978201634877383,
|
160 |
+
"grad_norm": 16.87480926513672,
|
161 |
+
"learning_rate": 0.00019353535353535355,
|
162 |
+
"loss": 12.2707,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.2506811989100817,
|
167 |
+
"grad_norm": 23.646879196166992,
|
168 |
+
"learning_rate": 0.00019313131313131315,
|
169 |
+
"loss": 11.918,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.2615803814713896,
|
174 |
+
"grad_norm": 18.714590072631836,
|
175 |
+
"learning_rate": 0.00019272727272727274,
|
176 |
+
"loss": 11.6272,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.2724795640326976,
|
181 |
+
"grad_norm": 35.362369537353516,
|
182 |
+
"learning_rate": 0.00019232323232323232,
|
183 |
+
"loss": 11.5307,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.28337874659400547,
|
188 |
+
"grad_norm": 22.232742309570312,
|
189 |
+
"learning_rate": 0.00019191919191919191,
|
190 |
+
"loss": 11.0798,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.29427792915531337,
|
195 |
+
"grad_norm": 22.175138473510742,
|
196 |
+
"learning_rate": 0.0001915151515151515,
|
197 |
+
"loss": 10.6351,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.30517711171662126,
|
202 |
+
"grad_norm": 26.256942749023438,
|
203 |
+
"learning_rate": 0.00019111111111111114,
|
204 |
+
"loss": 10.4008,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.31607629427792916,
|
209 |
+
"grad_norm": 24.899234771728516,
|
210 |
+
"learning_rate": 0.00019070707070707073,
|
211 |
+
"loss": 10.0295,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.32697547683923706,
|
216 |
+
"grad_norm": 15.740798950195312,
|
217 |
+
"learning_rate": 0.0001903030303030303,
|
218 |
+
"loss": 9.7172,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.33787465940054495,
|
223 |
+
"grad_norm": 27.80441665649414,
|
224 |
+
"learning_rate": 0.0001898989898989899,
|
225 |
+
"loss": 9.0562,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.34877384196185285,
|
230 |
+
"grad_norm": 45.844871520996094,
|
231 |
+
"learning_rate": 0.0001894949494949495,
|
232 |
+
"loss": 8.8467,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.35967302452316074,
|
237 |
+
"grad_norm": 6.738473892211914,
|
238 |
+
"learning_rate": 0.0001890909090909091,
|
239 |
+
"loss": 7.9078,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.37057220708446864,
|
244 |
+
"grad_norm": 3.9533674716949463,
|
245 |
+
"learning_rate": 0.0001886868686868687,
|
246 |
+
"loss": 7.4944,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.3814713896457766,
|
251 |
+
"grad_norm": 8.950474739074707,
|
252 |
+
"learning_rate": 0.0001882828282828283,
|
253 |
+
"loss": 7.1246,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.3923705722070845,
|
258 |
+
"grad_norm": 4.175976276397705,
|
259 |
+
"learning_rate": 0.0001878787878787879,
|
260 |
+
"loss": 6.8332,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.4032697547683924,
|
265 |
+
"grad_norm": 1.5284682512283325,
|
266 |
+
"learning_rate": 0.0001874747474747475,
|
267 |
+
"loss": 6.7993,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.4141689373297003,
|
272 |
+
"grad_norm": 1.4985376596450806,
|
273 |
+
"learning_rate": 0.0001870707070707071,
|
274 |
+
"loss": 6.7921,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.4250681198910082,
|
279 |
+
"grad_norm": 1.0437488555908203,
|
280 |
+
"learning_rate": 0.0001866666666666667,
|
281 |
+
"loss": 6.5349,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.4359673024523161,
|
286 |
+
"grad_norm": 1.4849172830581665,
|
287 |
+
"learning_rate": 0.00018626262626262628,
|
288 |
+
"loss": 6.7318,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.44686648501362397,
|
293 |
+
"grad_norm": 6.274806022644043,
|
294 |
+
"learning_rate": 0.00018585858585858586,
|
295 |
+
"loss": 6.6821,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.45776566757493187,
|
300 |
+
"grad_norm": 6.835639953613281,
|
301 |
+
"learning_rate": 0.00018545454545454545,
|
302 |
+
"loss": 6.4709,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.46866485013623976,
|
307 |
+
"grad_norm": 2.275062322616577,
|
308 |
+
"learning_rate": 0.00018505050505050505,
|
309 |
+
"loss": 6.4287,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.47956403269754766,
|
314 |
+
"grad_norm": 1.1775331497192383,
|
315 |
+
"learning_rate": 0.00018464646464646465,
|
316 |
+
"loss": 6.4365,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.4904632152588556,
|
321 |
+
"grad_norm": 1.0454274415969849,
|
322 |
+
"learning_rate": 0.00018424242424242427,
|
323 |
+
"loss": 6.4323,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.5013623978201635,
|
328 |
+
"grad_norm": 2.2385048866271973,
|
329 |
+
"learning_rate": 0.00018383838383838384,
|
330 |
+
"loss": 6.6629,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.5122615803814714,
|
335 |
+
"grad_norm": 0.8004893660545349,
|
336 |
+
"learning_rate": 0.00018343434343434344,
|
337 |
+
"loss": 6.6393,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.5231607629427792,
|
342 |
+
"grad_norm": 0.7514417767524719,
|
343 |
+
"learning_rate": 0.00018303030303030304,
|
344 |
+
"loss": 6.3857,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.5340599455040872,
|
349 |
+
"grad_norm": 1.1417890787124634,
|
350 |
+
"learning_rate": 0.00018262626262626264,
|
351 |
+
"loss": 6.5261,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.5449591280653951,
|
356 |
+
"grad_norm": 2.334674119949341,
|
357 |
+
"learning_rate": 0.00018222222222222224,
|
358 |
+
"loss": 6.45,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.555858310626703,
|
363 |
+
"grad_norm": 1.50180983543396,
|
364 |
+
"learning_rate": 0.00018181818181818183,
|
365 |
+
"loss": 6.3055,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.5667574931880109,
|
370 |
+
"grad_norm": 1.9359692335128784,
|
371 |
+
"learning_rate": 0.0001814141414141414,
|
372 |
+
"loss": 6.2799,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.5776566757493188,
|
377 |
+
"grad_norm": 2.2008886337280273,
|
378 |
+
"learning_rate": 0.00018101010101010103,
|
379 |
+
"loss": 6.2713,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.5885558583106267,
|
384 |
+
"grad_norm": 3.091736316680908,
|
385 |
+
"learning_rate": 0.00018060606060606063,
|
386 |
+
"loss": 6.5858,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.5994550408719346,
|
391 |
+
"grad_norm": 2.224456310272217,
|
392 |
+
"learning_rate": 0.00018020202020202023,
|
393 |
+
"loss": 6.2544,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.6103542234332425,
|
398 |
+
"grad_norm": 2.97121524810791,
|
399 |
+
"learning_rate": 0.0001797979797979798,
|
400 |
+
"loss": 6.2433,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.6212534059945504,
|
405 |
+
"grad_norm": 1.7177040576934814,
|
406 |
+
"learning_rate": 0.0001793939393939394,
|
407 |
+
"loss": 6.2307,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.6321525885558583,
|
412 |
+
"grad_norm": 0.4635346233844757,
|
413 |
+
"learning_rate": 0.000178989898989899,
|
414 |
+
"loss": 6.2002,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.6430517711171662,
|
419 |
+
"grad_norm": 0.9738274216651917,
|
420 |
+
"learning_rate": 0.0001785858585858586,
|
421 |
+
"loss": 6.2621,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.6539509536784741,
|
426 |
+
"grad_norm": 0.9515509605407715,
|
427 |
+
"learning_rate": 0.0001781818181818182,
|
428 |
+
"loss": 6.2735,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.6648501362397821,
|
433 |
+
"grad_norm": 0.38928309082984924,
|
434 |
+
"learning_rate": 0.00017777777777777779,
|
435 |
+
"loss": 6.2145,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.6757493188010899,
|
440 |
+
"grad_norm": 0.4064483046531677,
|
441 |
+
"learning_rate": 0.00017737373737373738,
|
442 |
+
"loss": 6.2032,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.6866485013623979,
|
447 |
+
"grad_norm": 0.5218994617462158,
|
448 |
+
"learning_rate": 0.00017696969696969698,
|
449 |
+
"loss": 6.2611,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.6975476839237057,
|
454 |
+
"grad_norm": 0.5422987341880798,
|
455 |
+
"learning_rate": 0.00017656565656565658,
|
456 |
+
"loss": 6.2076,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.7084468664850136,
|
461 |
+
"grad_norm": 0.38721132278442383,
|
462 |
+
"learning_rate": 0.00017616161616161618,
|
463 |
+
"loss": 6.2255,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.7193460490463215,
|
468 |
+
"grad_norm": 1.0110316276550293,
|
469 |
+
"learning_rate": 0.00017575757575757578,
|
470 |
+
"loss": 6.2988,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.7302452316076294,
|
475 |
+
"grad_norm": 0.33188217878341675,
|
476 |
+
"learning_rate": 0.00017535353535353535,
|
477 |
+
"loss": 6.1976,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.7411444141689373,
|
482 |
+
"grad_norm": 0.34784093499183655,
|
483 |
+
"learning_rate": 0.00017494949494949494,
|
484 |
+
"loss": 6.3306,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.7520435967302452,
|
489 |
+
"grad_norm": 0.1645226925611496,
|
490 |
+
"learning_rate": 0.00017454545454545454,
|
491 |
+
"loss": 6.1857,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.7629427792915532,
|
496 |
+
"grad_norm": 0.19698309898376465,
|
497 |
+
"learning_rate": 0.00017414141414141414,
|
498 |
+
"loss": 6.1652,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.773841961852861,
|
503 |
+
"grad_norm": 0.1376776397228241,
|
504 |
+
"learning_rate": 0.00017373737373737377,
|
505 |
+
"loss": 6.1559,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.784741144414169,
|
510 |
+
"grad_norm": 0.18504256010055542,
|
511 |
+
"learning_rate": 0.00017333333333333334,
|
512 |
+
"loss": 6.1365,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.7956403269754768,
|
517 |
+
"grad_norm": 0.21234065294265747,
|
518 |
+
"learning_rate": 0.00017292929292929293,
|
519 |
+
"loss": 6.1698,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.8065395095367848,
|
524 |
+
"grad_norm": 0.20268601179122925,
|
525 |
+
"learning_rate": 0.00017252525252525253,
|
526 |
+
"loss": 6.1746,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.8174386920980926,
|
531 |
+
"grad_norm": 0.23631519079208374,
|
532 |
+
"learning_rate": 0.00017212121212121213,
|
533 |
+
"loss": 6.1354,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.8283378746594006,
|
538 |
+
"grad_norm": 0.24041754007339478,
|
539 |
+
"learning_rate": 0.00017171717171717173,
|
540 |
+
"loss": 6.1546,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.8392370572207084,
|
545 |
+
"grad_norm": 0.1868537813425064,
|
546 |
+
"learning_rate": 0.00017131313131313133,
|
547 |
+
"loss": 6.151,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.8501362397820164,
|
552 |
+
"grad_norm": 0.29994234442710876,
|
553 |
+
"learning_rate": 0.0001709090909090909,
|
554 |
+
"loss": 6.1612,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.8610354223433242,
|
559 |
+
"grad_norm": 0.5775282979011536,
|
560 |
+
"learning_rate": 0.00017050505050505052,
|
561 |
+
"loss": 6.3783,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.8719346049046321,
|
566 |
+
"grad_norm": 1.5403401851654053,
|
567 |
+
"learning_rate": 0.00017010101010101012,
|
568 |
+
"loss": 6.2874,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.8828337874659401,
|
573 |
+
"grad_norm": 0.389077752828598,
|
574 |
+
"learning_rate": 0.00016969696969696972,
|
575 |
+
"loss": 6.179,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.8937329700272479,
|
580 |
+
"grad_norm": 0.38043642044067383,
|
581 |
+
"learning_rate": 0.00016929292929292932,
|
582 |
+
"loss": 6.2538,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.9046321525885559,
|
587 |
+
"grad_norm": 0.6061437726020813,
|
588 |
+
"learning_rate": 0.00016888888888888889,
|
589 |
+
"loss": 6.4058,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.9155313351498637,
|
594 |
+
"grad_norm": 0.24083693325519562,
|
595 |
+
"learning_rate": 0.00016848484848484848,
|
596 |
+
"loss": 6.2007,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.9264305177111717,
|
601 |
+
"grad_norm": 0.2530721426010132,
|
602 |
+
"learning_rate": 0.00016808080808080808,
|
603 |
+
"loss": 6.1851,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.9373297002724795,
|
608 |
+
"grad_norm": 0.3793930411338806,
|
609 |
+
"learning_rate": 0.00016767676767676768,
|
610 |
+
"loss": 6.1921,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.9482288828337875,
|
615 |
+
"grad_norm": 0.255757600069046,
|
616 |
+
"learning_rate": 0.00016727272727272728,
|
617 |
+
"loss": 6.2641,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.9591280653950953,
|
622 |
+
"grad_norm": 0.16223767399787903,
|
623 |
+
"learning_rate": 0.00016686868686868688,
|
624 |
+
"loss": 6.1847,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.9700272479564033,
|
629 |
+
"grad_norm": 0.14015568792819977,
|
630 |
+
"learning_rate": 0.00016646464646464647,
|
631 |
+
"loss": 6.1638,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.9809264305177112,
|
636 |
+
"grad_norm": 0.6141758561134338,
|
637 |
+
"learning_rate": 0.00016606060606060607,
|
638 |
+
"loss": 6.2167,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.9918256130790191,
|
643 |
+
"grad_norm": 0.4424732029438019,
|
644 |
+
"learning_rate": 0.00016565656565656567,
|
645 |
+
"loss": 6.3013,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 1.005449591280654,
|
650 |
+
"grad_norm": 0.405213862657547,
|
651 |
+
"learning_rate": 0.00016525252525252527,
|
652 |
+
"loss": 9.2423,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 1.0163487738419619,
|
657 |
+
"grad_norm": 0.8009450435638428,
|
658 |
+
"learning_rate": 0.00016484848484848487,
|
659 |
+
"loss": 6.1953,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 1.0272479564032697,
|
664 |
+
"grad_norm": 0.2201612889766693,
|
665 |
+
"learning_rate": 0.00016444444444444444,
|
666 |
+
"loss": 6.153,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 1.0381471389645776,
|
671 |
+
"grad_norm": 0.4194308817386627,
|
672 |
+
"learning_rate": 0.00016404040404040403,
|
673 |
+
"loss": 6.1968,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 1.0490463215258856,
|
678 |
+
"grad_norm": 0.6941304206848145,
|
679 |
+
"learning_rate": 0.00016363636363636366,
|
680 |
+
"loss": 6.9588,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 1.0599455040871935,
|
685 |
+
"grad_norm": 0.5405890941619873,
|
686 |
+
"learning_rate": 0.00016323232323232326,
|
687 |
+
"loss": 6.5007,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 1.0708446866485013,
|
692 |
+
"grad_norm": 0.6613783240318298,
|
693 |
+
"learning_rate": 0.00016282828282828283,
|
694 |
+
"loss": 6.1685,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 1.0817438692098094,
|
699 |
+
"grad_norm": 0.49628227949142456,
|
700 |
+
"learning_rate": 0.00016242424242424243,
|
701 |
+
"loss": 6.2215,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 1.0926430517711172,
|
706 |
+
"grad_norm": 0.2801539897918701,
|
707 |
+
"learning_rate": 0.00016202020202020202,
|
708 |
+
"loss": 6.1567,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 1.103542234332425,
|
713 |
+
"grad_norm": 0.2642604410648346,
|
714 |
+
"learning_rate": 0.00016161616161616162,
|
715 |
+
"loss": 6.1611,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 1.1144414168937329,
|
720 |
+
"grad_norm": 0.3278007209300995,
|
721 |
+
"learning_rate": 0.00016121212121212122,
|
722 |
+
"loss": 6.2144,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 1.125340599455041,
|
727 |
+
"grad_norm": 0.28854313492774963,
|
728 |
+
"learning_rate": 0.00016080808080808082,
|
729 |
+
"loss": 6.1837,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 1.1362397820163488,
|
734 |
+
"grad_norm": 0.1120542660355568,
|
735 |
+
"learning_rate": 0.0001604040404040404,
|
736 |
+
"loss": 6.1733,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 1.1471389645776566,
|
741 |
+
"grad_norm": 0.1502349078655243,
|
742 |
+
"learning_rate": 0.00016,
|
743 |
+
"loss": 6.1956,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 1.1580381471389645,
|
748 |
+
"grad_norm": 0.1573847085237503,
|
749 |
+
"learning_rate": 0.0001595959595959596,
|
750 |
+
"loss": 6.2238,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 1.1689373297002725,
|
755 |
+
"grad_norm": 0.24283528327941895,
|
756 |
+
"learning_rate": 0.0001591919191919192,
|
757 |
+
"loss": 6.1679,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 1.1798365122615804,
|
762 |
+
"grad_norm": 0.24594663083553314,
|
763 |
+
"learning_rate": 0.0001587878787878788,
|
764 |
+
"loss": 6.2147,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 1.1907356948228882,
|
769 |
+
"grad_norm": 0.3162429928779602,
|
770 |
+
"learning_rate": 0.00015838383838383838,
|
771 |
+
"loss": 6.239,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 1.2016348773841963,
|
776 |
+
"grad_norm": 0.24397960305213928,
|
777 |
+
"learning_rate": 0.00015797979797979798,
|
778 |
+
"loss": 6.4416,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 1.2125340599455041,
|
783 |
+
"grad_norm": 0.1755504310131073,
|
784 |
+
"learning_rate": 0.00015757575757575757,
|
785 |
+
"loss": 6.1848,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 1.223433242506812,
|
790 |
+
"grad_norm": 0.1865660697221756,
|
791 |
+
"learning_rate": 0.00015717171717171717,
|
792 |
+
"loss": 6.1807,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 1.2343324250681198,
|
797 |
+
"grad_norm": 0.5681672692298889,
|
798 |
+
"learning_rate": 0.0001567676767676768,
|
799 |
+
"loss": 7.1042,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 1.2452316076294279,
|
804 |
+
"grad_norm": 0.13271750509738922,
|
805 |
+
"learning_rate": 0.00015636363636363637,
|
806 |
+
"loss": 6.2829,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 1.2561307901907357,
|
811 |
+
"grad_norm": 0.21046936511993408,
|
812 |
+
"learning_rate": 0.00015595959595959597,
|
813 |
+
"loss": 6.1624,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 1.2670299727520435,
|
818 |
+
"grad_norm": 0.6139978170394897,
|
819 |
+
"learning_rate": 0.00015555555555555556,
|
820 |
+
"loss": 6.1552,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 1.2779291553133514,
|
825 |
+
"grad_norm": 0.47311800718307495,
|
826 |
+
"learning_rate": 0.00015515151515151516,
|
827 |
+
"loss": 6.1831,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 1.2888283378746594,
|
832 |
+
"grad_norm": 0.24481365084648132,
|
833 |
+
"learning_rate": 0.00015474747474747476,
|
834 |
+
"loss": 6.1404,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 1.2997275204359673,
|
839 |
+
"grad_norm": 0.2416616678237915,
|
840 |
+
"learning_rate": 0.00015434343434343436,
|
841 |
+
"loss": 6.1316,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 1.3106267029972751,
|
846 |
+
"grad_norm": 0.29993197321891785,
|
847 |
+
"learning_rate": 0.00015393939393939393,
|
848 |
+
"loss": 6.1391,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 1.3215258855585832,
|
853 |
+
"grad_norm": 0.19761894643306732,
|
854 |
+
"learning_rate": 0.00015353535353535353,
|
855 |
+
"loss": 6.178,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 1.332425068119891,
|
860 |
+
"grad_norm": 0.12814165651798248,
|
861 |
+
"learning_rate": 0.00015313131313131315,
|
862 |
+
"loss": 6.1696,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 1.3433242506811989,
|
867 |
+
"grad_norm": 0.7292453050613403,
|
868 |
+
"learning_rate": 0.00015272727272727275,
|
869 |
+
"loss": 6.206,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 1.354223433242507,
|
874 |
+
"grad_norm": 0.34973058104515076,
|
875 |
+
"learning_rate": 0.00015232323232323235,
|
876 |
+
"loss": 6.4659,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 1.3651226158038148,
|
881 |
+
"grad_norm": 0.22113573551177979,
|
882 |
+
"learning_rate": 0.00015191919191919192,
|
883 |
+
"loss": 6.2153,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 1.3760217983651226,
|
888 |
+
"grad_norm": 0.21217972040176392,
|
889 |
+
"learning_rate": 0.00015151515151515152,
|
890 |
+
"loss": 6.2934,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 1.3869209809264305,
|
895 |
+
"grad_norm": 0.20437318086624146,
|
896 |
+
"learning_rate": 0.0001511111111111111,
|
897 |
+
"loss": 6.2159,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 1.3978201634877383,
|
902 |
+
"grad_norm": 0.15652823448181152,
|
903 |
+
"learning_rate": 0.0001507070707070707,
|
904 |
+
"loss": 6.2017,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 1.4087193460490464,
|
909 |
+
"grad_norm": 0.13777923583984375,
|
910 |
+
"learning_rate": 0.0001503030303030303,
|
911 |
+
"loss": 6.2012,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 1.4196185286103542,
|
916 |
+
"grad_norm": 0.19372999668121338,
|
917 |
+
"learning_rate": 0.0001498989898989899,
|
918 |
+
"loss": 6.1927,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 1.430517711171662,
|
923 |
+
"grad_norm": 0.13652633130550385,
|
924 |
+
"learning_rate": 0.0001494949494949495,
|
925 |
+
"loss": 6.1932,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 1.44141689373297,
|
930 |
+
"grad_norm": 0.38320279121398926,
|
931 |
+
"learning_rate": 0.0001490909090909091,
|
932 |
+
"loss": 6.315,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 1.452316076294278,
|
937 |
+
"grad_norm": 0.1715274155139923,
|
938 |
+
"learning_rate": 0.0001486868686868687,
|
939 |
+
"loss": 6.2499,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 1.4632152588555858,
|
944 |
+
"grad_norm": 0.1598396748304367,
|
945 |
+
"learning_rate": 0.0001482828282828283,
|
946 |
+
"loss": 6.1881,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 1.4741144414168939,
|
951 |
+
"grad_norm": 0.15926583111286163,
|
952 |
+
"learning_rate": 0.0001478787878787879,
|
953 |
+
"loss": 6.2575,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 1.4850136239782017,
|
958 |
+
"grad_norm": 0.33166489005088806,
|
959 |
+
"learning_rate": 0.00014747474747474747,
|
960 |
+
"loss": 6.1834,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 1.4959128065395095,
|
965 |
+
"grad_norm": 0.3521062731742859,
|
966 |
+
"learning_rate": 0.00014707070707070706,
|
967 |
+
"loss": 6.1724,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 1.5068119891008176,
|
972 |
+
"grad_norm": 0.30115848779678345,
|
973 |
+
"learning_rate": 0.00014666666666666666,
|
974 |
+
"loss": 6.151,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 1.5177111716621252,
|
979 |
+
"grad_norm": 0.12073715031147003,
|
980 |
+
"learning_rate": 0.0001462626262626263,
|
981 |
+
"loss": 6.1674,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 1.5286103542234333,
|
986 |
+
"grad_norm": 0.47121262550354004,
|
987 |
+
"learning_rate": 0.00014585858585858586,
|
988 |
+
"loss": 6.3034,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 1.5395095367847411,
|
993 |
+
"grad_norm": 0.17591841518878937,
|
994 |
+
"learning_rate": 0.00014545454545454546,
|
995 |
+
"loss": 6.1417,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 1.550408719346049,
|
1000 |
+
"grad_norm": 0.13197541236877441,
|
1001 |
+
"learning_rate": 0.00014505050505050505,
|
1002 |
+
"loss": 6.1599,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 1.561307901907357,
|
1007 |
+
"grad_norm": 0.12980419397354126,
|
1008 |
+
"learning_rate": 0.00014464646464646465,
|
1009 |
+
"loss": 6.1491,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 1.5722070844686649,
|
1014 |
+
"grad_norm": 0.2677476704120636,
|
1015 |
+
"learning_rate": 0.00014424242424242425,
|
1016 |
+
"loss": 6.1894,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 1.5831062670299727,
|
1021 |
+
"grad_norm": 0.640482485294342,
|
1022 |
+
"learning_rate": 0.00014383838383838385,
|
1023 |
+
"loss": 6.5929,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 1.5940054495912808,
|
1028 |
+
"grad_norm": 0.11611925810575485,
|
1029 |
+
"learning_rate": 0.00014343434343434342,
|
1030 |
+
"loss": 6.1625,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 1.6049046321525886,
|
1035 |
+
"grad_norm": 0.31824928522109985,
|
1036 |
+
"learning_rate": 0.00014303030303030304,
|
1037 |
+
"loss": 6.1576,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 1.6158038147138964,
|
1042 |
+
"grad_norm": 0.3396945893764496,
|
1043 |
+
"learning_rate": 0.00014262626262626264,
|
1044 |
+
"loss": 6.1749,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 1.6267029972752045,
|
1049 |
+
"grad_norm": 0.36278408765792847,
|
1050 |
+
"learning_rate": 0.00014222222222222224,
|
1051 |
+
"loss": 6.2145,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 1.6376021798365121,
|
1056 |
+
"grad_norm": 0.2582668364048004,
|
1057 |
+
"learning_rate": 0.00014181818181818184,
|
1058 |
+
"loss": 6.1878,
|
1059 |
+
"step": 150
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 1.6485013623978202,
|
1063 |
+
"grad_norm": 0.12749724090099335,
|
1064 |
+
"learning_rate": 0.0001414141414141414,
|
1065 |
+
"loss": 6.1796,
|
1066 |
+
"step": 151
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 1.659400544959128,
|
1070 |
+
"grad_norm": 0.27475911378860474,
|
1071 |
+
"learning_rate": 0.000141010101010101,
|
1072 |
+
"loss": 6.1946,
|
1073 |
+
"step": 152
|
1074 |
+
},
|
1075 |
+
{
|
1076 |
+
"epoch": 1.6702997275204359,
|
1077 |
+
"grad_norm": 0.14458522200584412,
|
1078 |
+
"learning_rate": 0.0001406060606060606,
|
1079 |
+
"loss": 6.3475,
|
1080 |
+
"step": 153
|
1081 |
+
},
|
1082 |
+
{
|
1083 |
+
"epoch": 1.681198910081744,
|
1084 |
+
"grad_norm": 0.20999635756015778,
|
1085 |
+
"learning_rate": 0.0001402020202020202,
|
1086 |
+
"loss": 6.19,
|
1087 |
+
"step": 154
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 1.6920980926430518,
|
1091 |
+
"grad_norm": 0.16225522756576538,
|
1092 |
+
"learning_rate": 0.0001397979797979798,
|
1093 |
+
"loss": 6.3598,
|
1094 |
+
"step": 155
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 1.7029972752043596,
|
1098 |
+
"grad_norm": 0.11324774473905563,
|
1099 |
+
"learning_rate": 0.0001393939393939394,
|
1100 |
+
"loss": 6.1729,
|
1101 |
+
"step": 156
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 1.7138964577656677,
|
1105 |
+
"grad_norm": 0.16397441923618317,
|
1106 |
+
"learning_rate": 0.000138989898989899,
|
1107 |
+
"loss": 6.2364,
|
1108 |
+
"step": 157
|
1109 |
+
},
|
1110 |
+
{
|
1111 |
+
"epoch": 1.7247956403269755,
|
1112 |
+
"grad_norm": 0.31427308917045593,
|
1113 |
+
"learning_rate": 0.0001385858585858586,
|
1114 |
+
"loss": 6.6519,
|
1115 |
+
"step": 158
|
1116 |
+
},
|
1117 |
+
{
|
1118 |
+
"epoch": 1.7356948228882834,
|
1119 |
+
"grad_norm": 0.1903781294822693,
|
1120 |
+
"learning_rate": 0.0001381818181818182,
|
1121 |
+
"loss": 6.1424,
|
1122 |
+
"step": 159
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 1.7465940054495914,
|
1126 |
+
"grad_norm": 0.1074923425912857,
|
1127 |
+
"learning_rate": 0.0001377777777777778,
|
1128 |
+
"loss": 6.162,
|
1129 |
+
"step": 160
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 1.757493188010899,
|
1133 |
+
"grad_norm": 0.2343117892742157,
|
1134 |
+
"learning_rate": 0.0001373737373737374,
|
1135 |
+
"loss": 6.3699,
|
1136 |
+
"step": 161
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 1.768392370572207,
|
1140 |
+
"grad_norm": 0.22847014665603638,
|
1141 |
+
"learning_rate": 0.00013696969696969696,
|
1142 |
+
"loss": 6.158,
|
1143 |
+
"step": 162
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 1.779291553133515,
|
1147 |
+
"grad_norm": 0.17746838927268982,
|
1148 |
+
"learning_rate": 0.00013656565656565656,
|
1149 |
+
"loss": 6.1443,
|
1150 |
+
"step": 163
|
1151 |
+
},
|
1152 |
+
{
|
1153 |
+
"epoch": 1.7901907356948228,
|
1154 |
+
"grad_norm": 0.19379661977291107,
|
1155 |
+
"learning_rate": 0.00013616161616161618,
|
1156 |
+
"loss": 6.288,
|
1157 |
+
"step": 164
|
1158 |
+
},
|
1159 |
+
{
|
1160 |
+
"epoch": 1.8010899182561309,
|
1161 |
+
"grad_norm": 0.2187827080488205,
|
1162 |
+
"learning_rate": 0.00013575757575757578,
|
1163 |
+
"loss": 6.1312,
|
1164 |
+
"step": 165
|
1165 |
+
},
|
1166 |
+
{
|
1167 |
+
"epoch": 1.8119891008174387,
|
1168 |
+
"grad_norm": 0.2696266174316406,
|
1169 |
+
"learning_rate": 0.00013535353535353538,
|
1170 |
+
"loss": 6.1643,
|
1171 |
+
"step": 166
|
1172 |
+
},
|
1173 |
+
{
|
1174 |
+
"epoch": 1.8228882833787465,
|
1175 |
+
"grad_norm": 0.4230067729949951,
|
1176 |
+
"learning_rate": 0.00013494949494949495,
|
1177 |
+
"loss": 6.1366,
|
1178 |
+
"step": 167
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 1.8337874659400546,
|
1182 |
+
"grad_norm": 0.2398137003183365,
|
1183 |
+
"learning_rate": 0.00013454545454545455,
|
1184 |
+
"loss": 6.1562,
|
1185 |
+
"step": 168
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 1.8446866485013624,
|
1189 |
+
"grad_norm": 0.16632282733917236,
|
1190 |
+
"learning_rate": 0.00013414141414141414,
|
1191 |
+
"loss": 6.186,
|
1192 |
+
"step": 169
|
1193 |
+
},
|
1194 |
+
{
|
1195 |
+
"epoch": 1.8555858310626703,
|
1196 |
+
"grad_norm": 0.48356759548187256,
|
1197 |
+
"learning_rate": 0.00013373737373737374,
|
1198 |
+
"loss": 6.3463,
|
1199 |
+
"step": 170
|
1200 |
+
},
|
1201 |
+
{
|
1202 |
+
"epoch": 1.8664850136239783,
|
1203 |
+
"grad_norm": 0.16733959317207336,
|
1204 |
+
"learning_rate": 0.00013333333333333334,
|
1205 |
+
"loss": 6.177,
|
1206 |
+
"step": 171
|
1207 |
+
},
|
1208 |
+
{
|
1209 |
+
"epoch": 1.877384196185286,
|
1210 |
+
"grad_norm": 0.24873673915863037,
|
1211 |
+
"learning_rate": 0.00013292929292929294,
|
1212 |
+
"loss": 6.2373,
|
1213 |
+
"step": 172
|
1214 |
+
},
|
1215 |
+
{
|
1216 |
+
"epoch": 1.888283378746594,
|
1217 |
+
"grad_norm": 0.23225297033786774,
|
1218 |
+
"learning_rate": 0.00013252525252525254,
|
1219 |
+
"loss": 6.1933,
|
1220 |
+
"step": 173
|
1221 |
+
},
|
1222 |
+
{
|
1223 |
+
"epoch": 1.8991825613079019,
|
1224 |
+
"grad_norm": 0.473389595746994,
|
1225 |
+
"learning_rate": 0.00013212121212121213,
|
1226 |
+
"loss": 6.2052,
|
1227 |
+
"step": 174
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 1.9100817438692097,
|
1231 |
+
"grad_norm": 0.3113359212875366,
|
1232 |
+
"learning_rate": 0.00013171717171717173,
|
1233 |
+
"loss": 6.3197,
|
1234 |
+
"step": 175
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 1.9209809264305178,
|
1238 |
+
"grad_norm": 0.1677085906267166,
|
1239 |
+
"learning_rate": 0.00013131313131313133,
|
1240 |
+
"loss": 6.3585,
|
1241 |
+
"step": 176
|
1242 |
+
},
|
1243 |
+
{
|
1244 |
+
"epoch": 1.9318801089918256,
|
1245 |
+
"grad_norm": 0.1711427867412567,
|
1246 |
+
"learning_rate": 0.00013090909090909093,
|
1247 |
+
"loss": 6.2056,
|
1248 |
+
"step": 177
|
1249 |
+
},
|
1250 |
+
{
|
1251 |
+
"epoch": 1.9427792915531334,
|
1252 |
+
"grad_norm": 0.12511757016181946,
|
1253 |
+
"learning_rate": 0.0001305050505050505,
|
1254 |
+
"loss": 6.1898,
|
1255 |
+
"step": 178
|
1256 |
+
},
|
1257 |
+
{
|
1258 |
+
"epoch": 1.9536784741144415,
|
1259 |
+
"grad_norm": 0.15003643929958344,
|
1260 |
+
"learning_rate": 0.0001301010101010101,
|
1261 |
+
"loss": 6.18,
|
1262 |
+
"step": 179
|
1263 |
+
},
|
1264 |
+
{
|
1265 |
+
"epoch": 1.9645776566757494,
|
1266 |
+
"grad_norm": 0.18387942016124725,
|
1267 |
+
"learning_rate": 0.0001296969696969697,
|
1268 |
+
"loss": 6.1497,
|
1269 |
+
"step": 180
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.9754768392370572,
|
1273 |
+
"grad_norm": 0.09031075984239578,
|
1274 |
+
"learning_rate": 0.00012929292929292932,
|
1275 |
+
"loss": 6.1753,
|
1276 |
+
"step": 181
|
1277 |
+
},
|
1278 |
+
{
|
1279 |
+
"epoch": 1.9863760217983653,
|
1280 |
+
"grad_norm": 0.10767246037721634,
|
1281 |
+
"learning_rate": 0.00012888888888888892,
|
1282 |
+
"loss": 6.1599,
|
1283 |
+
"step": 182
|
1284 |
+
},
|
1285 |
+
{
|
1286 |
+
"epoch": 1.9972752043596729,
|
1287 |
+
"grad_norm": 0.45141157507896423,
|
1288 |
+
"learning_rate": 0.0001284848484848485,
|
1289 |
+
"loss": 9.3651,
|
1290 |
+
"step": 183
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 2.010899182561308,
|
1294 |
+
"grad_norm": 0.09891144186258316,
|
1295 |
+
"learning_rate": 0.00012808080808080809,
|
1296 |
+
"loss": 6.1438,
|
1297 |
+
"step": 184
|
1298 |
+
},
|
1299 |
+
{
|
1300 |
+
"epoch": 2.0217983651226157,
|
1301 |
+
"grad_norm": 0.13178829848766327,
|
1302 |
+
"learning_rate": 0.00012767676767676768,
|
1303 |
+
"loss": 6.1458,
|
1304 |
+
"step": 185
|
1305 |
+
},
|
1306 |
+
{
|
1307 |
+
"epoch": 2.0326975476839237,
|
1308 |
+
"grad_norm": 0.08824258297681808,
|
1309 |
+
"learning_rate": 0.00012727272727272728,
|
1310 |
+
"loss": 6.143,
|
1311 |
+
"step": 186
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 2.043596730245232,
|
1315 |
+
"grad_norm": 0.13943664729595184,
|
1316 |
+
"learning_rate": 0.00012686868686868688,
|
1317 |
+
"loss": 6.1356,
|
1318 |
+
"step": 187
|
1319 |
+
},
|
1320 |
+
{
|
1321 |
+
"epoch": 2.0544959128065394,
|
1322 |
+
"grad_norm": 0.14288043975830078,
|
1323 |
+
"learning_rate": 0.00012646464646464645,
|
1324 |
+
"loss": 6.1573,
|
1325 |
+
"step": 188
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 2.0653950953678475,
|
1329 |
+
"grad_norm": 0.2474461942911148,
|
1330 |
+
"learning_rate": 0.00012606060606060605,
|
1331 |
+
"loss": 6.2321,
|
1332 |
+
"step": 189
|
1333 |
+
},
|
1334 |
+
{
|
1335 |
+
"epoch": 2.076294277929155,
|
1336 |
+
"grad_norm": 0.13096056878566742,
|
1337 |
+
"learning_rate": 0.00012565656565656567,
|
1338 |
+
"loss": 6.2665,
|
1339 |
+
"step": 190
|
1340 |
+
},
|
1341 |
+
{
|
1342 |
+
"epoch": 2.087193460490463,
|
1343 |
+
"grad_norm": 0.21291935443878174,
|
1344 |
+
"learning_rate": 0.00012525252525252527,
|
1345 |
+
"loss": 6.1686,
|
1346 |
+
"step": 191
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 2.0980926430517712,
|
1350 |
+
"grad_norm": 0.13552981615066528,
|
1351 |
+
"learning_rate": 0.00012484848484848487,
|
1352 |
+
"loss": 6.178,
|
1353 |
+
"step": 192
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 2.108991825613079,
|
1357 |
+
"grad_norm": 0.09302832186222076,
|
1358 |
+
"learning_rate": 0.00012444444444444444,
|
1359 |
+
"loss": 6.1602,
|
1360 |
+
"step": 193
|
1361 |
+
},
|
1362 |
+
{
|
1363 |
+
"epoch": 2.119891008174387,
|
1364 |
+
"grad_norm": 0.5419220924377441,
|
1365 |
+
"learning_rate": 0.00012404040404040404,
|
1366 |
+
"loss": 6.2916,
|
1367 |
+
"step": 194
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 2.130790190735695,
|
1371 |
+
"grad_norm": 0.12538427114486694,
|
1372 |
+
"learning_rate": 0.00012363636363636364,
|
1373 |
+
"loss": 6.1507,
|
1374 |
+
"step": 195
|
1375 |
+
},
|
1376 |
+
{
|
1377 |
+
"epoch": 2.1416893732970026,
|
1378 |
+
"grad_norm": 0.5663388967514038,
|
1379 |
+
"learning_rate": 0.00012323232323232323,
|
1380 |
+
"loss": 6.154,
|
1381 |
+
"step": 196
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 2.1525885558583107,
|
1385 |
+
"grad_norm": 0.16043990850448608,
|
1386 |
+
"learning_rate": 0.00012282828282828283,
|
1387 |
+
"loss": 6.1679,
|
1388 |
+
"step": 197
|
1389 |
+
},
|
1390 |
+
{
|
1391 |
+
"epoch": 2.1634877384196187,
|
1392 |
+
"grad_norm": 0.140010267496109,
|
1393 |
+
"learning_rate": 0.00012242424242424243,
|
1394 |
+
"loss": 6.188,
|
1395 |
+
"step": 198
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 2.1743869209809263,
|
1399 |
+
"grad_norm": 0.08459494262933731,
|
1400 |
+
"learning_rate": 0.00012202020202020204,
|
1401 |
+
"loss": 6.1681,
|
1402 |
+
"step": 199
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 2.1852861035422344,
|
1406 |
+
"grad_norm": 0.40000060200691223,
|
1407 |
+
"learning_rate": 0.00012161616161616162,
|
1408 |
+
"loss": 6.8772,
|
1409 |
+
"step": 200
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 2.1961852861035425,
|
1413 |
+
"grad_norm": 0.18648391962051392,
|
1414 |
+
"learning_rate": 0.00012121212121212122,
|
1415 |
+
"loss": 6.1619,
|
1416 |
+
"step": 201
|
1417 |
+
},
|
1418 |
+
{
|
1419 |
+
"epoch": 2.20708446866485,
|
1420 |
+
"grad_norm": 0.5561273097991943,
|
1421 |
+
"learning_rate": 0.00012080808080808082,
|
1422 |
+
"loss": 6.2139,
|
1423 |
+
"step": 202
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 2.217983651226158,
|
1427 |
+
"grad_norm": 0.5014886856079102,
|
1428 |
+
"learning_rate": 0.0001204040404040404,
|
1429 |
+
"loss": 6.6783,
|
1430 |
+
"step": 203
|
1431 |
+
},
|
1432 |
+
{
|
1433 |
+
"epoch": 2.2288828337874658,
|
1434 |
+
"grad_norm": 0.2286769449710846,
|
1435 |
+
"learning_rate": 0.00012,
|
1436 |
+
"loss": 6.2043,
|
1437 |
+
"step": 204
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 2.239782016348774,
|
1441 |
+
"grad_norm": 0.33960846066474915,
|
1442 |
+
"learning_rate": 0.0001195959595959596,
|
1443 |
+
"loss": 6.157,
|
1444 |
+
"step": 205
|
1445 |
+
},
|
1446 |
+
{
|
1447 |
+
"epoch": 2.250681198910082,
|
1448 |
+
"grad_norm": 0.21916227042675018,
|
1449 |
+
"learning_rate": 0.00011919191919191919,
|
1450 |
+
"loss": 6.5121,
|
1451 |
+
"step": 206
|
1452 |
+
},
|
1453 |
+
{
|
1454 |
+
"epoch": 2.2615803814713895,
|
1455 |
+
"grad_norm": 0.40727755427360535,
|
1456 |
+
"learning_rate": 0.0001187878787878788,
|
1457 |
+
"loss": 6.1969,
|
1458 |
+
"step": 207
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 2.2724795640326976,
|
1462 |
+
"grad_norm": 0.20227251946926117,
|
1463 |
+
"learning_rate": 0.0001183838383838384,
|
1464 |
+
"loss": 6.3042,
|
1465 |
+
"step": 208
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 2.2833787465940056,
|
1469 |
+
"grad_norm": 0.262510746717453,
|
1470 |
+
"learning_rate": 0.00011797979797979799,
|
1471 |
+
"loss": 6.3083,
|
1472 |
+
"step": 209
|
1473 |
+
},
|
1474 |
+
{
|
1475 |
+
"epoch": 2.2942779291553133,
|
1476 |
+
"grad_norm": 0.3285979926586151,
|
1477 |
+
"learning_rate": 0.00011757575757575758,
|
1478 |
+
"loss": 6.1488,
|
1479 |
+
"step": 210
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 2.3051771117166213,
|
1483 |
+
"grad_norm": 0.5452210903167725,
|
1484 |
+
"learning_rate": 0.00011717171717171717,
|
1485 |
+
"loss": 6.5011,
|
1486 |
+
"step": 211
|
1487 |
+
},
|
1488 |
+
{
|
1489 |
+
"epoch": 2.316076294277929,
|
1490 |
+
"grad_norm": 0.14714978635311127,
|
1491 |
+
"learning_rate": 0.00011676767676767677,
|
1492 |
+
"loss": 6.1809,
|
1493 |
+
"step": 212
|
1494 |
+
},
|
1495 |
+
{
|
1496 |
+
"epoch": 2.326975476839237,
|
1497 |
+
"grad_norm": 0.31165456771850586,
|
1498 |
+
"learning_rate": 0.00011636363636363636,
|
1499 |
+
"loss": 6.2561,
|
1500 |
+
"step": 213
|
1501 |
+
},
|
1502 |
+
{
|
1503 |
+
"epoch": 2.337874659400545,
|
1504 |
+
"grad_norm": 0.18160106241703033,
|
1505 |
+
"learning_rate": 0.00011595959595959596,
|
1506 |
+
"loss": 6.1561,
|
1507 |
+
"step": 214
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 2.3487738419618527,
|
1511 |
+
"grad_norm": 0.35501718521118164,
|
1512 |
+
"learning_rate": 0.00011555555555555555,
|
1513 |
+
"loss": 6.1351,
|
1514 |
+
"step": 215
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 2.3596730245231607,
|
1518 |
+
"grad_norm": 0.18472979962825775,
|
1519 |
+
"learning_rate": 0.00011515151515151516,
|
1520 |
+
"loss": 6.1727,
|
1521 |
+
"step": 216
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 2.370572207084469,
|
1525 |
+
"grad_norm": 0.17979513108730316,
|
1526 |
+
"learning_rate": 0.00011474747474747476,
|
1527 |
+
"loss": 6.1407,
|
1528 |
+
"step": 217
|
1529 |
+
},
|
1530 |
+
{
|
1531 |
+
"epoch": 2.3814713896457764,
|
1532 |
+
"grad_norm": 0.1735665202140808,
|
1533 |
+
"learning_rate": 0.00011434343434343435,
|
1534 |
+
"loss": 6.1773,
|
1535 |
+
"step": 218
|
1536 |
+
},
|
1537 |
+
{
|
1538 |
+
"epoch": 2.3923705722070845,
|
1539 |
+
"grad_norm": 0.1667218953371048,
|
1540 |
+
"learning_rate": 0.00011393939393939394,
|
1541 |
+
"loss": 6.1469,
|
1542 |
+
"step": 219
|
1543 |
+
},
|
1544 |
+
{
|
1545 |
+
"epoch": 2.4032697547683926,
|
1546 |
+
"grad_norm": 0.12015088647603989,
|
1547 |
+
"learning_rate": 0.00011353535353535354,
|
1548 |
+
"loss": 6.1646,
|
1549 |
+
"step": 220
|
1550 |
+
},
|
1551 |
+
{
|
1552 |
+
"epoch": 2.4141689373297,
|
1553 |
+
"grad_norm": 0.12716157734394073,
|
1554 |
+
"learning_rate": 0.00011313131313131313,
|
1555 |
+
"loss": 6.1674,
|
1556 |
+
"step": 221
|
1557 |
+
},
|
1558 |
+
{
|
1559 |
+
"epoch": 2.4250681198910082,
|
1560 |
+
"grad_norm": 0.1907472461462021,
|
1561 |
+
"learning_rate": 0.00011272727272727272,
|
1562 |
+
"loss": 6.1589,
|
1563 |
+
"step": 222
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 2.4359673024523163,
|
1567 |
+
"grad_norm": 0.25412097573280334,
|
1568 |
+
"learning_rate": 0.00011232323232323232,
|
1569 |
+
"loss": 6.2231,
|
1570 |
+
"step": 223
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 2.446866485013624,
|
1574 |
+
"grad_norm": 0.13590645790100098,
|
1575 |
+
"learning_rate": 0.00011191919191919193,
|
1576 |
+
"loss": 6.1549,
|
1577 |
+
"step": 224
|
1578 |
+
},
|
1579 |
+
{
|
1580 |
+
"epoch": 2.457765667574932,
|
1581 |
+
"grad_norm": 0.16243083775043488,
|
1582 |
+
"learning_rate": 0.00011151515151515153,
|
1583 |
+
"loss": 6.1532,
|
1584 |
+
"step": 225
|
1585 |
+
},
|
1586 |
+
{
|
1587 |
+
"epoch": 2.4686648501362396,
|
1588 |
+
"grad_norm": 0.3192502558231354,
|
1589 |
+
"learning_rate": 0.00011111111111111112,
|
1590 |
+
"loss": 6.1976,
|
1591 |
+
"step": 226
|
1592 |
+
},
|
1593 |
+
{
|
1594 |
+
"epoch": 2.4795640326975477,
|
1595 |
+
"grad_norm": 0.11255048960447311,
|
1596 |
+
"learning_rate": 0.00011070707070707071,
|
1597 |
+
"loss": 6.1756,
|
1598 |
+
"step": 227
|
1599 |
+
},
|
1600 |
+
{
|
1601 |
+
"epoch": 2.4904632152588557,
|
1602 |
+
"grad_norm": 0.08019052445888519,
|
1603 |
+
"learning_rate": 0.00011030303030303031,
|
1604 |
+
"loss": 6.1651,
|
1605 |
+
"step": 228
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 2.5013623978201633,
|
1609 |
+
"grad_norm": 0.11216670274734497,
|
1610 |
+
"learning_rate": 0.0001098989898989899,
|
1611 |
+
"loss": 6.174,
|
1612 |
+
"step": 229
|
1613 |
+
},
|
1614 |
+
{
|
1615 |
+
"epoch": 2.5122615803814714,
|
1616 |
+
"grad_norm": 0.180108904838562,
|
1617 |
+
"learning_rate": 0.0001094949494949495,
|
1618 |
+
"loss": 6.1628,
|
1619 |
+
"step": 230
|
1620 |
+
},
|
1621 |
+
{
|
1622 |
+
"epoch": 2.523160762942779,
|
1623 |
+
"grad_norm": 0.16970708966255188,
|
1624 |
+
"learning_rate": 0.00010909090909090909,
|
1625 |
+
"loss": 6.1851,
|
1626 |
+
"step": 231
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 2.534059945504087,
|
1630 |
+
"grad_norm": 0.12635812163352966,
|
1631 |
+
"learning_rate": 0.00010868686868686868,
|
1632 |
+
"loss": 6.1696,
|
1633 |
+
"step": 232
|
1634 |
+
},
|
1635 |
+
{
|
1636 |
+
"epoch": 2.544959128065395,
|
1637 |
+
"grad_norm": 0.5308592915534973,
|
1638 |
+
"learning_rate": 0.0001082828282828283,
|
1639 |
+
"loss": 7.1268,
|
1640 |
+
"step": 233
|
1641 |
+
},
|
1642 |
+
{
|
1643 |
+
"epoch": 2.5558583106267028,
|
1644 |
+
"grad_norm": 0.16270631551742554,
|
1645 |
+
"learning_rate": 0.00010787878787878789,
|
1646 |
+
"loss": 6.1787,
|
1647 |
+
"step": 234
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 2.566757493188011,
|
1651 |
+
"grad_norm": 0.8060057759284973,
|
1652 |
+
"learning_rate": 0.00010747474747474748,
|
1653 |
+
"loss": 6.4044,
|
1654 |
+
"step": 235
|
1655 |
+
},
|
1656 |
+
{
|
1657 |
+
"epoch": 2.577656675749319,
|
1658 |
+
"grad_norm": 0.44751596450805664,
|
1659 |
+
"learning_rate": 0.00010707070707070708,
|
1660 |
+
"loss": 6.1638,
|
1661 |
+
"step": 236
|
1662 |
+
},
|
1663 |
+
{
|
1664 |
+
"epoch": 2.5885558583106265,
|
1665 |
+
"grad_norm": 0.299060583114624,
|
1666 |
+
"learning_rate": 0.00010666666666666667,
|
1667 |
+
"loss": 6.1527,
|
1668 |
+
"step": 237
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 2.5994550408719346,
|
1672 |
+
"grad_norm": 0.29560768604278564,
|
1673 |
+
"learning_rate": 0.00010626262626262626,
|
1674 |
+
"loss": 6.1387,
|
1675 |
+
"step": 238
|
1676 |
+
},
|
1677 |
+
{
|
1678 |
+
"epoch": 2.6103542234332426,
|
1679 |
+
"grad_norm": 0.31047800183296204,
|
1680 |
+
"learning_rate": 0.00010585858585858586,
|
1681 |
+
"loss": 6.1753,
|
1682 |
+
"step": 239
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 2.6212534059945503,
|
1686 |
+
"grad_norm": 0.23160408437252045,
|
1687 |
+
"learning_rate": 0.00010545454545454545,
|
1688 |
+
"loss": 6.384,
|
1689 |
+
"step": 240
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 2.6321525885558583,
|
1693 |
+
"grad_norm": 0.2616265118122101,
|
1694 |
+
"learning_rate": 0.00010505050505050507,
|
1695 |
+
"loss": 6.3272,
|
1696 |
+
"step": 241
|
1697 |
+
},
|
1698 |
+
{
|
1699 |
+
"epoch": 2.6430517711171664,
|
1700 |
+
"grad_norm": 0.17835183441638947,
|
1701 |
+
"learning_rate": 0.00010464646464646466,
|
1702 |
+
"loss": 6.1332,
|
1703 |
+
"step": 242
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 2.653950953678474,
|
1707 |
+
"grad_norm": 0.3156978487968445,
|
1708 |
+
"learning_rate": 0.00010424242424242425,
|
1709 |
+
"loss": 6.1321,
|
1710 |
+
"step": 243
|
1711 |
+
},
|
1712 |
+
{
|
1713 |
+
"epoch": 2.664850136239782,
|
1714 |
+
"grad_norm": 0.1692386120557785,
|
1715 |
+
"learning_rate": 0.00010383838383838385,
|
1716 |
+
"loss": 6.1671,
|
1717 |
+
"step": 244
|
1718 |
+
},
|
1719 |
+
{
|
1720 |
+
"epoch": 2.67574931880109,
|
1721 |
+
"grad_norm": 0.2413683384656906,
|
1722 |
+
"learning_rate": 0.00010343434343434344,
|
1723 |
+
"loss": 6.3664,
|
1724 |
+
"step": 245
|
1725 |
+
},
|
1726 |
+
{
|
1727 |
+
"epoch": 2.6866485013623977,
|
1728 |
+
"grad_norm": 0.12921543419361115,
|
1729 |
+
"learning_rate": 0.00010303030303030303,
|
1730 |
+
"loss": 6.1585,
|
1731 |
+
"step": 246
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 2.697547683923706,
|
1735 |
+
"grad_norm": 0.15248817205429077,
|
1736 |
+
"learning_rate": 0.00010262626262626263,
|
1737 |
+
"loss": 6.1404,
|
1738 |
+
"step": 247
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 2.708446866485014,
|
1742 |
+
"grad_norm": 0.20268793404102325,
|
1743 |
+
"learning_rate": 0.00010222222222222222,
|
1744 |
+
"loss": 6.2903,
|
1745 |
+
"step": 248
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 2.7193460490463215,
|
1749 |
+
"grad_norm": 0.1451648324728012,
|
1750 |
+
"learning_rate": 0.00010181818181818181,
|
1751 |
+
"loss": 6.167,
|
1752 |
+
"step": 249
|
1753 |
+
},
|
1754 |
+
{
|
1755 |
+
"epoch": 2.7302452316076296,
|
1756 |
+
"grad_norm": 0.14130540192127228,
|
1757 |
+
"learning_rate": 0.00010141414141414143,
|
1758 |
+
"loss": 6.1824,
|
1759 |
+
"step": 250
|
1760 |
+
},
|
1761 |
+
{
|
1762 |
+
"epoch": 2.741144414168937,
|
1763 |
+
"grad_norm": 0.16221533715724945,
|
1764 |
+
"learning_rate": 0.00010101010101010102,
|
1765 |
+
"loss": 6.1688,
|
1766 |
+
"step": 251
|
1767 |
+
},
|
1768 |
+
{
|
1769 |
+
"epoch": 2.7520435967302452,
|
1770 |
+
"grad_norm": 0.2507758140563965,
|
1771 |
+
"learning_rate": 0.00010060606060606062,
|
1772 |
+
"loss": 6.179,
|
1773 |
+
"step": 252
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 2.7629427792915533,
|
1777 |
+
"grad_norm": 0.13289335370063782,
|
1778 |
+
"learning_rate": 0.0001002020202020202,
|
1779 |
+
"loss": 6.1705,
|
1780 |
+
"step": 253
|
1781 |
+
},
|
1782 |
+
{
|
1783 |
+
"epoch": 2.773841961852861,
|
1784 |
+
"grad_norm": 0.13900728523731232,
|
1785 |
+
"learning_rate": 9.97979797979798e-05,
|
1786 |
+
"loss": 6.2319,
|
1787 |
+
"step": 254
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 2.784741144414169,
|
1791 |
+
"grad_norm": 0.1445474475622177,
|
1792 |
+
"learning_rate": 9.939393939393939e-05,
|
1793 |
+
"loss": 6.1917,
|
1794 |
+
"step": 255
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 2.7956403269754766,
|
1798 |
+
"grad_norm": 0.26752519607543945,
|
1799 |
+
"learning_rate": 9.8989898989899e-05,
|
1800 |
+
"loss": 6.1691,
|
1801 |
+
"step": 256
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 2.8065395095367847,
|
1805 |
+
"grad_norm": 0.37636271119117737,
|
1806 |
+
"learning_rate": 9.85858585858586e-05,
|
1807 |
+
"loss": 6.1943,
|
1808 |
+
"step": 257
|
1809 |
+
},
|
1810 |
+
{
|
1811 |
+
"epoch": 2.8174386920980927,
|
1812 |
+
"grad_norm": 0.11944714188575745,
|
1813 |
+
"learning_rate": 9.818181818181818e-05,
|
1814 |
+
"loss": 6.1893,
|
1815 |
+
"step": 258
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 2.8283378746594003,
|
1819 |
+
"grad_norm": 0.11981720477342606,
|
1820 |
+
"learning_rate": 9.777777777777778e-05,
|
1821 |
+
"loss": 6.1768,
|
1822 |
+
"step": 259
|
1823 |
+
},
|
1824 |
+
{
|
1825 |
+
"epoch": 2.8392370572207084,
|
1826 |
+
"grad_norm": 0.20344823598861694,
|
1827 |
+
"learning_rate": 9.737373737373738e-05,
|
1828 |
+
"loss": 6.205,
|
1829 |
+
"step": 260
|
1830 |
+
},
|
1831 |
+
{
|
1832 |
+
"epoch": 2.8501362397820165,
|
1833 |
+
"grad_norm": 0.15309491753578186,
|
1834 |
+
"learning_rate": 9.696969696969698e-05,
|
1835 |
+
"loss": 6.1888,
|
1836 |
+
"step": 261
|
1837 |
+
},
|
1838 |
+
{
|
1839 |
+
"epoch": 2.861035422343324,
|
1840 |
+
"grad_norm": 0.22223514318466187,
|
1841 |
+
"learning_rate": 9.656565656565657e-05,
|
1842 |
+
"loss": 6.2169,
|
1843 |
+
"step": 262
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 2.871934604904632,
|
1847 |
+
"grad_norm": 0.4575447142124176,
|
1848 |
+
"learning_rate": 9.616161616161616e-05,
|
1849 |
+
"loss": 6.1841,
|
1850 |
+
"step": 263
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 2.88283378746594,
|
1854 |
+
"grad_norm": 0.18480806052684784,
|
1855 |
+
"learning_rate": 9.575757575757576e-05,
|
1856 |
+
"loss": 6.3447,
|
1857 |
+
"step": 264
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 2.893732970027248,
|
1861 |
+
"grad_norm": 0.44275179505348206,
|
1862 |
+
"learning_rate": 9.535353535353537e-05,
|
1863 |
+
"loss": 6.1697,
|
1864 |
+
"step": 265
|
1865 |
+
},
|
1866 |
+
{
|
1867 |
+
"epoch": 2.904632152588556,
|
1868 |
+
"grad_norm": 0.5216860771179199,
|
1869 |
+
"learning_rate": 9.494949494949495e-05,
|
1870 |
+
"loss": 6.1836,
|
1871 |
+
"step": 266
|
1872 |
+
},
|
1873 |
+
{
|
1874 |
+
"epoch": 2.915531335149864,
|
1875 |
+
"grad_norm": 0.25538700819015503,
|
1876 |
+
"learning_rate": 9.454545454545455e-05,
|
1877 |
+
"loss": 6.1733,
|
1878 |
+
"step": 267
|
1879 |
+
},
|
1880 |
+
{
|
1881 |
+
"epoch": 2.9264305177111716,
|
1882 |
+
"grad_norm": 0.23962710797786713,
|
1883 |
+
"learning_rate": 9.414141414141415e-05,
|
1884 |
+
"loss": 6.1606,
|
1885 |
+
"step": 268
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 2.9373297002724796,
|
1889 |
+
"grad_norm": 0.33051827549934387,
|
1890 |
+
"learning_rate": 9.373737373737375e-05,
|
1891 |
+
"loss": 6.2506,
|
1892 |
+
"step": 269
|
1893 |
+
},
|
1894 |
+
{
|
1895 |
+
"epoch": 2.9482288828337877,
|
1896 |
+
"grad_norm": 0.3523387610912323,
|
1897 |
+
"learning_rate": 9.333333333333334e-05,
|
1898 |
+
"loss": 6.1995,
|
1899 |
+
"step": 270
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 2.9591280653950953,
|
1903 |
+
"grad_norm": 0.4528197646141052,
|
1904 |
+
"learning_rate": 9.292929292929293e-05,
|
1905 |
+
"loss": 6.5313,
|
1906 |
+
"step": 271
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 2.9700272479564034,
|
1910 |
+
"grad_norm": 0.15994518995285034,
|
1911 |
+
"learning_rate": 9.252525252525253e-05,
|
1912 |
+
"loss": 6.1704,
|
1913 |
+
"step": 272
|
1914 |
+
},
|
1915 |
+
{
|
1916 |
+
"epoch": 2.9809264305177114,
|
1917 |
+
"grad_norm": 0.4959411323070526,
|
1918 |
+
"learning_rate": 9.212121212121214e-05,
|
1919 |
+
"loss": 6.1982,
|
1920 |
+
"step": 273
|
1921 |
+
},
|
1922 |
+
{
|
1923 |
+
"epoch": 2.991825613079019,
|
1924 |
+
"grad_norm": 0.36732834577560425,
|
1925 |
+
"learning_rate": 9.171717171717172e-05,
|
1926 |
+
"loss": 6.2399,
|
1927 |
+
"step": 274
|
1928 |
+
},
|
1929 |
+
{
|
1930 |
+
"epoch": 3.005449591280654,
|
1931 |
+
"grad_norm": 0.41449519991874695,
|
1932 |
+
"learning_rate": 9.131313131313132e-05,
|
1933 |
+
"loss": 9.239,
|
1934 |
+
"step": 275
|
1935 |
+
},
|
1936 |
+
{
|
1937 |
+
"epoch": 3.016348773841962,
|
1938 |
+
"grad_norm": 0.49275797605514526,
|
1939 |
+
"learning_rate": 9.090909090909092e-05,
|
1940 |
+
"loss": 6.1771,
|
1941 |
+
"step": 276
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 3.02724795640327,
|
1945 |
+
"grad_norm": 0.14379490911960602,
|
1946 |
+
"learning_rate": 9.050505050505052e-05,
|
1947 |
+
"loss": 6.209,
|
1948 |
+
"step": 277
|
1949 |
+
},
|
1950 |
+
{
|
1951 |
+
"epoch": 3.0381471389645776,
|
1952 |
+
"grad_norm": 0.1562594473361969,
|
1953 |
+
"learning_rate": 9.010101010101011e-05,
|
1954 |
+
"loss": 6.1669,
|
1955 |
+
"step": 278
|
1956 |
+
},
|
1957 |
+
{
|
1958 |
+
"epoch": 3.0490463215258856,
|
1959 |
+
"grad_norm": 0.22215306758880615,
|
1960 |
+
"learning_rate": 8.96969696969697e-05,
|
1961 |
+
"loss": 6.534,
|
1962 |
+
"step": 279
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 3.0599455040871932,
|
1966 |
+
"grad_norm": 0.23347879946231842,
|
1967 |
+
"learning_rate": 8.92929292929293e-05,
|
1968 |
+
"loss": 6.154,
|
1969 |
+
"step": 280
|
1970 |
+
},
|
1971 |
+
{
|
1972 |
+
"epoch": 3.0708446866485013,
|
1973 |
+
"grad_norm": 0.1128433346748352,
|
1974 |
+
"learning_rate": 8.888888888888889e-05,
|
1975 |
+
"loss": 6.1795,
|
1976 |
+
"step": 281
|
1977 |
+
},
|
1978 |
+
{
|
1979 |
+
"epoch": 3.0817438692098094,
|
1980 |
+
"grad_norm": 0.12231786549091339,
|
1981 |
+
"learning_rate": 8.848484848484849e-05,
|
1982 |
+
"loss": 6.22,
|
1983 |
+
"step": 282
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 3.092643051771117,
|
1987 |
+
"grad_norm": 0.12375138700008392,
|
1988 |
+
"learning_rate": 8.808080808080809e-05,
|
1989 |
+
"loss": 6.3243,
|
1990 |
+
"step": 283
|
1991 |
+
},
|
1992 |
+
{
|
1993 |
+
"epoch": 3.103542234332425,
|
1994 |
+
"grad_norm": 0.14191976189613342,
|
1995 |
+
"learning_rate": 8.767676767676767e-05,
|
1996 |
+
"loss": 6.25,
|
1997 |
+
"step": 284
|
1998 |
+
},
|
1999 |
+
{
|
2000 |
+
"epoch": 3.114441416893733,
|
2001 |
+
"grad_norm": 0.17911039292812347,
|
2002 |
+
"learning_rate": 8.727272727272727e-05,
|
2003 |
+
"loss": 6.1752,
|
2004 |
+
"step": 285
|
2005 |
+
},
|
2006 |
+
{
|
2007 |
+
"epoch": 3.1253405994550407,
|
2008 |
+
"grad_norm": 0.13937656581401825,
|
2009 |
+
"learning_rate": 8.686868686868688e-05,
|
2010 |
+
"loss": 6.1562,
|
2011 |
+
"step": 286
|
2012 |
+
},
|
2013 |
+
{
|
2014 |
+
"epoch": 3.136239782016349,
|
2015 |
+
"grad_norm": 0.19013279676437378,
|
2016 |
+
"learning_rate": 8.646464646464647e-05,
|
2017 |
+
"loss": 6.1372,
|
2018 |
+
"step": 287
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 3.147138964577657,
|
2022 |
+
"grad_norm": 0.16956225037574768,
|
2023 |
+
"learning_rate": 8.606060606060606e-05,
|
2024 |
+
"loss": 6.1445,
|
2025 |
+
"step": 288
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 3.1580381471389645,
|
2029 |
+
"grad_norm": 0.08755031228065491,
|
2030 |
+
"learning_rate": 8.565656565656566e-05,
|
2031 |
+
"loss": 6.1511,
|
2032 |
+
"step": 289
|
2033 |
+
},
|
2034 |
+
{
|
2035 |
+
"epoch": 3.1689373297002725,
|
2036 |
+
"grad_norm": 0.1031273603439331,
|
2037 |
+
"learning_rate": 8.525252525252526e-05,
|
2038 |
+
"loss": 6.1424,
|
2039 |
+
"step": 290
|
2040 |
+
},
|
2041 |
+
{
|
2042 |
+
"epoch": 3.1798365122615806,
|
2043 |
+
"grad_norm": 0.14533282816410065,
|
2044 |
+
"learning_rate": 8.484848484848486e-05,
|
2045 |
+
"loss": 6.1505,
|
2046 |
+
"step": 291
|
2047 |
+
},
|
2048 |
+
{
|
2049 |
+
"epoch": 3.190735694822888,
|
2050 |
+
"grad_norm": 0.37659046053886414,
|
2051 |
+
"learning_rate": 8.444444444444444e-05,
|
2052 |
+
"loss": 6.6586,
|
2053 |
+
"step": 292
|
2054 |
+
},
|
2055 |
+
{
|
2056 |
+
"epoch": 3.2016348773841963,
|
2057 |
+
"grad_norm": 0.10601754486560822,
|
2058 |
+
"learning_rate": 8.404040404040404e-05,
|
2059 |
+
"loss": 6.143,
|
2060 |
+
"step": 293
|
2061 |
+
},
|
2062 |
+
{
|
2063 |
+
"epoch": 3.212534059945504,
|
2064 |
+
"grad_norm": 0.5452451109886169,
|
2065 |
+
"learning_rate": 8.363636363636364e-05,
|
2066 |
+
"loss": 7.1831,
|
2067 |
+
"step": 294
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 3.223433242506812,
|
2071 |
+
"grad_norm": 0.22060728073120117,
|
2072 |
+
"learning_rate": 8.323232323232324e-05,
|
2073 |
+
"loss": 6.1595,
|
2074 |
+
"step": 295
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 3.23433242506812,
|
2078 |
+
"grad_norm": 0.1550436168909073,
|
2079 |
+
"learning_rate": 8.282828282828283e-05,
|
2080 |
+
"loss": 6.2545,
|
2081 |
+
"step": 296
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 3.2452316076294276,
|
2085 |
+
"grad_norm": 0.22410456836223602,
|
2086 |
+
"learning_rate": 8.242424242424243e-05,
|
2087 |
+
"loss": 6.1355,
|
2088 |
+
"step": 297
|
2089 |
+
},
|
2090 |
+
{
|
2091 |
+
"epoch": 3.2561307901907357,
|
2092 |
+
"grad_norm": 0.21547560393810272,
|
2093 |
+
"learning_rate": 8.202020202020202e-05,
|
2094 |
+
"loss": 6.1469,
|
2095 |
+
"step": 298
|
2096 |
+
},
|
2097 |
+
{
|
2098 |
+
"epoch": 3.2670299727520438,
|
2099 |
+
"grad_norm": 0.14056307077407837,
|
2100 |
+
"learning_rate": 8.161616161616163e-05,
|
2101 |
+
"loss": 6.4813,
|
2102 |
+
"step": 299
|
2103 |
+
},
|
2104 |
+
{
|
2105 |
+
"epoch": 3.2779291553133514,
|
2106 |
+
"grad_norm": 0.14949879050254822,
|
2107 |
+
"learning_rate": 8.121212121212121e-05,
|
2108 |
+
"loss": 6.1359,
|
2109 |
+
"step": 300
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 3.2888283378746594,
|
2113 |
+
"grad_norm": 0.1382267326116562,
|
2114 |
+
"learning_rate": 8.080808080808081e-05,
|
2115 |
+
"loss": 6.2013,
|
2116 |
+
"step": 301
|
2117 |
+
},
|
2118 |
+
{
|
2119 |
+
"epoch": 3.299727520435967,
|
2120 |
+
"grad_norm": 0.19791223108768463,
|
2121 |
+
"learning_rate": 8.040404040404041e-05,
|
2122 |
+
"loss": 6.1286,
|
2123 |
+
"step": 302
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 3.310626702997275,
|
2127 |
+
"grad_norm": 0.13955998420715332,
|
2128 |
+
"learning_rate": 8e-05,
|
2129 |
+
"loss": 6.127,
|
2130 |
+
"step": 303
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 3.321525885558583,
|
2134 |
+
"grad_norm": 0.14550985395908356,
|
2135 |
+
"learning_rate": 7.95959595959596e-05,
|
2136 |
+
"loss": 6.1668,
|
2137 |
+
"step": 304
|
2138 |
+
},
|
2139 |
+
{
|
2140 |
+
"epoch": 3.332425068119891,
|
2141 |
+
"grad_norm": 0.1612524390220642,
|
2142 |
+
"learning_rate": 7.919191919191919e-05,
|
2143 |
+
"loss": 6.2293,
|
2144 |
+
"step": 305
|
2145 |
+
},
|
2146 |
+
{
|
2147 |
+
"epoch": 3.343324250681199,
|
2148 |
+
"grad_norm": 0.10381856560707092,
|
2149 |
+
"learning_rate": 7.878787878787879e-05,
|
2150 |
+
"loss": 6.1429,
|
2151 |
+
"step": 306
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 3.354223433242507,
|
2155 |
+
"grad_norm": 0.10719522833824158,
|
2156 |
+
"learning_rate": 7.83838383838384e-05,
|
2157 |
+
"loss": 6.1476,
|
2158 |
+
"step": 307
|
2159 |
+
},
|
2160 |
+
{
|
2161 |
+
"epoch": 3.3651226158038146,
|
2162 |
+
"grad_norm": 0.18627916276454926,
|
2163 |
+
"learning_rate": 7.797979797979798e-05,
|
2164 |
+
"loss": 6.1572,
|
2165 |
+
"step": 308
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 3.3760217983651226,
|
2169 |
+
"grad_norm": 0.10271579772233963,
|
2170 |
+
"learning_rate": 7.757575757575758e-05,
|
2171 |
+
"loss": 6.1598,
|
2172 |
+
"step": 309
|
2173 |
+
},
|
2174 |
+
{
|
2175 |
+
"epoch": 3.3869209809264307,
|
2176 |
+
"grad_norm": 0.19747163355350494,
|
2177 |
+
"learning_rate": 7.717171717171718e-05,
|
2178 |
+
"loss": 6.1679,
|
2179 |
+
"step": 310
|
2180 |
+
},
|
2181 |
+
{
|
2182 |
+
"epoch": 3.3978201634877383,
|
2183 |
+
"grad_norm": 0.2724840044975281,
|
2184 |
+
"learning_rate": 7.676767676767676e-05,
|
2185 |
+
"loss": 6.2574,
|
2186 |
+
"step": 311
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 3.4087193460490464,
|
2190 |
+
"grad_norm": 0.15871340036392212,
|
2191 |
+
"learning_rate": 7.636363636363637e-05,
|
2192 |
+
"loss": 6.3006,
|
2193 |
+
"step": 312
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 3.4196185286103544,
|
2197 |
+
"grad_norm": 0.19969478249549866,
|
2198 |
+
"learning_rate": 7.595959595959596e-05,
|
2199 |
+
"loss": 6.1685,
|
2200 |
+
"step": 313
|
2201 |
+
},
|
2202 |
+
{
|
2203 |
+
"epoch": 3.430517711171662,
|
2204 |
+
"grad_norm": 0.1830209493637085,
|
2205 |
+
"learning_rate": 7.555555555555556e-05,
|
2206 |
+
"loss": 6.2126,
|
2207 |
+
"step": 314
|
2208 |
+
},
|
2209 |
+
{
|
2210 |
+
"epoch": 3.44141689373297,
|
2211 |
+
"grad_norm": 0.12285900115966797,
|
2212 |
+
"learning_rate": 7.515151515151515e-05,
|
2213 |
+
"loss": 6.1792,
|
2214 |
+
"step": 315
|
2215 |
+
},
|
2216 |
+
{
|
2217 |
+
"epoch": 3.452316076294278,
|
2218 |
+
"grad_norm": 0.17864428460597992,
|
2219 |
+
"learning_rate": 7.474747474747475e-05,
|
2220 |
+
"loss": 6.3188,
|
2221 |
+
"step": 316
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 3.463215258855586,
|
2225 |
+
"grad_norm": 0.30143600702285767,
|
2226 |
+
"learning_rate": 7.434343434343435e-05,
|
2227 |
+
"loss": 6.2182,
|
2228 |
+
"step": 317
|
2229 |
+
},
|
2230 |
+
{
|
2231 |
+
"epoch": 3.474114441416894,
|
2232 |
+
"grad_norm": 0.215902641415596,
|
2233 |
+
"learning_rate": 7.393939393939395e-05,
|
2234 |
+
"loss": 6.1728,
|
2235 |
+
"step": 318
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 3.4850136239782015,
|
2239 |
+
"grad_norm": 0.2436136156320572,
|
2240 |
+
"learning_rate": 7.353535353535353e-05,
|
2241 |
+
"loss": 6.2123,
|
2242 |
+
"step": 319
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 3.4959128065395095,
|
2246 |
+
"grad_norm": 0.24740266799926758,
|
2247 |
+
"learning_rate": 7.313131313131314e-05,
|
2248 |
+
"loss": 6.1889,
|
2249 |
+
"step": 320
|
2250 |
+
},
|
2251 |
+
{
|
2252 |
+
"epoch": 3.5068119891008176,
|
2253 |
+
"grad_norm": 0.21778513491153717,
|
2254 |
+
"learning_rate": 7.272727272727273e-05,
|
2255 |
+
"loss": 6.1706,
|
2256 |
+
"step": 321
|
2257 |
+
},
|
2258 |
+
{
|
2259 |
+
"epoch": 3.517711171662125,
|
2260 |
+
"grad_norm": 0.22260497510433197,
|
2261 |
+
"learning_rate": 7.232323232323233e-05,
|
2262 |
+
"loss": 6.1825,
|
2263 |
+
"step": 322
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 3.5286103542234333,
|
2267 |
+
"grad_norm": 0.13955512642860413,
|
2268 |
+
"learning_rate": 7.191919191919192e-05,
|
2269 |
+
"loss": 6.1847,
|
2270 |
+
"step": 323
|
2271 |
+
},
|
2272 |
+
{
|
2273 |
+
"epoch": 3.539509536784741,
|
2274 |
+
"grad_norm": 0.34359583258628845,
|
2275 |
+
"learning_rate": 7.151515151515152e-05,
|
2276 |
+
"loss": 6.4338,
|
2277 |
+
"step": 324
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 3.550408719346049,
|
2281 |
+
"grad_norm": 0.10277872532606125,
|
2282 |
+
"learning_rate": 7.111111111111112e-05,
|
2283 |
+
"loss": 6.1621,
|
2284 |
+
"step": 325
|
2285 |
+
},
|
2286 |
+
{
|
2287 |
+
"epoch": 3.561307901907357,
|
2288 |
+
"grad_norm": 0.19088654220104218,
|
2289 |
+
"learning_rate": 7.07070707070707e-05,
|
2290 |
+
"loss": 6.1867,
|
2291 |
+
"step": 326
|
2292 |
+
},
|
2293 |
+
{
|
2294 |
+
"epoch": 3.5722070844686646,
|
2295 |
+
"grad_norm": 0.0887422040104866,
|
2296 |
+
"learning_rate": 7.03030303030303e-05,
|
2297 |
+
"loss": 6.141,
|
2298 |
+
"step": 327
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 3.5831062670299727,
|
2302 |
+
"grad_norm": 0.11330597847700119,
|
2303 |
+
"learning_rate": 6.98989898989899e-05,
|
2304 |
+
"loss": 6.1588,
|
2305 |
+
"step": 328
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 3.5940054495912808,
|
2309 |
+
"grad_norm": 0.09927017986774445,
|
2310 |
+
"learning_rate": 6.94949494949495e-05,
|
2311 |
+
"loss": 6.1231,
|
2312 |
+
"step": 329
|
2313 |
+
},
|
2314 |
+
{
|
2315 |
+
"epoch": 3.6049046321525884,
|
2316 |
+
"grad_norm": 0.10564055293798447,
|
2317 |
+
"learning_rate": 6.90909090909091e-05,
|
2318 |
+
"loss": 6.1484,
|
2319 |
+
"step": 330
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 3.6158038147138964,
|
2323 |
+
"grad_norm": 0.3282771706581116,
|
2324 |
+
"learning_rate": 6.86868686868687e-05,
|
2325 |
+
"loss": 6.1763,
|
2326 |
+
"step": 331
|
2327 |
+
},
|
2328 |
+
{
|
2329 |
+
"epoch": 3.6267029972752045,
|
2330 |
+
"grad_norm": 0.43109074234962463,
|
2331 |
+
"learning_rate": 6.828282828282828e-05,
|
2332 |
+
"loss": 6.2524,
|
2333 |
+
"step": 332
|
2334 |
+
},
|
2335 |
+
{
|
2336 |
+
"epoch": 3.637602179836512,
|
2337 |
+
"grad_norm": 0.13901947438716888,
|
2338 |
+
"learning_rate": 6.787878787878789e-05,
|
2339 |
+
"loss": 6.1351,
|
2340 |
+
"step": 333
|
2341 |
+
},
|
2342 |
+
{
|
2343 |
+
"epoch": 3.64850136239782,
|
2344 |
+
"grad_norm": 0.11033597588539124,
|
2345 |
+
"learning_rate": 6.747474747474747e-05,
|
2346 |
+
"loss": 6.1543,
|
2347 |
+
"step": 334
|
2348 |
+
},
|
2349 |
+
{
|
2350 |
+
"epoch": 3.6594005449591283,
|
2351 |
+
"grad_norm": 0.12363231182098389,
|
2352 |
+
"learning_rate": 6.707070707070707e-05,
|
2353 |
+
"loss": 6.1509,
|
2354 |
+
"step": 335
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 3.670299727520436,
|
2358 |
+
"grad_norm": 0.18957512080669403,
|
2359 |
+
"learning_rate": 6.666666666666667e-05,
|
2360 |
+
"loss": 6.1652,
|
2361 |
+
"step": 336
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 3.681198910081744,
|
2365 |
+
"grad_norm": 0.23333989083766937,
|
2366 |
+
"learning_rate": 6.626262626262627e-05,
|
2367 |
+
"loss": 6.1927,
|
2368 |
+
"step": 337
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 3.692098092643052,
|
2372 |
+
"grad_norm": 0.3563447892665863,
|
2373 |
+
"learning_rate": 6.585858585858587e-05,
|
2374 |
+
"loss": 6.1793,
|
2375 |
+
"step": 338
|
2376 |
+
},
|
2377 |
+
{
|
2378 |
+
"epoch": 3.7029972752043596,
|
2379 |
+
"grad_norm": 0.12097752094268799,
|
2380 |
+
"learning_rate": 6.545454545454546e-05,
|
2381 |
+
"loss": 6.1671,
|
2382 |
+
"step": 339
|
2383 |
+
},
|
2384 |
+
{
|
2385 |
+
"epoch": 3.7138964577656677,
|
2386 |
+
"grad_norm": 0.14230136573314667,
|
2387 |
+
"learning_rate": 6.505050505050505e-05,
|
2388 |
+
"loss": 6.1716,
|
2389 |
+
"step": 340
|
2390 |
+
},
|
2391 |
+
{
|
2392 |
+
"epoch": 3.7247956403269757,
|
2393 |
+
"grad_norm": 0.2817299962043762,
|
2394 |
+
"learning_rate": 6.464646464646466e-05,
|
2395 |
+
"loss": 6.1803,
|
2396 |
+
"step": 341
|
2397 |
+
},
|
2398 |
+
{
|
2399 |
+
"epoch": 3.7356948228882834,
|
2400 |
+
"grad_norm": 0.20600463449954987,
|
2401 |
+
"learning_rate": 6.424242424242424e-05,
|
2402 |
+
"loss": 6.3618,
|
2403 |
+
"step": 342
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 3.7465940054495914,
|
2407 |
+
"grad_norm": 0.22449436783790588,
|
2408 |
+
"learning_rate": 6.383838383838384e-05,
|
2409 |
+
"loss": 6.1726,
|
2410 |
+
"step": 343
|
2411 |
+
},
|
2412 |
+
{
|
2413 |
+
"epoch": 3.757493188010899,
|
2414 |
+
"grad_norm": 0.12208205461502075,
|
2415 |
+
"learning_rate": 6.343434343434344e-05,
|
2416 |
+
"loss": 6.1956,
|
2417 |
+
"step": 344
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 3.768392370572207,
|
2421 |
+
"grad_norm": 0.10846205800771713,
|
2422 |
+
"learning_rate": 6.303030303030302e-05,
|
2423 |
+
"loss": 6.1562,
|
2424 |
+
"step": 345
|
2425 |
+
},
|
2426 |
+
{
|
2427 |
+
"epoch": 3.7792915531335147,
|
2428 |
+
"grad_norm": 0.2708032727241516,
|
2429 |
+
"learning_rate": 6.262626262626264e-05,
|
2430 |
+
"loss": 6.2429,
|
2431 |
+
"step": 346
|
2432 |
+
},
|
2433 |
+
{
|
2434 |
+
"epoch": 3.790190735694823,
|
2435 |
+
"grad_norm": 0.42959117889404297,
|
2436 |
+
"learning_rate": 6.222222222222222e-05,
|
2437 |
+
"loss": 6.2097,
|
2438 |
+
"step": 347
|
2439 |
+
},
|
2440 |
+
{
|
2441 |
+
"epoch": 3.801089918256131,
|
2442 |
+
"grad_norm": 0.22440572082996368,
|
2443 |
+
"learning_rate": 6.181818181818182e-05,
|
2444 |
+
"loss": 6.3554,
|
2445 |
+
"step": 348
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 3.8119891008174385,
|
2449 |
+
"grad_norm": 0.2479640245437622,
|
2450 |
+
"learning_rate": 6.141414141414142e-05,
|
2451 |
+
"loss": 6.1556,
|
2452 |
+
"step": 349
|
2453 |
+
},
|
2454 |
+
{
|
2455 |
+
"epoch": 3.8228882833787465,
|
2456 |
+
"grad_norm": 0.49595651030540466,
|
2457 |
+
"learning_rate": 6.101010101010102e-05,
|
2458 |
+
"loss": 7.1389,
|
2459 |
+
"step": 350
|
2460 |
+
},
|
2461 |
+
{
|
2462 |
+
"epoch": 3.8337874659400546,
|
2463 |
+
"grad_norm": 0.18350739777088165,
|
2464 |
+
"learning_rate": 6.060606060606061e-05,
|
2465 |
+
"loss": 6.1918,
|
2466 |
+
"step": 351
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"epoch": 3.844686648501362,
|
2470 |
+
"grad_norm": 0.2975408136844635,
|
2471 |
+
"learning_rate": 6.02020202020202e-05,
|
2472 |
+
"loss": 6.1625,
|
2473 |
+
"step": 352
|
2474 |
+
},
|
2475 |
+
{
|
2476 |
+
"epoch": 3.8555858310626703,
|
2477 |
+
"grad_norm": 0.33965060114860535,
|
2478 |
+
"learning_rate": 5.97979797979798e-05,
|
2479 |
+
"loss": 6.1698,
|
2480 |
+
"step": 353
|
2481 |
+
},
|
2482 |
+
{
|
2483 |
+
"epoch": 3.8664850136239783,
|
2484 |
+
"grad_norm": 0.1836046725511551,
|
2485 |
+
"learning_rate": 5.93939393939394e-05,
|
2486 |
+
"loss": 6.1667,
|
2487 |
+
"step": 354
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 3.877384196185286,
|
2491 |
+
"grad_norm": 0.19976381957530975,
|
2492 |
+
"learning_rate": 5.8989898989898996e-05,
|
2493 |
+
"loss": 6.1561,
|
2494 |
+
"step": 355
|
2495 |
+
},
|
2496 |
+
{
|
2497 |
+
"epoch": 3.888283378746594,
|
2498 |
+
"grad_norm": 0.19982588291168213,
|
2499 |
+
"learning_rate": 5.858585858585859e-05,
|
2500 |
+
"loss": 6.277,
|
2501 |
+
"step": 356
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 3.899182561307902,
|
2505 |
+
"grad_norm": 0.11651279032230377,
|
2506 |
+
"learning_rate": 5.818181818181818e-05,
|
2507 |
+
"loss": 6.1483,
|
2508 |
+
"step": 357
|
2509 |
+
},
|
2510 |
+
{
|
2511 |
+
"epoch": 3.9100817438692097,
|
2512 |
+
"grad_norm": 0.27458274364471436,
|
2513 |
+
"learning_rate": 5.7777777777777776e-05,
|
2514 |
+
"loss": 6.1632,
|
2515 |
+
"step": 358
|
2516 |
+
},
|
2517 |
+
{
|
2518 |
+
"epoch": 3.9209809264305178,
|
2519 |
+
"grad_norm": 0.0916130468249321,
|
2520 |
+
"learning_rate": 5.737373737373738e-05,
|
2521 |
+
"loss": 6.1351,
|
2522 |
+
"step": 359
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 3.931880108991826,
|
2526 |
+
"grad_norm": 0.23624251782894135,
|
2527 |
+
"learning_rate": 5.696969696969697e-05,
|
2528 |
+
"loss": 6.3717,
|
2529 |
+
"step": 360
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 3.9427792915531334,
|
2533 |
+
"grad_norm": 0.14670449495315552,
|
2534 |
+
"learning_rate": 5.6565656565656563e-05,
|
2535 |
+
"loss": 6.1572,
|
2536 |
+
"step": 361
|
2537 |
+
},
|
2538 |
+
{
|
2539 |
+
"epoch": 3.9536784741144415,
|
2540 |
+
"grad_norm": 0.12288593500852585,
|
2541 |
+
"learning_rate": 5.616161616161616e-05,
|
2542 |
+
"loss": 6.1509,
|
2543 |
+
"step": 362
|
2544 |
+
},
|
2545 |
+
{
|
2546 |
+
"epoch": 3.9645776566757496,
|
2547 |
+
"grad_norm": 0.1172018051147461,
|
2548 |
+
"learning_rate": 5.5757575757575766e-05,
|
2549 |
+
"loss": 6.2154,
|
2550 |
+
"step": 363
|
2551 |
+
},
|
2552 |
+
{
|
2553 |
+
"epoch": 3.975476839237057,
|
2554 |
+
"grad_norm": 0.16450701653957367,
|
2555 |
+
"learning_rate": 5.535353535353536e-05,
|
2556 |
+
"loss": 6.1417,
|
2557 |
+
"step": 364
|
2558 |
+
},
|
2559 |
+
{
|
2560 |
+
"epoch": 3.9863760217983653,
|
2561 |
+
"grad_norm": 0.17729254066944122,
|
2562 |
+
"learning_rate": 5.494949494949495e-05,
|
2563 |
+
"loss": 6.237,
|
2564 |
+
"step": 365
|
2565 |
+
},
|
2566 |
+
{
|
2567 |
+
"epoch": 3.997275204359673,
|
2568 |
+
"grad_norm": 0.1622830182313919,
|
2569 |
+
"learning_rate": 5.4545454545454546e-05,
|
2570 |
+
"loss": 9.2183,
|
2571 |
+
"step": 366
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 4.010899182561308,
|
2575 |
+
"grad_norm": 0.25812089443206787,
|
2576 |
+
"learning_rate": 5.414141414141415e-05,
|
2577 |
+
"loss": 6.6206,
|
2578 |
+
"step": 367
|
2579 |
+
},
|
2580 |
+
{
|
2581 |
+
"epoch": 4.021798365122616,
|
2582 |
+
"grad_norm": 0.10862333327531815,
|
2583 |
+
"learning_rate": 5.373737373737374e-05,
|
2584 |
+
"loss": 6.1384,
|
2585 |
+
"step": 368
|
2586 |
+
},
|
2587 |
+
{
|
2588 |
+
"epoch": 4.032697547683924,
|
2589 |
+
"grad_norm": 0.23395223915576935,
|
2590 |
+
"learning_rate": 5.333333333333333e-05,
|
2591 |
+
"loss": 6.1301,
|
2592 |
+
"step": 369
|
2593 |
+
},
|
2594 |
+
{
|
2595 |
+
"epoch": 4.043596730245231,
|
2596 |
+
"grad_norm": 0.17671817541122437,
|
2597 |
+
"learning_rate": 5.292929292929293e-05,
|
2598 |
+
"loss": 6.1281,
|
2599 |
+
"step": 370
|
2600 |
+
},
|
2601 |
+
{
|
2602 |
+
"epoch": 4.05449591280654,
|
2603 |
+
"grad_norm": 0.18898046016693115,
|
2604 |
+
"learning_rate": 5.2525252525252536e-05,
|
2605 |
+
"loss": 6.1806,
|
2606 |
+
"step": 371
|
2607 |
+
},
|
2608 |
+
{
|
2609 |
+
"epoch": 4.0653950953678475,
|
2610 |
+
"grad_norm": 0.16608364880084991,
|
2611 |
+
"learning_rate": 5.212121212121213e-05,
|
2612 |
+
"loss": 6.1582,
|
2613 |
+
"step": 372
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 4.076294277929155,
|
2617 |
+
"grad_norm": 0.15272347629070282,
|
2618 |
+
"learning_rate": 5.171717171717172e-05,
|
2619 |
+
"loss": 6.1441,
|
2620 |
+
"step": 373
|
2621 |
+
},
|
2622 |
+
{
|
2623 |
+
"epoch": 4.087193460490464,
|
2624 |
+
"grad_norm": 0.14940135180950165,
|
2625 |
+
"learning_rate": 5.1313131313131316e-05,
|
2626 |
+
"loss": 6.1524,
|
2627 |
+
"step": 374
|
2628 |
+
},
|
2629 |
+
{
|
2630 |
+
"epoch": 4.098092643051771,
|
2631 |
+
"grad_norm": 0.12995606660842896,
|
2632 |
+
"learning_rate": 5.090909090909091e-05,
|
2633 |
+
"loss": 6.1294,
|
2634 |
+
"step": 375
|
2635 |
+
},
|
2636 |
+
{
|
2637 |
+
"epoch": 4.108991825613079,
|
2638 |
+
"grad_norm": 0.09847455471754074,
|
2639 |
+
"learning_rate": 5.050505050505051e-05,
|
2640 |
+
"loss": 6.1608,
|
2641 |
+
"step": 376
|
2642 |
+
},
|
2643 |
+
{
|
2644 |
+
"epoch": 4.1198910081743865,
|
2645 |
+
"grad_norm": 0.12721924483776093,
|
2646 |
+
"learning_rate": 5.01010101010101e-05,
|
2647 |
+
"loss": 6.1577,
|
2648 |
+
"step": 377
|
2649 |
+
},
|
2650 |
+
{
|
2651 |
+
"epoch": 4.130790190735695,
|
2652 |
+
"grad_norm": 0.16987353563308716,
|
2653 |
+
"learning_rate": 4.9696969696969694e-05,
|
2654 |
+
"loss": 6.1492,
|
2655 |
+
"step": 378
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 4.141689373297003,
|
2659 |
+
"grad_norm": 0.17095069587230682,
|
2660 |
+
"learning_rate": 4.92929292929293e-05,
|
2661 |
+
"loss": 6.1358,
|
2662 |
+
"step": 379
|
2663 |
+
},
|
2664 |
+
{
|
2665 |
+
"epoch": 4.15258855585831,
|
2666 |
+
"grad_norm": 0.12413057684898376,
|
2667 |
+
"learning_rate": 4.888888888888889e-05,
|
2668 |
+
"loss": 6.1557,
|
2669 |
+
"step": 380
|
2670 |
+
},
|
2671 |
+
{
|
2672 |
+
"epoch": 4.163487738419619,
|
2673 |
+
"grad_norm": 0.09834663569927216,
|
2674 |
+
"learning_rate": 4.848484848484849e-05,
|
2675 |
+
"loss": 6.1509,
|
2676 |
+
"step": 381
|
2677 |
+
},
|
2678 |
+
{
|
2679 |
+
"epoch": 4.174386920980926,
|
2680 |
+
"grad_norm": 0.15776708722114563,
|
2681 |
+
"learning_rate": 4.808080808080808e-05,
|
2682 |
+
"loss": 6.1801,
|
2683 |
+
"step": 382
|
2684 |
+
},
|
2685 |
+
{
|
2686 |
+
"epoch": 4.185286103542234,
|
2687 |
+
"grad_norm": 0.14047148823738098,
|
2688 |
+
"learning_rate": 4.7676767676767684e-05,
|
2689 |
+
"loss": 6.17,
|
2690 |
+
"step": 383
|
2691 |
+
},
|
2692 |
+
{
|
2693 |
+
"epoch": 4.1961852861035425,
|
2694 |
+
"grad_norm": 0.4055856764316559,
|
2695 |
+
"learning_rate": 4.7272727272727275e-05,
|
2696 |
+
"loss": 6.2462,
|
2697 |
+
"step": 384
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 4.20708446866485,
|
2701 |
+
"grad_norm": 0.12411222606897354,
|
2702 |
+
"learning_rate": 4.686868686868687e-05,
|
2703 |
+
"loss": 6.1751,
|
2704 |
+
"step": 385
|
2705 |
+
},
|
2706 |
+
{
|
2707 |
+
"epoch": 4.217983651226158,
|
2708 |
+
"grad_norm": 0.1417582631111145,
|
2709 |
+
"learning_rate": 4.6464646464646464e-05,
|
2710 |
+
"loss": 6.207,
|
2711 |
+
"step": 386
|
2712 |
+
},
|
2713 |
+
{
|
2714 |
+
"epoch": 4.228882833787466,
|
2715 |
+
"grad_norm": 0.1599162071943283,
|
2716 |
+
"learning_rate": 4.606060606060607e-05,
|
2717 |
+
"loss": 6.1669,
|
2718 |
+
"step": 387
|
2719 |
+
},
|
2720 |
+
{
|
2721 |
+
"epoch": 4.239782016348774,
|
2722 |
+
"grad_norm": 0.11022761464118958,
|
2723 |
+
"learning_rate": 4.565656565656566e-05,
|
2724 |
+
"loss": 6.1717,
|
2725 |
+
"step": 388
|
2726 |
+
},
|
2727 |
+
{
|
2728 |
+
"epoch": 4.2506811989100814,
|
2729 |
+
"grad_norm": 0.2099771499633789,
|
2730 |
+
"learning_rate": 4.525252525252526e-05,
|
2731 |
+
"loss": 6.1848,
|
2732 |
+
"step": 389
|
2733 |
+
},
|
2734 |
+
{
|
2735 |
+
"epoch": 4.26158038147139,
|
2736 |
+
"grad_norm": 0.38737088441848755,
|
2737 |
+
"learning_rate": 4.484848484848485e-05,
|
2738 |
+
"loss": 6.1843,
|
2739 |
+
"step": 390
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 4.272479564032698,
|
2743 |
+
"grad_norm": 0.19913600385189056,
|
2744 |
+
"learning_rate": 4.4444444444444447e-05,
|
2745 |
+
"loss": 6.181,
|
2746 |
+
"step": 391
|
2747 |
+
},
|
2748 |
+
{
|
2749 |
+
"epoch": 4.283378746594005,
|
2750 |
+
"grad_norm": 0.18423688411712646,
|
2751 |
+
"learning_rate": 4.4040404040404044e-05,
|
2752 |
+
"loss": 6.1798,
|
2753 |
+
"step": 392
|
2754 |
+
},
|
2755 |
+
{
|
2756 |
+
"epoch": 4.294277929155314,
|
2757 |
+
"grad_norm": 0.17174512147903442,
|
2758 |
+
"learning_rate": 4.3636363636363636e-05,
|
2759 |
+
"loss": 6.2697,
|
2760 |
+
"step": 393
|
2761 |
+
},
|
2762 |
+
{
|
2763 |
+
"epoch": 4.305177111716621,
|
2764 |
+
"grad_norm": 0.1219327375292778,
|
2765 |
+
"learning_rate": 4.3232323232323234e-05,
|
2766 |
+
"loss": 6.1861,
|
2767 |
+
"step": 394
|
2768 |
+
},
|
2769 |
+
{
|
2770 |
+
"epoch": 4.316076294277929,
|
2771 |
+
"grad_norm": 0.5196271538734436,
|
2772 |
+
"learning_rate": 4.282828282828283e-05,
|
2773 |
+
"loss": 6.5272,
|
2774 |
+
"step": 395
|
2775 |
+
},
|
2776 |
+
{
|
2777 |
+
"epoch": 4.3269754768392374,
|
2778 |
+
"grad_norm": 0.17318467795848846,
|
2779 |
+
"learning_rate": 4.242424242424243e-05,
|
2780 |
+
"loss": 6.1996,
|
2781 |
+
"step": 396
|
2782 |
+
},
|
2783 |
+
{
|
2784 |
+
"epoch": 4.337874659400545,
|
2785 |
+
"grad_norm": 0.40889430046081543,
|
2786 |
+
"learning_rate": 4.202020202020202e-05,
|
2787 |
+
"loss": 6.908,
|
2788 |
+
"step": 397
|
2789 |
+
},
|
2790 |
+
{
|
2791 |
+
"epoch": 4.348773841961853,
|
2792 |
+
"grad_norm": 0.18795502185821533,
|
2793 |
+
"learning_rate": 4.161616161616162e-05,
|
2794 |
+
"loss": 6.2444,
|
2795 |
+
"step": 398
|
2796 |
+
},
|
2797 |
+
{
|
2798 |
+
"epoch": 4.359673024523161,
|
2799 |
+
"grad_norm": 0.1756502389907837,
|
2800 |
+
"learning_rate": 4.1212121212121216e-05,
|
2801 |
+
"loss": 6.1558,
|
2802 |
+
"step": 399
|
2803 |
+
},
|
2804 |
+
{
|
2805 |
+
"epoch": 4.370572207084469,
|
2806 |
+
"grad_norm": 0.20153924822807312,
|
2807 |
+
"learning_rate": 4.0808080808080814e-05,
|
2808 |
+
"loss": 6.1704,
|
2809 |
+
"step": 400
|
2810 |
+
},
|
2811 |
+
{
|
2812 |
+
"epoch": 4.381471389645776,
|
2813 |
+
"grad_norm": 0.14148367941379547,
|
2814 |
+
"learning_rate": 4.0404040404040405e-05,
|
2815 |
+
"loss": 6.1617,
|
2816 |
+
"step": 401
|
2817 |
+
},
|
2818 |
+
{
|
2819 |
+
"epoch": 4.392370572207085,
|
2820 |
+
"grad_norm": 0.16998320817947388,
|
2821 |
+
"learning_rate": 4e-05,
|
2822 |
+
"loss": 6.1476,
|
2823 |
+
"step": 402
|
2824 |
+
},
|
2825 |
+
{
|
2826 |
+
"epoch": 4.4032697547683926,
|
2827 |
+
"grad_norm": 0.23891212046146393,
|
2828 |
+
"learning_rate": 3.9595959595959594e-05,
|
2829 |
+
"loss": 6.3065,
|
2830 |
+
"step": 403
|
2831 |
+
},
|
2832 |
+
{
|
2833 |
+
"epoch": 4.4141689373297,
|
2834 |
+
"grad_norm": 0.17936837673187256,
|
2835 |
+
"learning_rate": 3.91919191919192e-05,
|
2836 |
+
"loss": 6.141,
|
2837 |
+
"step": 404
|
2838 |
+
},
|
2839 |
+
{
|
2840 |
+
"epoch": 4.425068119891008,
|
2841 |
+
"grad_norm": 0.13204631209373474,
|
2842 |
+
"learning_rate": 3.878787878787879e-05,
|
2843 |
+
"loss": 6.1693,
|
2844 |
+
"step": 405
|
2845 |
+
},
|
2846 |
+
{
|
2847 |
+
"epoch": 4.435967302452316,
|
2848 |
+
"grad_norm": 0.23752065002918243,
|
2849 |
+
"learning_rate": 3.838383838383838e-05,
|
2850 |
+
"loss": 6.1486,
|
2851 |
+
"step": 406
|
2852 |
+
},
|
2853 |
+
{
|
2854 |
+
"epoch": 4.446866485013624,
|
2855 |
+
"grad_norm": 0.13474120199680328,
|
2856 |
+
"learning_rate": 3.797979797979798e-05,
|
2857 |
+
"loss": 6.1781,
|
2858 |
+
"step": 407
|
2859 |
+
},
|
2860 |
+
{
|
2861 |
+
"epoch": 4.4577656675749315,
|
2862 |
+
"grad_norm": 0.639192521572113,
|
2863 |
+
"learning_rate": 3.757575757575758e-05,
|
2864 |
+
"loss": 7.1072,
|
2865 |
+
"step": 408
|
2866 |
+
},
|
2867 |
+
{
|
2868 |
+
"epoch": 4.46866485013624,
|
2869 |
+
"grad_norm": 0.31699126958847046,
|
2870 |
+
"learning_rate": 3.7171717171717175e-05,
|
2871 |
+
"loss": 6.1528,
|
2872 |
+
"step": 409
|
2873 |
+
},
|
2874 |
+
{
|
2875 |
+
"epoch": 4.479564032697548,
|
2876 |
+
"grad_norm": 0.14006993174552917,
|
2877 |
+
"learning_rate": 3.6767676767676766e-05,
|
2878 |
+
"loss": 6.1284,
|
2879 |
+
"step": 410
|
2880 |
+
},
|
2881 |
+
{
|
2882 |
+
"epoch": 4.490463215258855,
|
2883 |
+
"grad_norm": 0.18349085748195648,
|
2884 |
+
"learning_rate": 3.6363636363636364e-05,
|
2885 |
+
"loss": 6.4731,
|
2886 |
+
"step": 411
|
2887 |
+
},
|
2888 |
+
{
|
2889 |
+
"epoch": 4.501362397820164,
|
2890 |
+
"grad_norm": 0.16099974513053894,
|
2891 |
+
"learning_rate": 3.595959595959596e-05,
|
2892 |
+
"loss": 6.1471,
|
2893 |
+
"step": 412
|
2894 |
+
},
|
2895 |
+
{
|
2896 |
+
"epoch": 4.512261580381471,
|
2897 |
+
"grad_norm": 0.17679904401302338,
|
2898 |
+
"learning_rate": 3.555555555555556e-05,
|
2899 |
+
"loss": 6.1535,
|
2900 |
+
"step": 413
|
2901 |
+
},
|
2902 |
+
{
|
2903 |
+
"epoch": 4.523160762942779,
|
2904 |
+
"grad_norm": 0.16737085580825806,
|
2905 |
+
"learning_rate": 3.515151515151515e-05,
|
2906 |
+
"loss": 6.1319,
|
2907 |
+
"step": 414
|
2908 |
+
},
|
2909 |
+
{
|
2910 |
+
"epoch": 4.5340599455040875,
|
2911 |
+
"grad_norm": 0.11516544967889786,
|
2912 |
+
"learning_rate": 3.474747474747475e-05,
|
2913 |
+
"loss": 6.1876,
|
2914 |
+
"step": 415
|
2915 |
+
},
|
2916 |
+
{
|
2917 |
+
"epoch": 4.544959128065395,
|
2918 |
+
"grad_norm": 0.13226546347141266,
|
2919 |
+
"learning_rate": 3.434343434343435e-05,
|
2920 |
+
"loss": 6.1415,
|
2921 |
+
"step": 416
|
2922 |
+
},
|
2923 |
+
{
|
2924 |
+
"epoch": 4.555858310626703,
|
2925 |
+
"grad_norm": 0.5673292875289917,
|
2926 |
+
"learning_rate": 3.3939393939393945e-05,
|
2927 |
+
"loss": 6.1813,
|
2928 |
+
"step": 417
|
2929 |
+
},
|
2930 |
+
{
|
2931 |
+
"epoch": 4.566757493188011,
|
2932 |
+
"grad_norm": 0.19020290672779083,
|
2933 |
+
"learning_rate": 3.3535353535353536e-05,
|
2934 |
+
"loss": 6.1366,
|
2935 |
+
"step": 418
|
2936 |
+
},
|
2937 |
+
{
|
2938 |
+
"epoch": 4.577656675749319,
|
2939 |
+
"grad_norm": 0.1316557228565216,
|
2940 |
+
"learning_rate": 3.3131313131313134e-05,
|
2941 |
+
"loss": 6.1256,
|
2942 |
+
"step": 419
|
2943 |
+
},
|
2944 |
+
{
|
2945 |
+
"epoch": 4.5885558583106265,
|
2946 |
+
"grad_norm": 0.18218891322612762,
|
2947 |
+
"learning_rate": 3.272727272727273e-05,
|
2948 |
+
"loss": 6.1428,
|
2949 |
+
"step": 420
|
2950 |
+
},
|
2951 |
+
{
|
2952 |
+
"epoch": 4.599455040871934,
|
2953 |
+
"grad_norm": 0.16241154074668884,
|
2954 |
+
"learning_rate": 3.232323232323233e-05,
|
2955 |
+
"loss": 6.3538,
|
2956 |
+
"step": 421
|
2957 |
+
},
|
2958 |
+
{
|
2959 |
+
"epoch": 4.610354223433243,
|
2960 |
+
"grad_norm": 0.24633854627609253,
|
2961 |
+
"learning_rate": 3.191919191919192e-05,
|
2962 |
+
"loss": 6.1339,
|
2963 |
+
"step": 422
|
2964 |
+
},
|
2965 |
+
{
|
2966 |
+
"epoch": 4.62125340599455,
|
2967 |
+
"grad_norm": 0.13929039239883423,
|
2968 |
+
"learning_rate": 3.151515151515151e-05,
|
2969 |
+
"loss": 6.1458,
|
2970 |
+
"step": 423
|
2971 |
+
},
|
2972 |
+
{
|
2973 |
+
"epoch": 4.632152588555858,
|
2974 |
+
"grad_norm": 0.18816447257995605,
|
2975 |
+
"learning_rate": 3.111111111111111e-05,
|
2976 |
+
"loss": 6.2432,
|
2977 |
+
"step": 424
|
2978 |
+
},
|
2979 |
+
{
|
2980 |
+
"epoch": 4.643051771117166,
|
2981 |
+
"grad_norm": 0.20620077848434448,
|
2982 |
+
"learning_rate": 3.070707070707071e-05,
|
2983 |
+
"loss": 6.156,
|
2984 |
+
"step": 425
|
2985 |
+
},
|
2986 |
+
{
|
2987 |
+
"epoch": 4.653950953678474,
|
2988 |
+
"grad_norm": 0.20312055945396423,
|
2989 |
+
"learning_rate": 3.0303030303030306e-05,
|
2990 |
+
"loss": 6.1537,
|
2991 |
+
"step": 426
|
2992 |
+
},
|
2993 |
+
{
|
2994 |
+
"epoch": 4.664850136239782,
|
2995 |
+
"grad_norm": 0.12666474282741547,
|
2996 |
+
"learning_rate": 2.98989898989899e-05,
|
2997 |
+
"loss": 6.2204,
|
2998 |
+
"step": 427
|
2999 |
+
},
|
3000 |
+
{
|
3001 |
+
"epoch": 4.67574931880109,
|
3002 |
+
"grad_norm": 0.41980618238449097,
|
3003 |
+
"learning_rate": 2.9494949494949498e-05,
|
3004 |
+
"loss": 6.5506,
|
3005 |
+
"step": 428
|
3006 |
+
},
|
3007 |
+
{
|
3008 |
+
"epoch": 4.686648501362398,
|
3009 |
+
"grad_norm": 0.24480164051055908,
|
3010 |
+
"learning_rate": 2.909090909090909e-05,
|
3011 |
+
"loss": 6.1571,
|
3012 |
+
"step": 429
|
3013 |
+
},
|
3014 |
+
{
|
3015 |
+
"epoch": 4.697547683923705,
|
3016 |
+
"grad_norm": 0.2902083098888397,
|
3017 |
+
"learning_rate": 2.868686868686869e-05,
|
3018 |
+
"loss": 6.1515,
|
3019 |
+
"step": 430
|
3020 |
+
},
|
3021 |
+
{
|
3022 |
+
"epoch": 4.708446866485014,
|
3023 |
+
"grad_norm": 0.11313210427761078,
|
3024 |
+
"learning_rate": 2.8282828282828282e-05,
|
3025 |
+
"loss": 6.203,
|
3026 |
+
"step": 431
|
3027 |
+
},
|
3028 |
+
{
|
3029 |
+
"epoch": 4.7193460490463215,
|
3030 |
+
"grad_norm": 0.14203494787216187,
|
3031 |
+
"learning_rate": 2.7878787878787883e-05,
|
3032 |
+
"loss": 6.1618,
|
3033 |
+
"step": 432
|
3034 |
+
},
|
3035 |
+
{
|
3036 |
+
"epoch": 4.730245231607629,
|
3037 |
+
"grad_norm": 0.13528816401958466,
|
3038 |
+
"learning_rate": 2.7474747474747474e-05,
|
3039 |
+
"loss": 6.3833,
|
3040 |
+
"step": 433
|
3041 |
+
},
|
3042 |
+
{
|
3043 |
+
"epoch": 4.741144414168938,
|
3044 |
+
"grad_norm": 0.11331304907798767,
|
3045 |
+
"learning_rate": 2.7070707070707075e-05,
|
3046 |
+
"loss": 6.1472,
|
3047 |
+
"step": 434
|
3048 |
+
},
|
3049 |
+
{
|
3050 |
+
"epoch": 4.752043596730245,
|
3051 |
+
"grad_norm": 0.11952386051416397,
|
3052 |
+
"learning_rate": 2.6666666666666667e-05,
|
3053 |
+
"loss": 6.1477,
|
3054 |
+
"step": 435
|
3055 |
+
},
|
3056 |
+
{
|
3057 |
+
"epoch": 4.762942779291553,
|
3058 |
+
"grad_norm": 0.22013674676418304,
|
3059 |
+
"learning_rate": 2.6262626262626268e-05,
|
3060 |
+
"loss": 6.1598,
|
3061 |
+
"step": 436
|
3062 |
+
},
|
3063 |
+
{
|
3064 |
+
"epoch": 4.773841961852861,
|
3065 |
+
"grad_norm": 0.10620447248220444,
|
3066 |
+
"learning_rate": 2.585858585858586e-05,
|
3067 |
+
"loss": 6.2546,
|
3068 |
+
"step": 437
|
3069 |
+
},
|
3070 |
+
{
|
3071 |
+
"epoch": 4.784741144414169,
|
3072 |
+
"grad_norm": 0.1305541694164276,
|
3073 |
+
"learning_rate": 2.5454545454545454e-05,
|
3074 |
+
"loss": 6.2223,
|
3075 |
+
"step": 438
|
3076 |
+
},
|
3077 |
+
{
|
3078 |
+
"epoch": 4.795640326975477,
|
3079 |
+
"grad_norm": 0.14448855817317963,
|
3080 |
+
"learning_rate": 2.505050505050505e-05,
|
3081 |
+
"loss": 6.1602,
|
3082 |
+
"step": 439
|
3083 |
+
},
|
3084 |
+
{
|
3085 |
+
"epoch": 4.806539509536785,
|
3086 |
+
"grad_norm": 0.1863837093114853,
|
3087 |
+
"learning_rate": 2.464646464646465e-05,
|
3088 |
+
"loss": 6.145,
|
3089 |
+
"step": 440
|
3090 |
+
},
|
3091 |
+
{
|
3092 |
+
"epoch": 4.817438692098093,
|
3093 |
+
"grad_norm": 0.47183990478515625,
|
3094 |
+
"learning_rate": 2.4242424242424244e-05,
|
3095 |
+
"loss": 6.3824,
|
3096 |
+
"step": 441
|
3097 |
+
},
|
3098 |
+
{
|
3099 |
+
"epoch": 4.8283378746594,
|
3100 |
+
"grad_norm": 0.18477211892604828,
|
3101 |
+
"learning_rate": 2.3838383838383842e-05,
|
3102 |
+
"loss": 6.1644,
|
3103 |
+
"step": 442
|
3104 |
+
},
|
3105 |
+
{
|
3106 |
+
"epoch": 4.839237057220709,
|
3107 |
+
"grad_norm": 0.36106404662132263,
|
3108 |
+
"learning_rate": 2.3434343434343436e-05,
|
3109 |
+
"loss": 6.1992,
|
3110 |
+
"step": 443
|
3111 |
+
},
|
3112 |
+
{
|
3113 |
+
"epoch": 4.8501362397820165,
|
3114 |
+
"grad_norm": 0.11133147776126862,
|
3115 |
+
"learning_rate": 2.3030303030303034e-05,
|
3116 |
+
"loss": 6.1298,
|
3117 |
+
"step": 444
|
3118 |
+
},
|
3119 |
+
{
|
3120 |
+
"epoch": 4.861035422343324,
|
3121 |
+
"grad_norm": 0.4021960198879242,
|
3122 |
+
"learning_rate": 2.262626262626263e-05,
|
3123 |
+
"loss": 6.2763,
|
3124 |
+
"step": 445
|
3125 |
+
},
|
3126 |
+
{
|
3127 |
+
"epoch": 4.871934604904633,
|
3128 |
+
"grad_norm": 0.14010433852672577,
|
3129 |
+
"learning_rate": 2.2222222222222223e-05,
|
3130 |
+
"loss": 6.1838,
|
3131 |
+
"step": 446
|
3132 |
+
},
|
3133 |
+
{
|
3134 |
+
"epoch": 4.88283378746594,
|
3135 |
+
"grad_norm": 0.45312055945396423,
|
3136 |
+
"learning_rate": 2.1818181818181818e-05,
|
3137 |
+
"loss": 6.66,
|
3138 |
+
"step": 447
|
3139 |
+
},
|
3140 |
+
{
|
3141 |
+
"epoch": 4.893732970027248,
|
3142 |
+
"grad_norm": 0.1600738912820816,
|
3143 |
+
"learning_rate": 2.1414141414141416e-05,
|
3144 |
+
"loss": 6.1646,
|
3145 |
+
"step": 448
|
3146 |
+
},
|
3147 |
+
{
|
3148 |
+
"epoch": 4.904632152588556,
|
3149 |
+
"grad_norm": 0.11380810290575027,
|
3150 |
+
"learning_rate": 2.101010101010101e-05,
|
3151 |
+
"loss": 6.1415,
|
3152 |
+
"step": 449
|
3153 |
+
},
|
3154 |
+
{
|
3155 |
+
"epoch": 4.915531335149864,
|
3156 |
+
"grad_norm": 0.14316502213478088,
|
3157 |
+
"learning_rate": 2.0606060606060608e-05,
|
3158 |
+
"loss": 6.1984,
|
3159 |
+
"step": 450
|
3160 |
+
},
|
3161 |
+
{
|
3162 |
+
"epoch": 4.926430517711172,
|
3163 |
+
"grad_norm": 0.2457677721977234,
|
3164 |
+
"learning_rate": 2.0202020202020203e-05,
|
3165 |
+
"loss": 6.1522,
|
3166 |
+
"step": 451
|
3167 |
+
},
|
3168 |
+
{
|
3169 |
+
"epoch": 4.937329700272479,
|
3170 |
+
"grad_norm": 0.15555907785892487,
|
3171 |
+
"learning_rate": 1.9797979797979797e-05,
|
3172 |
+
"loss": 6.1647,
|
3173 |
+
"step": 452
|
3174 |
+
},
|
3175 |
+
{
|
3176 |
+
"epoch": 4.948228882833788,
|
3177 |
+
"grad_norm": 0.12678752839565277,
|
3178 |
+
"learning_rate": 1.9393939393939395e-05,
|
3179 |
+
"loss": 6.1495,
|
3180 |
+
"step": 453
|
3181 |
+
},
|
3182 |
+
{
|
3183 |
+
"epoch": 4.959128065395095,
|
3184 |
+
"grad_norm": 0.1315479725599289,
|
3185 |
+
"learning_rate": 1.898989898989899e-05,
|
3186 |
+
"loss": 6.1946,
|
3187 |
+
"step": 454
|
3188 |
+
},
|
3189 |
+
{
|
3190 |
+
"epoch": 4.970027247956403,
|
3191 |
+
"grad_norm": 0.22341807186603546,
|
3192 |
+
"learning_rate": 1.8585858585858588e-05,
|
3193 |
+
"loss": 6.14,
|
3194 |
+
"step": 455
|
3195 |
+
},
|
3196 |
+
{
|
3197 |
+
"epoch": 4.9809264305177114,
|
3198 |
+
"grad_norm": 0.397432804107666,
|
3199 |
+
"learning_rate": 1.8181818181818182e-05,
|
3200 |
+
"loss": 6.1562,
|
3201 |
+
"step": 456
|
3202 |
+
},
|
3203 |
+
{
|
3204 |
+
"epoch": 4.991825613079019,
|
3205 |
+
"grad_norm": 0.16656984388828278,
|
3206 |
+
"learning_rate": 1.777777777777778e-05,
|
3207 |
+
"loss": 6.1628,
|
3208 |
+
"step": 457
|
3209 |
+
},
|
3210 |
+
{
|
3211 |
+
"epoch": 5.005449591280654,
|
3212 |
+
"grad_norm": 0.47680985927581787,
|
3213 |
+
"learning_rate": 1.7373737373737375e-05,
|
3214 |
+
"loss": 9.2237,
|
3215 |
+
"step": 458
|
3216 |
+
},
|
3217 |
+
{
|
3218 |
+
"epoch": 5.016348773841962,
|
3219 |
+
"grad_norm": 0.13037891685962677,
|
3220 |
+
"learning_rate": 1.6969696969696972e-05,
|
3221 |
+
"loss": 6.1438,
|
3222 |
+
"step": 459
|
3223 |
+
},
|
3224 |
+
{
|
3225 |
+
"epoch": 5.0272479564032695,
|
3226 |
+
"grad_norm": 0.12159968167543411,
|
3227 |
+
"learning_rate": 1.6565656565656567e-05,
|
3228 |
+
"loss": 6.1595,
|
3229 |
+
"step": 460
|
3230 |
+
},
|
3231 |
+
{
|
3232 |
+
"epoch": 5.038147138964578,
|
3233 |
+
"grad_norm": 0.11064036190509796,
|
3234 |
+
"learning_rate": 1.6161616161616165e-05,
|
3235 |
+
"loss": 6.1593,
|
3236 |
+
"step": 461
|
3237 |
+
},
|
3238 |
+
{
|
3239 |
+
"epoch": 5.049046321525886,
|
3240 |
+
"grad_norm": 0.1583862155675888,
|
3241 |
+
"learning_rate": 1.5757575757575756e-05,
|
3242 |
+
"loss": 6.1594,
|
3243 |
+
"step": 462
|
3244 |
+
},
|
3245 |
+
{
|
3246 |
+
"epoch": 5.059945504087193,
|
3247 |
+
"grad_norm": 0.2619314193725586,
|
3248 |
+
"learning_rate": 1.5353535353535354e-05,
|
3249 |
+
"loss": 6.3912,
|
3250 |
+
"step": 463
|
3251 |
+
},
|
3252 |
+
{
|
3253 |
+
"epoch": 5.070844686648502,
|
3254 |
+
"grad_norm": 0.10678429901599884,
|
3255 |
+
"learning_rate": 1.494949494949495e-05,
|
3256 |
+
"loss": 6.1448,
|
3257 |
+
"step": 464
|
3258 |
+
},
|
3259 |
+
{
|
3260 |
+
"epoch": 5.081743869209809,
|
3261 |
+
"grad_norm": 0.24632836878299713,
|
3262 |
+
"learning_rate": 1.4545454545454545e-05,
|
3263 |
+
"loss": 6.1786,
|
3264 |
+
"step": 465
|
3265 |
+
},
|
3266 |
+
{
|
3267 |
+
"epoch": 5.092643051771117,
|
3268 |
+
"grad_norm": 0.24659158289432526,
|
3269 |
+
"learning_rate": 1.4141414141414141e-05,
|
3270 |
+
"loss": 6.2495,
|
3271 |
+
"step": 466
|
3272 |
+
},
|
3273 |
+
{
|
3274 |
+
"epoch": 5.1035422343324255,
|
3275 |
+
"grad_norm": 0.10519186407327652,
|
3276 |
+
"learning_rate": 1.3737373737373737e-05,
|
3277 |
+
"loss": 6.1399,
|
3278 |
+
"step": 467
|
3279 |
+
},
|
3280 |
+
{
|
3281 |
+
"epoch": 5.114441416893733,
|
3282 |
+
"grad_norm": 0.30278512835502625,
|
3283 |
+
"learning_rate": 1.3333333333333333e-05,
|
3284 |
+
"loss": 6.1993,
|
3285 |
+
"step": 468
|
3286 |
+
},
|
3287 |
+
{
|
3288 |
+
"epoch": 5.125340599455041,
|
3289 |
+
"grad_norm": 0.41121378540992737,
|
3290 |
+
"learning_rate": 1.292929292929293e-05,
|
3291 |
+
"loss": 6.3494,
|
3292 |
+
"step": 469
|
3293 |
+
},
|
3294 |
+
{
|
3295 |
+
"epoch": 5.136239782016348,
|
3296 |
+
"grad_norm": 0.2749239504337311,
|
3297 |
+
"learning_rate": 1.2525252525252526e-05,
|
3298 |
+
"loss": 6.1745,
|
3299 |
+
"step": 470
|
3300 |
+
},
|
3301 |
+
{
|
3302 |
+
"epoch": 5.147138964577657,
|
3303 |
+
"grad_norm": 0.3106517791748047,
|
3304 |
+
"learning_rate": 1.2121212121212122e-05,
|
3305 |
+
"loss": 6.2632,
|
3306 |
+
"step": 471
|
3307 |
+
},
|
3308 |
+
{
|
3309 |
+
"epoch": 5.1580381471389645,
|
3310 |
+
"grad_norm": 0.19723156094551086,
|
3311 |
+
"learning_rate": 1.1717171717171718e-05,
|
3312 |
+
"loss": 6.1638,
|
3313 |
+
"step": 472
|
3314 |
+
},
|
3315 |
+
{
|
3316 |
+
"epoch": 5.168937329700272,
|
3317 |
+
"grad_norm": 0.38709595799446106,
|
3318 |
+
"learning_rate": 1.1313131313131314e-05,
|
3319 |
+
"loss": 6.3415,
|
3320 |
+
"step": 473
|
3321 |
+
},
|
3322 |
+
{
|
3323 |
+
"epoch": 5.179836512261581,
|
3324 |
+
"grad_norm": 0.1426631212234497,
|
3325 |
+
"learning_rate": 1.0909090909090909e-05,
|
3326 |
+
"loss": 6.3154,
|
3327 |
+
"step": 474
|
3328 |
+
},
|
3329 |
+
{
|
3330 |
+
"epoch": 5.190735694822888,
|
3331 |
+
"grad_norm": 0.23347443342208862,
|
3332 |
+
"learning_rate": 1.0505050505050505e-05,
|
3333 |
+
"loss": 6.1717,
|
3334 |
+
"step": 475
|
3335 |
+
},
|
3336 |
+
{
|
3337 |
+
"epoch": 5.201634877384196,
|
3338 |
+
"grad_norm": 0.09223368018865585,
|
3339 |
+
"learning_rate": 1.0101010101010101e-05,
|
3340 |
+
"loss": 6.1606,
|
3341 |
+
"step": 476
|
3342 |
+
},
|
3343 |
+
{
|
3344 |
+
"epoch": 5.212534059945504,
|
3345 |
+
"grad_norm": 0.1321372389793396,
|
3346 |
+
"learning_rate": 9.696969696969698e-06,
|
3347 |
+
"loss": 6.2569,
|
3348 |
+
"step": 477
|
3349 |
+
},
|
3350 |
+
{
|
3351 |
+
"epoch": 5.223433242506812,
|
3352 |
+
"grad_norm": 0.14801448583602905,
|
3353 |
+
"learning_rate": 9.292929292929294e-06,
|
3354 |
+
"loss": 6.1669,
|
3355 |
+
"step": 478
|
3356 |
+
},
|
3357 |
+
{
|
3358 |
+
"epoch": 5.23433242506812,
|
3359 |
+
"grad_norm": 0.20771123468875885,
|
3360 |
+
"learning_rate": 8.88888888888889e-06,
|
3361 |
+
"loss": 6.173,
|
3362 |
+
"step": 479
|
3363 |
+
},
|
3364 |
+
{
|
3365 |
+
"epoch": 5.245231607629428,
|
3366 |
+
"grad_norm": 0.12525993585586548,
|
3367 |
+
"learning_rate": 8.484848484848486e-06,
|
3368 |
+
"loss": 6.171,
|
3369 |
+
"step": 480
|
3370 |
+
},
|
3371 |
+
{
|
3372 |
+
"epoch": 5.256130790190736,
|
3373 |
+
"grad_norm": 0.12884493172168732,
|
3374 |
+
"learning_rate": 8.080808080808082e-06,
|
3375 |
+
"loss": 6.1318,
|
3376 |
+
"step": 481
|
3377 |
+
},
|
3378 |
+
{
|
3379 |
+
"epoch": 5.267029972752043,
|
3380 |
+
"grad_norm": 0.1414600908756256,
|
3381 |
+
"learning_rate": 7.676767676767677e-06,
|
3382 |
+
"loss": 6.1838,
|
3383 |
+
"step": 482
|
3384 |
+
},
|
3385 |
+
{
|
3386 |
+
"epoch": 5.277929155313352,
|
3387 |
+
"grad_norm": 0.25564873218536377,
|
3388 |
+
"learning_rate": 7.272727272727272e-06,
|
3389 |
+
"loss": 6.1501,
|
3390 |
+
"step": 483
|
3391 |
+
},
|
3392 |
+
{
|
3393 |
+
"epoch": 5.2888283378746594,
|
3394 |
+
"grad_norm": 0.3402186334133148,
|
3395 |
+
"learning_rate": 6.8686868686868685e-06,
|
3396 |
+
"loss": 6.855,
|
3397 |
+
"step": 484
|
3398 |
+
},
|
3399 |
+
{
|
3400 |
+
"epoch": 5.299727520435967,
|
3401 |
+
"grad_norm": 0.21217402815818787,
|
3402 |
+
"learning_rate": 6.464646464646465e-06,
|
3403 |
+
"loss": 6.1712,
|
3404 |
+
"step": 485
|
3405 |
+
},
|
3406 |
+
{
|
3407 |
+
"epoch": 5.310626702997276,
|
3408 |
+
"grad_norm": 0.20217765867710114,
|
3409 |
+
"learning_rate": 6.060606060606061e-06,
|
3410 |
+
"loss": 6.1735,
|
3411 |
+
"step": 486
|
3412 |
+
},
|
3413 |
+
{
|
3414 |
+
"epoch": 5.321525885558583,
|
3415 |
+
"grad_norm": 0.14054284989833832,
|
3416 |
+
"learning_rate": 5.656565656565657e-06,
|
3417 |
+
"loss": 6.1637,
|
3418 |
+
"step": 487
|
3419 |
+
},
|
3420 |
+
{
|
3421 |
+
"epoch": 5.332425068119891,
|
3422 |
+
"grad_norm": 0.22656294703483582,
|
3423 |
+
"learning_rate": 5.2525252525252526e-06,
|
3424 |
+
"loss": 6.1563,
|
3425 |
+
"step": 488
|
3426 |
+
},
|
3427 |
+
{
|
3428 |
+
"epoch": 5.343324250681199,
|
3429 |
+
"grad_norm": 0.10825368016958237,
|
3430 |
+
"learning_rate": 4.848484848484849e-06,
|
3431 |
+
"loss": 6.202,
|
3432 |
+
"step": 489
|
3433 |
+
},
|
3434 |
+
{
|
3435 |
+
"epoch": 5.354223433242507,
|
3436 |
+
"grad_norm": 0.17495879530906677,
|
3437 |
+
"learning_rate": 4.444444444444445e-06,
|
3438 |
+
"loss": 6.2115,
|
3439 |
+
"step": 490
|
3440 |
+
},
|
3441 |
+
{
|
3442 |
+
"epoch": 5.3651226158038146,
|
3443 |
+
"grad_norm": 0.10381829738616943,
|
3444 |
+
"learning_rate": 4.040404040404041e-06,
|
3445 |
+
"loss": 6.1697,
|
3446 |
+
"step": 491
|
3447 |
+
},
|
3448 |
+
{
|
3449 |
+
"epoch": 5.376021798365123,
|
3450 |
+
"grad_norm": 0.1631442904472351,
|
3451 |
+
"learning_rate": 3.636363636363636e-06,
|
3452 |
+
"loss": 6.1498,
|
3453 |
+
"step": 492
|
3454 |
+
},
|
3455 |
+
{
|
3456 |
+
"epoch": 5.386920980926431,
|
3457 |
+
"grad_norm": 0.13070239126682281,
|
3458 |
+
"learning_rate": 3.2323232323232324e-06,
|
3459 |
+
"loss": 6.1829,
|
3460 |
+
"step": 493
|
3461 |
+
},
|
3462 |
+
{
|
3463 |
+
"epoch": 5.397820163487738,
|
3464 |
+
"grad_norm": 0.13861213624477386,
|
3465 |
+
"learning_rate": 2.8282828282828286e-06,
|
3466 |
+
"loss": 6.1574,
|
3467 |
+
"step": 494
|
3468 |
+
},
|
3469 |
+
{
|
3470 |
+
"epoch": 5.408719346049046,
|
3471 |
+
"grad_norm": 0.24785035848617554,
|
3472 |
+
"learning_rate": 2.4242424242424244e-06,
|
3473 |
+
"loss": 6.5561,
|
3474 |
+
"step": 495
|
3475 |
+
},
|
3476 |
+
{
|
3477 |
+
"epoch": 5.419618528610354,
|
3478 |
+
"grad_norm": 0.12529440224170685,
|
3479 |
+
"learning_rate": 2.0202020202020206e-06,
|
3480 |
+
"loss": 6.168,
|
3481 |
+
"step": 496
|
3482 |
+
},
|
3483 |
+
{
|
3484 |
+
"epoch": 5.430517711171662,
|
3485 |
+
"grad_norm": 0.14261850714683533,
|
3486 |
+
"learning_rate": 1.6161616161616162e-06,
|
3487 |
+
"loss": 6.1755,
|
3488 |
+
"step": 497
|
3489 |
+
},
|
3490 |
+
{
|
3491 |
+
"epoch": 5.44141689373297,
|
3492 |
+
"grad_norm": 0.3609119951725006,
|
3493 |
+
"learning_rate": 1.2121212121212122e-06,
|
3494 |
+
"loss": 6.1591,
|
3495 |
+
"step": 498
|
3496 |
+
},
|
3497 |
+
{
|
3498 |
+
"epoch": 5.452316076294278,
|
3499 |
+
"grad_norm": 0.19529031217098236,
|
3500 |
+
"learning_rate": 8.080808080808081e-07,
|
3501 |
+
"loss": 6.2801,
|
3502 |
+
"step": 499
|
3503 |
+
},
|
3504 |
+
{
|
3505 |
+
"epoch": 5.463215258855586,
|
3506 |
+
"grad_norm": 0.1783263236284256,
|
3507 |
+
"learning_rate": 4.0404040404040405e-07,
|
3508 |
+
"loss": 6.1468,
|
3509 |
+
"step": 500
|
3510 |
+
}
|
3511 |
+
],
|
3512 |
+
"logging_steps": 1,
|
3513 |
+
"max_steps": 500,
|
3514 |
+
"num_input_tokens_seen": 0,
|
3515 |
+
"num_train_epochs": 6,
|
3516 |
+
"save_steps": 500,
|
3517 |
+
"stateful_callbacks": {
|
3518 |
+
"TrainerControl": {
|
3519 |
+
"args": {
|
3520 |
+
"should_epoch_stop": false,
|
3521 |
+
"should_evaluate": false,
|
3522 |
+
"should_log": false,
|
3523 |
+
"should_save": true,
|
3524 |
+
"should_training_stop": true
|
3525 |
+
},
|
3526 |
+
"attributes": {}
|
3527 |
+
}
|
3528 |
+
},
|
3529 |
+
"total_flos": 1.2096532119552e+16,
|
3530 |
+
"train_batch_size": 2,
|
3531 |
+
"trial_name": null,
|
3532 |
+
"trial_params": null
|
3533 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4eb371b0917bd726d2b675ee72899f4e8d8c4c68b7d92fa0ceb8e6b355378bc0
|
3 |
+
size 5496
|