Hugging Face's logo

NLPForUA
/
Llama-3.1-8B-Instruct-zno-cot

Text Generation
PEFT
Safetensors
Ukrainian
conversational
Model card Files Community
1
niksyromyatnikov commited on
Commit
b97030e
·
verified ·
1 Parent(s): ad7836b

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. .ipynb_checkpoints/adapter_config-checkpoint.json +37 -0
  3. README.md +202 -3
  4. adapter_config.json +37 -0
  5. adapter_model.safetensors +3 -0
  6. optimizer.pt +3 -0
  7. rng_state.pth +3 -0
  8. scheduler.pt +3 -0
  9. special_tokens_map.json +17 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +2068 -0
  12. trainer_state.json +3089 -0
  13. 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
.ipynb_checkpoints/adapter_config-checkpoint.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "k_proj",
27
+ "q_proj",
28
+ "o_proj",
29
+ "down_proj",
30
+ "gate_proj",
31
+ "v_proj",
32
+ "up_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
README.md CHANGED
@@ -1,3 +1,202 @@
1
- ---
2
- license: llama3.1
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.14.0
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 16,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "k_proj",
27
+ "q_proj",
28
+ "o_proj",
29
+ "down_proj",
30
+ "gate_proj",
31
+ "v_proj",
32
+ "up_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca30f3adfdddbe98ad4d159606254569341c2c243d08b1cf16bd73f06c7b6487
3
+ size 167832240
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4eee33c3c607d9910d6d3f5754fb17adbe52120b3c641618d6d217bb25ef063
3
+ size 85723732
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0397b4ffb0f16955f277399bef39c10f95774ef11bddfd57a089a7f402b9bac5
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:badd16cd61c5da6553a58c97808f965dafa25ed2956ff0f9478782b93dce50d0
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|finetune_right_pad_id|>"
17
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89e7f2180ba598b166b631d64b2b2ba1d4fad8977a4c716b907c0eb2903f56a3
3
+ size 17210019
tokenizer_config.json ADDED
@@ -0,0 +1,2068 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "128000": {
6
+ "content": "<|begin_of_text|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "128001": {
14
+ "content": "<|end_of_text|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "128002": {
22
+ "content": "<|reserved_special_token_0|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "128003": {
30
+ "content": "<|reserved_special_token_1|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "128004": {
38
+ "content": "<|finetune_right_pad_id|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "128005": {
46
+ "content": "<|reserved_special_token_2|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "128006": {
54
+ "content": "<|start_header_id|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "128007": {
62
+ "content": "<|end_header_id|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "128008": {
70
+ "content": "<|eom_id|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "128009": {
78
+ "content": "<|eot_id|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "128010": {
86
+ "content": "<|python_tag|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "128011": {
94
+ "content": "<|reserved_special_token_3|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "128012": {
102
+ "content": "<|reserved_special_token_4|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "128013": {
110
+ "content": "<|reserved_special_token_5|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "128014": {
118
+ "content": "<|reserved_special_token_6|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "128015": {
126
+ "content": "<|reserved_special_token_7|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "128016": {
134
+ "content": "<|reserved_special_token_8|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "128017": {
142
+ "content": "<|reserved_special_token_9|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "128018": {
150
+ "content": "<|reserved_special_token_10|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "128019": {
158
+ "content": "<|reserved_special_token_11|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "128020": {
166
+ "content": "<|reserved_special_token_12|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "128021": {
174
+ "content": "<|reserved_special_token_13|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "128022": {
182
+ "content": "<|reserved_special_token_14|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "128023": {
190
+ "content": "<|reserved_special_token_15|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "128024": {
198
+ "content": "<|reserved_special_token_16|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "128025": {
206
+ "content": "<|reserved_special_token_17|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "128026": {
214
+ "content": "<|reserved_special_token_18|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "128027": {
222
+ "content": "<|reserved_special_token_19|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "128028": {
230
+ "content": "<|reserved_special_token_20|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "128029": {
238
+ "content": "<|reserved_special_token_21|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "128030": {
246
+ "content": "<|reserved_special_token_22|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "128031": {
254
+ "content": "<|reserved_special_token_23|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "128032": {
262
+ "content": "<|reserved_special_token_24|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "128033": {
270
+ "content": "<|reserved_special_token_25|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "128034": {
278
+ "content": "<|reserved_special_token_26|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "128035": {
286
+ "content": "<|reserved_special_token_27|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "128036": {
294
+ "content": "<|reserved_special_token_28|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "128037": {
302
+ "content": "<|reserved_special_token_29|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "128038": {
310
+ "content": "<|reserved_special_token_30|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "128039": {
318
+ "content": "<|reserved_special_token_31|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "128040": {
326
+ "content": "<|reserved_special_token_32|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "128041": {
334
+ "content": "<|reserved_special_token_33|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "128042": {
342
+ "content": "<|reserved_special_token_34|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "128043": {
350
+ "content": "<|reserved_special_token_35|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "128044": {
358
+ "content": "<|reserved_special_token_36|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "128045": {
366
+ "content": "<|reserved_special_token_37|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "128046": {
374
+ "content": "<|reserved_special_token_38|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "128047": {
382
+ "content": "<|reserved_special_token_39|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "128048": {
390
+ "content": "<|reserved_special_token_40|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "128049": {
398
+ "content": "<|reserved_special_token_41|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "128050": {
406
+ "content": "<|reserved_special_token_42|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "128051": {
414
+ "content": "<|reserved_special_token_43|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "128052": {
422
+ "content": "<|reserved_special_token_44|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "128053": {
430
+ "content": "<|reserved_special_token_45|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "128054": {
438
+ "content": "<|reserved_special_token_46|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "128055": {
446
+ "content": "<|reserved_special_token_47|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "128056": {
454
+ "content": "<|reserved_special_token_48|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "128057": {
462
+ "content": "<|reserved_special_token_49|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "128058": {
470
+ "content": "<|reserved_special_token_50|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "128059": {
478
+ "content": "<|reserved_special_token_51|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "128060": {
486
+ "content": "<|reserved_special_token_52|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "128061": {
494
+ "content": "<|reserved_special_token_53|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "128062": {
502
+ "content": "<|reserved_special_token_54|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "128063": {
510
+ "content": "<|reserved_special_token_55|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "128064": {
518
+ "content": "<|reserved_special_token_56|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "128065": {
526
+ "content": "<|reserved_special_token_57|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "128066": {
534
+ "content": "<|reserved_special_token_58|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "128067": {
542
+ "content": "<|reserved_special_token_59|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "128068": {
550
+ "content": "<|reserved_special_token_60|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "128069": {
558
+ "content": "<|reserved_special_token_61|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "128070": {
566
+ "content": "<|reserved_special_token_62|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "128071": {
574
+ "content": "<|reserved_special_token_63|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "128072": {
582
+ "content": "<|reserved_special_token_64|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "128073": {
590
+ "content": "<|reserved_special_token_65|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "128074": {
598
+ "content": "<|reserved_special_token_66|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "128075": {
606
+ "content": "<|reserved_special_token_67|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "128076": {
614
+ "content": "<|reserved_special_token_68|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "128077": {
622
+ "content": "<|reserved_special_token_69|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "128078": {
630
+ "content": "<|reserved_special_token_70|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "128079": {
638
+ "content": "<|reserved_special_token_71|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "128080": {
646
+ "content": "<|reserved_special_token_72|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "128081": {
654
+ "content": "<|reserved_special_token_73|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "128082": {
662
+ "content": "<|reserved_special_token_74|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "128083": {
670
+ "content": "<|reserved_special_token_75|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "128084": {
678
+ "content": "<|reserved_special_token_76|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "128085": {
686
+ "content": "<|reserved_special_token_77|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "128086": {
694
+ "content": "<|reserved_special_token_78|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "128087": {
702
+ "content": "<|reserved_special_token_79|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "128088": {
710
+ "content": "<|reserved_special_token_80|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "128089": {
718
+ "content": "<|reserved_special_token_81|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "128090": {
726
+ "content": "<|reserved_special_token_82|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "128091": {
734
+ "content": "<|reserved_special_token_83|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "128092": {
742
+ "content": "<|reserved_special_token_84|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "128093": {
750
+ "content": "<|reserved_special_token_85|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "128094": {
758
+ "content": "<|reserved_special_token_86|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "128095": {
766
+ "content": "<|reserved_special_token_87|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "128096": {
774
+ "content": "<|reserved_special_token_88|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "128097": {
782
+ "content": "<|reserved_special_token_89|>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "128098": {
790
+ "content": "<|reserved_special_token_90|>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "128099": {
798
+ "content": "<|reserved_special_token_91|>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "128100": {
806
+ "content": "<|reserved_special_token_92|>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "128101": {
814
+ "content": "<|reserved_special_token_93|>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "128102": {
822
+ "content": "<|reserved_special_token_94|>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "128103": {
830
+ "content": "<|reserved_special_token_95|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "128104": {
838
+ "content": "<|reserved_special_token_96|>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "128105": {
846
+ "content": "<|reserved_special_token_97|>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "128106": {
854
+ "content": "<|reserved_special_token_98|>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "128107": {
862
+ "content": "<|reserved_special_token_99|>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "128108": {
870
+ "content": "<|reserved_special_token_100|>",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "128109": {
878
+ "content": "<|reserved_special_token_101|>",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "128110": {
886
+ "content": "<|reserved_special_token_102|>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "128111": {
894
+ "content": "<|reserved_special_token_103|>",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "128112": {
902
+ "content": "<|reserved_special_token_104|>",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "128113": {
910
+ "content": "<|reserved_special_token_105|>",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "128114": {
918
+ "content": "<|reserved_special_token_106|>",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "128115": {
926
+ "content": "<|reserved_special_token_107|>",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "128116": {
934
+ "content": "<|reserved_special_token_108|>",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "128117": {
942
+ "content": "<|reserved_special_token_109|>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "128118": {
950
+ "content": "<|reserved_special_token_110|>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "128119": {
958
+ "content": "<|reserved_special_token_111|>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "128120": {
966
+ "content": "<|reserved_special_token_112|>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "128121": {
974
+ "content": "<|reserved_special_token_113|>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "128122": {
982
+ "content": "<|reserved_special_token_114|>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "128123": {
990
+ "content": "<|reserved_special_token_115|>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "128124": {
998
+ "content": "<|reserved_special_token_116|>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "128125": {
1006
+ "content": "<|reserved_special_token_117|>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "128126": {
1014
+ "content": "<|reserved_special_token_118|>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "128127": {
1022
+ "content": "<|reserved_special_token_119|>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "128128": {
1030
+ "content": "<|reserved_special_token_120|>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "128129": {
1038
+ "content": "<|reserved_special_token_121|>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "128130": {
1046
+ "content": "<|reserved_special_token_122|>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "128131": {
1054
+ "content": "<|reserved_special_token_123|>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "128132": {
1062
+ "content": "<|reserved_special_token_124|>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "128133": {
1070
+ "content": "<|reserved_special_token_125|>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "128134": {
1078
+ "content": "<|reserved_special_token_126|>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "128135": {
1086
+ "content": "<|reserved_special_token_127|>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "128136": {
1094
+ "content": "<|reserved_special_token_128|>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "128137": {
1102
+ "content": "<|reserved_special_token_129|>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "128138": {
1110
+ "content": "<|reserved_special_token_130|>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "128139": {
1118
+ "content": "<|reserved_special_token_131|>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "128140": {
1126
+ "content": "<|reserved_special_token_132|>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "128141": {
1134
+ "content": "<|reserved_special_token_133|>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "128142": {
1142
+ "content": "<|reserved_special_token_134|>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "128143": {
1150
+ "content": "<|reserved_special_token_135|>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "128144": {
1158
+ "content": "<|reserved_special_token_136|>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "128145": {
1166
+ "content": "<|reserved_special_token_137|>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "128146": {
1174
+ "content": "<|reserved_special_token_138|>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "128147": {
1182
+ "content": "<|reserved_special_token_139|>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "128148": {
1190
+ "content": "<|reserved_special_token_140|>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "128149": {
1198
+ "content": "<|reserved_special_token_141|>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "128150": {
1206
+ "content": "<|reserved_special_token_142|>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "128151": {
1214
+ "content": "<|reserved_special_token_143|>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "128152": {
1222
+ "content": "<|reserved_special_token_144|>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "128153": {
1230
+ "content": "<|reserved_special_token_145|>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "128154": {
1238
+ "content": "<|reserved_special_token_146|>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "128155": {
1246
+ "content": "<|reserved_special_token_147|>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "128156": {
1254
+ "content": "<|reserved_special_token_148|>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "128157": {
1262
+ "content": "<|reserved_special_token_149|>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "128158": {
1270
+ "content": "<|reserved_special_token_150|>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "128159": {
1278
+ "content": "<|reserved_special_token_151|>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "128160": {
1286
+ "content": "<|reserved_special_token_152|>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "128161": {
1294
+ "content": "<|reserved_special_token_153|>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "128162": {
1302
+ "content": "<|reserved_special_token_154|>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "128163": {
1310
+ "content": "<|reserved_special_token_155|>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "128164": {
1318
+ "content": "<|reserved_special_token_156|>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "128165": {
1326
+ "content": "<|reserved_special_token_157|>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "128166": {
1334
+ "content": "<|reserved_special_token_158|>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "128167": {
1342
+ "content": "<|reserved_special_token_159|>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "128168": {
1350
+ "content": "<|reserved_special_token_160|>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "128169": {
1358
+ "content": "<|reserved_special_token_161|>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "128170": {
1366
+ "content": "<|reserved_special_token_162|>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "128171": {
1374
+ "content": "<|reserved_special_token_163|>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "128172": {
1382
+ "content": "<|reserved_special_token_164|>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "128173": {
1390
+ "content": "<|reserved_special_token_165|>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "128174": {
1398
+ "content": "<|reserved_special_token_166|>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "128175": {
1406
+ "content": "<|reserved_special_token_167|>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ },
1413
+ "128176": {
1414
+ "content": "<|reserved_special_token_168|>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": true
1420
+ },
1421
+ "128177": {
1422
+ "content": "<|reserved_special_token_169|>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": true
1428
+ },
1429
+ "128178": {
1430
+ "content": "<|reserved_special_token_170|>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": true
1436
+ },
1437
+ "128179": {
1438
+ "content": "<|reserved_special_token_171|>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": true
1444
+ },
1445
+ "128180": {
1446
+ "content": "<|reserved_special_token_172|>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": true
1452
+ },
1453
+ "128181": {
1454
+ "content": "<|reserved_special_token_173|>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": true
1460
+ },
1461
+ "128182": {
1462
+ "content": "<|reserved_special_token_174|>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": true
1468
+ },
1469
+ "128183": {
1470
+ "content": "<|reserved_special_token_175|>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": true
1476
+ },
1477
+ "128184": {
1478
+ "content": "<|reserved_special_token_176|>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": true
1484
+ },
1485
+ "128185": {
1486
+ "content": "<|reserved_special_token_177|>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": true
1492
+ },
1493
+ "128186": {
1494
+ "content": "<|reserved_special_token_178|>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": true
1500
+ },
1501
+ "128187": {
1502
+ "content": "<|reserved_special_token_179|>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": true
1508
+ },
1509
+ "128188": {
1510
+ "content": "<|reserved_special_token_180|>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": true
1516
+ },
1517
+ "128189": {
1518
+ "content": "<|reserved_special_token_181|>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": true
1524
+ },
1525
+ "128190": {
1526
+ "content": "<|reserved_special_token_182|>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": true
1532
+ },
1533
+ "128191": {
1534
+ "content": "<|reserved_special_token_183|>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": true
1540
+ },
1541
+ "128192": {
1542
+ "content": "<|reserved_special_token_184|>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": true
1548
+ },
1549
+ "128193": {
1550
+ "content": "<|reserved_special_token_185|>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": true
1556
+ },
1557
+ "128194": {
1558
+ "content": "<|reserved_special_token_186|>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": true
1564
+ },
1565
+ "128195": {
1566
+ "content": "<|reserved_special_token_187|>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": true
1572
+ },
1573
+ "128196": {
1574
+ "content": "<|reserved_special_token_188|>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": true
1580
+ },
1581
+ "128197": {
1582
+ "content": "<|reserved_special_token_189|>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": true
1588
+ },
1589
+ "128198": {
1590
+ "content": "<|reserved_special_token_190|>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": true
1596
+ },
1597
+ "128199": {
1598
+ "content": "<|reserved_special_token_191|>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": true
1604
+ },
1605
+ "128200": {
1606
+ "content": "<|reserved_special_token_192|>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": true
1612
+ },
1613
+ "128201": {
1614
+ "content": "<|reserved_special_token_193|>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": true
1620
+ },
1621
+ "128202": {
1622
+ "content": "<|reserved_special_token_194|>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": true
1628
+ },
1629
+ "128203": {
1630
+ "content": "<|reserved_special_token_195|>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": true
1636
+ },
1637
+ "128204": {
1638
+ "content": "<|reserved_special_token_196|>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": true
1644
+ },
1645
+ "128205": {
1646
+ "content": "<|reserved_special_token_197|>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": true
1652
+ },
1653
+ "128206": {
1654
+ "content": "<|reserved_special_token_198|>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": true
1660
+ },
1661
+ "128207": {
1662
+ "content": "<|reserved_special_token_199|>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": true
1668
+ },
1669
+ "128208": {
1670
+ "content": "<|reserved_special_token_200|>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": true
1676
+ },
1677
+ "128209": {
1678
+ "content": "<|reserved_special_token_201|>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": true
1684
+ },
1685
+ "128210": {
1686
+ "content": "<|reserved_special_token_202|>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": true
1692
+ },
1693
+ "128211": {
1694
+ "content": "<|reserved_special_token_203|>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": true
1700
+ },
1701
+ "128212": {
1702
+ "content": "<|reserved_special_token_204|>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": true
1708
+ },
1709
+ "128213": {
1710
+ "content": "<|reserved_special_token_205|>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": true
1716
+ },
1717
+ "128214": {
1718
+ "content": "<|reserved_special_token_206|>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": true
1724
+ },
1725
+ "128215": {
1726
+ "content": "<|reserved_special_token_207|>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": true
1732
+ },
1733
+ "128216": {
1734
+ "content": "<|reserved_special_token_208|>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": true
1740
+ },
1741
+ "128217": {
1742
+ "content": "<|reserved_special_token_209|>",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": true
1748
+ },
1749
+ "128218": {
1750
+ "content": "<|reserved_special_token_210|>",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": true
1756
+ },
1757
+ "128219": {
1758
+ "content": "<|reserved_special_token_211|>",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": true
1764
+ },
1765
+ "128220": {
1766
+ "content": "<|reserved_special_token_212|>",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": true
1772
+ },
1773
+ "128221": {
1774
+ "content": "<|reserved_special_token_213|>",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": true
1780
+ },
1781
+ "128222": {
1782
+ "content": "<|reserved_special_token_214|>",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": true
1788
+ },
1789
+ "128223": {
1790
+ "content": "<|reserved_special_token_215|>",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": true
1796
+ },
1797
+ "128224": {
1798
+ "content": "<|reserved_special_token_216|>",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": true
1804
+ },
1805
+ "128225": {
1806
+ "content": "<|reserved_special_token_217|>",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": true
1812
+ },
1813
+ "128226": {
1814
+ "content": "<|reserved_special_token_218|>",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": true
1820
+ },
1821
+ "128227": {
1822
+ "content": "<|reserved_special_token_219|>",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": true
1828
+ },
1829
+ "128228": {
1830
+ "content": "<|reserved_special_token_220|>",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": true
1836
+ },
1837
+ "128229": {
1838
+ "content": "<|reserved_special_token_221|>",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": true
1844
+ },
1845
+ "128230": {
1846
+ "content": "<|reserved_special_token_222|>",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": true
1852
+ },
1853
+ "128231": {
1854
+ "content": "<|reserved_special_token_223|>",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": true
1860
+ },
1861
+ "128232": {
1862
+ "content": "<|reserved_special_token_224|>",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": true
1868
+ },
1869
+ "128233": {
1870
+ "content": "<|reserved_special_token_225|>",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": true
1876
+ },
1877
+ "128234": {
1878
+ "content": "<|reserved_special_token_226|>",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": true
1884
+ },
1885
+ "128235": {
1886
+ "content": "<|reserved_special_token_227|>",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": true
1892
+ },
1893
+ "128236": {
1894
+ "content": "<|reserved_special_token_228|>",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": true
1900
+ },
1901
+ "128237": {
1902
+ "content": "<|reserved_special_token_229|>",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": true
1908
+ },
1909
+ "128238": {
1910
+ "content": "<|reserved_special_token_230|>",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": true
1916
+ },
1917
+ "128239": {
1918
+ "content": "<|reserved_special_token_231|>",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": true
1924
+ },
1925
+ "128240": {
1926
+ "content": "<|reserved_special_token_232|>",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": true
1932
+ },
1933
+ "128241": {
1934
+ "content": "<|reserved_special_token_233|>",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": true
1940
+ },
1941
+ "128242": {
1942
+ "content": "<|reserved_special_token_234|>",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": true
1948
+ },
1949
+ "128243": {
1950
+ "content": "<|reserved_special_token_235|>",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": true
1956
+ },
1957
+ "128244": {
1958
+ "content": "<|reserved_special_token_236|>",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": true
1964
+ },
1965
+ "128245": {
1966
+ "content": "<|reserved_special_token_237|>",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": true
1972
+ },
1973
+ "128246": {
1974
+ "content": "<|reserved_special_token_238|>",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": true
1980
+ },
1981
+ "128247": {
1982
+ "content": "<|reserved_special_token_239|>",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": true
1988
+ },
1989
+ "128248": {
1990
+ "content": "<|reserved_special_token_240|>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": true
1996
+ },
1997
+ "128249": {
1998
+ "content": "<|reserved_special_token_241|>",
1999
+ "lstrip": false,
2000
+ "normalized": false,
2001
+ "rstrip": false,
2002
+ "single_word": false,
2003
+ "special": true
2004
+ },
2005
+ "128250": {
2006
+ "content": "<|reserved_special_token_242|>",
2007
+ "lstrip": false,
2008
+ "normalized": false,
2009
+ "rstrip": false,
2010
+ "single_word": false,
2011
+ "special": true
2012
+ },
2013
+ "128251": {
2014
+ "content": "<|reserved_special_token_243|>",
2015
+ "lstrip": false,
2016
+ "normalized": false,
2017
+ "rstrip": false,
2018
+ "single_word": false,
2019
+ "special": true
2020
+ },
2021
+ "128252": {
2022
+ "content": "<|reserved_special_token_244|>",
2023
+ "lstrip": false,
2024
+ "normalized": false,
2025
+ "rstrip": false,
2026
+ "single_word": false,
2027
+ "special": true
2028
+ },
2029
+ "128253": {
2030
+ "content": "<|reserved_special_token_245|>",
2031
+ "lstrip": false,
2032
+ "normalized": false,
2033
+ "rstrip": false,
2034
+ "single_word": false,
2035
+ "special": true
2036
+ },
2037
+ "128254": {
2038
+ "content": "<|reserved_special_token_246|>",
2039
+ "lstrip": false,
2040
+ "normalized": false,
2041
+ "rstrip": false,
2042
+ "single_word": false,
2043
+ "special": true
2044
+ },
2045
+ "128255": {
2046
+ "content": "<|reserved_special_token_247|>",
2047
+ "lstrip": false,
2048
+ "normalized": false,
2049
+ "rstrip": false,
2050
+ "single_word": false,
2051
+ "special": true
2052
+ }
2053
+ },
2054
+ "bos_token": "<|begin_of_text|>",
2055
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2056
+ "clean_up_tokenization_spaces": true,
2057
+ "eos_token": "<|eot_id|>",
2058
+ "extra_special_tokens": {},
2059
+ "max_sequence_length": 3072,
2060
+ "model_input_names": [
2061
+ "input_ids",
2062
+ "attention_mask"
2063
+ ],
2064
+ "model_max_length": 3072,
2065
+ "pad_token": "<|finetune_right_pad_id|>",
2066
+ "padding_side": "right",
2067
+ "tokenizer_class": "PreTrainedTokenizerFast"
2068
+ }
trainer_state.json ADDED
@@ -0,0 +1,3089 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.3772375583648682,
3
+ "best_model_checkpoint": "4bit_repro_03022025/host8_seed_42_full_det_fp16_no_flash_attn_fix_pad_llama-3.1-instruct-l16-cot-wt-4ep-lr3e04-ws20-bs4-ga4-fp16-05022025/checkpoint-109",
4
+ "epoch": 3.9655172413793105,
5
+ "eval_steps": 500,
6
+ "global_step": 432,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.009195402298850575,
13
+ "grad_norm": 1.2664293050765991,
14
+ "learning_rate": 1.4999999999999999e-05,
15
+ "loss": 2.501,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.01839080459770115,
20
+ "grad_norm": 0.8997858762741089,
21
+ "learning_rate": 2.9999999999999997e-05,
22
+ "loss": 2.5106,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.027586206896551724,
27
+ "grad_norm": 1.056443214416504,
28
+ "learning_rate": 4.4999999999999996e-05,
29
+ "loss": 2.3968,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.0367816091954023,
34
+ "grad_norm": 0.7283720374107361,
35
+ "learning_rate": 5.9999999999999995e-05,
36
+ "loss": 2.2734,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.04597701149425287,
41
+ "grad_norm": 2.1415610313415527,
42
+ "learning_rate": 7.5e-05,
43
+ "loss": 2.3937,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.05517241379310345,
48
+ "grad_norm": 0.9106594920158386,
49
+ "learning_rate": 8.999999999999999e-05,
50
+ "loss": 2.2477,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.06436781609195402,
55
+ "grad_norm": 0.5318637490272522,
56
+ "learning_rate": 0.00010499999999999999,
57
+ "loss": 2.315,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.0735632183908046,
62
+ "grad_norm": 0.5165982246398926,
63
+ "learning_rate": 0.00011999999999999999,
64
+ "loss": 2.2767,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.08275862068965517,
69
+ "grad_norm": 0.6848683953285217,
70
+ "learning_rate": 0.000135,
71
+ "loss": 2.1223,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.09195402298850575,
76
+ "grad_norm": 0.9631755948066711,
77
+ "learning_rate": 0.00015,
78
+ "loss": 1.8723,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.10114942528735632,
83
+ "grad_norm": 0.5025399923324585,
84
+ "learning_rate": 0.000165,
85
+ "loss": 1.903,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.1103448275862069,
90
+ "grad_norm": 0.6477987170219421,
91
+ "learning_rate": 0.00017999999999999998,
92
+ "loss": 1.8794,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.11954022988505747,
97
+ "grad_norm": 0.8744252324104309,
98
+ "learning_rate": 0.000195,
99
+ "loss": 1.5671,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.12873563218390804,
104
+ "grad_norm": 0.5130301713943481,
105
+ "learning_rate": 0.00020999999999999998,
106
+ "loss": 1.7795,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.13793103448275862,
111
+ "grad_norm": 0.40617436170578003,
112
+ "learning_rate": 0.000225,
113
+ "loss": 1.763,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.1471264367816092,
118
+ "grad_norm": 0.46318596601486206,
119
+ "learning_rate": 0.00023999999999999998,
120
+ "loss": 1.9987,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.15632183908045977,
125
+ "grad_norm": 0.5236511826515198,
126
+ "learning_rate": 0.00025499999999999996,
127
+ "loss": 1.4979,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.16551724137931034,
132
+ "grad_norm": 0.5424871444702148,
133
+ "learning_rate": 0.00027,
134
+ "loss": 1.4402,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.17471264367816092,
139
+ "grad_norm": 0.4224435091018677,
140
+ "learning_rate": 0.000285,
141
+ "loss": 1.4267,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.1839080459770115,
146
+ "grad_norm": 0.3918392062187195,
147
+ "learning_rate": 0.0003,
148
+ "loss": 1.682,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.19310344827586207,
153
+ "grad_norm": 0.38505086302757263,
154
+ "learning_rate": 0.00029927184466019415,
155
+ "loss": 1.8057,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.20229885057471264,
160
+ "grad_norm": 0.3489862382411957,
161
+ "learning_rate": 0.00029854368932038833,
162
+ "loss": 1.7206,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.21149425287356322,
167
+ "grad_norm": 0.42483219504356384,
168
+ "learning_rate": 0.0002978155339805825,
169
+ "loss": 1.5119,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.2206896551724138,
174
+ "grad_norm": 0.3796898424625397,
175
+ "learning_rate": 0.0002970873786407767,
176
+ "loss": 1.6089,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.22988505747126436,
181
+ "grad_norm": 0.32184913754463196,
182
+ "learning_rate": 0.00029635922330097087,
183
+ "loss": 1.7786,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.23908045977011494,
188
+ "grad_norm": 0.35197311639785767,
189
+ "learning_rate": 0.00029563106796116505,
190
+ "loss": 1.5639,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.2482758620689655,
195
+ "grad_norm": 0.4310867488384247,
196
+ "learning_rate": 0.0002949029126213592,
197
+ "loss": 1.5192,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.2574712643678161,
202
+ "grad_norm": 0.3951260447502136,
203
+ "learning_rate": 0.00029417475728155335,
204
+ "loss": 1.4559,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.26666666666666666,
209
+ "grad_norm": 0.3948059678077698,
210
+ "learning_rate": 0.00029344660194174753,
211
+ "loss": 1.7552,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.27586206896551724,
216
+ "grad_norm": 0.3327697515487671,
217
+ "learning_rate": 0.0002927184466019417,
218
+ "loss": 1.9249,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.2850574712643678,
223
+ "grad_norm": 0.3762843906879425,
224
+ "learning_rate": 0.0002919902912621359,
225
+ "loss": 1.6966,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.2942528735632184,
230
+ "grad_norm": 0.3671524226665497,
231
+ "learning_rate": 0.00029126213592233006,
232
+ "loss": 1.4718,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.30344827586206896,
237
+ "grad_norm": 0.5411608815193176,
238
+ "learning_rate": 0.00029053398058252424,
239
+ "loss": 1.3394,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.31264367816091954,
244
+ "grad_norm": 0.4906865656375885,
245
+ "learning_rate": 0.0002898058252427184,
246
+ "loss": 1.688,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.3218390804597701,
251
+ "grad_norm": 0.4257373511791229,
252
+ "learning_rate": 0.0002890776699029126,
253
+ "loss": 1.7126,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.3310344827586207,
258
+ "grad_norm": 0.44731780886650085,
259
+ "learning_rate": 0.0002883495145631068,
260
+ "loss": 1.5332,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.34022988505747126,
265
+ "grad_norm": 0.34879976511001587,
266
+ "learning_rate": 0.00028762135922330096,
267
+ "loss": 1.6599,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.34942528735632183,
272
+ "grad_norm": 0.328622043132782,
273
+ "learning_rate": 0.00028689320388349513,
274
+ "loss": 1.7865,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.3586206896551724,
279
+ "grad_norm": 0.4515538811683655,
280
+ "learning_rate": 0.0002861650485436893,
281
+ "loss": 1.3684,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.367816091954023,
286
+ "grad_norm": 0.39751267433166504,
287
+ "learning_rate": 0.0002854368932038835,
288
+ "loss": 1.7847,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.37701149425287356,
293
+ "grad_norm": 0.33651894330978394,
294
+ "learning_rate": 0.00028470873786407767,
295
+ "loss": 1.602,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.38620689655172413,
300
+ "grad_norm": 0.5487242341041565,
301
+ "learning_rate": 0.00028398058252427185,
302
+ "loss": 1.2588,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.3954022988505747,
307
+ "grad_norm": 0.373512327671051,
308
+ "learning_rate": 0.00028325242718446603,
309
+ "loss": 1.5344,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.4045977011494253,
314
+ "grad_norm": 0.4022233486175537,
315
+ "learning_rate": 0.00028252427184466015,
316
+ "loss": 1.4503,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.41379310344827586,
321
+ "grad_norm": 0.4379498064517975,
322
+ "learning_rate": 0.00028179611650485433,
323
+ "loss": 1.3271,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.42298850574712643,
328
+ "grad_norm": 0.3380189538002014,
329
+ "learning_rate": 0.0002810679611650485,
330
+ "loss": 1.6746,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.432183908045977,
335
+ "grad_norm": 0.41873887181282043,
336
+ "learning_rate": 0.0002803398058252427,
337
+ "loss": 1.4792,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.4413793103448276,
342
+ "grad_norm": 0.3990491032600403,
343
+ "learning_rate": 0.00027961165048543687,
344
+ "loss": 1.4309,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.45057471264367815,
349
+ "grad_norm": 0.41645604372024536,
350
+ "learning_rate": 0.00027888349514563105,
351
+ "loss": 1.4003,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.45977011494252873,
356
+ "grad_norm": 0.46974533796310425,
357
+ "learning_rate": 0.0002781553398058252,
358
+ "loss": 1.2245,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.4689655172413793,
363
+ "grad_norm": 0.36877307295799255,
364
+ "learning_rate": 0.0002774271844660194,
365
+ "loss": 1.5979,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.4781609195402299,
370
+ "grad_norm": 0.35563924908638,
371
+ "learning_rate": 0.0002766990291262136,
372
+ "loss": 1.3965,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.48735632183908045,
377
+ "grad_norm": 0.44057121872901917,
378
+ "learning_rate": 0.00027597087378640776,
379
+ "loss": 1.2961,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.496551724137931,
384
+ "grad_norm": 0.46805521845817566,
385
+ "learning_rate": 0.00027524271844660194,
386
+ "loss": 1.2184,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.5057471264367817,
391
+ "grad_norm": 0.3901378810405731,
392
+ "learning_rate": 0.0002745145631067961,
393
+ "loss": 1.6127,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.5149425287356322,
398
+ "grad_norm": 0.471978098154068,
399
+ "learning_rate": 0.0002737864077669903,
400
+ "loss": 1.4896,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.5241379310344828,
405
+ "grad_norm": 0.4229693114757538,
406
+ "learning_rate": 0.0002730582524271845,
407
+ "loss": 1.3084,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.5333333333333333,
412
+ "grad_norm": 0.4022842049598694,
413
+ "learning_rate": 0.00027233009708737865,
414
+ "loss": 1.464,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.542528735632184,
419
+ "grad_norm": 0.4753398895263672,
420
+ "learning_rate": 0.0002716019417475728,
421
+ "loss": 1.4227,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.5517241379310345,
426
+ "grad_norm": 0.3991449475288391,
427
+ "learning_rate": 0.00027087378640776696,
428
+ "loss": 1.4973,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.5609195402298851,
433
+ "grad_norm": 0.5638157725334167,
434
+ "learning_rate": 0.00027014563106796114,
435
+ "loss": 1.3702,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.5701149425287356,
440
+ "grad_norm": 0.3964412808418274,
441
+ "learning_rate": 0.0002694174757281553,
442
+ "loss": 1.3154,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.5793103448275863,
447
+ "grad_norm": 0.4884161055088043,
448
+ "learning_rate": 0.0002686893203883495,
449
+ "loss": 1.2915,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.5885057471264368,
454
+ "grad_norm": 0.5821394920349121,
455
+ "learning_rate": 0.00026796116504854367,
456
+ "loss": 1.1925,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.5977011494252874,
461
+ "grad_norm": 0.8125529289245605,
462
+ "learning_rate": 0.00026723300970873785,
463
+ "loss": 1.4684,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.6068965517241379,
468
+ "grad_norm": 0.46448639035224915,
469
+ "learning_rate": 0.00026650485436893203,
470
+ "loss": 1.0113,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.6160919540229886,
475
+ "grad_norm": 0.5045990347862244,
476
+ "learning_rate": 0.0002657766990291262,
477
+ "loss": 1.424,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.6252873563218391,
482
+ "grad_norm": 0.4608731269836426,
483
+ "learning_rate": 0.0002650485436893204,
484
+ "loss": 1.4203,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.6344827586206897,
489
+ "grad_norm": 0.6361207962036133,
490
+ "learning_rate": 0.00026432038834951456,
491
+ "loss": 1.4455,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.6436781609195402,
496
+ "grad_norm": 0.4667050838470459,
497
+ "learning_rate": 0.00026359223300970874,
498
+ "loss": 1.3269,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.6528735632183909,
503
+ "grad_norm": 0.5672599673271179,
504
+ "learning_rate": 0.0002628640776699029,
505
+ "loss": 1.2629,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.6620689655172414,
510
+ "grad_norm": 0.5386179089546204,
511
+ "learning_rate": 0.00026213592233009705,
512
+ "loss": 1.2188,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.671264367816092,
517
+ "grad_norm": 0.4968770146369934,
518
+ "learning_rate": 0.0002614077669902912,
519
+ "loss": 1.3148,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.6804597701149425,
524
+ "grad_norm": 0.5847041010856628,
525
+ "learning_rate": 0.0002606796116504854,
526
+ "loss": 1.457,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.6896551724137931,
531
+ "grad_norm": 0.5828786492347717,
532
+ "learning_rate": 0.0002599514563106796,
533
+ "loss": 1.2948,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.6988505747126437,
538
+ "grad_norm": 0.7716859579086304,
539
+ "learning_rate": 0.00025922330097087376,
540
+ "loss": 1.5078,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.7080459770114943,
545
+ "grad_norm": 0.6014898419380188,
546
+ "learning_rate": 0.00025849514563106794,
547
+ "loss": 1.2796,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.7172413793103448,
552
+ "grad_norm": 0.5102112293243408,
553
+ "learning_rate": 0.0002577669902912621,
554
+ "loss": 1.178,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.7264367816091954,
559
+ "grad_norm": 0.5293049812316895,
560
+ "learning_rate": 0.0002570388349514563,
561
+ "loss": 1.6404,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.735632183908046,
566
+ "grad_norm": 0.5157208442687988,
567
+ "learning_rate": 0.0002563106796116505,
568
+ "loss": 1.4367,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.7448275862068966,
573
+ "grad_norm": 0.4517700672149658,
574
+ "learning_rate": 0.0002555825242718446,
575
+ "loss": 1.3063,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.7540229885057471,
580
+ "grad_norm": 0.42310649156570435,
581
+ "learning_rate": 0.0002548543689320388,
582
+ "loss": 1.2749,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.7632183908045977,
587
+ "grad_norm": 0.5767822861671448,
588
+ "learning_rate": 0.00025412621359223296,
589
+ "loss": 1.3432,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.7724137931034483,
594
+ "grad_norm": 0.49889254570007324,
595
+ "learning_rate": 0.00025339805825242714,
596
+ "loss": 1.3629,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.7816091954022989,
601
+ "grad_norm": 0.5736685395240784,
602
+ "learning_rate": 0.0002526699029126213,
603
+ "loss": 1.1754,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.7908045977011494,
608
+ "grad_norm": 0.4891297221183777,
609
+ "learning_rate": 0.0002519417475728155,
610
+ "loss": 1.2404,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.8,
615
+ "grad_norm": 0.45507243275642395,
616
+ "learning_rate": 0.00025121359223300967,
617
+ "loss": 1.3653,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.8091954022988506,
622
+ "grad_norm": 0.43236321210861206,
623
+ "learning_rate": 0.00025048543689320385,
624
+ "loss": 1.3037,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.8183908045977012,
629
+ "grad_norm": 0.5662382245063782,
630
+ "learning_rate": 0.00024975728155339803,
631
+ "loss": 1.2031,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.8275862068965517,
636
+ "grad_norm": 0.5644109845161438,
637
+ "learning_rate": 0.0002490291262135922,
638
+ "loss": 1.0595,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.8367816091954023,
643
+ "grad_norm": 0.4636576473712921,
644
+ "learning_rate": 0.0002483009708737864,
645
+ "loss": 1.3056,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.8459770114942529,
650
+ "grad_norm": 0.4858672022819519,
651
+ "learning_rate": 0.00024757281553398056,
652
+ "loss": 1.1215,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.8551724137931035,
657
+ "grad_norm": 0.5379095673561096,
658
+ "learning_rate": 0.00024684466019417474,
659
+ "loss": 1.0833,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.864367816091954,
664
+ "grad_norm": 0.6066029667854309,
665
+ "learning_rate": 0.0002461165048543689,
666
+ "loss": 1.1953,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.8735632183908046,
671
+ "grad_norm": 0.5864242315292358,
672
+ "learning_rate": 0.0002453883495145631,
673
+ "loss": 1.2868,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.8827586206896552,
678
+ "grad_norm": 0.47946035861968994,
679
+ "learning_rate": 0.0002446601941747572,
680
+ "loss": 1.0682,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.8919540229885058,
685
+ "grad_norm": 0.5266394019126892,
686
+ "learning_rate": 0.00024393203883495143,
687
+ "loss": 1.2363,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.9011494252873563,
692
+ "grad_norm": 0.49734389781951904,
693
+ "learning_rate": 0.0002432038834951456,
694
+ "loss": 1.2858,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.9103448275862069,
699
+ "grad_norm": 0.5391829013824463,
700
+ "learning_rate": 0.0002424757281553398,
701
+ "loss": 1.1882,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.9195402298850575,
706
+ "grad_norm": 0.4663216769695282,
707
+ "learning_rate": 0.00024174757281553394,
708
+ "loss": 1.1461,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.9287356321839081,
713
+ "grad_norm": 0.5432461500167847,
714
+ "learning_rate": 0.00024101941747572812,
715
+ "loss": 1.134,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.9379310344827586,
720
+ "grad_norm": 0.6043102145195007,
721
+ "learning_rate": 0.0002402912621359223,
722
+ "loss": 1.0859,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.9471264367816092,
727
+ "grad_norm": 0.5635194778442383,
728
+ "learning_rate": 0.00023956310679611648,
729
+ "loss": 1.0828,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.9563218390804598,
734
+ "grad_norm": 0.5683427453041077,
735
+ "learning_rate": 0.00023883495145631065,
736
+ "loss": 1.0066,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.9655172413793104,
741
+ "grad_norm": 0.550366997718811,
742
+ "learning_rate": 0.00023810679611650483,
743
+ "loss": 1.0664,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.9747126436781609,
748
+ "grad_norm": 0.5590884685516357,
749
+ "learning_rate": 0.000237378640776699,
750
+ "loss": 1.3188,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.9839080459770115,
755
+ "grad_norm": 0.49222445487976074,
756
+ "learning_rate": 0.0002366504854368932,
757
+ "loss": 1.1888,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.993103448275862,
762
+ "grad_norm": 0.5352950096130371,
763
+ "learning_rate": 0.00023592233009708734,
764
+ "loss": 0.9848,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 1.0,
769
+ "grad_norm": 0.6914329528808594,
770
+ "learning_rate": 0.00023519417475728152,
771
+ "loss": 1.1814,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 1.0,
776
+ "eval_loss": 1.3772375583648682,
777
+ "eval_runtime": 70.9021,
778
+ "eval_samples_per_second": 4.683,
779
+ "eval_steps_per_second": 2.341,
780
+ "step": 109
781
+ },
782
+ {
783
+ "epoch": 1.0091954022988505,
784
+ "grad_norm": 0.5395228862762451,
785
+ "learning_rate": 0.0002344660194174757,
786
+ "loss": 1.0255,
787
+ "step": 110
788
+ },
789
+ {
790
+ "epoch": 1.018390804597701,
791
+ "grad_norm": 0.5161539316177368,
792
+ "learning_rate": 0.00023373786407766988,
793
+ "loss": 1.0072,
794
+ "step": 111
795
+ },
796
+ {
797
+ "epoch": 1.0275862068965518,
798
+ "grad_norm": 0.4717608094215393,
799
+ "learning_rate": 0.00023300970873786406,
800
+ "loss": 0.9007,
801
+ "step": 112
802
+ },
803
+ {
804
+ "epoch": 1.0367816091954023,
805
+ "grad_norm": 0.6422189474105835,
806
+ "learning_rate": 0.00023228155339805823,
807
+ "loss": 1.1458,
808
+ "step": 113
809
+ },
810
+ {
811
+ "epoch": 1.0459770114942528,
812
+ "grad_norm": 0.5921640992164612,
813
+ "learning_rate": 0.0002315533980582524,
814
+ "loss": 1.0321,
815
+ "step": 114
816
+ },
817
+ {
818
+ "epoch": 1.0551724137931036,
819
+ "grad_norm": 0.6381415128707886,
820
+ "learning_rate": 0.0002308252427184466,
821
+ "loss": 1.0119,
822
+ "step": 115
823
+ },
824
+ {
825
+ "epoch": 1.064367816091954,
826
+ "grad_norm": 0.49388617277145386,
827
+ "learning_rate": 0.00023009708737864074,
828
+ "loss": 0.9483,
829
+ "step": 116
830
+ },
831
+ {
832
+ "epoch": 1.0735632183908046,
833
+ "grad_norm": 0.669136106967926,
834
+ "learning_rate": 0.00022936893203883492,
835
+ "loss": 1.0767,
836
+ "step": 117
837
+ },
838
+ {
839
+ "epoch": 1.0827586206896551,
840
+ "grad_norm": 0.5716057419776917,
841
+ "learning_rate": 0.0002286407766990291,
842
+ "loss": 1.0632,
843
+ "step": 118
844
+ },
845
+ {
846
+ "epoch": 1.0919540229885056,
847
+ "grad_norm": 0.5134244561195374,
848
+ "learning_rate": 0.00022791262135922328,
849
+ "loss": 0.9554,
850
+ "step": 119
851
+ },
852
+ {
853
+ "epoch": 1.1011494252873564,
854
+ "grad_norm": 0.49190524220466614,
855
+ "learning_rate": 0.00022718446601941746,
856
+ "loss": 0.9927,
857
+ "step": 120
858
+ },
859
+ {
860
+ "epoch": 1.110344827586207,
861
+ "grad_norm": 0.7558183073997498,
862
+ "learning_rate": 0.00022645631067961164,
863
+ "loss": 1.0067,
864
+ "step": 121
865
+ },
866
+ {
867
+ "epoch": 1.1195402298850574,
868
+ "grad_norm": 0.5597643852233887,
869
+ "learning_rate": 0.00022572815533980582,
870
+ "loss": 0.8869,
871
+ "step": 122
872
+ },
873
+ {
874
+ "epoch": 1.1287356321839082,
875
+ "grad_norm": 0.6764683127403259,
876
+ "learning_rate": 0.000225,
877
+ "loss": 0.9806,
878
+ "step": 123
879
+ },
880
+ {
881
+ "epoch": 1.1379310344827587,
882
+ "grad_norm": 0.5788061618804932,
883
+ "learning_rate": 0.00022427184466019415,
884
+ "loss": 1.0121,
885
+ "step": 124
886
+ },
887
+ {
888
+ "epoch": 1.1471264367816092,
889
+ "grad_norm": 0.5578724145889282,
890
+ "learning_rate": 0.00022354368932038832,
891
+ "loss": 0.91,
892
+ "step": 125
893
+ },
894
+ {
895
+ "epoch": 1.1563218390804597,
896
+ "grad_norm": 0.5371822714805603,
897
+ "learning_rate": 0.0002228155339805825,
898
+ "loss": 0.8422,
899
+ "step": 126
900
+ },
901
+ {
902
+ "epoch": 1.1655172413793102,
903
+ "grad_norm": 0.7994176149368286,
904
+ "learning_rate": 0.00022208737864077668,
905
+ "loss": 0.9105,
906
+ "step": 127
907
+ },
908
+ {
909
+ "epoch": 1.174712643678161,
910
+ "grad_norm": 0.5430970788002014,
911
+ "learning_rate": 0.00022135922330097086,
912
+ "loss": 0.9843,
913
+ "step": 128
914
+ },
915
+ {
916
+ "epoch": 1.1839080459770115,
917
+ "grad_norm": 0.5710289478302002,
918
+ "learning_rate": 0.00022063106796116504,
919
+ "loss": 0.9191,
920
+ "step": 129
921
+ },
922
+ {
923
+ "epoch": 1.193103448275862,
924
+ "grad_norm": 0.6985263228416443,
925
+ "learning_rate": 0.00021990291262135922,
926
+ "loss": 0.892,
927
+ "step": 130
928
+ },
929
+ {
930
+ "epoch": 1.2022988505747128,
931
+ "grad_norm": 0.532593309879303,
932
+ "learning_rate": 0.00021917475728155337,
933
+ "loss": 0.7993,
934
+ "step": 131
935
+ },
936
+ {
937
+ "epoch": 1.2114942528735633,
938
+ "grad_norm": 0.5657442808151245,
939
+ "learning_rate": 0.00021844660194174755,
940
+ "loss": 0.8961,
941
+ "step": 132
942
+ },
943
+ {
944
+ "epoch": 1.2206896551724138,
945
+ "grad_norm": 0.5356594920158386,
946
+ "learning_rate": 0.00021771844660194173,
947
+ "loss": 0.867,
948
+ "step": 133
949
+ },
950
+ {
951
+ "epoch": 1.2298850574712643,
952
+ "grad_norm": 0.9694854617118835,
953
+ "learning_rate": 0.0002169902912621359,
954
+ "loss": 0.8823,
955
+ "step": 134
956
+ },
957
+ {
958
+ "epoch": 1.2390804597701148,
959
+ "grad_norm": 0.5810908675193787,
960
+ "learning_rate": 0.00021626213592233008,
961
+ "loss": 0.9571,
962
+ "step": 135
963
+ },
964
+ {
965
+ "epoch": 1.2482758620689656,
966
+ "grad_norm": 0.5119120478630066,
967
+ "learning_rate": 0.00021553398058252426,
968
+ "loss": 1.0567,
969
+ "step": 136
970
+ },
971
+ {
972
+ "epoch": 1.257471264367816,
973
+ "grad_norm": 0.5349586009979248,
974
+ "learning_rate": 0.00021480582524271844,
975
+ "loss": 0.8422,
976
+ "step": 137
977
+ },
978
+ {
979
+ "epoch": 1.2666666666666666,
980
+ "grad_norm": 0.5498553514480591,
981
+ "learning_rate": 0.00021407766990291262,
982
+ "loss": 0.9509,
983
+ "step": 138
984
+ },
985
+ {
986
+ "epoch": 1.2758620689655173,
987
+ "grad_norm": 0.6952114701271057,
988
+ "learning_rate": 0.00021334951456310677,
989
+ "loss": 1.062,
990
+ "step": 139
991
+ },
992
+ {
993
+ "epoch": 1.2850574712643679,
994
+ "grad_norm": 0.5768996477127075,
995
+ "learning_rate": 0.00021262135922330095,
996
+ "loss": 0.9139,
997
+ "step": 140
998
+ },
999
+ {
1000
+ "epoch": 1.2942528735632184,
1001
+ "grad_norm": 0.559478759765625,
1002
+ "learning_rate": 0.00021189320388349513,
1003
+ "loss": 1.0465,
1004
+ "step": 141
1005
+ },
1006
+ {
1007
+ "epoch": 1.303448275862069,
1008
+ "grad_norm": 0.5405702590942383,
1009
+ "learning_rate": 0.0002111650485436893,
1010
+ "loss": 0.7433,
1011
+ "step": 142
1012
+ },
1013
+ {
1014
+ "epoch": 1.3126436781609194,
1015
+ "grad_norm": 0.5924260020256042,
1016
+ "learning_rate": 0.00021043689320388349,
1017
+ "loss": 0.6828,
1018
+ "step": 143
1019
+ },
1020
+ {
1021
+ "epoch": 1.3218390804597702,
1022
+ "grad_norm": 0.7219521403312683,
1023
+ "learning_rate": 0.00020970873786407766,
1024
+ "loss": 0.8972,
1025
+ "step": 144
1026
+ },
1027
+ {
1028
+ "epoch": 1.3310344827586207,
1029
+ "grad_norm": 0.8541707396507263,
1030
+ "learning_rate": 0.00020898058252427184,
1031
+ "loss": 0.7595,
1032
+ "step": 145
1033
+ },
1034
+ {
1035
+ "epoch": 1.3402298850574712,
1036
+ "grad_norm": 0.5988287925720215,
1037
+ "learning_rate": 0.00020825242718446602,
1038
+ "loss": 0.7803,
1039
+ "step": 146
1040
+ },
1041
+ {
1042
+ "epoch": 1.349425287356322,
1043
+ "grad_norm": 0.6142683625221252,
1044
+ "learning_rate": 0.00020752427184466017,
1045
+ "loss": 0.8507,
1046
+ "step": 147
1047
+ },
1048
+ {
1049
+ "epoch": 1.3586206896551725,
1050
+ "grad_norm": 0.5336320400238037,
1051
+ "learning_rate": 0.00020679611650485435,
1052
+ "loss": 0.7742,
1053
+ "step": 148
1054
+ },
1055
+ {
1056
+ "epoch": 1.367816091954023,
1057
+ "grad_norm": 0.5284804701805115,
1058
+ "learning_rate": 0.00020606796116504853,
1059
+ "loss": 0.6759,
1060
+ "step": 149
1061
+ },
1062
+ {
1063
+ "epoch": 1.3770114942528735,
1064
+ "grad_norm": 0.4955348074436188,
1065
+ "learning_rate": 0.0002053398058252427,
1066
+ "loss": 0.7054,
1067
+ "step": 150
1068
+ },
1069
+ {
1070
+ "epoch": 1.386206896551724,
1071
+ "grad_norm": 0.5454412698745728,
1072
+ "learning_rate": 0.0002046116504854369,
1073
+ "loss": 0.8826,
1074
+ "step": 151
1075
+ },
1076
+ {
1077
+ "epoch": 1.3954022988505748,
1078
+ "grad_norm": 0.7631385326385498,
1079
+ "learning_rate": 0.00020388349514563107,
1080
+ "loss": 0.8582,
1081
+ "step": 152
1082
+ },
1083
+ {
1084
+ "epoch": 1.4045977011494253,
1085
+ "grad_norm": 0.5374491810798645,
1086
+ "learning_rate": 0.00020315533980582524,
1087
+ "loss": 0.9728,
1088
+ "step": 153
1089
+ },
1090
+ {
1091
+ "epoch": 1.4137931034482758,
1092
+ "grad_norm": 0.5633158087730408,
1093
+ "learning_rate": 0.00020242718446601942,
1094
+ "loss": 0.8275,
1095
+ "step": 154
1096
+ },
1097
+ {
1098
+ "epoch": 1.4229885057471265,
1099
+ "grad_norm": 0.572356641292572,
1100
+ "learning_rate": 0.00020169902912621357,
1101
+ "loss": 0.6565,
1102
+ "step": 155
1103
+ },
1104
+ {
1105
+ "epoch": 1.432183908045977,
1106
+ "grad_norm": 0.6513031125068665,
1107
+ "learning_rate": 0.00020097087378640775,
1108
+ "loss": 0.9112,
1109
+ "step": 156
1110
+ },
1111
+ {
1112
+ "epoch": 1.4413793103448276,
1113
+ "grad_norm": 0.48528391122817993,
1114
+ "learning_rate": 0.00020024271844660193,
1115
+ "loss": 0.7623,
1116
+ "step": 157
1117
+ },
1118
+ {
1119
+ "epoch": 1.450574712643678,
1120
+ "grad_norm": 0.47339922189712524,
1121
+ "learning_rate": 0.0001995145631067961,
1122
+ "loss": 0.621,
1123
+ "step": 158
1124
+ },
1125
+ {
1126
+ "epoch": 1.4597701149425286,
1127
+ "grad_norm": 0.5684221386909485,
1128
+ "learning_rate": 0.0001987864077669903,
1129
+ "loss": 0.7902,
1130
+ "step": 159
1131
+ },
1132
+ {
1133
+ "epoch": 1.4689655172413794,
1134
+ "grad_norm": 0.87876296043396,
1135
+ "learning_rate": 0.00019805825242718447,
1136
+ "loss": 0.9629,
1137
+ "step": 160
1138
+ },
1139
+ {
1140
+ "epoch": 1.4781609195402299,
1141
+ "grad_norm": 0.5925374031066895,
1142
+ "learning_rate": 0.00019733009708737865,
1143
+ "loss": 0.9815,
1144
+ "step": 161
1145
+ },
1146
+ {
1147
+ "epoch": 1.4873563218390804,
1148
+ "grad_norm": 0.48992210626602173,
1149
+ "learning_rate": 0.0001966019417475728,
1150
+ "loss": 0.6662,
1151
+ "step": 162
1152
+ },
1153
+ {
1154
+ "epoch": 1.4965517241379311,
1155
+ "grad_norm": 0.9017893075942993,
1156
+ "learning_rate": 0.00019587378640776698,
1157
+ "loss": 0.7229,
1158
+ "step": 163
1159
+ },
1160
+ {
1161
+ "epoch": 1.5057471264367817,
1162
+ "grad_norm": 0.6186094880104065,
1163
+ "learning_rate": 0.00019514563106796116,
1164
+ "loss": 0.6594,
1165
+ "step": 164
1166
+ },
1167
+ {
1168
+ "epoch": 1.5149425287356322,
1169
+ "grad_norm": 0.5197699069976807,
1170
+ "learning_rate": 0.00019441747572815533,
1171
+ "loss": 0.8404,
1172
+ "step": 165
1173
+ },
1174
+ {
1175
+ "epoch": 1.524137931034483,
1176
+ "grad_norm": 0.4972164034843445,
1177
+ "learning_rate": 0.0001936893203883495,
1178
+ "loss": 0.8106,
1179
+ "step": 166
1180
+ },
1181
+ {
1182
+ "epoch": 1.5333333333333332,
1183
+ "grad_norm": 0.5052672028541565,
1184
+ "learning_rate": 0.0001929611650485437,
1185
+ "loss": 0.7682,
1186
+ "step": 167
1187
+ },
1188
+ {
1189
+ "epoch": 1.542528735632184,
1190
+ "grad_norm": 1.1433080434799194,
1191
+ "learning_rate": 0.00019223300970873787,
1192
+ "loss": 0.8409,
1193
+ "step": 168
1194
+ },
1195
+ {
1196
+ "epoch": 1.5517241379310345,
1197
+ "grad_norm": 0.730868399143219,
1198
+ "learning_rate": 0.00019150485436893205,
1199
+ "loss": 0.7541,
1200
+ "step": 169
1201
+ },
1202
+ {
1203
+ "epoch": 1.560919540229885,
1204
+ "grad_norm": 0.7178101539611816,
1205
+ "learning_rate": 0.0001907766990291262,
1206
+ "loss": 0.6899,
1207
+ "step": 170
1208
+ },
1209
+ {
1210
+ "epoch": 1.5701149425287357,
1211
+ "grad_norm": 0.5060885548591614,
1212
+ "learning_rate": 0.00019004854368932038,
1213
+ "loss": 0.97,
1214
+ "step": 171
1215
+ },
1216
+ {
1217
+ "epoch": 1.5793103448275863,
1218
+ "grad_norm": 0.7058172821998596,
1219
+ "learning_rate": 0.00018932038834951456,
1220
+ "loss": 0.8883,
1221
+ "step": 172
1222
+ },
1223
+ {
1224
+ "epoch": 1.5885057471264368,
1225
+ "grad_norm": 0.6002851128578186,
1226
+ "learning_rate": 0.00018859223300970874,
1227
+ "loss": 0.8808,
1228
+ "step": 173
1229
+ },
1230
+ {
1231
+ "epoch": 1.5977011494252875,
1232
+ "grad_norm": 0.5641213059425354,
1233
+ "learning_rate": 0.00018786407766990291,
1234
+ "loss": 0.6536,
1235
+ "step": 174
1236
+ },
1237
+ {
1238
+ "epoch": 1.6068965517241378,
1239
+ "grad_norm": 0.621860146522522,
1240
+ "learning_rate": 0.00018713592233009707,
1241
+ "loss": 0.784,
1242
+ "step": 175
1243
+ },
1244
+ {
1245
+ "epoch": 1.6160919540229886,
1246
+ "grad_norm": 0.6033377051353455,
1247
+ "learning_rate": 0.00018640776699029122,
1248
+ "loss": 0.8755,
1249
+ "step": 176
1250
+ },
1251
+ {
1252
+ "epoch": 1.625287356321839,
1253
+ "grad_norm": 0.7301514148712158,
1254
+ "learning_rate": 0.0001856796116504854,
1255
+ "loss": 0.5401,
1256
+ "step": 177
1257
+ },
1258
+ {
1259
+ "epoch": 1.6344827586206896,
1260
+ "grad_norm": 0.6001805067062378,
1261
+ "learning_rate": 0.00018495145631067957,
1262
+ "loss": 0.5086,
1263
+ "step": 178
1264
+ },
1265
+ {
1266
+ "epoch": 1.6436781609195403,
1267
+ "grad_norm": 0.5408189296722412,
1268
+ "learning_rate": 0.00018422330097087375,
1269
+ "loss": 0.8864,
1270
+ "step": 179
1271
+ },
1272
+ {
1273
+ "epoch": 1.6528735632183909,
1274
+ "grad_norm": 0.548526406288147,
1275
+ "learning_rate": 0.00018349514563106793,
1276
+ "loss": 0.7745,
1277
+ "step": 180
1278
+ },
1279
+ {
1280
+ "epoch": 1.6620689655172414,
1281
+ "grad_norm": 0.5930566787719727,
1282
+ "learning_rate": 0.0001827669902912621,
1283
+ "loss": 0.8096,
1284
+ "step": 181
1285
+ },
1286
+ {
1287
+ "epoch": 1.6712643678160921,
1288
+ "grad_norm": 0.5918225049972534,
1289
+ "learning_rate": 0.0001820388349514563,
1290
+ "loss": 0.8386,
1291
+ "step": 182
1292
+ },
1293
+ {
1294
+ "epoch": 1.6804597701149424,
1295
+ "grad_norm": 0.5837062001228333,
1296
+ "learning_rate": 0.00018131067961165047,
1297
+ "loss": 0.6873,
1298
+ "step": 183
1299
+ },
1300
+ {
1301
+ "epoch": 1.6896551724137931,
1302
+ "grad_norm": 0.5399461984634399,
1303
+ "learning_rate": 0.00018058252427184462,
1304
+ "loss": 0.8788,
1305
+ "step": 184
1306
+ },
1307
+ {
1308
+ "epoch": 1.6988505747126437,
1309
+ "grad_norm": 0.48315730690956116,
1310
+ "learning_rate": 0.0001798543689320388,
1311
+ "loss": 0.7834,
1312
+ "step": 185
1313
+ },
1314
+ {
1315
+ "epoch": 1.7080459770114942,
1316
+ "grad_norm": 0.5982978343963623,
1317
+ "learning_rate": 0.00017912621359223298,
1318
+ "loss": 0.6913,
1319
+ "step": 186
1320
+ },
1321
+ {
1322
+ "epoch": 1.717241379310345,
1323
+ "grad_norm": 0.9199710488319397,
1324
+ "learning_rate": 0.00017839805825242716,
1325
+ "loss": 0.6592,
1326
+ "step": 187
1327
+ },
1328
+ {
1329
+ "epoch": 1.7264367816091954,
1330
+ "grad_norm": 0.8085829615592957,
1331
+ "learning_rate": 0.00017766990291262133,
1332
+ "loss": 0.7439,
1333
+ "step": 188
1334
+ },
1335
+ {
1336
+ "epoch": 1.735632183908046,
1337
+ "grad_norm": 0.6275731325149536,
1338
+ "learning_rate": 0.0001769417475728155,
1339
+ "loss": 0.7331,
1340
+ "step": 189
1341
+ },
1342
+ {
1343
+ "epoch": 1.7448275862068967,
1344
+ "grad_norm": 0.5255990624427795,
1345
+ "learning_rate": 0.0001762135922330097,
1346
+ "loss": 0.7255,
1347
+ "step": 190
1348
+ },
1349
+ {
1350
+ "epoch": 1.754022988505747,
1351
+ "grad_norm": 0.5680968165397644,
1352
+ "learning_rate": 0.00017548543689320387,
1353
+ "loss": 0.7446,
1354
+ "step": 191
1355
+ },
1356
+ {
1357
+ "epoch": 1.7632183908045977,
1358
+ "grad_norm": 0.5626929402351379,
1359
+ "learning_rate": 0.00017475728155339802,
1360
+ "loss": 0.7948,
1361
+ "step": 192
1362
+ },
1363
+ {
1364
+ "epoch": 1.7724137931034483,
1365
+ "grad_norm": 0.4922776222229004,
1366
+ "learning_rate": 0.0001740291262135922,
1367
+ "loss": 0.6568,
1368
+ "step": 193
1369
+ },
1370
+ {
1371
+ "epoch": 1.7816091954022988,
1372
+ "grad_norm": 0.5294581651687622,
1373
+ "learning_rate": 0.00017330097087378638,
1374
+ "loss": 0.5458,
1375
+ "step": 194
1376
+ },
1377
+ {
1378
+ "epoch": 1.7908045977011495,
1379
+ "grad_norm": 0.5421092510223389,
1380
+ "learning_rate": 0.00017257281553398056,
1381
+ "loss": 0.6159,
1382
+ "step": 195
1383
+ },
1384
+ {
1385
+ "epoch": 1.8,
1386
+ "grad_norm": 0.7755627036094666,
1387
+ "learning_rate": 0.00017184466019417474,
1388
+ "loss": 0.7165,
1389
+ "step": 196
1390
+ },
1391
+ {
1392
+ "epoch": 1.8091954022988506,
1393
+ "grad_norm": 0.9723690748214722,
1394
+ "learning_rate": 0.00017111650485436891,
1395
+ "loss": 0.7743,
1396
+ "step": 197
1397
+ },
1398
+ {
1399
+ "epoch": 1.8183908045977013,
1400
+ "grad_norm": 0.6832698583602905,
1401
+ "learning_rate": 0.0001703883495145631,
1402
+ "loss": 0.7539,
1403
+ "step": 198
1404
+ },
1405
+ {
1406
+ "epoch": 1.8275862068965516,
1407
+ "grad_norm": 0.592229962348938,
1408
+ "learning_rate": 0.00016966019417475724,
1409
+ "loss": 0.6838,
1410
+ "step": 199
1411
+ },
1412
+ {
1413
+ "epoch": 1.8367816091954023,
1414
+ "grad_norm": 0.5979653596878052,
1415
+ "learning_rate": 0.00016893203883495142,
1416
+ "loss": 0.5518,
1417
+ "step": 200
1418
+ },
1419
+ {
1420
+ "epoch": 1.8459770114942529,
1421
+ "grad_norm": 0.5223293304443359,
1422
+ "learning_rate": 0.0001682038834951456,
1423
+ "loss": 0.5327,
1424
+ "step": 201
1425
+ },
1426
+ {
1427
+ "epoch": 1.8551724137931034,
1428
+ "grad_norm": 0.5753535032272339,
1429
+ "learning_rate": 0.00016747572815533978,
1430
+ "loss": 0.5783,
1431
+ "step": 202
1432
+ },
1433
+ {
1434
+ "epoch": 1.8643678160919541,
1435
+ "grad_norm": 0.4552556276321411,
1436
+ "learning_rate": 0.00016674757281553396,
1437
+ "loss": 0.726,
1438
+ "step": 203
1439
+ },
1440
+ {
1441
+ "epoch": 1.8735632183908046,
1442
+ "grad_norm": 0.46313363313674927,
1443
+ "learning_rate": 0.00016601941747572814,
1444
+ "loss": 0.7472,
1445
+ "step": 204
1446
+ },
1447
+ {
1448
+ "epoch": 1.8827586206896552,
1449
+ "grad_norm": 0.7298106551170349,
1450
+ "learning_rate": 0.00016529126213592232,
1451
+ "loss": 0.6869,
1452
+ "step": 205
1453
+ },
1454
+ {
1455
+ "epoch": 1.891954022988506,
1456
+ "grad_norm": 0.45026591420173645,
1457
+ "learning_rate": 0.0001645631067961165,
1458
+ "loss": 0.6929,
1459
+ "step": 206
1460
+ },
1461
+ {
1462
+ "epoch": 1.9011494252873562,
1463
+ "grad_norm": 0.5525459051132202,
1464
+ "learning_rate": 0.00016383495145631065,
1465
+ "loss": 0.6441,
1466
+ "step": 207
1467
+ },
1468
+ {
1469
+ "epoch": 1.910344827586207,
1470
+ "grad_norm": 0.5456161499023438,
1471
+ "learning_rate": 0.00016310679611650483,
1472
+ "loss": 0.8553,
1473
+ "step": 208
1474
+ },
1475
+ {
1476
+ "epoch": 1.9195402298850575,
1477
+ "grad_norm": 0.5439329147338867,
1478
+ "learning_rate": 0.000162378640776699,
1479
+ "loss": 0.7111,
1480
+ "step": 209
1481
+ },
1482
+ {
1483
+ "epoch": 1.928735632183908,
1484
+ "grad_norm": 0.49237221479415894,
1485
+ "learning_rate": 0.00016165048543689318,
1486
+ "loss": 0.6243,
1487
+ "step": 210
1488
+ },
1489
+ {
1490
+ "epoch": 1.9379310344827587,
1491
+ "grad_norm": 0.493568480014801,
1492
+ "learning_rate": 0.00016092233009708736,
1493
+ "loss": 0.5351,
1494
+ "step": 211
1495
+ },
1496
+ {
1497
+ "epoch": 1.9471264367816092,
1498
+ "grad_norm": 0.6934286952018738,
1499
+ "learning_rate": 0.00016019417475728154,
1500
+ "loss": 0.7098,
1501
+ "step": 212
1502
+ },
1503
+ {
1504
+ "epoch": 1.9563218390804598,
1505
+ "grad_norm": 0.47321686148643494,
1506
+ "learning_rate": 0.00015946601941747572,
1507
+ "loss": 0.5246,
1508
+ "step": 213
1509
+ },
1510
+ {
1511
+ "epoch": 1.9655172413793105,
1512
+ "grad_norm": 0.4709272086620331,
1513
+ "learning_rate": 0.0001587378640776699,
1514
+ "loss": 0.5498,
1515
+ "step": 214
1516
+ },
1517
+ {
1518
+ "epoch": 1.9747126436781608,
1519
+ "grad_norm": 0.5461050271987915,
1520
+ "learning_rate": 0.00015800970873786405,
1521
+ "loss": 0.9668,
1522
+ "step": 215
1523
+ },
1524
+ {
1525
+ "epoch": 1.9839080459770115,
1526
+ "grad_norm": 0.5588494539260864,
1527
+ "learning_rate": 0.00015728155339805823,
1528
+ "loss": 0.9515,
1529
+ "step": 216
1530
+ },
1531
+ {
1532
+ "epoch": 1.993103448275862,
1533
+ "grad_norm": 0.6440616846084595,
1534
+ "learning_rate": 0.0001565533980582524,
1535
+ "loss": 0.7871,
1536
+ "step": 217
1537
+ },
1538
+ {
1539
+ "epoch": 2.0,
1540
+ "grad_norm": 0.6609704494476318,
1541
+ "learning_rate": 0.00015582524271844658,
1542
+ "loss": 0.9322,
1543
+ "step": 218
1544
+ },
1545
+ {
1546
+ "epoch": 2.0,
1547
+ "eval_loss": 1.3917137384414673,
1548
+ "eval_runtime": 70.9533,
1549
+ "eval_samples_per_second": 4.679,
1550
+ "eval_steps_per_second": 2.34,
1551
+ "step": 218
1552
+ },
1553
+ {
1554
+ "epoch": 2.0091954022988507,
1555
+ "grad_norm": 0.6179903745651245,
1556
+ "learning_rate": 0.00015509708737864076,
1557
+ "loss": 0.4927,
1558
+ "step": 219
1559
+ },
1560
+ {
1561
+ "epoch": 2.018390804597701,
1562
+ "grad_norm": 0.48804861307144165,
1563
+ "learning_rate": 0.00015436893203883494,
1564
+ "loss": 0.6208,
1565
+ "step": 220
1566
+ },
1567
+ {
1568
+ "epoch": 2.027586206896552,
1569
+ "grad_norm": 0.5461186766624451,
1570
+ "learning_rate": 0.00015364077669902912,
1571
+ "loss": 0.5774,
1572
+ "step": 221
1573
+ },
1574
+ {
1575
+ "epoch": 2.036781609195402,
1576
+ "grad_norm": 0.4856977164745331,
1577
+ "learning_rate": 0.0001529126213592233,
1578
+ "loss": 0.6426,
1579
+ "step": 222
1580
+ },
1581
+ {
1582
+ "epoch": 2.045977011494253,
1583
+ "grad_norm": 0.3683694005012512,
1584
+ "learning_rate": 0.00015218446601941745,
1585
+ "loss": 0.4752,
1586
+ "step": 223
1587
+ },
1588
+ {
1589
+ "epoch": 2.0551724137931036,
1590
+ "grad_norm": 0.5229505300521851,
1591
+ "learning_rate": 0.00015145631067961163,
1592
+ "loss": 0.5244,
1593
+ "step": 224
1594
+ },
1595
+ {
1596
+ "epoch": 2.064367816091954,
1597
+ "grad_norm": 0.4558103084564209,
1598
+ "learning_rate": 0.0001507281553398058,
1599
+ "loss": 0.5453,
1600
+ "step": 225
1601
+ },
1602
+ {
1603
+ "epoch": 2.0735632183908046,
1604
+ "grad_norm": 0.49105018377304077,
1605
+ "learning_rate": 0.00015,
1606
+ "loss": 0.4759,
1607
+ "step": 226
1608
+ },
1609
+ {
1610
+ "epoch": 2.0827586206896553,
1611
+ "grad_norm": 0.6662527322769165,
1612
+ "learning_rate": 0.00014927184466019417,
1613
+ "loss": 0.8146,
1614
+ "step": 227
1615
+ },
1616
+ {
1617
+ "epoch": 2.0919540229885056,
1618
+ "grad_norm": 0.6585009694099426,
1619
+ "learning_rate": 0.00014854368932038834,
1620
+ "loss": 0.4853,
1621
+ "step": 228
1622
+ },
1623
+ {
1624
+ "epoch": 2.1011494252873564,
1625
+ "grad_norm": 0.46196475625038147,
1626
+ "learning_rate": 0.00014781553398058252,
1627
+ "loss": 0.5042,
1628
+ "step": 229
1629
+ },
1630
+ {
1631
+ "epoch": 2.110344827586207,
1632
+ "grad_norm": 0.4975808262825012,
1633
+ "learning_rate": 0.00014708737864077667,
1634
+ "loss": 0.5507,
1635
+ "step": 230
1636
+ },
1637
+ {
1638
+ "epoch": 2.1195402298850574,
1639
+ "grad_norm": 0.4535251259803772,
1640
+ "learning_rate": 0.00014635922330097085,
1641
+ "loss": 0.5138,
1642
+ "step": 231
1643
+ },
1644
+ {
1645
+ "epoch": 2.128735632183908,
1646
+ "grad_norm": 0.5737034678459167,
1647
+ "learning_rate": 0.00014563106796116503,
1648
+ "loss": 0.6338,
1649
+ "step": 232
1650
+ },
1651
+ {
1652
+ "epoch": 2.1379310344827585,
1653
+ "grad_norm": 0.4570606052875519,
1654
+ "learning_rate": 0.0001449029126213592,
1655
+ "loss": 0.4852,
1656
+ "step": 233
1657
+ },
1658
+ {
1659
+ "epoch": 2.147126436781609,
1660
+ "grad_norm": 0.571922242641449,
1661
+ "learning_rate": 0.0001441747572815534,
1662
+ "loss": 0.6671,
1663
+ "step": 234
1664
+ },
1665
+ {
1666
+ "epoch": 2.15632183908046,
1667
+ "grad_norm": 0.5813591480255127,
1668
+ "learning_rate": 0.00014344660194174757,
1669
+ "loss": 0.6764,
1670
+ "step": 235
1671
+ },
1672
+ {
1673
+ "epoch": 2.1655172413793102,
1674
+ "grad_norm": 0.6348188519477844,
1675
+ "learning_rate": 0.00014271844660194175,
1676
+ "loss": 0.5268,
1677
+ "step": 236
1678
+ },
1679
+ {
1680
+ "epoch": 2.174712643678161,
1681
+ "grad_norm": 0.5119661688804626,
1682
+ "learning_rate": 0.00014199029126213592,
1683
+ "loss": 0.6359,
1684
+ "step": 237
1685
+ },
1686
+ {
1687
+ "epoch": 2.1839080459770113,
1688
+ "grad_norm": 0.478588342666626,
1689
+ "learning_rate": 0.00014126213592233008,
1690
+ "loss": 0.6315,
1691
+ "step": 238
1692
+ },
1693
+ {
1694
+ "epoch": 2.193103448275862,
1695
+ "grad_norm": 0.4163134694099426,
1696
+ "learning_rate": 0.00014053398058252425,
1697
+ "loss": 0.5183,
1698
+ "step": 239
1699
+ },
1700
+ {
1701
+ "epoch": 2.2022988505747128,
1702
+ "grad_norm": 0.4251859188079834,
1703
+ "learning_rate": 0.00013980582524271843,
1704
+ "loss": 0.4611,
1705
+ "step": 240
1706
+ },
1707
+ {
1708
+ "epoch": 2.211494252873563,
1709
+ "grad_norm": 0.6032213568687439,
1710
+ "learning_rate": 0.0001390776699029126,
1711
+ "loss": 0.8345,
1712
+ "step": 241
1713
+ },
1714
+ {
1715
+ "epoch": 2.220689655172414,
1716
+ "grad_norm": 0.48562517762184143,
1717
+ "learning_rate": 0.0001383495145631068,
1718
+ "loss": 0.4118,
1719
+ "step": 242
1720
+ },
1721
+ {
1722
+ "epoch": 2.2298850574712645,
1723
+ "grad_norm": 0.45934462547302246,
1724
+ "learning_rate": 0.00013762135922330097,
1725
+ "loss": 0.4099,
1726
+ "step": 243
1727
+ },
1728
+ {
1729
+ "epoch": 2.239080459770115,
1730
+ "grad_norm": 0.5195468068122864,
1731
+ "learning_rate": 0.00013689320388349515,
1732
+ "loss": 0.6766,
1733
+ "step": 244
1734
+ },
1735
+ {
1736
+ "epoch": 2.2482758620689656,
1737
+ "grad_norm": 0.5700232982635498,
1738
+ "learning_rate": 0.00013616504854368933,
1739
+ "loss": 0.8323,
1740
+ "step": 245
1741
+ },
1742
+ {
1743
+ "epoch": 2.2574712643678163,
1744
+ "grad_norm": 0.4179138243198395,
1745
+ "learning_rate": 0.00013543689320388348,
1746
+ "loss": 0.3745,
1747
+ "step": 246
1748
+ },
1749
+ {
1750
+ "epoch": 2.2666666666666666,
1751
+ "grad_norm": 0.5863101482391357,
1752
+ "learning_rate": 0.00013470873786407766,
1753
+ "loss": 0.7907,
1754
+ "step": 247
1755
+ },
1756
+ {
1757
+ "epoch": 2.2758620689655173,
1758
+ "grad_norm": 0.3810423016548157,
1759
+ "learning_rate": 0.00013398058252427184,
1760
+ "loss": 0.3766,
1761
+ "step": 248
1762
+ },
1763
+ {
1764
+ "epoch": 2.2850574712643676,
1765
+ "grad_norm": 0.6277771592140198,
1766
+ "learning_rate": 0.00013325242718446601,
1767
+ "loss": 0.6325,
1768
+ "step": 249
1769
+ },
1770
+ {
1771
+ "epoch": 2.2942528735632184,
1772
+ "grad_norm": 0.5368175506591797,
1773
+ "learning_rate": 0.0001325242718446602,
1774
+ "loss": 0.8255,
1775
+ "step": 250
1776
+ },
1777
+ {
1778
+ "epoch": 2.303448275862069,
1779
+ "grad_norm": 0.5138571262359619,
1780
+ "learning_rate": 0.00013179611650485437,
1781
+ "loss": 0.5017,
1782
+ "step": 251
1783
+ },
1784
+ {
1785
+ "epoch": 2.3126436781609194,
1786
+ "grad_norm": 0.42882323265075684,
1787
+ "learning_rate": 0.00013106796116504852,
1788
+ "loss": 0.4303,
1789
+ "step": 252
1790
+ },
1791
+ {
1792
+ "epoch": 2.32183908045977,
1793
+ "grad_norm": 0.4786723256111145,
1794
+ "learning_rate": 0.0001303398058252427,
1795
+ "loss": 0.5765,
1796
+ "step": 253
1797
+ },
1798
+ {
1799
+ "epoch": 2.3310344827586205,
1800
+ "grad_norm": 0.39283815026283264,
1801
+ "learning_rate": 0.00012961165048543688,
1802
+ "loss": 0.4495,
1803
+ "step": 254
1804
+ },
1805
+ {
1806
+ "epoch": 2.340229885057471,
1807
+ "grad_norm": 0.4181981086730957,
1808
+ "learning_rate": 0.00012888349514563106,
1809
+ "loss": 0.4583,
1810
+ "step": 255
1811
+ },
1812
+ {
1813
+ "epoch": 2.349425287356322,
1814
+ "grad_norm": 0.5347463488578796,
1815
+ "learning_rate": 0.00012815533980582524,
1816
+ "loss": 0.6027,
1817
+ "step": 256
1818
+ },
1819
+ {
1820
+ "epoch": 2.3586206896551722,
1821
+ "grad_norm": 0.578888475894928,
1822
+ "learning_rate": 0.0001274271844660194,
1823
+ "loss": 0.7933,
1824
+ "step": 257
1825
+ },
1826
+ {
1827
+ "epoch": 2.367816091954023,
1828
+ "grad_norm": 0.5870189666748047,
1829
+ "learning_rate": 0.00012669902912621357,
1830
+ "loss": 0.4751,
1831
+ "step": 258
1832
+ },
1833
+ {
1834
+ "epoch": 2.3770114942528737,
1835
+ "grad_norm": 0.43344399333000183,
1836
+ "learning_rate": 0.00012597087378640775,
1837
+ "loss": 0.6022,
1838
+ "step": 259
1839
+ },
1840
+ {
1841
+ "epoch": 2.386206896551724,
1842
+ "grad_norm": 0.5693091750144958,
1843
+ "learning_rate": 0.00012524271844660192,
1844
+ "loss": 0.6392,
1845
+ "step": 260
1846
+ },
1847
+ {
1848
+ "epoch": 2.3954022988505748,
1849
+ "grad_norm": 0.5089174509048462,
1850
+ "learning_rate": 0.0001245145631067961,
1851
+ "loss": 0.6056,
1852
+ "step": 261
1853
+ },
1854
+ {
1855
+ "epoch": 2.4045977011494255,
1856
+ "grad_norm": 0.35980507731437683,
1857
+ "learning_rate": 0.00012378640776699028,
1858
+ "loss": 0.4163,
1859
+ "step": 262
1860
+ },
1861
+ {
1862
+ "epoch": 2.413793103448276,
1863
+ "grad_norm": 0.47071072459220886,
1864
+ "learning_rate": 0.00012305825242718446,
1865
+ "loss": 0.3934,
1866
+ "step": 263
1867
+ },
1868
+ {
1869
+ "epoch": 2.4229885057471265,
1870
+ "grad_norm": 0.44740450382232666,
1871
+ "learning_rate": 0.0001223300970873786,
1872
+ "loss": 0.3688,
1873
+ "step": 264
1874
+ },
1875
+ {
1876
+ "epoch": 2.432183908045977,
1877
+ "grad_norm": 0.3945635259151459,
1878
+ "learning_rate": 0.0001216019417475728,
1879
+ "loss": 0.44,
1880
+ "step": 265
1881
+ },
1882
+ {
1883
+ "epoch": 2.4413793103448276,
1884
+ "grad_norm": 0.5359259843826294,
1885
+ "learning_rate": 0.00012087378640776697,
1886
+ "loss": 0.7224,
1887
+ "step": 266
1888
+ },
1889
+ {
1890
+ "epoch": 2.4505747126436783,
1891
+ "grad_norm": 0.47032058238983154,
1892
+ "learning_rate": 0.00012014563106796115,
1893
+ "loss": 0.5569,
1894
+ "step": 267
1895
+ },
1896
+ {
1897
+ "epoch": 2.4597701149425286,
1898
+ "grad_norm": 0.37549111247062683,
1899
+ "learning_rate": 0.00011941747572815533,
1900
+ "loss": 0.431,
1901
+ "step": 268
1902
+ },
1903
+ {
1904
+ "epoch": 2.4689655172413794,
1905
+ "grad_norm": 0.39742720127105713,
1906
+ "learning_rate": 0.0001186893203883495,
1907
+ "loss": 0.4328,
1908
+ "step": 269
1909
+ },
1910
+ {
1911
+ "epoch": 2.4781609195402297,
1912
+ "grad_norm": 0.3550657629966736,
1913
+ "learning_rate": 0.00011796116504854367,
1914
+ "loss": 0.377,
1915
+ "step": 270
1916
+ },
1917
+ {
1918
+ "epoch": 2.4873563218390804,
1919
+ "grad_norm": 0.4095318615436554,
1920
+ "learning_rate": 0.00011723300970873785,
1921
+ "loss": 0.4171,
1922
+ "step": 271
1923
+ },
1924
+ {
1925
+ "epoch": 2.496551724137931,
1926
+ "grad_norm": 0.512859582901001,
1927
+ "learning_rate": 0.00011650485436893203,
1928
+ "loss": 0.8625,
1929
+ "step": 272
1930
+ },
1931
+ {
1932
+ "epoch": 2.5057471264367814,
1933
+ "grad_norm": 0.3573138117790222,
1934
+ "learning_rate": 0.0001157766990291262,
1935
+ "loss": 0.2954,
1936
+ "step": 273
1937
+ },
1938
+ {
1939
+ "epoch": 2.514942528735632,
1940
+ "grad_norm": 0.38249099254608154,
1941
+ "learning_rate": 0.00011504854368932037,
1942
+ "loss": 0.5005,
1943
+ "step": 274
1944
+ },
1945
+ {
1946
+ "epoch": 2.524137931034483,
1947
+ "grad_norm": 0.47415104508399963,
1948
+ "learning_rate": 0.00011432038834951455,
1949
+ "loss": 0.538,
1950
+ "step": 275
1951
+ },
1952
+ {
1953
+ "epoch": 2.533333333333333,
1954
+ "grad_norm": 0.2491881549358368,
1955
+ "learning_rate": 0.00011359223300970873,
1956
+ "loss": 0.2644,
1957
+ "step": 276
1958
+ },
1959
+ {
1960
+ "epoch": 2.542528735632184,
1961
+ "grad_norm": 0.44782719016075134,
1962
+ "learning_rate": 0.00011286407766990291,
1963
+ "loss": 0.5777,
1964
+ "step": 277
1965
+ },
1966
+ {
1967
+ "epoch": 2.5517241379310347,
1968
+ "grad_norm": 0.416042685508728,
1969
+ "learning_rate": 0.00011213592233009707,
1970
+ "loss": 0.5316,
1971
+ "step": 278
1972
+ },
1973
+ {
1974
+ "epoch": 2.560919540229885,
1975
+ "grad_norm": 0.3350113034248352,
1976
+ "learning_rate": 0.00011140776699029125,
1977
+ "loss": 0.3597,
1978
+ "step": 279
1979
+ },
1980
+ {
1981
+ "epoch": 2.5701149425287357,
1982
+ "grad_norm": 0.2985689640045166,
1983
+ "learning_rate": 0.00011067961165048543,
1984
+ "loss": 0.3409,
1985
+ "step": 280
1986
+ },
1987
+ {
1988
+ "epoch": 2.5793103448275865,
1989
+ "grad_norm": 0.3801935613155365,
1990
+ "learning_rate": 0.00010995145631067961,
1991
+ "loss": 0.4334,
1992
+ "step": 281
1993
+ },
1994
+ {
1995
+ "epoch": 2.5885057471264368,
1996
+ "grad_norm": 0.42416247725486755,
1997
+ "learning_rate": 0.00010922330097087377,
1998
+ "loss": 0.4395,
1999
+ "step": 282
2000
+ },
2001
+ {
2002
+ "epoch": 2.5977011494252875,
2003
+ "grad_norm": 0.5186505913734436,
2004
+ "learning_rate": 0.00010849514563106795,
2005
+ "loss": 0.6245,
2006
+ "step": 283
2007
+ },
2008
+ {
2009
+ "epoch": 2.606896551724138,
2010
+ "grad_norm": 0.3158859312534332,
2011
+ "learning_rate": 0.00010776699029126213,
2012
+ "loss": 0.3056,
2013
+ "step": 284
2014
+ },
2015
+ {
2016
+ "epoch": 2.6160919540229886,
2017
+ "grad_norm": 0.761823832988739,
2018
+ "learning_rate": 0.00010703883495145631,
2019
+ "loss": 0.4312,
2020
+ "step": 285
2021
+ },
2022
+ {
2023
+ "epoch": 2.625287356321839,
2024
+ "grad_norm": 0.38367024064064026,
2025
+ "learning_rate": 0.00010631067961165047,
2026
+ "loss": 0.4427,
2027
+ "step": 286
2028
+ },
2029
+ {
2030
+ "epoch": 2.6344827586206896,
2031
+ "grad_norm": 0.389691561460495,
2032
+ "learning_rate": 0.00010558252427184465,
2033
+ "loss": 0.3895,
2034
+ "step": 287
2035
+ },
2036
+ {
2037
+ "epoch": 2.6436781609195403,
2038
+ "grad_norm": 0.29964563250541687,
2039
+ "learning_rate": 0.00010485436893203883,
2040
+ "loss": 0.2478,
2041
+ "step": 288
2042
+ },
2043
+ {
2044
+ "epoch": 2.6528735632183906,
2045
+ "grad_norm": 0.45362621545791626,
2046
+ "learning_rate": 0.00010412621359223301,
2047
+ "loss": 0.5568,
2048
+ "step": 289
2049
+ },
2050
+ {
2051
+ "epoch": 2.6620689655172414,
2052
+ "grad_norm": 0.509632408618927,
2053
+ "learning_rate": 0.00010339805825242718,
2054
+ "loss": 0.5516,
2055
+ "step": 290
2056
+ },
2057
+ {
2058
+ "epoch": 2.671264367816092,
2059
+ "grad_norm": 0.4448017477989197,
2060
+ "learning_rate": 0.00010266990291262135,
2061
+ "loss": 0.6105,
2062
+ "step": 291
2063
+ },
2064
+ {
2065
+ "epoch": 2.6804597701149424,
2066
+ "grad_norm": 0.3983929455280304,
2067
+ "learning_rate": 0.00010194174757281553,
2068
+ "loss": 0.4041,
2069
+ "step": 292
2070
+ },
2071
+ {
2072
+ "epoch": 2.689655172413793,
2073
+ "grad_norm": 0.43729811906814575,
2074
+ "learning_rate": 0.00010121359223300971,
2075
+ "loss": 0.6012,
2076
+ "step": 293
2077
+ },
2078
+ {
2079
+ "epoch": 2.698850574712644,
2080
+ "grad_norm": 0.38785648345947266,
2081
+ "learning_rate": 0.00010048543689320388,
2082
+ "loss": 0.4812,
2083
+ "step": 294
2084
+ },
2085
+ {
2086
+ "epoch": 2.708045977011494,
2087
+ "grad_norm": 0.6477203369140625,
2088
+ "learning_rate": 9.975728155339806e-05,
2089
+ "loss": 0.8292,
2090
+ "step": 295
2091
+ },
2092
+ {
2093
+ "epoch": 2.717241379310345,
2094
+ "grad_norm": 0.5400519967079163,
2095
+ "learning_rate": 9.902912621359223e-05,
2096
+ "loss": 0.6755,
2097
+ "step": 296
2098
+ },
2099
+ {
2100
+ "epoch": 2.7264367816091957,
2101
+ "grad_norm": 0.39632365107536316,
2102
+ "learning_rate": 9.83009708737864e-05,
2103
+ "loss": 0.4604,
2104
+ "step": 297
2105
+ },
2106
+ {
2107
+ "epoch": 2.735632183908046,
2108
+ "grad_norm": 0.4676194190979004,
2109
+ "learning_rate": 9.757281553398058e-05,
2110
+ "loss": 0.5986,
2111
+ "step": 298
2112
+ },
2113
+ {
2114
+ "epoch": 2.7448275862068967,
2115
+ "grad_norm": 0.34826210141181946,
2116
+ "learning_rate": 9.684466019417476e-05,
2117
+ "loss": 0.4151,
2118
+ "step": 299
2119
+ },
2120
+ {
2121
+ "epoch": 2.754022988505747,
2122
+ "grad_norm": 0.4393360912799835,
2123
+ "learning_rate": 9.611650485436893e-05,
2124
+ "loss": 0.4995,
2125
+ "step": 300
2126
+ },
2127
+ {
2128
+ "epoch": 2.7632183908045977,
2129
+ "grad_norm": 0.39754021167755127,
2130
+ "learning_rate": 9.53883495145631e-05,
2131
+ "loss": 0.4783,
2132
+ "step": 301
2133
+ },
2134
+ {
2135
+ "epoch": 2.772413793103448,
2136
+ "grad_norm": 0.5463854074478149,
2137
+ "learning_rate": 9.466019417475728e-05,
2138
+ "loss": 0.5441,
2139
+ "step": 302
2140
+ },
2141
+ {
2142
+ "epoch": 2.781609195402299,
2143
+ "grad_norm": 0.3881894648075104,
2144
+ "learning_rate": 9.393203883495146e-05,
2145
+ "loss": 0.3949,
2146
+ "step": 303
2147
+ },
2148
+ {
2149
+ "epoch": 2.7908045977011495,
2150
+ "grad_norm": 0.5275911688804626,
2151
+ "learning_rate": 9.320388349514561e-05,
2152
+ "loss": 0.6102,
2153
+ "step": 304
2154
+ },
2155
+ {
2156
+ "epoch": 2.8,
2157
+ "grad_norm": 0.3656928241252899,
2158
+ "learning_rate": 9.247572815533979e-05,
2159
+ "loss": 0.4045,
2160
+ "step": 305
2161
+ },
2162
+ {
2163
+ "epoch": 2.8091954022988506,
2164
+ "grad_norm": 0.35572561621665955,
2165
+ "learning_rate": 9.174757281553397e-05,
2166
+ "loss": 0.3061,
2167
+ "step": 306
2168
+ },
2169
+ {
2170
+ "epoch": 2.8183908045977013,
2171
+ "grad_norm": 0.569115400314331,
2172
+ "learning_rate": 9.101941747572814e-05,
2173
+ "loss": 0.8109,
2174
+ "step": 307
2175
+ },
2176
+ {
2177
+ "epoch": 2.8275862068965516,
2178
+ "grad_norm": 0.29033228754997253,
2179
+ "learning_rate": 9.029126213592231e-05,
2180
+ "loss": 0.317,
2181
+ "step": 308
2182
+ },
2183
+ {
2184
+ "epoch": 2.8367816091954023,
2185
+ "grad_norm": 0.3231950104236603,
2186
+ "learning_rate": 8.956310679611649e-05,
2187
+ "loss": 0.3689,
2188
+ "step": 309
2189
+ },
2190
+ {
2191
+ "epoch": 2.845977011494253,
2192
+ "grad_norm": 0.374177485704422,
2193
+ "learning_rate": 8.883495145631067e-05,
2194
+ "loss": 0.3802,
2195
+ "step": 310
2196
+ },
2197
+ {
2198
+ "epoch": 2.8551724137931034,
2199
+ "grad_norm": 0.25250348448753357,
2200
+ "learning_rate": 8.810679611650485e-05,
2201
+ "loss": 0.236,
2202
+ "step": 311
2203
+ },
2204
+ {
2205
+ "epoch": 2.864367816091954,
2206
+ "grad_norm": 0.5510450005531311,
2207
+ "learning_rate": 8.737864077669901e-05,
2208
+ "loss": 0.6565,
2209
+ "step": 312
2210
+ },
2211
+ {
2212
+ "epoch": 2.873563218390805,
2213
+ "grad_norm": 0.32372424006462097,
2214
+ "learning_rate": 8.665048543689319e-05,
2215
+ "loss": 0.4243,
2216
+ "step": 313
2217
+ },
2218
+ {
2219
+ "epoch": 2.882758620689655,
2220
+ "grad_norm": 0.34822607040405273,
2221
+ "learning_rate": 8.592233009708737e-05,
2222
+ "loss": 0.3775,
2223
+ "step": 314
2224
+ },
2225
+ {
2226
+ "epoch": 2.891954022988506,
2227
+ "grad_norm": 0.535407304763794,
2228
+ "learning_rate": 8.519417475728155e-05,
2229
+ "loss": 0.7348,
2230
+ "step": 315
2231
+ },
2232
+ {
2233
+ "epoch": 2.901149425287356,
2234
+ "grad_norm": 0.46572351455688477,
2235
+ "learning_rate": 8.446601941747571e-05,
2236
+ "loss": 0.5116,
2237
+ "step": 316
2238
+ },
2239
+ {
2240
+ "epoch": 2.910344827586207,
2241
+ "grad_norm": 0.6060393452644348,
2242
+ "learning_rate": 8.373786407766989e-05,
2243
+ "loss": 0.8337,
2244
+ "step": 317
2245
+ },
2246
+ {
2247
+ "epoch": 2.9195402298850572,
2248
+ "grad_norm": 0.3930990397930145,
2249
+ "learning_rate": 8.300970873786407e-05,
2250
+ "loss": 0.4314,
2251
+ "step": 318
2252
+ },
2253
+ {
2254
+ "epoch": 2.928735632183908,
2255
+ "grad_norm": 0.3868286907672882,
2256
+ "learning_rate": 8.228155339805825e-05,
2257
+ "loss": 0.3842,
2258
+ "step": 319
2259
+ },
2260
+ {
2261
+ "epoch": 2.9379310344827587,
2262
+ "grad_norm": 0.5302227139472961,
2263
+ "learning_rate": 8.155339805825241e-05,
2264
+ "loss": 0.7226,
2265
+ "step": 320
2266
+ },
2267
+ {
2268
+ "epoch": 2.947126436781609,
2269
+ "grad_norm": 0.46904534101486206,
2270
+ "learning_rate": 8.082524271844659e-05,
2271
+ "loss": 0.5142,
2272
+ "step": 321
2273
+ },
2274
+ {
2275
+ "epoch": 2.9563218390804598,
2276
+ "grad_norm": 0.4153412878513336,
2277
+ "learning_rate": 8.009708737864077e-05,
2278
+ "loss": 0.4995,
2279
+ "step": 322
2280
+ },
2281
+ {
2282
+ "epoch": 2.9655172413793105,
2283
+ "grad_norm": 0.3775100111961365,
2284
+ "learning_rate": 7.936893203883495e-05,
2285
+ "loss": 0.4082,
2286
+ "step": 323
2287
+ },
2288
+ {
2289
+ "epoch": 2.974712643678161,
2290
+ "grad_norm": 0.49698036909103394,
2291
+ "learning_rate": 7.864077669902911e-05,
2292
+ "loss": 0.58,
2293
+ "step": 324
2294
+ },
2295
+ {
2296
+ "epoch": 2.9839080459770115,
2297
+ "grad_norm": 0.6160023808479309,
2298
+ "learning_rate": 7.791262135922329e-05,
2299
+ "loss": 0.6326,
2300
+ "step": 325
2301
+ },
2302
+ {
2303
+ "epoch": 2.9931034482758623,
2304
+ "grad_norm": 0.5694648623466492,
2305
+ "learning_rate": 7.718446601941747e-05,
2306
+ "loss": 0.5942,
2307
+ "step": 326
2308
+ },
2309
+ {
2310
+ "epoch": 3.0,
2311
+ "grad_norm": 0.6814332604408264,
2312
+ "learning_rate": 7.645631067961165e-05,
2313
+ "loss": 0.7482,
2314
+ "step": 327
2315
+ },
2316
+ {
2317
+ "epoch": 3.0,
2318
+ "eval_loss": 1.406995415687561,
2319
+ "eval_runtime": 70.8982,
2320
+ "eval_samples_per_second": 4.683,
2321
+ "eval_steps_per_second": 2.341,
2322
+ "step": 327
2323
+ },
2324
+ {
2325
+ "epoch": 3.0091954022988507,
2326
+ "grad_norm": 0.3148242235183716,
2327
+ "learning_rate": 7.572815533980581e-05,
2328
+ "loss": 0.2836,
2329
+ "step": 328
2330
+ },
2331
+ {
2332
+ "epoch": 3.018390804597701,
2333
+ "grad_norm": 0.2789768576622009,
2334
+ "learning_rate": 7.5e-05,
2335
+ "loss": 0.2641,
2336
+ "step": 329
2337
+ },
2338
+ {
2339
+ "epoch": 3.027586206896552,
2340
+ "grad_norm": 0.3457227051258087,
2341
+ "learning_rate": 7.427184466019417e-05,
2342
+ "loss": 0.3137,
2343
+ "step": 330
2344
+ },
2345
+ {
2346
+ "epoch": 3.036781609195402,
2347
+ "grad_norm": 0.3316015601158142,
2348
+ "learning_rate": 7.354368932038834e-05,
2349
+ "loss": 0.3261,
2350
+ "step": 331
2351
+ },
2352
+ {
2353
+ "epoch": 3.045977011494253,
2354
+ "grad_norm": 0.44476330280303955,
2355
+ "learning_rate": 7.281553398058252e-05,
2356
+ "loss": 0.446,
2357
+ "step": 332
2358
+ },
2359
+ {
2360
+ "epoch": 3.0551724137931036,
2361
+ "grad_norm": 0.4332521855831146,
2362
+ "learning_rate": 7.20873786407767e-05,
2363
+ "loss": 0.4406,
2364
+ "step": 333
2365
+ },
2366
+ {
2367
+ "epoch": 3.064367816091954,
2368
+ "grad_norm": 0.3380160331726074,
2369
+ "learning_rate": 7.135922330097087e-05,
2370
+ "loss": 0.2874,
2371
+ "step": 334
2372
+ },
2373
+ {
2374
+ "epoch": 3.0735632183908046,
2375
+ "grad_norm": 0.341746985912323,
2376
+ "learning_rate": 7.063106796116504e-05,
2377
+ "loss": 0.306,
2378
+ "step": 335
2379
+ },
2380
+ {
2381
+ "epoch": 3.0827586206896553,
2382
+ "grad_norm": 0.6307492256164551,
2383
+ "learning_rate": 6.990291262135922e-05,
2384
+ "loss": 0.682,
2385
+ "step": 336
2386
+ },
2387
+ {
2388
+ "epoch": 3.0919540229885056,
2389
+ "grad_norm": 0.5883364677429199,
2390
+ "learning_rate": 6.91747572815534e-05,
2391
+ "loss": 0.5423,
2392
+ "step": 337
2393
+ },
2394
+ {
2395
+ "epoch": 3.1011494252873564,
2396
+ "grad_norm": 0.36848077178001404,
2397
+ "learning_rate": 6.844660194174757e-05,
2398
+ "loss": 0.3521,
2399
+ "step": 338
2400
+ },
2401
+ {
2402
+ "epoch": 3.110344827586207,
2403
+ "grad_norm": 0.38027411699295044,
2404
+ "learning_rate": 6.771844660194174e-05,
2405
+ "loss": 0.3215,
2406
+ "step": 339
2407
+ },
2408
+ {
2409
+ "epoch": 3.1195402298850574,
2410
+ "grad_norm": 0.45381873846054077,
2411
+ "learning_rate": 6.699029126213592e-05,
2412
+ "loss": 0.5169,
2413
+ "step": 340
2414
+ },
2415
+ {
2416
+ "epoch": 3.128735632183908,
2417
+ "grad_norm": 0.574475884437561,
2418
+ "learning_rate": 6.62621359223301e-05,
2419
+ "loss": 0.5358,
2420
+ "step": 341
2421
+ },
2422
+ {
2423
+ "epoch": 3.1379310344827585,
2424
+ "grad_norm": 0.6136448979377747,
2425
+ "learning_rate": 6.553398058252426e-05,
2426
+ "loss": 0.7514,
2427
+ "step": 342
2428
+ },
2429
+ {
2430
+ "epoch": 3.147126436781609,
2431
+ "grad_norm": 0.32782498002052307,
2432
+ "learning_rate": 6.480582524271844e-05,
2433
+ "loss": 0.3133,
2434
+ "step": 343
2435
+ },
2436
+ {
2437
+ "epoch": 3.15632183908046,
2438
+ "grad_norm": 0.4657121002674103,
2439
+ "learning_rate": 6.407766990291262e-05,
2440
+ "loss": 0.4632,
2441
+ "step": 344
2442
+ },
2443
+ {
2444
+ "epoch": 3.1655172413793102,
2445
+ "grad_norm": 0.33205467462539673,
2446
+ "learning_rate": 6.334951456310678e-05,
2447
+ "loss": 0.298,
2448
+ "step": 345
2449
+ },
2450
+ {
2451
+ "epoch": 3.174712643678161,
2452
+ "grad_norm": 0.37659305334091187,
2453
+ "learning_rate": 6.262135922330096e-05,
2454
+ "loss": 0.2884,
2455
+ "step": 346
2456
+ },
2457
+ {
2458
+ "epoch": 3.1839080459770113,
2459
+ "grad_norm": 0.47502419352531433,
2460
+ "learning_rate": 6.189320388349514e-05,
2461
+ "loss": 0.5064,
2462
+ "step": 347
2463
+ },
2464
+ {
2465
+ "epoch": 3.193103448275862,
2466
+ "grad_norm": 0.6712875366210938,
2467
+ "learning_rate": 6.11650485436893e-05,
2468
+ "loss": 0.6806,
2469
+ "step": 348
2470
+ },
2471
+ {
2472
+ "epoch": 3.2022988505747128,
2473
+ "grad_norm": 0.5198653340339661,
2474
+ "learning_rate": 6.0436893203883485e-05,
2475
+ "loss": 0.5421,
2476
+ "step": 349
2477
+ },
2478
+ {
2479
+ "epoch": 3.211494252873563,
2480
+ "grad_norm": 0.43809249997138977,
2481
+ "learning_rate": 5.9708737864077663e-05,
2482
+ "loss": 0.4123,
2483
+ "step": 350
2484
+ },
2485
+ {
2486
+ "epoch": 3.220689655172414,
2487
+ "grad_norm": 0.3182849884033203,
2488
+ "learning_rate": 5.8980582524271835e-05,
2489
+ "loss": 0.3025,
2490
+ "step": 351
2491
+ },
2492
+ {
2493
+ "epoch": 3.2298850574712645,
2494
+ "grad_norm": 0.32380396127700806,
2495
+ "learning_rate": 5.8252427184466014e-05,
2496
+ "loss": 0.3006,
2497
+ "step": 352
2498
+ },
2499
+ {
2500
+ "epoch": 3.239080459770115,
2501
+ "grad_norm": 0.32146674394607544,
2502
+ "learning_rate": 5.7524271844660186e-05,
2503
+ "loss": 0.2698,
2504
+ "step": 353
2505
+ },
2506
+ {
2507
+ "epoch": 3.2482758620689656,
2508
+ "grad_norm": 0.3990193009376526,
2509
+ "learning_rate": 5.6796116504854364e-05,
2510
+ "loss": 0.379,
2511
+ "step": 354
2512
+ },
2513
+ {
2514
+ "epoch": 3.2574712643678163,
2515
+ "grad_norm": 0.5906070470809937,
2516
+ "learning_rate": 5.6067961165048536e-05,
2517
+ "loss": 0.5351,
2518
+ "step": 355
2519
+ },
2520
+ {
2521
+ "epoch": 3.2666666666666666,
2522
+ "grad_norm": 0.4367024004459381,
2523
+ "learning_rate": 5.5339805825242715e-05,
2524
+ "loss": 0.4316,
2525
+ "step": 356
2526
+ },
2527
+ {
2528
+ "epoch": 3.2758620689655173,
2529
+ "grad_norm": 0.4074479639530182,
2530
+ "learning_rate": 5.461165048543689e-05,
2531
+ "loss": 0.323,
2532
+ "step": 357
2533
+ },
2534
+ {
2535
+ "epoch": 3.2850574712643676,
2536
+ "grad_norm": 0.3967445194721222,
2537
+ "learning_rate": 5.3883495145631065e-05,
2538
+ "loss": 0.3267,
2539
+ "step": 358
2540
+ },
2541
+ {
2542
+ "epoch": 3.2942528735632184,
2543
+ "grad_norm": 0.4907247722148895,
2544
+ "learning_rate": 5.315533980582524e-05,
2545
+ "loss": 0.4108,
2546
+ "step": 359
2547
+ },
2548
+ {
2549
+ "epoch": 3.303448275862069,
2550
+ "grad_norm": 0.24740606546401978,
2551
+ "learning_rate": 5.2427184466019416e-05,
2552
+ "loss": 0.1978,
2553
+ "step": 360
2554
+ },
2555
+ {
2556
+ "epoch": 3.3126436781609194,
2557
+ "grad_norm": 0.6829200387001038,
2558
+ "learning_rate": 5.169902912621359e-05,
2559
+ "loss": 0.6487,
2560
+ "step": 361
2561
+ },
2562
+ {
2563
+ "epoch": 3.32183908045977,
2564
+ "grad_norm": 0.5345665216445923,
2565
+ "learning_rate": 5.0970873786407766e-05,
2566
+ "loss": 0.4638,
2567
+ "step": 362
2568
+ },
2569
+ {
2570
+ "epoch": 3.3310344827586205,
2571
+ "grad_norm": 0.3852749466896057,
2572
+ "learning_rate": 5.024271844660194e-05,
2573
+ "loss": 0.4437,
2574
+ "step": 363
2575
+ },
2576
+ {
2577
+ "epoch": 3.340229885057471,
2578
+ "grad_norm": 0.3901817202568054,
2579
+ "learning_rate": 4.951456310679612e-05,
2580
+ "loss": 0.425,
2581
+ "step": 364
2582
+ },
2583
+ {
2584
+ "epoch": 3.349425287356322,
2585
+ "grad_norm": 0.5544285178184509,
2586
+ "learning_rate": 4.878640776699029e-05,
2587
+ "loss": 0.4356,
2588
+ "step": 365
2589
+ },
2590
+ {
2591
+ "epoch": 3.3586206896551722,
2592
+ "grad_norm": 0.49693530797958374,
2593
+ "learning_rate": 4.805825242718447e-05,
2594
+ "loss": 0.4442,
2595
+ "step": 366
2596
+ },
2597
+ {
2598
+ "epoch": 3.367816091954023,
2599
+ "grad_norm": 0.48270636796951294,
2600
+ "learning_rate": 4.733009708737864e-05,
2601
+ "loss": 0.5047,
2602
+ "step": 367
2603
+ },
2604
+ {
2605
+ "epoch": 3.3770114942528737,
2606
+ "grad_norm": 0.5815203189849854,
2607
+ "learning_rate": 4.6601941747572804e-05,
2608
+ "loss": 0.7068,
2609
+ "step": 368
2610
+ },
2611
+ {
2612
+ "epoch": 3.386206896551724,
2613
+ "grad_norm": 0.6433053612709045,
2614
+ "learning_rate": 4.587378640776698e-05,
2615
+ "loss": 0.5708,
2616
+ "step": 369
2617
+ },
2618
+ {
2619
+ "epoch": 3.3954022988505748,
2620
+ "grad_norm": 0.35983002185821533,
2621
+ "learning_rate": 4.5145631067961155e-05,
2622
+ "loss": 0.289,
2623
+ "step": 370
2624
+ },
2625
+ {
2626
+ "epoch": 3.4045977011494255,
2627
+ "grad_norm": 0.4140273630619049,
2628
+ "learning_rate": 4.4417475728155334e-05,
2629
+ "loss": 0.4028,
2630
+ "step": 371
2631
+ },
2632
+ {
2633
+ "epoch": 3.413793103448276,
2634
+ "grad_norm": 0.36001721024513245,
2635
+ "learning_rate": 4.3689320388349505e-05,
2636
+ "loss": 0.3798,
2637
+ "step": 372
2638
+ },
2639
+ {
2640
+ "epoch": 3.4229885057471265,
2641
+ "grad_norm": 0.3390791416168213,
2642
+ "learning_rate": 4.2961165048543684e-05,
2643
+ "loss": 0.271,
2644
+ "step": 373
2645
+ },
2646
+ {
2647
+ "epoch": 3.432183908045977,
2648
+ "grad_norm": 0.44555366039276123,
2649
+ "learning_rate": 4.2233009708737856e-05,
2650
+ "loss": 0.3578,
2651
+ "step": 374
2652
+ },
2653
+ {
2654
+ "epoch": 3.4413793103448276,
2655
+ "grad_norm": 0.5408360958099365,
2656
+ "learning_rate": 4.1504854368932035e-05,
2657
+ "loss": 0.6705,
2658
+ "step": 375
2659
+ },
2660
+ {
2661
+ "epoch": 3.4505747126436783,
2662
+ "grad_norm": 0.3276488482952118,
2663
+ "learning_rate": 4.0776699029126206e-05,
2664
+ "loss": 0.302,
2665
+ "step": 376
2666
+ },
2667
+ {
2668
+ "epoch": 3.4597701149425286,
2669
+ "grad_norm": 0.5470909476280212,
2670
+ "learning_rate": 4.0048543689320385e-05,
2671
+ "loss": 0.4292,
2672
+ "step": 377
2673
+ },
2674
+ {
2675
+ "epoch": 3.4689655172413794,
2676
+ "grad_norm": 0.3690268099308014,
2677
+ "learning_rate": 3.932038834951456e-05,
2678
+ "loss": 0.3245,
2679
+ "step": 378
2680
+ },
2681
+ {
2682
+ "epoch": 3.4781609195402297,
2683
+ "grad_norm": 0.5388251543045044,
2684
+ "learning_rate": 3.8592233009708736e-05,
2685
+ "loss": 0.5772,
2686
+ "step": 379
2687
+ },
2688
+ {
2689
+ "epoch": 3.4873563218390804,
2690
+ "grad_norm": 0.39318031072616577,
2691
+ "learning_rate": 3.786407766990291e-05,
2692
+ "loss": 0.3266,
2693
+ "step": 380
2694
+ },
2695
+ {
2696
+ "epoch": 3.496551724137931,
2697
+ "grad_norm": 0.3929058313369751,
2698
+ "learning_rate": 3.7135922330097086e-05,
2699
+ "loss": 0.3401,
2700
+ "step": 381
2701
+ },
2702
+ {
2703
+ "epoch": 3.5057471264367814,
2704
+ "grad_norm": 0.4667484760284424,
2705
+ "learning_rate": 3.640776699029126e-05,
2706
+ "loss": 0.3983,
2707
+ "step": 382
2708
+ },
2709
+ {
2710
+ "epoch": 3.514942528735632,
2711
+ "grad_norm": 0.4457002282142639,
2712
+ "learning_rate": 3.5679611650485437e-05,
2713
+ "loss": 0.3478,
2714
+ "step": 383
2715
+ },
2716
+ {
2717
+ "epoch": 3.524137931034483,
2718
+ "grad_norm": 0.4100305736064911,
2719
+ "learning_rate": 3.495145631067961e-05,
2720
+ "loss": 0.3732,
2721
+ "step": 384
2722
+ },
2723
+ {
2724
+ "epoch": 3.533333333333333,
2725
+ "grad_norm": 0.46938103437423706,
2726
+ "learning_rate": 3.422330097087379e-05,
2727
+ "loss": 0.4959,
2728
+ "step": 385
2729
+ },
2730
+ {
2731
+ "epoch": 3.542528735632184,
2732
+ "grad_norm": 0.6163147687911987,
2733
+ "learning_rate": 3.349514563106796e-05,
2734
+ "loss": 0.6359,
2735
+ "step": 386
2736
+ },
2737
+ {
2738
+ "epoch": 3.5517241379310347,
2739
+ "grad_norm": 0.39543232321739197,
2740
+ "learning_rate": 3.276699029126213e-05,
2741
+ "loss": 0.3193,
2742
+ "step": 387
2743
+ },
2744
+ {
2745
+ "epoch": 3.560919540229885,
2746
+ "grad_norm": 0.3851659297943115,
2747
+ "learning_rate": 3.203883495145631e-05,
2748
+ "loss": 0.2912,
2749
+ "step": 388
2750
+ },
2751
+ {
2752
+ "epoch": 3.5701149425287357,
2753
+ "grad_norm": 0.31686195731163025,
2754
+ "learning_rate": 3.131067961165048e-05,
2755
+ "loss": 0.2545,
2756
+ "step": 389
2757
+ },
2758
+ {
2759
+ "epoch": 3.5793103448275865,
2760
+ "grad_norm": 0.4179750084877014,
2761
+ "learning_rate": 3.058252427184465e-05,
2762
+ "loss": 0.3569,
2763
+ "step": 390
2764
+ },
2765
+ {
2766
+ "epoch": 3.5885057471264368,
2767
+ "grad_norm": 0.49302592873573303,
2768
+ "learning_rate": 2.9854368932038832e-05,
2769
+ "loss": 0.4231,
2770
+ "step": 391
2771
+ },
2772
+ {
2773
+ "epoch": 3.5977011494252875,
2774
+ "grad_norm": 0.4251144826412201,
2775
+ "learning_rate": 2.9126213592233007e-05,
2776
+ "loss": 0.363,
2777
+ "step": 392
2778
+ },
2779
+ {
2780
+ "epoch": 3.606896551724138,
2781
+ "grad_norm": 0.5428581237792969,
2782
+ "learning_rate": 2.8398058252427182e-05,
2783
+ "loss": 0.491,
2784
+ "step": 393
2785
+ },
2786
+ {
2787
+ "epoch": 3.6160919540229886,
2788
+ "grad_norm": 0.4546624720096588,
2789
+ "learning_rate": 2.7669902912621357e-05,
2790
+ "loss": 0.4286,
2791
+ "step": 394
2792
+ },
2793
+ {
2794
+ "epoch": 3.625287356321839,
2795
+ "grad_norm": 0.6219410300254822,
2796
+ "learning_rate": 2.6941747572815533e-05,
2797
+ "loss": 0.5962,
2798
+ "step": 395
2799
+ },
2800
+ {
2801
+ "epoch": 3.6344827586206896,
2802
+ "grad_norm": 0.4943522810935974,
2803
+ "learning_rate": 2.6213592233009708e-05,
2804
+ "loss": 0.3746,
2805
+ "step": 396
2806
+ },
2807
+ {
2808
+ "epoch": 3.6436781609195403,
2809
+ "grad_norm": 0.34759849309921265,
2810
+ "learning_rate": 2.5485436893203883e-05,
2811
+ "loss": 0.3504,
2812
+ "step": 397
2813
+ },
2814
+ {
2815
+ "epoch": 3.6528735632183906,
2816
+ "grad_norm": 0.45892637968063354,
2817
+ "learning_rate": 2.475728155339806e-05,
2818
+ "loss": 0.2571,
2819
+ "step": 398
2820
+ },
2821
+ {
2822
+ "epoch": 3.6620689655172414,
2823
+ "grad_norm": 0.4840629994869232,
2824
+ "learning_rate": 2.4029126213592234e-05,
2825
+ "loss": 0.4038,
2826
+ "step": 399
2827
+ },
2828
+ {
2829
+ "epoch": 3.671264367816092,
2830
+ "grad_norm": 0.5587469339370728,
2831
+ "learning_rate": 2.3300970873786402e-05,
2832
+ "loss": 0.6057,
2833
+ "step": 400
2834
+ },
2835
+ {
2836
+ "epoch": 3.6804597701149424,
2837
+ "grad_norm": 0.30649712681770325,
2838
+ "learning_rate": 2.2572815533980577e-05,
2839
+ "loss": 0.2603,
2840
+ "step": 401
2841
+ },
2842
+ {
2843
+ "epoch": 3.689655172413793,
2844
+ "grad_norm": 0.41518911719322205,
2845
+ "learning_rate": 2.1844660194174753e-05,
2846
+ "loss": 0.3146,
2847
+ "step": 402
2848
+ },
2849
+ {
2850
+ "epoch": 3.698850574712644,
2851
+ "grad_norm": 0.596571147441864,
2852
+ "learning_rate": 2.1116504854368928e-05,
2853
+ "loss": 0.6675,
2854
+ "step": 403
2855
+ },
2856
+ {
2857
+ "epoch": 3.708045977011494,
2858
+ "grad_norm": 0.4106796085834503,
2859
+ "learning_rate": 2.0388349514563103e-05,
2860
+ "loss": 0.4136,
2861
+ "step": 404
2862
+ },
2863
+ {
2864
+ "epoch": 3.717241379310345,
2865
+ "grad_norm": 0.5261825323104858,
2866
+ "learning_rate": 1.966019417475728e-05,
2867
+ "loss": 0.6104,
2868
+ "step": 405
2869
+ },
2870
+ {
2871
+ "epoch": 3.7264367816091957,
2872
+ "grad_norm": 0.5117531418800354,
2873
+ "learning_rate": 1.8932038834951454e-05,
2874
+ "loss": 0.4088,
2875
+ "step": 406
2876
+ },
2877
+ {
2878
+ "epoch": 3.735632183908046,
2879
+ "grad_norm": 0.46011051535606384,
2880
+ "learning_rate": 1.820388349514563e-05,
2881
+ "loss": 0.3203,
2882
+ "step": 407
2883
+ },
2884
+ {
2885
+ "epoch": 3.7448275862068967,
2886
+ "grad_norm": 0.5213779211044312,
2887
+ "learning_rate": 1.7475728155339804e-05,
2888
+ "loss": 0.4547,
2889
+ "step": 408
2890
+ },
2891
+ {
2892
+ "epoch": 3.754022988505747,
2893
+ "grad_norm": 0.6189706921577454,
2894
+ "learning_rate": 1.674757281553398e-05,
2895
+ "loss": 0.4992,
2896
+ "step": 409
2897
+ },
2898
+ {
2899
+ "epoch": 3.7632183908045977,
2900
+ "grad_norm": 0.38668373227119446,
2901
+ "learning_rate": 1.6019417475728155e-05,
2902
+ "loss": 0.3237,
2903
+ "step": 410
2904
+ },
2905
+ {
2906
+ "epoch": 3.772413793103448,
2907
+ "grad_norm": 0.6517217755317688,
2908
+ "learning_rate": 1.5291262135922327e-05,
2909
+ "loss": 0.6421,
2910
+ "step": 411
2911
+ },
2912
+ {
2913
+ "epoch": 3.781609195402299,
2914
+ "grad_norm": 0.4396495223045349,
2915
+ "learning_rate": 1.4563106796116503e-05,
2916
+ "loss": 0.4529,
2917
+ "step": 412
2918
+ },
2919
+ {
2920
+ "epoch": 3.7908045977011495,
2921
+ "grad_norm": 0.5464988350868225,
2922
+ "learning_rate": 1.3834951456310679e-05,
2923
+ "loss": 0.5085,
2924
+ "step": 413
2925
+ },
2926
+ {
2927
+ "epoch": 3.8,
2928
+ "grad_norm": 0.49847450852394104,
2929
+ "learning_rate": 1.3106796116504854e-05,
2930
+ "loss": 0.4448,
2931
+ "step": 414
2932
+ },
2933
+ {
2934
+ "epoch": 3.8091954022988506,
2935
+ "grad_norm": 0.26215147972106934,
2936
+ "learning_rate": 1.237864077669903e-05,
2937
+ "loss": 0.207,
2938
+ "step": 415
2939
+ },
2940
+ {
2941
+ "epoch": 3.8183908045977013,
2942
+ "grad_norm": 0.5166394710540771,
2943
+ "learning_rate": 1.1650485436893201e-05,
2944
+ "loss": 0.4386,
2945
+ "step": 416
2946
+ },
2947
+ {
2948
+ "epoch": 3.8275862068965516,
2949
+ "grad_norm": 0.3470999002456665,
2950
+ "learning_rate": 1.0922330097087376e-05,
2951
+ "loss": 0.3337,
2952
+ "step": 417
2953
+ },
2954
+ {
2955
+ "epoch": 3.8367816091954023,
2956
+ "grad_norm": 0.41472527384757996,
2957
+ "learning_rate": 1.0194174757281552e-05,
2958
+ "loss": 0.3873,
2959
+ "step": 418
2960
+ },
2961
+ {
2962
+ "epoch": 3.845977011494253,
2963
+ "grad_norm": 0.3731400668621063,
2964
+ "learning_rate": 9.466019417475727e-06,
2965
+ "loss": 0.3003,
2966
+ "step": 419
2967
+ },
2968
+ {
2969
+ "epoch": 3.8551724137931034,
2970
+ "grad_norm": 0.4794781506061554,
2971
+ "learning_rate": 8.737864077669902e-06,
2972
+ "loss": 0.4373,
2973
+ "step": 420
2974
+ },
2975
+ {
2976
+ "epoch": 3.864367816091954,
2977
+ "grad_norm": 0.4784807562828064,
2978
+ "learning_rate": 8.009708737864077e-06,
2979
+ "loss": 0.3727,
2980
+ "step": 421
2981
+ },
2982
+ {
2983
+ "epoch": 3.873563218390805,
2984
+ "grad_norm": 0.4147201478481293,
2985
+ "learning_rate": 7.281553398058252e-06,
2986
+ "loss": 0.416,
2987
+ "step": 422
2988
+ },
2989
+ {
2990
+ "epoch": 3.882758620689655,
2991
+ "grad_norm": 0.33760857582092285,
2992
+ "learning_rate": 6.553398058252427e-06,
2993
+ "loss": 0.2351,
2994
+ "step": 423
2995
+ },
2996
+ {
2997
+ "epoch": 3.891954022988506,
2998
+ "grad_norm": 0.38601207733154297,
2999
+ "learning_rate": 5.8252427184466006e-06,
3000
+ "loss": 0.328,
3001
+ "step": 424
3002
+ },
3003
+ {
3004
+ "epoch": 3.901149425287356,
3005
+ "grad_norm": 0.5886791944503784,
3006
+ "learning_rate": 5.097087378640776e-06,
3007
+ "loss": 0.523,
3008
+ "step": 425
3009
+ },
3010
+ {
3011
+ "epoch": 3.910344827586207,
3012
+ "grad_norm": 0.497087687253952,
3013
+ "learning_rate": 4.368932038834951e-06,
3014
+ "loss": 0.4786,
3015
+ "step": 426
3016
+ },
3017
+ {
3018
+ "epoch": 3.9195402298850572,
3019
+ "grad_norm": 0.29946476221084595,
3020
+ "learning_rate": 3.640776699029126e-06,
3021
+ "loss": 0.208,
3022
+ "step": 427
3023
+ },
3024
+ {
3025
+ "epoch": 3.928735632183908,
3026
+ "grad_norm": 0.4071413576602936,
3027
+ "learning_rate": 2.9126213592233003e-06,
3028
+ "loss": 0.3595,
3029
+ "step": 428
3030
+ },
3031
+ {
3032
+ "epoch": 3.9379310344827587,
3033
+ "grad_norm": 0.4986608624458313,
3034
+ "learning_rate": 2.1844660194174755e-06,
3035
+ "loss": 0.3931,
3036
+ "step": 429
3037
+ },
3038
+ {
3039
+ "epoch": 3.947126436781609,
3040
+ "grad_norm": 0.32442793250083923,
3041
+ "learning_rate": 1.4563106796116501e-06,
3042
+ "loss": 0.4026,
3043
+ "step": 430
3044
+ },
3045
+ {
3046
+ "epoch": 3.9563218390804598,
3047
+ "grad_norm": 0.6014803051948547,
3048
+ "learning_rate": 7.281553398058251e-07,
3049
+ "loss": 0.6049,
3050
+ "step": 431
3051
+ },
3052
+ {
3053
+ "epoch": 3.9655172413793105,
3054
+ "grad_norm": 0.6689134836196899,
3055
+ "learning_rate": 0.0,
3056
+ "loss": 0.6334,
3057
+ "step": 432
3058
+ },
3059
+ {
3060
+ "epoch": 3.9655172413793105,
3061
+ "eval_loss": 1.4621280431747437,
3062
+ "eval_runtime": 70.3815,
3063
+ "eval_samples_per_second": 4.717,
3064
+ "eval_steps_per_second": 2.359,
3065
+ "step": 432
3066
+ }
3067
+ ],
3068
+ "logging_steps": 1,
3069
+ "max_steps": 432,
3070
+ "num_input_tokens_seen": 0,
3071
+ "num_train_epochs": 4,
3072
+ "save_steps": 500,
3073
+ "stateful_callbacks": {
3074
+ "TrainerControl": {
3075
+ "args": {
3076
+ "should_epoch_stop": false,
3077
+ "should_evaluate": false,
3078
+ "should_log": false,
3079
+ "should_save": true,
3080
+ "should_training_stop": true
3081
+ },
3082
+ "attributes": {}
3083
+ }
3084
+ },
3085
+ "total_flos": 3.5357902367421235e+17,
3086
+ "train_batch_size": 4,
3087
+ "trial_name": null,
3088
+ "trial_params": null
3089
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acd81a569a42721e920ace2751b5c751ad3a84c069d98ec31b55ba48b6c15f42
3
+ size 5816