Hugging Face's logo

jjee2
/
lora_recycle

TensorBoard
Safetensors
GGUF
conversational
Model card Files
xet
 Metrics Community
jjee2 commited on
Commit
8b943b6
·
verified ·
1 Parent(s): f6e7181

Add Espresso-AI__search-llm

Browse files
Files changed (13) hide show
  1. .gitattributes +1 -0
  2. Espresso-AI__search-llm/.gitattributes +36 -0
  3. Espresso-AI__search-llm/README.md +202 -0
  4. Espresso-AI__search-llm/adapter_config.json +37 -0
  5. Espresso-AI__search-llm/adapter_model.safetensors +3 -0
  6. Espresso-AI__search-llm/optimizer.pt +3 -0
  7. Espresso-AI__search-llm/rng_state.pth +3 -0
  8. Espresso-AI__search-llm/scheduler.pt +3 -0
  9. Espresso-AI__search-llm/special_tokens_map.json +23 -0
  10. Espresso-AI__search-llm/tokenizer.json +3 -0
  11. Espresso-AI__search-llm/tokenizer_config.json +2065 -0
  12. Espresso-AI__search-llm/trainer_state.json +3526 -0
  13. Espresso-AI__search-llm/training_args.bin +3 -0
.gitattributes CHANGED
@@ -635,3 +635,4 @@ Adun__Meta-Llama-3.1-8B-FP16-Instruct-sql-v2/checkpoint-1000/tokenizer.json filt
635
  Adun__Meta-Llama-3.1-8B-FP16-Instruct-sql-v2/checkpoint-1128/tokenizer.json filter=lfs diff=lfs merge=lfs -text
636
  Adun__Meta-Llama-3.1-8B-FP16-Instruct-sql-v2/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
637
  leedahyeon__0226_origin_data/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
635
  Adun__Meta-Llama-3.1-8B-FP16-Instruct-sql-v2/checkpoint-1128/tokenizer.json filter=lfs diff=lfs merge=lfs -text
636
  Adun__Meta-Llama-3.1-8B-FP16-Instruct-sql-v2/checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
637
  leedahyeon__0226_origin_data/tokenizer.json filter=lfs diff=lfs merge=lfs -text
638
+ Espresso-AI__search-llm/tokenizer.json filter=lfs diff=lfs merge=lfs -text
Espresso-AI__search-llm/.gitattributes ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tar filter=lfs diff=lfs merge=lfs -text
29
+ *.tflite filter=lfs diff=lfs merge=lfs -text
30
+ *.tgz filter=lfs diff=lfs merge=lfs -text
31
+ *.wasm filter=lfs diff=lfs merge=lfs -text
32
+ *.xz 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
Espresso-AI__search-llm/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/Meta-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
Espresso-AI__search-llm/adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/Meta-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": 128,
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": 64,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "o_proj",
27
+ "down_proj",
28
+ "v_proj",
29
+ "k_proj",
30
+ "up_proj",
31
+ "gate_proj",
32
+ "q_proj"
33
+ ],
34
+ "task_type": "CAUSAL_LM",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
Espresso-AI__search-llm/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ac8b36f7140baaf1142284ae1df74254aedd0821e75650c661f2de09bb09a4a
3
+ size 671149168
Espresso-AI__search-llm/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:788ef3ed37d90da5943878ee0818b0bba3dee7f2a544215f8a4172ecbf42df6a
3
+ size 1342555602
Espresso-AI__search-llm/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca9022b20613501d7bacff4c4ef0a5c0dfdb4a0c6064de9c44161f6f6991b9d5
3
+ size 14244
Espresso-AI__search-llm/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bafb43f78038685b4b43f960d76d6887f563b198db907d83236411719feb94b2
3
+ size 1064
Espresso-AI__search-llm/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|finetune_right_pad_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
Espresso-AI__search-llm/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f90a0ee1b41702c7b233b02234294a53bc0684a08d3bcd8c8ff702e9a12f64
3
+ size 17210019
Espresso-AI__search-llm/tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "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",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "extra_special_tokens": {},
2057
+ "model_input_names": [
2058
+ "input_ids",
2059
+ "attention_mask"
2060
+ ],
2061
+ "model_max_length": 131072,
2062
+ "pad_token": "<|finetune_right_pad_id|>",
2063
+ "padding_side": "right",
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
Espresso-AI__search-llm/trainer_state.json ADDED
@@ -0,0 +1,3526 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 24996,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008001280204832774,
13
+ "grad_norm": 0.9324016571044922,
14
+ "learning_rate": 2.0000000000000003e-06,
15
+ "loss": 2.0562,
16
+ "step": 50
17
+ },
18
+ {
19
+ "epoch": 0.016002560409665547,
20
+ "grad_norm": 0.4582217037677765,
21
+ "learning_rate": 4.000000000000001e-06,
22
+ "loss": 1.9037,
23
+ "step": 100
24
+ },
25
+ {
26
+ "epoch": 0.02400384061449832,
27
+ "grad_norm": 0.6721668243408203,
28
+ "learning_rate": 6e-06,
29
+ "loss": 1.6957,
30
+ "step": 150
31
+ },
32
+ {
33
+ "epoch": 0.032005120819331094,
34
+ "grad_norm": 0.6238133907318115,
35
+ "learning_rate": 8.000000000000001e-06,
36
+ "loss": 1.5897,
37
+ "step": 200
38
+ },
39
+ {
40
+ "epoch": 0.04000640102416387,
41
+ "grad_norm": 0.6062737703323364,
42
+ "learning_rate": 1e-05,
43
+ "loss": 1.5664,
44
+ "step": 250
45
+ },
46
+ {
47
+ "epoch": 0.04800768122899664,
48
+ "grad_norm": 0.6185649633407593,
49
+ "learning_rate": 1.2e-05,
50
+ "loss": 1.5315,
51
+ "step": 300
52
+ },
53
+ {
54
+ "epoch": 0.05600896143382941,
55
+ "grad_norm": 0.6351732611656189,
56
+ "learning_rate": 1.4000000000000001e-05,
57
+ "loss": 1.4996,
58
+ "step": 350
59
+ },
60
+ {
61
+ "epoch": 0.06401024163866219,
62
+ "grad_norm": 0.6717058420181274,
63
+ "learning_rate": 1.6000000000000003e-05,
64
+ "loss": 1.4784,
65
+ "step": 400
66
+ },
67
+ {
68
+ "epoch": 0.07201152184349496,
69
+ "grad_norm": 0.6665578484535217,
70
+ "learning_rate": 1.8e-05,
71
+ "loss": 1.4795,
72
+ "step": 450
73
+ },
74
+ {
75
+ "epoch": 0.08001280204832774,
76
+ "grad_norm": 0.5694233775138855,
77
+ "learning_rate": 2e-05,
78
+ "loss": 1.4583,
79
+ "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.0880140822531605,
83
+ "grad_norm": 0.6044241786003113,
84
+ "learning_rate": 2.2000000000000003e-05,
85
+ "loss": 1.4392,
86
+ "step": 550
87
+ },
88
+ {
89
+ "epoch": 0.09601536245799328,
90
+ "grad_norm": 0.6153579354286194,
91
+ "learning_rate": 2.4e-05,
92
+ "loss": 1.436,
93
+ "step": 600
94
+ },
95
+ {
96
+ "epoch": 0.10401664266282605,
97
+ "grad_norm": 0.5287560224533081,
98
+ "learning_rate": 2.6000000000000002e-05,
99
+ "loss": 1.4244,
100
+ "step": 650
101
+ },
102
+ {
103
+ "epoch": 0.11201792286765883,
104
+ "grad_norm": 0.5597755908966064,
105
+ "learning_rate": 2.8000000000000003e-05,
106
+ "loss": 1.4369,
107
+ "step": 700
108
+ },
109
+ {
110
+ "epoch": 0.1200192030724916,
111
+ "grad_norm": 0.4981745183467865,
112
+ "learning_rate": 3e-05,
113
+ "loss": 1.3981,
114
+ "step": 750
115
+ },
116
+ {
117
+ "epoch": 0.12802048327732438,
118
+ "grad_norm": 0.48743560910224915,
119
+ "learning_rate": 3.2000000000000005e-05,
120
+ "loss": 1.4009,
121
+ "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.13602176348215714,
125
+ "grad_norm": 0.5637604594230652,
126
+ "learning_rate": 3.4000000000000007e-05,
127
+ "loss": 1.4028,
128
+ "step": 850
129
+ },
130
+ {
131
+ "epoch": 0.14402304368698993,
132
+ "grad_norm": 0.470486581325531,
133
+ "learning_rate": 3.6e-05,
134
+ "loss": 1.3938,
135
+ "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.1520243238918227,
139
+ "grad_norm": 0.5075104236602783,
140
+ "learning_rate": 3.8e-05,
141
+ "loss": 1.3859,
142
+ "step": 950
143
+ },
144
+ {
145
+ "epoch": 0.16002560409665548,
146
+ "grad_norm": 0.4708271324634552,
147
+ "learning_rate": 4e-05,
148
+ "loss": 1.3865,
149
+ "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.16802688430148824,
153
+ "grad_norm": 0.3994545638561249,
154
+ "learning_rate": 4.2e-05,
155
+ "loss": 1.4072,
156
+ "step": 1050
157
+ },
158
+ {
159
+ "epoch": 0.176028164506321,
160
+ "grad_norm": 0.4936317801475525,
161
+ "learning_rate": 4.4000000000000006e-05,
162
+ "loss": 1.3828,
163
+ "step": 1100
164
+ },
165
+ {
166
+ "epoch": 0.1840294447111538,
167
+ "grad_norm": 0.3775925934314728,
168
+ "learning_rate": 4.600000000000001e-05,
169
+ "loss": 1.4046,
170
+ "step": 1150
171
+ },
172
+ {
173
+ "epoch": 0.19203072491598655,
174
+ "grad_norm": 0.45916563272476196,
175
+ "learning_rate": 4.8e-05,
176
+ "loss": 1.3725,
177
+ "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.20003200512081934,
181
+ "grad_norm": 0.42247775197029114,
182
+ "learning_rate": 5e-05,
183
+ "loss": 1.371,
184
+ "step": 1250
185
+ },
186
+ {
187
+ "epoch": 0.2080332853256521,
188
+ "grad_norm": 0.4264281392097473,
189
+ "learning_rate": 5.2000000000000004e-05,
190
+ "loss": 1.3729,
191
+ "step": 1300
192
+ },
193
+ {
194
+ "epoch": 0.2160345655304849,
195
+ "grad_norm": 0.3741685152053833,
196
+ "learning_rate": 5.4000000000000005e-05,
197
+ "loss": 1.3621,
198
+ "step": 1350
199
+ },
200
+ {
201
+ "epoch": 0.22403584573531765,
202
+ "grad_norm": 0.392640084028244,
203
+ "learning_rate": 5.6000000000000006e-05,
204
+ "loss": 1.3557,
205
+ "step": 1400
206
+ },
207
+ {
208
+ "epoch": 0.2320371259401504,
209
+ "grad_norm": 0.3837718367576599,
210
+ "learning_rate": 5.8e-05,
211
+ "loss": 1.3599,
212
+ "step": 1450
213
+ },
214
+ {
215
+ "epoch": 0.2400384061449832,
216
+ "grad_norm": 0.36931145191192627,
217
+ "learning_rate": 6e-05,
218
+ "loss": 1.3527,
219
+ "step": 1500
220
+ },
221
+ {
222
+ "epoch": 0.24803968634981596,
223
+ "grad_norm": 0.4106380343437195,
224
+ "learning_rate": 6.2e-05,
225
+ "loss": 1.3531,
226
+ "step": 1550
227
+ },
228
+ {
229
+ "epoch": 0.25604096655464875,
230
+ "grad_norm": 0.41261059045791626,
231
+ "learning_rate": 6.400000000000001e-05,
232
+ "loss": 1.3722,
233
+ "step": 1600
234
+ },
235
+ {
236
+ "epoch": 0.2640422467594815,
237
+ "grad_norm": 0.3928689658641815,
238
+ "learning_rate": 6.6e-05,
239
+ "loss": 1.3423,
240
+ "step": 1650
241
+ },
242
+ {
243
+ "epoch": 0.2720435269643143,
244
+ "grad_norm": 0.4072926640510559,
245
+ "learning_rate": 6.800000000000001e-05,
246
+ "loss": 1.3458,
247
+ "step": 1700
248
+ },
249
+ {
250
+ "epoch": 0.28004480716914704,
251
+ "grad_norm": 0.3700864315032959,
252
+ "learning_rate": 7e-05,
253
+ "loss": 1.3566,
254
+ "step": 1750
255
+ },
256
+ {
257
+ "epoch": 0.28804608737397985,
258
+ "grad_norm": 0.36805135011672974,
259
+ "learning_rate": 7.2e-05,
260
+ "loss": 1.3124,
261
+ "step": 1800
262
+ },
263
+ {
264
+ "epoch": 0.2960473675788126,
265
+ "grad_norm": 0.39832988381385803,
266
+ "learning_rate": 7.4e-05,
267
+ "loss": 1.3408,
268
+ "step": 1850
269
+ },
270
+ {
271
+ "epoch": 0.3040486477836454,
272
+ "grad_norm": 0.4116155505180359,
273
+ "learning_rate": 7.6e-05,
274
+ "loss": 1.3259,
275
+ "step": 1900
276
+ },
277
+ {
278
+ "epoch": 0.31204992798847814,
279
+ "grad_norm": 0.3844102919101715,
280
+ "learning_rate": 7.800000000000001e-05,
281
+ "loss": 1.3223,
282
+ "step": 1950
283
+ },
284
+ {
285
+ "epoch": 0.32005120819331095,
286
+ "grad_norm": 0.36435940861701965,
287
+ "learning_rate": 8e-05,
288
+ "loss": 1.3493,
289
+ "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.3280524883981437,
293
+ "grad_norm": 0.40303346514701843,
294
+ "learning_rate": 8.2e-05,
295
+ "loss": 1.313,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.3360537686029765,
300
+ "grad_norm": 0.3959302604198456,
301
+ "learning_rate": 8.4e-05,
302
+ "loss": 1.3116,
303
+ "step": 2100
304
+ },
305
+ {
306
+ "epoch": 0.34405504880780924,
307
+ "grad_norm": 0.42148756980895996,
308
+ "learning_rate": 8.6e-05,
309
+ "loss": 1.3172,
310
+ "step": 2150
311
+ },
312
+ {
313
+ "epoch": 0.352056329012642,
314
+ "grad_norm": 0.35398295521736145,
315
+ "learning_rate": 8.800000000000001e-05,
316
+ "loss": 1.3123,
317
+ "step": 2200
318
+ },
319
+ {
320
+ "epoch": 0.3600576092174748,
321
+ "grad_norm": 0.32611459493637085,
322
+ "learning_rate": 9e-05,
323
+ "loss": 1.3291,
324
+ "step": 2250
325
+ },
326
+ {
327
+ "epoch": 0.3680588894223076,
328
+ "grad_norm": 0.3089679777622223,
329
+ "learning_rate": 9.200000000000001e-05,
330
+ "loss": 1.3162,
331
+ "step": 2300
332
+ },
333
+ {
334
+ "epoch": 0.37606016962714034,
335
+ "grad_norm": 0.38052898645401,
336
+ "learning_rate": 9.4e-05,
337
+ "loss": 1.2888,
338
+ "step": 2350
339
+ },
340
+ {
341
+ "epoch": 0.3840614498319731,
342
+ "grad_norm": 0.40810805559158325,
343
+ "learning_rate": 9.6e-05,
344
+ "loss": 1.292,
345
+ "step": 2400
346
+ },
347
+ {
348
+ "epoch": 0.39206273003680586,
349
+ "grad_norm": 0.3573181927204132,
350
+ "learning_rate": 9.8e-05,
351
+ "loss": 1.3094,
352
+ "step": 2450
353
+ },
354
+ {
355
+ "epoch": 0.4000640102416387,
356
+ "grad_norm": 0.3486098349094391,
357
+ "learning_rate": 0.0001,
358
+ "loss": 1.2908,
359
+ "step": 2500
360
+ },
361
+ {
362
+ "epoch": 0.40806529044647144,
363
+ "grad_norm": 0.4237920045852661,
364
+ "learning_rate": 9.999878110192404e-05,
365
+ "loss": 1.2868,
366
+ "step": 2550
367
+ },
368
+ {
369
+ "epoch": 0.4160665706513042,
370
+ "grad_norm": 0.3493655025959015,
371
+ "learning_rate": 9.999512446712467e-05,
372
+ "loss": 1.3221,
373
+ "step": 2600
374
+ },
375
+ {
376
+ "epoch": 0.42406785085613696,
377
+ "grad_norm": 0.3716041147708893,
378
+ "learning_rate": 9.998903027388448e-05,
379
+ "loss": 1.2728,
380
+ "step": 2650
381
+ },
382
+ {
383
+ "epoch": 0.4320691310609698,
384
+ "grad_norm": 0.43094709515571594,
385
+ "learning_rate": 9.998049881933149e-05,
386
+ "loss": 1.2864,
387
+ "step": 2700
388
+ },
389
+ {
390
+ "epoch": 0.44007041126580254,
391
+ "grad_norm": 0.379719078540802,
392
+ "learning_rate": 9.996953051942463e-05,
393
+ "loss": 1.2956,
394
+ "step": 2750
395
+ },
396
+ {
397
+ "epoch": 0.4480716914706353,
398
+ "grad_norm": 0.45424267649650574,
399
+ "learning_rate": 9.995612590893352e-05,
400
+ "loss": 1.2927,
401
+ "step": 2800
402
+ },
403
+ {
404
+ "epoch": 0.45607297167546806,
405
+ "grad_norm": 0.34709858894348145,
406
+ "learning_rate": 9.99402856414123e-05,
407
+ "loss": 1.2801,
408
+ "step": 2850
409
+ },
410
+ {
411
+ "epoch": 0.4640742518803008,
412
+ "grad_norm": 0.3956676423549652,
413
+ "learning_rate": 9.992201048916783e-05,
414
+ "loss": 1.2869,
415
+ "step": 2900
416
+ },
417
+ {
418
+ "epoch": 0.47207553208513364,
419
+ "grad_norm": 0.3462512493133545,
420
+ "learning_rate": 9.990130134322201e-05,
421
+ "loss": 1.268,
422
+ "step": 2950
423
+ },
424
+ {
425
+ "epoch": 0.4800768122899664,
426
+ "grad_norm": 0.3835497796535492,
427
+ "learning_rate": 9.987815921326842e-05,
428
+ "loss": 1.254,
429
+ "step": 3000
430
+ },
431
+ {
432
+ "epoch": 0.48807809249479917,
433
+ "grad_norm": 0.37989285588264465,
434
+ "learning_rate": 9.98525852276229e-05,
435
+ "loss": 1.2869,
436
+ "step": 3050
437
+ },
438
+ {
439
+ "epoch": 0.4960793726996319,
440
+ "grad_norm": 0.3443322777748108,
441
+ "learning_rate": 9.982458063316877e-05,
442
+ "loss": 1.2933,
443
+ "step": 3100
444
+ },
445
+ {
446
+ "epoch": 0.5040806529044647,
447
+ "grad_norm": 0.32426556944847107,
448
+ "learning_rate": 9.979414679529588e-05,
449
+ "loss": 1.2756,
450
+ "step": 3150
451
+ },
452
+ {
453
+ "epoch": 0.5120819331092975,
454
+ "grad_norm": 0.4362022578716278,
455
+ "learning_rate": 9.976128519783405e-05,
456
+ "loss": 1.251,
457
+ "step": 3200
458
+ },
459
+ {
460
+ "epoch": 0.5200832133141302,
461
+ "grad_norm": 0.3969637155532837,
462
+ "learning_rate": 9.972599744298086e-05,
463
+ "loss": 1.2593,
464
+ "step": 3250
465
+ },
466
+ {
467
+ "epoch": 0.528084493518963,
468
+ "grad_norm": 0.41199642419815063,
469
+ "learning_rate": 9.96882852512233e-05,
470
+ "loss": 1.2484,
471
+ "step": 3300
472
+ },
473
+ {
474
+ "epoch": 0.5360857737237958,
475
+ "grad_norm": 0.3282572329044342,
476
+ "learning_rate": 9.964815046125412e-05,
477
+ "loss": 1.2559,
478
+ "step": 3350
479
+ },
480
+ {
481
+ "epoch": 0.5440870539286286,
482
+ "grad_norm": 0.4450869858264923,
483
+ "learning_rate": 9.960559502988208e-05,
484
+ "loss": 1.2488,
485
+ "step": 3400
486
+ },
487
+ {
488
+ "epoch": 0.5520883341334614,
489
+ "grad_norm": 0.356630802154541,
490
+ "learning_rate": 9.956062103193648e-05,
491
+ "loss": 1.2688,
492
+ "step": 3450
493
+ },
494
+ {
495
+ "epoch": 0.5600896143382941,
496
+ "grad_norm": 0.35085442662239075,
497
+ "learning_rate": 9.95132306601661e-05,
498
+ "loss": 1.2398,
499
+ "step": 3500
500
+ },
501
+ {
502
+ "epoch": 0.5680908945431269,
503
+ "grad_norm": 0.4403521716594696,
504
+ "learning_rate": 9.946342622513229e-05,
505
+ "loss": 1.2442,
506
+ "step": 3550
507
+ },
508
+ {
509
+ "epoch": 0.5760921747479597,
510
+ "grad_norm": 0.4456493854522705,
511
+ "learning_rate": 9.941121015509621e-05,
512
+ "loss": 1.2413,
513
+ "step": 3600
514
+ },
515
+ {
516
+ "epoch": 0.5840934549527924,
517
+ "grad_norm": 0.4137299954891205,
518
+ "learning_rate": 9.935658499590059e-05,
519
+ "loss": 1.2546,
520
+ "step": 3650
521
+ },
522
+ {
523
+ "epoch": 0.5920947351576252,
524
+ "grad_norm": 0.3572884798049927,
525
+ "learning_rate": 9.929955341084547e-05,
526
+ "loss": 1.2533,
527
+ "step": 3700
528
+ },
529
+ {
530
+ "epoch": 0.600096015362458,
531
+ "grad_norm": 0.42966127395629883,
532
+ "learning_rate": 9.924011818055843e-05,
533
+ "loss": 1.2389,
534
+ "step": 3750
535
+ },
536
+ {
537
+ "epoch": 0.6080972955672908,
538
+ "grad_norm": 0.4403945803642273,
539
+ "learning_rate": 9.917828220285896e-05,
540
+ "loss": 1.2198,
541
+ "step": 3800
542
+ },
543
+ {
544
+ "epoch": 0.6160985757721236,
545
+ "grad_norm": 0.4667624235153198,
546
+ "learning_rate": 9.911404849261726e-05,
547
+ "loss": 1.2417,
548
+ "step": 3850
549
+ },
550
+ {
551
+ "epoch": 0.6240998559769563,
552
+ "grad_norm": 0.6005256772041321,
553
+ "learning_rate": 9.904742018160715e-05,
554
+ "loss": 1.2006,
555
+ "step": 3900
556
+ },
557
+ {
558
+ "epoch": 0.6321011361817891,
559
+ "grad_norm": 0.3864199221134186,
560
+ "learning_rate": 9.897840051835343e-05,
561
+ "loss": 1.2164,
562
+ "step": 3950
563
+ },
564
+ {
565
+ "epoch": 0.6401024163866219,
566
+ "grad_norm": 0.5411766171455383,
567
+ "learning_rate": 9.89069928679735e-05,
568
+ "loss": 1.2187,
569
+ "step": 4000
570
+ },
571
+ {
572
+ "epoch": 0.6481036965914546,
573
+ "grad_norm": 0.38500306010246277,
574
+ "learning_rate": 9.883320071201325e-05,
575
+ "loss": 1.2363,
576
+ "step": 4050
577
+ },
578
+ {
579
+ "epoch": 0.6561049767962874,
580
+ "grad_norm": 0.4081592559814453,
581
+ "learning_rate": 9.875702764827737e-05,
582
+ "loss": 1.2247,
583
+ "step": 4100
584
+ },
585
+ {
586
+ "epoch": 0.6641062570011201,
587
+ "grad_norm": 0.43678033351898193,
588
+ "learning_rate": 9.86784773906539e-05,
589
+ "loss": 1.2323,
590
+ "step": 4150
591
+ },
592
+ {
593
+ "epoch": 0.672107537205953,
594
+ "grad_norm": 0.4319170117378235,
595
+ "learning_rate": 9.859755376893314e-05,
596
+ "loss": 1.1906,
597
+ "step": 4200
598
+ },
599
+ {
600
+ "epoch": 0.6801088174107858,
601
+ "grad_norm": 0.4729995131492615,
602
+ "learning_rate": 9.851426072862098e-05,
603
+ "loss": 1.2098,
604
+ "step": 4250
605
+ },
606
+ {
607
+ "epoch": 0.6881100976156185,
608
+ "grad_norm": 0.4233373701572418,
609
+ "learning_rate": 9.842860233074645e-05,
610
+ "loss": 1.204,
611
+ "step": 4300
612
+ },
613
+ {
614
+ "epoch": 0.6961113778204513,
615
+ "grad_norm": 0.48369497060775757,
616
+ "learning_rate": 9.834058275166383e-05,
617
+ "loss": 1.2046,
618
+ "step": 4350
619
+ },
620
+ {
621
+ "epoch": 0.704112658025284,
622
+ "grad_norm": 0.36634331941604614,
623
+ "learning_rate": 9.825020628284896e-05,
624
+ "loss": 1.2117,
625
+ "step": 4400
626
+ },
627
+ {
628
+ "epoch": 0.7121139382301168,
629
+ "grad_norm": 0.41213107109069824,
630
+ "learning_rate": 9.815747733068995e-05,
631
+ "loss": 1.1977,
632
+ "step": 4450
633
+ },
634
+ {
635
+ "epoch": 0.7201152184349496,
636
+ "grad_norm": 0.37744736671447754,
637
+ "learning_rate": 9.80624004162725e-05,
638
+ "loss": 1.2372,
639
+ "step": 4500
640
+ },
641
+ {
642
+ "epoch": 0.7281164986397823,
643
+ "grad_norm": 0.49204540252685547,
644
+ "learning_rate": 9.79649801751593e-05,
645
+ "loss": 1.2191,
646
+ "step": 4550
647
+ },
648
+ {
649
+ "epoch": 0.7361177788446152,
650
+ "grad_norm": 0.42844048142433167,
651
+ "learning_rate": 9.786522135716415e-05,
652
+ "loss": 1.2114,
653
+ "step": 4600
654
+ },
655
+ {
656
+ "epoch": 0.7441190590494479,
657
+ "grad_norm": 0.5176280736923218,
658
+ "learning_rate": 9.776312882612028e-05,
659
+ "loss": 1.2041,
660
+ "step": 4650
661
+ },
662
+ {
663
+ "epoch": 0.7521203392542807,
664
+ "grad_norm": 0.44180744886398315,
665
+ "learning_rate": 9.765870755964331e-05,
666
+ "loss": 1.2096,
667
+ "step": 4700
668
+ },
669
+ {
670
+ "epoch": 0.7601216194591135,
671
+ "grad_norm": 0.4751160442829132,
672
+ "learning_rate": 9.755196264888846e-05,
673
+ "loss": 1.1928,
674
+ "step": 4750
675
+ },
676
+ {
677
+ "epoch": 0.7681228996639462,
678
+ "grad_norm": 0.4147936999797821,
679
+ "learning_rate": 9.744289929830236e-05,
680
+ "loss": 1.2183,
681
+ "step": 4800
682
+ },
683
+ {
684
+ "epoch": 0.776124179868779,
685
+ "grad_norm": 0.45143744349479675,
686
+ "learning_rate": 9.733152282536936e-05,
687
+ "loss": 1.1798,
688
+ "step": 4850
689
+ },
690
+ {
691
+ "epoch": 0.7841254600736117,
692
+ "grad_norm": 0.46376484632492065,
693
+ "learning_rate": 9.721783866035218e-05,
694
+ "loss": 1.1871,
695
+ "step": 4900
696
+ },
697
+ {
698
+ "epoch": 0.7921267402784445,
699
+ "grad_norm": 0.4516090154647827,
700
+ "learning_rate": 9.710185234602727e-05,
701
+ "loss": 1.1901,
702
+ "step": 4950
703
+ },
704
+ {
705
+ "epoch": 0.8001280204832774,
706
+ "grad_norm": 0.4624463617801666,
707
+ "learning_rate": 9.698356953741438e-05,
708
+ "loss": 1.1848,
709
+ "step": 5000
710
+ },
711
+ {
712
+ "epoch": 0.8081293006881101,
713
+ "grad_norm": 0.41177043318748474,
714
+ "learning_rate": 9.686299600150108e-05,
715
+ "loss": 1.1934,
716
+ "step": 5050
717
+ },
718
+ {
719
+ "epoch": 0.8161305808929429,
720
+ "grad_norm": 0.46030393242836,
721
+ "learning_rate": 9.674013761696136e-05,
722
+ "loss": 1.1695,
723
+ "step": 5100
724
+ },
725
+ {
726
+ "epoch": 0.8241318610977757,
727
+ "grad_norm": 0.48872360587120056,
728
+ "learning_rate": 9.661500037386921e-05,
729
+ "loss": 1.192,
730
+ "step": 5150
731
+ },
732
+ {
733
+ "epoch": 0.8321331413026084,
734
+ "grad_norm": 0.36913803219795227,
735
+ "learning_rate": 9.648759037340638e-05,
736
+ "loss": 1.1624,
737
+ "step": 5200
738
+ },
739
+ {
740
+ "epoch": 0.8401344215074412,
741
+ "grad_norm": 0.5374457836151123,
742
+ "learning_rate": 9.635791382756508e-05,
743
+ "loss": 1.1847,
744
+ "step": 5250
745
+ },
746
+ {
747
+ "epoch": 0.8481357017122739,
748
+ "grad_norm": 0.43082547187805176,
749
+ "learning_rate": 9.622597705884496e-05,
750
+ "loss": 1.1798,
751
+ "step": 5300
752
+ },
753
+ {
754
+ "epoch": 0.8561369819171067,
755
+ "grad_norm": 0.4757367968559265,
756
+ "learning_rate": 9.609178649994499e-05,
757
+ "loss": 1.185,
758
+ "step": 5350
759
+ },
760
+ {
761
+ "epoch": 0.8641382621219396,
762
+ "grad_norm": 0.41058582067489624,
763
+ "learning_rate": 9.595534869344974e-05,
764
+ "loss": 1.18,
765
+ "step": 5400
766
+ },
767
+ {
768
+ "epoch": 0.8721395423267723,
769
+ "grad_norm": 0.4382982552051544,
770
+ "learning_rate": 9.581667029151039e-05,
771
+ "loss": 1.1977,
772
+ "step": 5450
773
+ },
774
+ {
775
+ "epoch": 0.8801408225316051,
776
+ "grad_norm": 0.44662296772003174,
777
+ "learning_rate": 9.567575805552042e-05,
778
+ "loss": 1.1841,
779
+ "step": 5500
780
+ },
781
+ {
782
+ "epoch": 0.8881421027364378,
783
+ "grad_norm": 0.4811069071292877,
784
+ "learning_rate": 9.553261885578597e-05,
785
+ "loss": 1.1765,
786
+ "step": 5550
787
+ },
788
+ {
789
+ "epoch": 0.8961433829412706,
790
+ "grad_norm": 0.4336834251880646,
791
+ "learning_rate": 9.538725967119087e-05,
792
+ "loss": 1.1879,
793
+ "step": 5600
794
+ },
795
+ {
796
+ "epoch": 0.9041446631461034,
797
+ "grad_norm": 0.44644805788993835,
798
+ "learning_rate": 9.523968758885631e-05,
799
+ "loss": 1.2058,
800
+ "step": 5650
801
+ },
802
+ {
803
+ "epoch": 0.9121459433509361,
804
+ "grad_norm": 0.4499703347682953,
805
+ "learning_rate": 9.508990980379537e-05,
806
+ "loss": 1.1397,
807
+ "step": 5700
808
+ },
809
+ {
810
+ "epoch": 0.920147223555769,
811
+ "grad_norm": 0.4322624206542969,
812
+ "learning_rate": 9.493793361856226e-05,
813
+ "loss": 1.1396,
814
+ "step": 5750
815
+ },
816
+ {
817
+ "epoch": 0.9281485037606017,
818
+ "grad_norm": 0.43696922063827515,
819
+ "learning_rate": 9.478376644289613e-05,
820
+ "loss": 1.1698,
821
+ "step": 5800
822
+ },
823
+ {
824
+ "epoch": 0.9361497839654345,
825
+ "grad_norm": 0.4423019587993622,
826
+ "learning_rate": 9.462741579335992e-05,
827
+ "loss": 1.1365,
828
+ "step": 5850
829
+ },
830
+ {
831
+ "epoch": 0.9441510641702673,
832
+ "grad_norm": 0.4975908696651459,
833
+ "learning_rate": 9.44688892929739e-05,
834
+ "loss": 1.1775,
835
+ "step": 5900
836
+ },
837
+ {
838
+ "epoch": 0.9521523443751,
839
+ "grad_norm": 0.49656620621681213,
840
+ "learning_rate": 9.430819467084392e-05,
841
+ "loss": 1.141,
842
+ "step": 5950
843
+ },
844
+ {
845
+ "epoch": 0.9601536245799328,
846
+ "grad_norm": 0.4862751066684723,
847
+ "learning_rate": 9.414533976178458e-05,
848
+ "loss": 1.144,
849
+ "step": 6000
850
+ },
851
+ {
852
+ "epoch": 0.9681549047847655,
853
+ "grad_norm": 0.5158004760742188,
854
+ "learning_rate": 9.398033250593733e-05,
855
+ "loss": 1.1603,
856
+ "step": 6050
857
+ },
858
+ {
859
+ "epoch": 0.9761561849895983,
860
+ "grad_norm": 0.4406384229660034,
861
+ "learning_rate": 9.381318094838321e-05,
862
+ "loss": 1.1351,
863
+ "step": 6100
864
+ },
865
+ {
866
+ "epoch": 0.9841574651944311,
867
+ "grad_norm": 0.4819541573524475,
868
+ "learning_rate": 9.36438932387507e-05,
869
+ "loss": 1.172,
870
+ "step": 6150
871
+ },
872
+ {
873
+ "epoch": 0.9921587453992639,
874
+ "grad_norm": 0.4627222418785095,
875
+ "learning_rate": 9.347247763081835e-05,
876
+ "loss": 1.1587,
877
+ "step": 6200
878
+ },
879
+ {
880
+ "epoch": 1.0001600256040966,
881
+ "grad_norm": 0.4336191713809967,
882
+ "learning_rate": 9.329894248211233e-05,
883
+ "loss": 1.1324,
884
+ "step": 6250
885
+ },
886
+ {
887
+ "epoch": 1.0081613058089294,
888
+ "grad_norm": 0.5482844114303589,
889
+ "learning_rate": 9.312329625349902e-05,
890
+ "loss": 1.0647,
891
+ "step": 6300
892
+ },
893
+ {
894
+ "epoch": 1.0161625860137622,
895
+ "grad_norm": 0.48142924904823303,
896
+ "learning_rate": 9.294554750877242e-05,
897
+ "loss": 1.0681,
898
+ "step": 6350
899
+ },
900
+ {
901
+ "epoch": 1.024163866218595,
902
+ "grad_norm": 0.45703792572021484,
903
+ "learning_rate": 9.276570491423664e-05,
904
+ "loss": 1.0956,
905
+ "step": 6400
906
+ },
907
+ {
908
+ "epoch": 1.0321651464234278,
909
+ "grad_norm": 0.5305693745613098,
910
+ "learning_rate": 9.258377723828338e-05,
911
+ "loss": 1.0476,
912
+ "step": 6450
913
+ },
914
+ {
915
+ "epoch": 1.0401664266282604,
916
+ "grad_norm": 0.5061540603637695,
917
+ "learning_rate": 9.23997733509644e-05,
918
+ "loss": 1.0613,
919
+ "step": 6500
920
+ },
921
+ {
922
+ "epoch": 1.0481677068330932,
923
+ "grad_norm": 0.4534345865249634,
924
+ "learning_rate": 9.221370222355908e-05,
925
+ "loss": 1.0604,
926
+ "step": 6550
927
+ },
928
+ {
929
+ "epoch": 1.056168987037926,
930
+ "grad_norm": 0.5327995419502258,
931
+ "learning_rate": 9.202557292813697e-05,
932
+ "loss": 1.0396,
933
+ "step": 6600
934
+ },
935
+ {
936
+ "epoch": 1.0641702672427589,
937
+ "grad_norm": 0.5349058508872986,
938
+ "learning_rate": 9.183539463711555e-05,
939
+ "loss": 1.0909,
940
+ "step": 6650
941
+ },
942
+ {
943
+ "epoch": 1.0721715474475917,
944
+ "grad_norm": 0.5274565815925598,
945
+ "learning_rate": 9.16431766228129e-05,
946
+ "loss": 1.0539,
947
+ "step": 6700
948
+ },
949
+ {
950
+ "epoch": 1.0801728276524245,
951
+ "grad_norm": 0.5548765659332275,
952
+ "learning_rate": 9.144892825699577e-05,
953
+ "loss": 1.0438,
954
+ "step": 6750
955
+ },
956
+ {
957
+ "epoch": 1.088174107857257,
958
+ "grad_norm": 0.5511574745178223,
959
+ "learning_rate": 9.125265901042251e-05,
960
+ "loss": 1.091,
961
+ "step": 6800
962
+ },
963
+ {
964
+ "epoch": 1.09617538806209,
965
+ "grad_norm": 0.5760679841041565,
966
+ "learning_rate": 9.105437845238141e-05,
967
+ "loss": 1.0522,
968
+ "step": 6850
969
+ },
970
+ {
971
+ "epoch": 1.1041766682669227,
972
+ "grad_norm": 0.6349498629570007,
973
+ "learning_rate": 9.085409625022411e-05,
974
+ "loss": 1.0592,
975
+ "step": 6900
976
+ },
977
+ {
978
+ "epoch": 1.1121779484717556,
979
+ "grad_norm": 0.6243582963943481,
980
+ "learning_rate": 9.065182216889423e-05,
981
+ "loss": 1.0683,
982
+ "step": 6950
983
+ },
984
+ {
985
+ "epoch": 1.1201792286765881,
986
+ "grad_norm": 0.5389096140861511,
987
+ "learning_rate": 9.04475660704513e-05,
988
+ "loss": 1.0549,
989
+ "step": 7000
990
+ },
991
+ {
992
+ "epoch": 1.128180508881421,
993
+ "grad_norm": 0.4826034605503082,
994
+ "learning_rate": 9.024133791358995e-05,
995
+ "loss": 1.078,
996
+ "step": 7050
997
+ },
998
+ {
999
+ "epoch": 1.1361817890862538,
1000
+ "grad_norm": 0.517662525177002,
1001
+ "learning_rate": 9.003314775315433e-05,
1002
+ "loss": 1.0857,
1003
+ "step": 7100
1004
+ },
1005
+ {
1006
+ "epoch": 1.1441830692910866,
1007
+ "grad_norm": 0.5285195112228394,
1008
+ "learning_rate": 8.982300573964788e-05,
1009
+ "loss": 1.0449,
1010
+ "step": 7150
1011
+ },
1012
+ {
1013
+ "epoch": 1.1521843494959194,
1014
+ "grad_norm": 0.47838062047958374,
1015
+ "learning_rate": 8.961092211873841e-05,
1016
+ "loss": 1.035,
1017
+ "step": 7200
1018
+ },
1019
+ {
1020
+ "epoch": 1.1601856297007522,
1021
+ "grad_norm": 0.5411238670349121,
1022
+ "learning_rate": 8.939690723075865e-05,
1023
+ "loss": 1.058,
1024
+ "step": 7250
1025
+ },
1026
+ {
1027
+ "epoch": 1.1681869099055848,
1028
+ "grad_norm": 0.49349942803382874,
1029
+ "learning_rate": 8.9180971510202e-05,
1030
+ "loss": 1.0567,
1031
+ "step": 7300
1032
+ },
1033
+ {
1034
+ "epoch": 1.1761881901104176,
1035
+ "grad_norm": 0.5397252440452576,
1036
+ "learning_rate": 8.896312548521382e-05,
1037
+ "loss": 1.0842,
1038
+ "step": 7350
1039
+ },
1040
+ {
1041
+ "epoch": 1.1841894703152505,
1042
+ "grad_norm": 0.5732976794242859,
1043
+ "learning_rate": 8.874337977707817e-05,
1044
+ "loss": 1.0581,
1045
+ "step": 7400
1046
+ },
1047
+ {
1048
+ "epoch": 1.1921907505200833,
1049
+ "grad_norm": 0.4691354036331177,
1050
+ "learning_rate": 8.852174509969984e-05,
1051
+ "loss": 1.0205,
1052
+ "step": 7450
1053
+ },
1054
+ {
1055
+ "epoch": 1.2001920307249159,
1056
+ "grad_norm": 0.6526204943656921,
1057
+ "learning_rate": 8.829823225908214e-05,
1058
+ "loss": 1.0387,
1059
+ "step": 7500
1060
+ },
1061
+ {
1062
+ "epoch": 1.2081933109297487,
1063
+ "grad_norm": 0.46403875946998596,
1064
+ "learning_rate": 8.80728521527999e-05,
1065
+ "loss": 1.0554,
1066
+ "step": 7550
1067
+ },
1068
+ {
1069
+ "epoch": 1.2161945911345815,
1070
+ "grad_norm": 0.462835431098938,
1071
+ "learning_rate": 8.784561576946824e-05,
1072
+ "loss": 1.0503,
1073
+ "step": 7600
1074
+ },
1075
+ {
1076
+ "epoch": 1.2241958713394143,
1077
+ "grad_norm": 0.5204878449440002,
1078
+ "learning_rate": 8.76165341882068e-05,
1079
+ "loss": 1.0815,
1080
+ "step": 7650
1081
+ },
1082
+ {
1083
+ "epoch": 1.2321971515442471,
1084
+ "grad_norm": 0.5061752796173096,
1085
+ "learning_rate": 8.738561857809949e-05,
1086
+ "loss": 1.0534,
1087
+ "step": 7700
1088
+ },
1089
+ {
1090
+ "epoch": 1.24019843174908,
1091
+ "grad_norm": 0.5491166710853577,
1092
+ "learning_rate": 8.715288019765006e-05,
1093
+ "loss": 1.0625,
1094
+ "step": 7750
1095
+ },
1096
+ {
1097
+ "epoch": 1.2481997119539125,
1098
+ "grad_norm": 0.4824821650981903,
1099
+ "learning_rate": 8.691833039423305e-05,
1100
+ "loss": 1.0473,
1101
+ "step": 7800
1102
+ },
1103
+ {
1104
+ "epoch": 1.2562009921587454,
1105
+ "grad_norm": 0.5545431971549988,
1106
+ "learning_rate": 8.668198060354065e-05,
1107
+ "loss": 1.0432,
1108
+ "step": 7850
1109
+ },
1110
+ {
1111
+ "epoch": 1.2642022723635782,
1112
+ "grad_norm": 0.5635075569152832,
1113
+ "learning_rate": 8.644384234902503e-05,
1114
+ "loss": 1.0473,
1115
+ "step": 7900
1116
+ },
1117
+ {
1118
+ "epoch": 1.272203552568411,
1119
+ "grad_norm": 0.49760839343070984,
1120
+ "learning_rate": 8.620392724133661e-05,
1121
+ "loss": 1.0616,
1122
+ "step": 7950
1123
+ },
1124
+ {
1125
+ "epoch": 1.2802048327732436,
1126
+ "grad_norm": 0.6228436231613159,
1127
+ "learning_rate": 8.596224697775795e-05,
1128
+ "loss": 1.0722,
1129
+ "step": 8000
1130
+ },
1131
+ {
1132
+ "epoch": 1.2882061129780764,
1133
+ "grad_norm": 0.5831848978996277,
1134
+ "learning_rate": 8.571881334163334e-05,
1135
+ "loss": 1.0581,
1136
+ "step": 8050
1137
+ },
1138
+ {
1139
+ "epoch": 1.2962073931829092,
1140
+ "grad_norm": 0.4925413131713867,
1141
+ "learning_rate": 8.547363820179442e-05,
1142
+ "loss": 1.0429,
1143
+ "step": 8100
1144
+ },
1145
+ {
1146
+ "epoch": 1.304208673387742,
1147
+ "grad_norm": 0.5401794910430908,
1148
+ "learning_rate": 8.522673351198143e-05,
1149
+ "loss": 1.0366,
1150
+ "step": 8150
1151
+ },
1152
+ {
1153
+ "epoch": 1.3122099535925749,
1154
+ "grad_norm": 0.5081512928009033,
1155
+ "learning_rate": 8.497811131026046e-05,
1156
+ "loss": 1.0464,
1157
+ "step": 8200
1158
+ },
1159
+ {
1160
+ "epoch": 1.3202112337974077,
1161
+ "grad_norm": 0.5704318881034851,
1162
+ "learning_rate": 8.472778371843641e-05,
1163
+ "loss": 1.0509,
1164
+ "step": 8250
1165
+ },
1166
+ {
1167
+ "epoch": 1.3282125140022405,
1168
+ "grad_norm": 0.505493700504303,
1169
+ "learning_rate": 8.447576294146209e-05,
1170
+ "loss": 1.0713,
1171
+ "step": 8300
1172
+ },
1173
+ {
1174
+ "epoch": 1.336213794207073,
1175
+ "grad_norm": 0.5492855906486511,
1176
+ "learning_rate": 8.422206126684311e-05,
1177
+ "loss": 1.0385,
1178
+ "step": 8350
1179
+ },
1180
+ {
1181
+ "epoch": 1.344215074411906,
1182
+ "grad_norm": 0.4849604666233063,
1183
+ "learning_rate": 8.39666910640388e-05,
1184
+ "loss": 1.0422,
1185
+ "step": 8400
1186
+ },
1187
+ {
1188
+ "epoch": 1.3522163546167387,
1189
+ "grad_norm": 0.5335291624069214,
1190
+ "learning_rate": 8.370966478385907e-05,
1191
+ "loss": 1.0235,
1192
+ "step": 8450
1193
+ },
1194
+ {
1195
+ "epoch": 1.3602176348215713,
1196
+ "grad_norm": 0.5804494619369507,
1197
+ "learning_rate": 8.345099495785753e-05,
1198
+ "loss": 1.0069,
1199
+ "step": 8500
1200
+ },
1201
+ {
1202
+ "epoch": 1.3682189150264041,
1203
+ "grad_norm": 0.5363398194313049,
1204
+ "learning_rate": 8.319069419772023e-05,
1205
+ "loss": 1.0402,
1206
+ "step": 8550
1207
+ },
1208
+ {
1209
+ "epoch": 1.376220195231237,
1210
+ "grad_norm": 0.6018884181976318,
1211
+ "learning_rate": 8.292877519465105e-05,
1212
+ "loss": 1.031,
1213
+ "step": 8600
1214
+ },
1215
+ {
1216
+ "epoch": 1.3842214754360698,
1217
+ "grad_norm": 0.5088986158370972,
1218
+ "learning_rate": 8.266525071875273e-05,
1219
+ "loss": 1.0349,
1220
+ "step": 8650
1221
+ },
1222
+ {
1223
+ "epoch": 1.3922227556409026,
1224
+ "grad_norm": 0.575141191482544,
1225
+ "learning_rate": 8.240013361840436e-05,
1226
+ "loss": 1.019,
1227
+ "step": 8700
1228
+ },
1229
+ {
1230
+ "epoch": 1.4002240358457354,
1231
+ "grad_norm": 0.5023386478424072,
1232
+ "learning_rate": 8.21334368196348e-05,
1233
+ "loss": 1.0428,
1234
+ "step": 8750
1235
+ },
1236
+ {
1237
+ "epoch": 1.4082253160505682,
1238
+ "grad_norm": 0.5338187217712402,
1239
+ "learning_rate": 8.186517332549276e-05,
1240
+ "loss": 1.0188,
1241
+ "step": 8800
1242
+ },
1243
+ {
1244
+ "epoch": 1.4162265962554008,
1245
+ "grad_norm": 0.5415542721748352,
1246
+ "learning_rate": 8.159535621541243e-05,
1247
+ "loss": 1.0172,
1248
+ "step": 8850
1249
+ },
1250
+ {
1251
+ "epoch": 1.4242278764602336,
1252
+ "grad_norm": 0.4934610426425934,
1253
+ "learning_rate": 8.13239986445761e-05,
1254
+ "loss": 1.0249,
1255
+ "step": 8900
1256
+ },
1257
+ {
1258
+ "epoch": 1.4322291566650664,
1259
+ "grad_norm": 0.5592052936553955,
1260
+ "learning_rate": 8.10511138432726e-05,
1261
+ "loss": 1.0295,
1262
+ "step": 8950
1263
+ },
1264
+ {
1265
+ "epoch": 1.4402304368698993,
1266
+ "grad_norm": 0.5904792547225952,
1267
+ "learning_rate": 8.07767151162523e-05,
1268
+ "loss": 1.0427,
1269
+ "step": 9000
1270
+ },
1271
+ {
1272
+ "epoch": 1.4482317170747319,
1273
+ "grad_norm": 0.5952058434486389,
1274
+ "learning_rate": 8.050081584207843e-05,
1275
+ "loss": 1.0504,
1276
+ "step": 9050
1277
+ },
1278
+ {
1279
+ "epoch": 1.4562329972795647,
1280
+ "grad_norm": 0.49933668971061707,
1281
+ "learning_rate": 8.022342947247474e-05,
1282
+ "loss": 1.0391,
1283
+ "step": 9100
1284
+ },
1285
+ {
1286
+ "epoch": 1.4642342774843975,
1287
+ "grad_norm": 0.5853399634361267,
1288
+ "learning_rate": 7.994456953166973e-05,
1289
+ "loss": 1.0013,
1290
+ "step": 9150
1291
+ },
1292
+ {
1293
+ "epoch": 1.4722355576892303,
1294
+ "grad_norm": 0.6290839910507202,
1295
+ "learning_rate": 7.966424961573722e-05,
1296
+ "loss": 1.0159,
1297
+ "step": 9200
1298
+ },
1299
+ {
1300
+ "epoch": 1.4802368378940631,
1301
+ "grad_norm": 0.6153242588043213,
1302
+ "learning_rate": 7.938248339193346e-05,
1303
+ "loss": 1.0312,
1304
+ "step": 9250
1305
+ },
1306
+ {
1307
+ "epoch": 1.488238118098896,
1308
+ "grad_norm": 0.5723234415054321,
1309
+ "learning_rate": 7.909928459803077e-05,
1310
+ "loss": 1.0198,
1311
+ "step": 9300
1312
+ },
1313
+ {
1314
+ "epoch": 1.4962393983037285,
1315
+ "grad_norm": 0.5766580700874329,
1316
+ "learning_rate": 7.881466704164774e-05,
1317
+ "loss": 0.9915,
1318
+ "step": 9350
1319
+ },
1320
+ {
1321
+ "epoch": 1.5042406785085614,
1322
+ "grad_norm": 0.6211101412773132,
1323
+ "learning_rate": 7.852864459957605e-05,
1324
+ "loss": 1.0324,
1325
+ "step": 9400
1326
+ },
1327
+ {
1328
+ "epoch": 1.5122419587133942,
1329
+ "grad_norm": 0.5500127673149109,
1330
+ "learning_rate": 7.824123121710387e-05,
1331
+ "loss": 1.0316,
1332
+ "step": 9450
1333
+ },
1334
+ {
1335
+ "epoch": 1.5202432389182268,
1336
+ "grad_norm": 0.6087145209312439,
1337
+ "learning_rate": 7.795244090733597e-05,
1338
+ "loss": 1.0334,
1339
+ "step": 9500
1340
+ },
1341
+ {
1342
+ "epoch": 1.5282445191230596,
1343
+ "grad_norm": 0.5456790924072266,
1344
+ "learning_rate": 7.766228775051045e-05,
1345
+ "loss": 1.0243,
1346
+ "step": 9550
1347
+ },
1348
+ {
1349
+ "epoch": 1.5362457993278924,
1350
+ "grad_norm": 0.613003671169281,
1351
+ "learning_rate": 7.737078589331229e-05,
1352
+ "loss": 0.9954,
1353
+ "step": 9600
1354
+ },
1355
+ {
1356
+ "epoch": 1.5442470795327252,
1357
+ "grad_norm": 0.5732637047767639,
1358
+ "learning_rate": 7.707794954818363e-05,
1359
+ "loss": 1.0172,
1360
+ "step": 9650
1361
+ },
1362
+ {
1363
+ "epoch": 1.552248359737558,
1364
+ "grad_norm": 0.5933035612106323,
1365
+ "learning_rate": 7.678379299263076e-05,
1366
+ "loss": 1.0049,
1367
+ "step": 9700
1368
+ },
1369
+ {
1370
+ "epoch": 1.5602496399423909,
1371
+ "grad_norm": 0.5576400756835938,
1372
+ "learning_rate": 7.648833056852807e-05,
1373
+ "loss": 0.9918,
1374
+ "step": 9750
1375
+ },
1376
+ {
1377
+ "epoch": 1.5682509201472237,
1378
+ "grad_norm": 0.4915982782840729,
1379
+ "learning_rate": 7.619157668141877e-05,
1380
+ "loss": 0.9949,
1381
+ "step": 9800
1382
+ },
1383
+ {
1384
+ "epoch": 1.5762522003520565,
1385
+ "grad_norm": 0.5492275357246399,
1386
+ "learning_rate": 7.58935457998125e-05,
1387
+ "loss": 1.0233,
1388
+ "step": 9850
1389
+ },
1390
+ {
1391
+ "epoch": 1.584253480556889,
1392
+ "grad_norm": 0.5720072984695435,
1393
+ "learning_rate": 7.559425245448006e-05,
1394
+ "loss": 1.053,
1395
+ "step": 9900
1396
+ },
1397
+ {
1398
+ "epoch": 1.592254760761722,
1399
+ "grad_norm": 0.5385164022445679,
1400
+ "learning_rate": 7.529371123774471e-05,
1401
+ "loss": 1.0329,
1402
+ "step": 9950
1403
+ },
1404
+ {
1405
+ "epoch": 1.6002560409665545,
1406
+ "grad_norm": 0.5508076548576355,
1407
+ "learning_rate": 7.49919368027709e-05,
1408
+ "loss": 1.0156,
1409
+ "step": 10000
1410
+ },
1411
+ {
1412
+ "epoch": 1.6082573211713873,
1413
+ "grad_norm": 0.5111932754516602,
1414
+ "learning_rate": 7.468894386284976e-05,
1415
+ "loss": 1.0061,
1416
+ "step": 10050
1417
+ },
1418
+ {
1419
+ "epoch": 1.6162586013762201,
1420
+ "grad_norm": 0.5652381777763367,
1421
+ "learning_rate": 7.438474719068173e-05,
1422
+ "loss": 0.999,
1423
+ "step": 10100
1424
+ },
1425
+ {
1426
+ "epoch": 1.624259881581053,
1427
+ "grad_norm": 0.5519747138023376,
1428
+ "learning_rate": 7.407936161765637e-05,
1429
+ "loss": 1.0129,
1430
+ "step": 10150
1431
+ },
1432
+ {
1433
+ "epoch": 1.6322611617858858,
1434
+ "grad_norm": 0.5380906462669373,
1435
+ "learning_rate": 7.377280203312917e-05,
1436
+ "loss": 0.9991,
1437
+ "step": 10200
1438
+ },
1439
+ {
1440
+ "epoch": 1.6402624419907186,
1441
+ "grad_norm": 0.635221540927887,
1442
+ "learning_rate": 7.346508338369563e-05,
1443
+ "loss": 0.9889,
1444
+ "step": 10250
1445
+ },
1446
+ {
1447
+ "epoch": 1.6482637221955514,
1448
+ "grad_norm": 0.4963364005088806,
1449
+ "learning_rate": 7.315622067246254e-05,
1450
+ "loss": 0.9808,
1451
+ "step": 10300
1452
+ },
1453
+ {
1454
+ "epoch": 1.6562650024003842,
1455
+ "grad_norm": 0.5576931238174438,
1456
+ "learning_rate": 7.28462289583165e-05,
1457
+ "loss": 1.0122,
1458
+ "step": 10350
1459
+ },
1460
+ {
1461
+ "epoch": 1.6642662826052168,
1462
+ "grad_norm": 0.5357556343078613,
1463
+ "learning_rate": 7.253512335518964e-05,
1464
+ "loss": 1.0193,
1465
+ "step": 10400
1466
+ },
1467
+ {
1468
+ "epoch": 1.6722675628100496,
1469
+ "grad_norm": 0.5757668018341064,
1470
+ "learning_rate": 7.22229190313228e-05,
1471
+ "loss": 1.0032,
1472
+ "step": 10450
1473
+ },
1474
+ {
1475
+ "epoch": 1.6802688430148822,
1476
+ "grad_norm": 0.5368041396141052,
1477
+ "learning_rate": 7.1909631208526e-05,
1478
+ "loss": 1.0159,
1479
+ "step": 10500
1480
+ },
1481
+ {
1482
+ "epoch": 1.688270123219715,
1483
+ "grad_norm": 0.5617921948432922,
1484
+ "learning_rate": 7.15952751614362e-05,
1485
+ "loss": 1.0178,
1486
+ "step": 10550
1487
+ },
1488
+ {
1489
+ "epoch": 1.6962714034245479,
1490
+ "grad_norm": 0.6092725396156311,
1491
+ "learning_rate": 7.127986621677263e-05,
1492
+ "loss": 1.0112,
1493
+ "step": 10600
1494
+ },
1495
+ {
1496
+ "epoch": 1.7042726836293807,
1497
+ "grad_norm": 0.6592617034912109,
1498
+ "learning_rate": 7.096341975258953e-05,
1499
+ "loss": 0.9944,
1500
+ "step": 10650
1501
+ },
1502
+ {
1503
+ "epoch": 1.7122739638342135,
1504
+ "grad_norm": 0.5574333667755127,
1505
+ "learning_rate": 7.064595119752636e-05,
1506
+ "loss": 0.9896,
1507
+ "step": 10700
1508
+ },
1509
+ {
1510
+ "epoch": 1.7202752440390463,
1511
+ "grad_norm": 0.5796050429344177,
1512
+ "learning_rate": 7.032747603005552e-05,
1513
+ "loss": 1.0099,
1514
+ "step": 10750
1515
+ },
1516
+ {
1517
+ "epoch": 1.7282765242438791,
1518
+ "grad_norm": 0.5359869599342346,
1519
+ "learning_rate": 7.00080097777278e-05,
1520
+ "loss": 0.976,
1521
+ "step": 10800
1522
+ },
1523
+ {
1524
+ "epoch": 1.736277804448712,
1525
+ "grad_norm": 0.533762514591217,
1526
+ "learning_rate": 6.968756801641523e-05,
1527
+ "loss": 1.011,
1528
+ "step": 10850
1529
+ },
1530
+ {
1531
+ "epoch": 1.7442790846535445,
1532
+ "grad_norm": 0.6239184141159058,
1533
+ "learning_rate": 6.936616636955164e-05,
1534
+ "loss": 0.9971,
1535
+ "step": 10900
1536
+ },
1537
+ {
1538
+ "epoch": 1.7522803648583773,
1539
+ "grad_norm": 0.6219179034233093,
1540
+ "learning_rate": 6.904382050737096e-05,
1541
+ "loss": 1.0195,
1542
+ "step": 10950
1543
+ },
1544
+ {
1545
+ "epoch": 1.7602816450632102,
1546
+ "grad_norm": 0.6290085315704346,
1547
+ "learning_rate": 6.872054614614328e-05,
1548
+ "loss": 1.0393,
1549
+ "step": 11000
1550
+ },
1551
+ {
1552
+ "epoch": 1.7682829252680428,
1553
+ "grad_norm": 0.6031250953674316,
1554
+ "learning_rate": 6.839635904740846e-05,
1555
+ "loss": 1.013,
1556
+ "step": 11050
1557
+ },
1558
+ {
1559
+ "epoch": 1.7762842054728756,
1560
+ "grad_norm": 0.5307977199554443,
1561
+ "learning_rate": 6.807127501720773e-05,
1562
+ "loss": 0.9924,
1563
+ "step": 11100
1564
+ },
1565
+ {
1566
+ "epoch": 1.7842854856777084,
1567
+ "grad_norm": 0.593413233757019,
1568
+ "learning_rate": 6.774530990531308e-05,
1569
+ "loss": 0.9848,
1570
+ "step": 11150
1571
+ },
1572
+ {
1573
+ "epoch": 1.7922867658825412,
1574
+ "grad_norm": 0.5930994749069214,
1575
+ "learning_rate": 6.741847960445437e-05,
1576
+ "loss": 0.9891,
1577
+ "step": 11200
1578
+ },
1579
+ {
1580
+ "epoch": 1.800288046087374,
1581
+ "grad_norm": 0.5843376517295837,
1582
+ "learning_rate": 6.709080004954465e-05,
1583
+ "loss": 1.0075,
1584
+ "step": 11250
1585
+ },
1586
+ {
1587
+ "epoch": 1.8082893262922068,
1588
+ "grad_norm": 0.6507195830345154,
1589
+ "learning_rate": 6.676228721690301e-05,
1590
+ "loss": 0.9872,
1591
+ "step": 11300
1592
+ },
1593
+ {
1594
+ "epoch": 1.8162906064970397,
1595
+ "grad_norm": 0.502108097076416,
1596
+ "learning_rate": 6.64329571234759e-05,
1597
+ "loss": 0.9898,
1598
+ "step": 11350
1599
+ },
1600
+ {
1601
+ "epoch": 1.8242918867018723,
1602
+ "grad_norm": 0.6289730072021484,
1603
+ "learning_rate": 6.610282582605597e-05,
1604
+ "loss": 0.9886,
1605
+ "step": 11400
1606
+ },
1607
+ {
1608
+ "epoch": 1.832293166906705,
1609
+ "grad_norm": 0.5781500935554504,
1610
+ "learning_rate": 6.577190942049937e-05,
1611
+ "loss": 1.0211,
1612
+ "step": 11450
1613
+ },
1614
+ {
1615
+ "epoch": 1.840294447111538,
1616
+ "grad_norm": 0.6279985308647156,
1617
+ "learning_rate": 6.544022404094092e-05,
1618
+ "loss": 1.0123,
1619
+ "step": 11500
1620
+ },
1621
+ {
1622
+ "epoch": 1.8482957273163705,
1623
+ "grad_norm": 0.6612405180931091,
1624
+ "learning_rate": 6.51077858590074e-05,
1625
+ "loss": 0.9978,
1626
+ "step": 11550
1627
+ },
1628
+ {
1629
+ "epoch": 1.8562970075212033,
1630
+ "grad_norm": 0.6027297973632812,
1631
+ "learning_rate": 6.477461108302927e-05,
1632
+ "loss": 0.9786,
1633
+ "step": 11600
1634
+ },
1635
+ {
1636
+ "epoch": 1.8642982877260361,
1637
+ "grad_norm": 0.6454290151596069,
1638
+ "learning_rate": 6.444071595725026e-05,
1639
+ "loss": 0.9692,
1640
+ "step": 11650
1641
+ },
1642
+ {
1643
+ "epoch": 1.872299567930869,
1644
+ "grad_norm": 0.5385527014732361,
1645
+ "learning_rate": 6.410611676103542e-05,
1646
+ "loss": 0.9789,
1647
+ "step": 11700
1648
+ },
1649
+ {
1650
+ "epoch": 1.8803008481357018,
1651
+ "grad_norm": 0.5324643850326538,
1652
+ "learning_rate": 6.37708298080774e-05,
1653
+ "loss": 0.9892,
1654
+ "step": 11750
1655
+ },
1656
+ {
1657
+ "epoch": 1.8883021283405346,
1658
+ "grad_norm": 0.5693587064743042,
1659
+ "learning_rate": 6.343487144560108e-05,
1660
+ "loss": 0.9881,
1661
+ "step": 11800
1662
+ },
1663
+ {
1664
+ "epoch": 1.8963034085453674,
1665
+ "grad_norm": 0.6578769683837891,
1666
+ "learning_rate": 6.309825805356654e-05,
1667
+ "loss": 0.9871,
1668
+ "step": 11850
1669
+ },
1670
+ {
1671
+ "epoch": 1.9043046887502,
1672
+ "grad_norm": 0.5471733212471008,
1673
+ "learning_rate": 6.276100604387039e-05,
1674
+ "loss": 1.0013,
1675
+ "step": 11900
1676
+ },
1677
+ {
1678
+ "epoch": 1.9123059689550328,
1679
+ "grad_norm": 0.6353397369384766,
1680
+ "learning_rate": 6.24231318595457e-05,
1681
+ "loss": 0.9653,
1682
+ "step": 11950
1683
+ },
1684
+ {
1685
+ "epoch": 1.9203072491598656,
1686
+ "grad_norm": 0.5183307528495789,
1687
+ "learning_rate": 6.208465197396013e-05,
1688
+ "loss": 0.9833,
1689
+ "step": 12000
1690
+ },
1691
+ {
1692
+ "epoch": 1.9283085293646982,
1693
+ "grad_norm": 0.539452850818634,
1694
+ "learning_rate": 6.1745582890013e-05,
1695
+ "loss": 0.9686,
1696
+ "step": 12050
1697
+ },
1698
+ {
1699
+ "epoch": 1.936309809569531,
1700
+ "grad_norm": 0.681061863899231,
1701
+ "learning_rate": 6.140594113933042e-05,
1702
+ "loss": 0.9814,
1703
+ "step": 12100
1704
+ },
1705
+ {
1706
+ "epoch": 1.9443110897743638,
1707
+ "grad_norm": 0.6232041716575623,
1708
+ "learning_rate": 6.106574328145949e-05,
1709
+ "loss": 0.9858,
1710
+ "step": 12150
1711
+ },
1712
+ {
1713
+ "epoch": 1.9523123699791967,
1714
+ "grad_norm": 0.5435238480567932,
1715
+ "learning_rate": 6.072500590306076e-05,
1716
+ "loss": 0.9921,
1717
+ "step": 12200
1718
+ },
1719
+ {
1720
+ "epoch": 1.9603136501840295,
1721
+ "grad_norm": 0.6599912047386169,
1722
+ "learning_rate": 6.038374561709964e-05,
1723
+ "loss": 0.9627,
1724
+ "step": 12250
1725
+ },
1726
+ {
1727
+ "epoch": 1.9683149303888623,
1728
+ "grad_norm": 0.6491255760192871,
1729
+ "learning_rate": 6.0041979062036356e-05,
1730
+ "loss": 1.0074,
1731
+ "step": 12300
1732
+ },
1733
+ {
1734
+ "epoch": 1.976316210593695,
1735
+ "grad_norm": 0.545872688293457,
1736
+ "learning_rate": 5.969972290101478e-05,
1737
+ "loss": 0.9769,
1738
+ "step": 12350
1739
+ },
1740
+ {
1741
+ "epoch": 1.984317490798528,
1742
+ "grad_norm": 0.5526396632194519,
1743
+ "learning_rate": 5.935699382104994e-05,
1744
+ "loss": 0.9853,
1745
+ "step": 12400
1746
+ },
1747
+ {
1748
+ "epoch": 1.9923187710033605,
1749
+ "grad_norm": 0.5161740183830261,
1750
+ "learning_rate": 5.901380853221448e-05,
1751
+ "loss": 1.0122,
1752
+ "step": 12450
1753
+ },
1754
+ {
1755
+ "epoch": 2.000320051208193,
1756
+ "grad_norm": 0.501007080078125,
1757
+ "learning_rate": 5.867018376682396e-05,
1758
+ "loss": 1.0062,
1759
+ "step": 12500
1760
+ },
1761
+ {
1762
+ "epoch": 2.008321331413026,
1763
+ "grad_norm": 0.6925072073936462,
1764
+ "learning_rate": 5.832613627862097e-05,
1765
+ "loss": 0.8524,
1766
+ "step": 12550
1767
+ },
1768
+ {
1769
+ "epoch": 2.0163226116178588,
1770
+ "grad_norm": 0.6264834403991699,
1771
+ "learning_rate": 5.798168284195837e-05,
1772
+ "loss": 0.8474,
1773
+ "step": 12600
1774
+ },
1775
+ {
1776
+ "epoch": 2.0243238918226916,
1777
+ "grad_norm": 0.543258786201477,
1778
+ "learning_rate": 5.7636840250981405e-05,
1779
+ "loss": 0.819,
1780
+ "step": 12650
1781
+ },
1782
+ {
1783
+ "epoch": 2.0323251720275244,
1784
+ "grad_norm": 0.5597353577613831,
1785
+ "learning_rate": 5.729162531880892e-05,
1786
+ "loss": 0.8635,
1787
+ "step": 12700
1788
+ },
1789
+ {
1790
+ "epoch": 2.040326452232357,
1791
+ "grad_norm": 0.8554184436798096,
1792
+ "learning_rate": 5.694605487671357e-05,
1793
+ "loss": 0.8283,
1794
+ "step": 12750
1795
+ },
1796
+ {
1797
+ "epoch": 2.04832773243719,
1798
+ "grad_norm": 0.5572032332420349,
1799
+ "learning_rate": 5.6600145773301206e-05,
1800
+ "loss": 0.8744,
1801
+ "step": 12800
1802
+ },
1803
+ {
1804
+ "epoch": 2.056329012642023,
1805
+ "grad_norm": 0.6553796529769897,
1806
+ "learning_rate": 5.625391487368949e-05,
1807
+ "loss": 0.8572,
1808
+ "step": 12850
1809
+ },
1810
+ {
1811
+ "epoch": 2.0643302928468557,
1812
+ "grad_norm": 0.6666269302368164,
1813
+ "learning_rate": 5.590737905868551e-05,
1814
+ "loss": 0.8625,
1815
+ "step": 12900
1816
+ },
1817
+ {
1818
+ "epoch": 2.0723315730516885,
1819
+ "grad_norm": 0.6420098543167114,
1820
+ "learning_rate": 5.5560555223962784e-05,
1821
+ "loss": 0.8571,
1822
+ "step": 12950
1823
+ },
1824
+ {
1825
+ "epoch": 2.080332853256521,
1826
+ "grad_norm": 0.6100978255271912,
1827
+ "learning_rate": 5.5213460279237496e-05,
1828
+ "loss": 0.8579,
1829
+ "step": 13000
1830
+ },
1831
+ {
1832
+ "epoch": 2.0883341334613537,
1833
+ "grad_norm": 0.5606010556221008,
1834
+ "learning_rate": 5.4866111147444085e-05,
1835
+ "loss": 0.8715,
1836
+ "step": 13050
1837
+ },
1838
+ {
1839
+ "epoch": 2.0963354136661865,
1840
+ "grad_norm": 0.6860626339912415,
1841
+ "learning_rate": 5.4518524763910076e-05,
1842
+ "loss": 0.8513,
1843
+ "step": 13100
1844
+ },
1845
+ {
1846
+ "epoch": 2.1043366938710193,
1847
+ "grad_norm": 0.7012873291969299,
1848
+ "learning_rate": 5.4170718075530404e-05,
1849
+ "loss": 0.8454,
1850
+ "step": 13150
1851
+ },
1852
+ {
1853
+ "epoch": 2.112337974075852,
1854
+ "grad_norm": 0.6773386597633362,
1855
+ "learning_rate": 5.382270803994126e-05,
1856
+ "loss": 0.881,
1857
+ "step": 13200
1858
+ },
1859
+ {
1860
+ "epoch": 2.120339254280685,
1861
+ "grad_norm": 0.7174808382987976,
1862
+ "learning_rate": 5.347451162469309e-05,
1863
+ "loss": 0.858,
1864
+ "step": 13250
1865
+ },
1866
+ {
1867
+ "epoch": 2.1283405344855177,
1868
+ "grad_norm": 0.6617708206176758,
1869
+ "learning_rate": 5.3126145806423575e-05,
1870
+ "loss": 0.8531,
1871
+ "step": 13300
1872
+ },
1873
+ {
1874
+ "epoch": 2.1363418146903506,
1875
+ "grad_norm": 0.7019938826560974,
1876
+ "learning_rate": 5.277762757002971e-05,
1877
+ "loss": 0.8665,
1878
+ "step": 13350
1879
+ },
1880
+ {
1881
+ "epoch": 2.1443430948951834,
1882
+ "grad_norm": 0.6727155447006226,
1883
+ "learning_rate": 5.2428973907839804e-05,
1884
+ "loss": 0.8528,
1885
+ "step": 13400
1886
+ },
1887
+ {
1888
+ "epoch": 2.152344375100016,
1889
+ "grad_norm": 0.6648008227348328,
1890
+ "learning_rate": 5.208020181878499e-05,
1891
+ "loss": 0.8399,
1892
+ "step": 13450
1893
+ },
1894
+ {
1895
+ "epoch": 2.160345655304849,
1896
+ "grad_norm": 0.6274258494377136,
1897
+ "learning_rate": 5.173132830757039e-05,
1898
+ "loss": 0.8662,
1899
+ "step": 13500
1900
+ },
1901
+ {
1902
+ "epoch": 2.1683469355096814,
1903
+ "grad_norm": 0.6117835640907288,
1904
+ "learning_rate": 5.138237038384608e-05,
1905
+ "loss": 0.8503,
1906
+ "step": 13550
1907
+ },
1908
+ {
1909
+ "epoch": 2.176348215714514,
1910
+ "grad_norm": 0.6691561341285706,
1911
+ "learning_rate": 5.103334506137772e-05,
1912
+ "loss": 0.8645,
1913
+ "step": 13600
1914
+ },
1915
+ {
1916
+ "epoch": 2.184349495919347,
1917
+ "grad_norm": 0.5877872109413147,
1918
+ "learning_rate": 5.0684269357217084e-05,
1919
+ "loss": 0.8555,
1920
+ "step": 13650
1921
+ },
1922
+ {
1923
+ "epoch": 2.19235077612418,
1924
+ "grad_norm": 0.717145562171936,
1925
+ "learning_rate": 5.033516029087231e-05,
1926
+ "loss": 0.8799,
1927
+ "step": 13700
1928
+ },
1929
+ {
1930
+ "epoch": 2.2003520563290127,
1931
+ "grad_norm": 0.6587306261062622,
1932
+ "learning_rate": 4.99860348834782e-05,
1933
+ "loss": 0.88,
1934
+ "step": 13750
1935
+ },
1936
+ {
1937
+ "epoch": 2.2083533365338455,
1938
+ "grad_norm": 0.6128435134887695,
1939
+ "learning_rate": 4.963691015696624e-05,
1940
+ "loss": 0.853,
1941
+ "step": 13800
1942
+ },
1943
+ {
1944
+ "epoch": 2.2163546167386783,
1945
+ "grad_norm": 0.5783178210258484,
1946
+ "learning_rate": 4.928780313323473e-05,
1947
+ "loss": 0.8863,
1948
+ "step": 13850
1949
+ },
1950
+ {
1951
+ "epoch": 2.224355896943511,
1952
+ "grad_norm": 0.6364635825157166,
1953
+ "learning_rate": 4.893873083331882e-05,
1954
+ "loss": 0.8378,
1955
+ "step": 13900
1956
+ },
1957
+ {
1958
+ "epoch": 2.232357177148344,
1959
+ "grad_norm": 0.7266676425933838,
1960
+ "learning_rate": 4.8589710276560744e-05,
1961
+ "loss": 0.8647,
1962
+ "step": 13950
1963
+ },
1964
+ {
1965
+ "epoch": 2.2403584573531763,
1966
+ "grad_norm": 0.6661261916160583,
1967
+ "learning_rate": 4.8240758479779884e-05,
1968
+ "loss": 0.835,
1969
+ "step": 14000
1970
+ },
1971
+ {
1972
+ "epoch": 2.248359737558009,
1973
+ "grad_norm": 0.7814577221870422,
1974
+ "learning_rate": 4.789189245644318e-05,
1975
+ "loss": 0.8379,
1976
+ "step": 14050
1977
+ },
1978
+ {
1979
+ "epoch": 2.256361017762842,
1980
+ "grad_norm": 0.6463228464126587,
1981
+ "learning_rate": 4.754312921583564e-05,
1982
+ "loss": 0.8628,
1983
+ "step": 14100
1984
+ },
1985
+ {
1986
+ "epoch": 2.2643622979676747,
1987
+ "grad_norm": 0.7221981883049011,
1988
+ "learning_rate": 4.719448576223096e-05,
1989
+ "loss": 0.8565,
1990
+ "step": 14150
1991
+ },
1992
+ {
1993
+ "epoch": 2.2723635781725076,
1994
+ "grad_norm": 0.6834704279899597,
1995
+ "learning_rate": 4.684597909406253e-05,
1996
+ "loss": 0.8776,
1997
+ "step": 14200
1998
+ },
1999
+ {
2000
+ "epoch": 2.2803648583773404,
2001
+ "grad_norm": 0.6285929083824158,
2002
+ "learning_rate": 4.649762620309466e-05,
2003
+ "loss": 0.8356,
2004
+ "step": 14250
2005
+ },
2006
+ {
2007
+ "epoch": 2.288366138582173,
2008
+ "grad_norm": 0.6223785281181335,
2009
+ "learning_rate": 4.61494440735941e-05,
2010
+ "loss": 0.834,
2011
+ "step": 14300
2012
+ },
2013
+ {
2014
+ "epoch": 2.296367418787006,
2015
+ "grad_norm": 0.7635972499847412,
2016
+ "learning_rate": 4.580144968150192e-05,
2017
+ "loss": 0.8603,
2018
+ "step": 14350
2019
+ },
2020
+ {
2021
+ "epoch": 2.304368698991839,
2022
+ "grad_norm": 0.6658472418785095,
2023
+ "learning_rate": 4.5453659993605944e-05,
2024
+ "loss": 0.8393,
2025
+ "step": 14400
2026
+ },
2027
+ {
2028
+ "epoch": 2.3123699791966716,
2029
+ "grad_norm": 0.6321608424186707,
2030
+ "learning_rate": 4.510609196671345e-05,
2031
+ "loss": 0.8416,
2032
+ "step": 14450
2033
+ },
2034
+ {
2035
+ "epoch": 2.3203712594015045,
2036
+ "grad_norm": 0.6526052355766296,
2037
+ "learning_rate": 4.4758762546824364e-05,
2038
+ "loss": 0.8696,
2039
+ "step": 14500
2040
+ },
2041
+ {
2042
+ "epoch": 2.328372539606337,
2043
+ "grad_norm": 0.6651396751403809,
2044
+ "learning_rate": 4.441168866830516e-05,
2045
+ "loss": 0.8619,
2046
+ "step": 14550
2047
+ },
2048
+ {
2049
+ "epoch": 2.3363738198111696,
2050
+ "grad_norm": 0.6737195253372192,
2051
+ "learning_rate": 4.406488725306317e-05,
2052
+ "loss": 0.8447,
2053
+ "step": 14600
2054
+ },
2055
+ {
2056
+ "epoch": 2.3443751000160025,
2057
+ "grad_norm": 0.5813534259796143,
2058
+ "learning_rate": 4.3718375209721505e-05,
2059
+ "loss": 0.8468,
2060
+ "step": 14650
2061
+ },
2062
+ {
2063
+ "epoch": 2.3523763802208353,
2064
+ "grad_norm": 0.7838544249534607,
2065
+ "learning_rate": 4.337216943279464e-05,
2066
+ "loss": 0.8344,
2067
+ "step": 14700
2068
+ },
2069
+ {
2070
+ "epoch": 2.360377660425668,
2071
+ "grad_norm": 0.6356272101402283,
2072
+ "learning_rate": 4.3026286801864854e-05,
2073
+ "loss": 0.8699,
2074
+ "step": 14750
2075
+ },
2076
+ {
2077
+ "epoch": 2.368378940630501,
2078
+ "grad_norm": 0.6201728582382202,
2079
+ "learning_rate": 4.268074418075903e-05,
2080
+ "loss": 0.8515,
2081
+ "step": 14800
2082
+ },
2083
+ {
2084
+ "epoch": 2.3763802208353337,
2085
+ "grad_norm": 0.6424387693405151,
2086
+ "learning_rate": 4.233555841672663e-05,
2087
+ "loss": 0.8429,
2088
+ "step": 14850
2089
+ },
2090
+ {
2091
+ "epoch": 2.3843815010401666,
2092
+ "grad_norm": 0.6518192291259766,
2093
+ "learning_rate": 4.1990746339618216e-05,
2094
+ "loss": 0.8666,
2095
+ "step": 14900
2096
+ },
2097
+ {
2098
+ "epoch": 2.3923827812449994,
2099
+ "grad_norm": 0.7236935496330261,
2100
+ "learning_rate": 4.164632476106484e-05,
2101
+ "loss": 0.8478,
2102
+ "step": 14950
2103
+ },
2104
+ {
2105
+ "epoch": 2.4003840614498317,
2106
+ "grad_norm": 0.692077100276947,
2107
+ "learning_rate": 4.13023104736585e-05,
2108
+ "loss": 0.8756,
2109
+ "step": 15000
2110
+ },
2111
+ {
2112
+ "epoch": 2.4083853416546646,
2113
+ "grad_norm": 0.6063551306724548,
2114
+ "learning_rate": 4.095872025013333e-05,
2115
+ "loss": 0.8221,
2116
+ "step": 15050
2117
+ },
2118
+ {
2119
+ "epoch": 2.4163866218594974,
2120
+ "grad_norm": 0.5967947840690613,
2121
+ "learning_rate": 4.0615570842547815e-05,
2122
+ "loss": 0.8731,
2123
+ "step": 15100
2124
+ },
2125
+ {
2126
+ "epoch": 2.42438790206433,
2127
+ "grad_norm": 0.7256248593330383,
2128
+ "learning_rate": 4.0272878981468045e-05,
2129
+ "loss": 0.8614,
2130
+ "step": 15150
2131
+ },
2132
+ {
2133
+ "epoch": 2.432389182269163,
2134
+ "grad_norm": 0.6148253083229065,
2135
+ "learning_rate": 3.9930661375152045e-05,
2136
+ "loss": 0.8337,
2137
+ "step": 15200
2138
+ },
2139
+ {
2140
+ "epoch": 2.440390462473996,
2141
+ "grad_norm": 0.6977733373641968,
2142
+ "learning_rate": 3.958893470873509e-05,
2143
+ "loss": 0.8235,
2144
+ "step": 15250
2145
+ },
2146
+ {
2147
+ "epoch": 2.4483917426788286,
2148
+ "grad_norm": 0.6713569164276123,
2149
+ "learning_rate": 3.924771564341621e-05,
2150
+ "loss": 0.8301,
2151
+ "step": 15300
2152
+ },
2153
+ {
2154
+ "epoch": 2.4563930228836615,
2155
+ "grad_norm": 0.637150228023529,
2156
+ "learning_rate": 3.890702081564593e-05,
2157
+ "loss": 0.8355,
2158
+ "step": 15350
2159
+ },
2160
+ {
2161
+ "epoch": 2.4643943030884943,
2162
+ "grad_norm": 0.6515012383460999,
2163
+ "learning_rate": 3.856686683631502e-05,
2164
+ "loss": 0.8547,
2165
+ "step": 15400
2166
+ },
2167
+ {
2168
+ "epoch": 2.472395583293327,
2169
+ "grad_norm": 0.6041115522384644,
2170
+ "learning_rate": 3.822727028994471e-05,
2171
+ "loss": 0.8421,
2172
+ "step": 15450
2173
+ },
2174
+ {
2175
+ "epoch": 2.48039686349816,
2176
+ "grad_norm": 0.6472122073173523,
2177
+ "learning_rate": 3.788824773387811e-05,
2178
+ "loss": 0.838,
2179
+ "step": 15500
2180
+ },
2181
+ {
2182
+ "epoch": 2.4883981437029927,
2183
+ "grad_norm": 0.7198679447174072,
2184
+ "learning_rate": 3.754981569747287e-05,
2185
+ "loss": 0.8213,
2186
+ "step": 15550
2187
+ },
2188
+ {
2189
+ "epoch": 2.496399423907825,
2190
+ "grad_norm": 0.6885024309158325,
2191
+ "learning_rate": 3.721199068129527e-05,
2192
+ "loss": 0.8354,
2193
+ "step": 15600
2194
+ },
2195
+ {
2196
+ "epoch": 2.504400704112658,
2197
+ "grad_norm": 0.6485710740089417,
2198
+ "learning_rate": 3.6874789156315835e-05,
2199
+ "loss": 0.8633,
2200
+ "step": 15650
2201
+ },
2202
+ {
2203
+ "epoch": 2.5124019843174907,
2204
+ "grad_norm": 0.6844043135643005,
2205
+ "learning_rate": 3.6538227563106164e-05,
2206
+ "loss": 0.8105,
2207
+ "step": 15700
2208
+ },
2209
+ {
2210
+ "epoch": 2.5204032645223235,
2211
+ "grad_norm": 0.8702924847602844,
2212
+ "learning_rate": 3.6202322311037374e-05,
2213
+ "loss": 0.8121,
2214
+ "step": 15750
2215
+ },
2216
+ {
2217
+ "epoch": 2.5284045447271564,
2218
+ "grad_norm": 0.7209028005599976,
2219
+ "learning_rate": 3.586708977748012e-05,
2220
+ "loss": 0.8758,
2221
+ "step": 15800
2222
+ },
2223
+ {
2224
+ "epoch": 2.536405824931989,
2225
+ "grad_norm": 0.6202672123908997,
2226
+ "learning_rate": 3.553254630700597e-05,
2227
+ "loss": 0.8474,
2228
+ "step": 15850
2229
+ },
2230
+ {
2231
+ "epoch": 2.544407105136822,
2232
+ "grad_norm": 0.6669834852218628,
2233
+ "learning_rate": 3.5198708210590626e-05,
2234
+ "loss": 0.8482,
2235
+ "step": 15900
2236
+ },
2237
+ {
2238
+ "epoch": 2.552408385341655,
2239
+ "grad_norm": 0.6584005951881409,
2240
+ "learning_rate": 3.486559176481865e-05,
2241
+ "loss": 0.8416,
2242
+ "step": 15950
2243
+ },
2244
+ {
2245
+ "epoch": 2.560409665546487,
2246
+ "grad_norm": 0.5252745747566223,
2247
+ "learning_rate": 3.4533213211089825e-05,
2248
+ "loss": 0.8401,
2249
+ "step": 16000
2250
+ },
2251
+ {
2252
+ "epoch": 2.56841094575132,
2253
+ "grad_norm": 0.6504681706428528,
2254
+ "learning_rate": 3.4201588754827314e-05,
2255
+ "loss": 0.8486,
2256
+ "step": 16050
2257
+ },
2258
+ {
2259
+ "epoch": 2.576412225956153,
2260
+ "grad_norm": 0.7693225741386414,
2261
+ "learning_rate": 3.387073456468761e-05,
2262
+ "loss": 0.845,
2263
+ "step": 16100
2264
+ },
2265
+ {
2266
+ "epoch": 2.5844135061609856,
2267
+ "grad_norm": 0.6965412497520447,
2268
+ "learning_rate": 3.354066677177214e-05,
2269
+ "loss": 0.8568,
2270
+ "step": 16150
2271
+ },
2272
+ {
2273
+ "epoch": 2.5924147863658185,
2274
+ "grad_norm": 0.6364871859550476,
2275
+ "learning_rate": 3.321140146884081e-05,
2276
+ "loss": 0.8693,
2277
+ "step": 16200
2278
+ },
2279
+ {
2280
+ "epoch": 2.6004160665706513,
2281
+ "grad_norm": 0.7464070916175842,
2282
+ "learning_rate": 3.288295470952737e-05,
2283
+ "loss": 0.8566,
2284
+ "step": 16250
2285
+ },
2286
+ {
2287
+ "epoch": 2.608417346775484,
2288
+ "grad_norm": 0.6804706454277039,
2289
+ "learning_rate": 3.255534250755678e-05,
2290
+ "loss": 0.8708,
2291
+ "step": 16300
2292
+ },
2293
+ {
2294
+ "epoch": 2.616418626980317,
2295
+ "grad_norm": 0.6775168776512146,
2296
+ "learning_rate": 3.222858083596431e-05,
2297
+ "loss": 0.8558,
2298
+ "step": 16350
2299
+ },
2300
+ {
2301
+ "epoch": 2.6244199071851497,
2302
+ "grad_norm": 0.7037110924720764,
2303
+ "learning_rate": 3.190268562631688e-05,
2304
+ "loss": 0.8313,
2305
+ "step": 16400
2306
+ },
2307
+ {
2308
+ "epoch": 2.6324211873899825,
2309
+ "grad_norm": 0.5500233173370361,
2310
+ "learning_rate": 3.157767276793626e-05,
2311
+ "loss": 0.7998,
2312
+ "step": 16450
2313
+ },
2314
+ {
2315
+ "epoch": 2.6404224675948154,
2316
+ "grad_norm": 0.7002319097518921,
2317
+ "learning_rate": 3.125355810712435e-05,
2318
+ "loss": 0.8247,
2319
+ "step": 16500
2320
+ },
2321
+ {
2322
+ "epoch": 2.648423747799648,
2323
+ "grad_norm": 0.7857663631439209,
2324
+ "learning_rate": 3.093035744639061e-05,
2325
+ "loss": 0.8318,
2326
+ "step": 16550
2327
+ },
2328
+ {
2329
+ "epoch": 2.656425028004481,
2330
+ "grad_norm": 0.7866588830947876,
2331
+ "learning_rate": 3.06080865436816e-05,
2332
+ "loss": 0.814,
2333
+ "step": 16600
2334
+ },
2335
+ {
2336
+ "epoch": 2.6644263082093134,
2337
+ "grad_norm": 0.6732119917869568,
2338
+ "learning_rate": 3.0286761111612626e-05,
2339
+ "loss": 0.8527,
2340
+ "step": 16650
2341
+ },
2342
+ {
2343
+ "epoch": 2.672427588414146,
2344
+ "grad_norm": 0.6847143769264221,
2345
+ "learning_rate": 2.9966396816701725e-05,
2346
+ "loss": 0.8012,
2347
+ "step": 16700
2348
+ },
2349
+ {
2350
+ "epoch": 2.680428868618979,
2351
+ "grad_norm": 0.6862397193908691,
2352
+ "learning_rate": 2.964700927860581e-05,
2353
+ "loss": 0.817,
2354
+ "step": 16750
2355
+ },
2356
+ {
2357
+ "epoch": 2.688430148823812,
2358
+ "grad_norm": 0.6373656988143921,
2359
+ "learning_rate": 2.9328614069359128e-05,
2360
+ "loss": 0.8625,
2361
+ "step": 16800
2362
+ },
2363
+ {
2364
+ "epoch": 2.6964314290286446,
2365
+ "grad_norm": 0.7099259495735168,
2366
+ "learning_rate": 2.9011226712613937e-05,
2367
+ "loss": 0.8445,
2368
+ "step": 16850
2369
+ },
2370
+ {
2371
+ "epoch": 2.7044327092334774,
2372
+ "grad_norm": 0.6120832562446594,
2373
+ "learning_rate": 2.8694862682883866e-05,
2374
+ "loss": 0.7982,
2375
+ "step": 16900
2376
+ },
2377
+ {
2378
+ "epoch": 2.7124339894383103,
2379
+ "grad_norm": 0.8442961573600769,
2380
+ "learning_rate": 2.8379537404789124e-05,
2381
+ "loss": 0.8307,
2382
+ "step": 16950
2383
+ },
2384
+ {
2385
+ "epoch": 2.7204352696431426,
2386
+ "grad_norm": 0.6093111634254456,
2387
+ "learning_rate": 2.8065266252304712e-05,
2388
+ "loss": 0.7811,
2389
+ "step": 17000
2390
+ },
2391
+ {
2392
+ "epoch": 2.7284365498479755,
2393
+ "grad_norm": 0.6981213092803955,
2394
+ "learning_rate": 2.775206454801079e-05,
2395
+ "loss": 0.8533,
2396
+ "step": 17050
2397
+ },
2398
+ {
2399
+ "epoch": 2.7364378300528083,
2400
+ "grad_norm": 0.696796178817749,
2401
+ "learning_rate": 2.7439947562345546e-05,
2402
+ "loss": 0.8182,
2403
+ "step": 17100
2404
+ },
2405
+ {
2406
+ "epoch": 2.744439110257641,
2407
+ "grad_norm": 0.6803203225135803,
2408
+ "learning_rate": 2.7128930512860658e-05,
2409
+ "loss": 0.8391,
2410
+ "step": 17150
2411
+ },
2412
+ {
2413
+ "epoch": 2.752440390462474,
2414
+ "grad_norm": 0.6710325479507446,
2415
+ "learning_rate": 2.6819028563479505e-05,
2416
+ "loss": 0.8229,
2417
+ "step": 17200
2418
+ },
2419
+ {
2420
+ "epoch": 2.7604416706673067,
2421
+ "grad_norm": 0.7354364395141602,
2422
+ "learning_rate": 2.6510256823757667e-05,
2423
+ "loss": 0.8121,
2424
+ "step": 17250
2425
+ },
2426
+ {
2427
+ "epoch": 2.7684429508721395,
2428
+ "grad_norm": 0.7637900710105896,
2429
+ "learning_rate": 2.6202630348146324e-05,
2430
+ "loss": 0.84,
2431
+ "step": 17300
2432
+ },
2433
+ {
2434
+ "epoch": 2.7764442310769724,
2435
+ "grad_norm": 0.587841808795929,
2436
+ "learning_rate": 2.589616413525824e-05,
2437
+ "loss": 0.8117,
2438
+ "step": 17350
2439
+ },
2440
+ {
2441
+ "epoch": 2.784445511281805,
2442
+ "grad_norm": 0.667797327041626,
2443
+ "learning_rate": 2.559087312713651e-05,
2444
+ "loss": 0.8131,
2445
+ "step": 17400
2446
+ },
2447
+ {
2448
+ "epoch": 2.792446791486638,
2449
+ "grad_norm": 0.5983754992485046,
2450
+ "learning_rate": 2.5286772208526027e-05,
2451
+ "loss": 0.8309,
2452
+ "step": 17450
2453
+ },
2454
+ {
2455
+ "epoch": 2.800448071691471,
2456
+ "grad_norm": 0.7884683012962341,
2457
+ "learning_rate": 2.4983876206147776e-05,
2458
+ "loss": 0.8208,
2459
+ "step": 17500
2460
+ },
2461
+ {
2462
+ "epoch": 2.8084493518963036,
2463
+ "grad_norm": 0.6957002878189087,
2464
+ "learning_rate": 2.4682199887975938e-05,
2465
+ "loss": 0.8699,
2466
+ "step": 17550
2467
+ },
2468
+ {
2469
+ "epoch": 2.8164506321011364,
2470
+ "grad_norm": 0.5889870524406433,
2471
+ "learning_rate": 2.438175796251786e-05,
2472
+ "loss": 0.8282,
2473
+ "step": 17600
2474
+ },
2475
+ {
2476
+ "epoch": 2.824451912305969,
2477
+ "grad_norm": 0.7357444167137146,
2478
+ "learning_rate": 2.4082565078096935e-05,
2479
+ "loss": 0.8025,
2480
+ "step": 17650
2481
+ },
2482
+ {
2483
+ "epoch": 2.8324531925108016,
2484
+ "grad_norm": 0.8791075348854065,
2485
+ "learning_rate": 2.3784635822138424e-05,
2486
+ "loss": 0.8338,
2487
+ "step": 17700
2488
+ },
2489
+ {
2490
+ "epoch": 2.8404544727156344,
2491
+ "grad_norm": 0.6486666202545166,
2492
+ "learning_rate": 2.348798472045819e-05,
2493
+ "loss": 0.8221,
2494
+ "step": 17750
2495
+ },
2496
+ {
2497
+ "epoch": 2.8484557529204673,
2498
+ "grad_norm": 0.6927144527435303,
2499
+ "learning_rate": 2.3192626236554516e-05,
2500
+ "loss": 0.8249,
2501
+ "step": 17800
2502
+ },
2503
+ {
2504
+ "epoch": 2.8564570331253,
2505
+ "grad_norm": 0.7874731421470642,
2506
+ "learning_rate": 2.2898574770902914e-05,
2507
+ "loss": 0.8267,
2508
+ "step": 17850
2509
+ },
2510
+ {
2511
+ "epoch": 2.864458313330133,
2512
+ "grad_norm": 0.6948744654655457,
2513
+ "learning_rate": 2.260584466025401e-05,
2514
+ "loss": 0.8139,
2515
+ "step": 17900
2516
+ },
2517
+ {
2518
+ "epoch": 2.8724595935349657,
2519
+ "grad_norm": 0.6847252249717712,
2520
+ "learning_rate": 2.231445017693454e-05,
2521
+ "loss": 0.8432,
2522
+ "step": 17950
2523
+ },
2524
+ {
2525
+ "epoch": 2.8804608737397985,
2526
+ "grad_norm": 0.6781948804855347,
2527
+ "learning_rate": 2.2024405528151547e-05,
2528
+ "loss": 0.8298,
2529
+ "step": 18000
2530
+ },
2531
+ {
2532
+ "epoch": 2.888462153944631,
2533
+ "grad_norm": 0.6336878538131714,
2534
+ "learning_rate": 2.1735724855299567e-05,
2535
+ "loss": 0.81,
2536
+ "step": 18050
2537
+ },
2538
+ {
2539
+ "epoch": 2.8964634341494637,
2540
+ "grad_norm": 0.6111786365509033,
2541
+ "learning_rate": 2.1448422233271254e-05,
2542
+ "loss": 0.7977,
2543
+ "step": 18100
2544
+ },
2545
+ {
2546
+ "epoch": 2.9044647143542965,
2547
+ "grad_norm": 0.7334992289543152,
2548
+ "learning_rate": 2.116251166977118e-05,
2549
+ "loss": 0.8221,
2550
+ "step": 18150
2551
+ },
2552
+ {
2553
+ "epoch": 2.9124659945591294,
2554
+ "grad_norm": 0.8408239483833313,
2555
+ "learning_rate": 2.0878007104632775e-05,
2556
+ "loss": 0.8597,
2557
+ "step": 18200
2558
+ },
2559
+ {
2560
+ "epoch": 2.920467274763962,
2561
+ "grad_norm": 0.6892300248146057,
2562
+ "learning_rate": 2.059492240913866e-05,
2563
+ "loss": 0.8088,
2564
+ "step": 18250
2565
+ },
2566
+ {
2567
+ "epoch": 2.928468554968795,
2568
+ "grad_norm": 0.5887216925621033,
2569
+ "learning_rate": 2.0313271385344522e-05,
2570
+ "loss": 0.8207,
2571
+ "step": 18300
2572
+ },
2573
+ {
2574
+ "epoch": 2.936469835173628,
2575
+ "grad_norm": 0.6477887630462646,
2576
+ "learning_rate": 2.0033067765406004e-05,
2577
+ "loss": 0.839,
2578
+ "step": 18350
2579
+ },
2580
+ {
2581
+ "epoch": 2.9444711153784606,
2582
+ "grad_norm": 0.7348781228065491,
2583
+ "learning_rate": 1.9754325210909174e-05,
2584
+ "loss": 0.8412,
2585
+ "step": 18400
2586
+ },
2587
+ {
2588
+ "epoch": 2.9524723955832934,
2589
+ "grad_norm": 0.6994746923446655,
2590
+ "learning_rate": 1.947705731220462e-05,
2591
+ "loss": 0.8069,
2592
+ "step": 18450
2593
+ },
2594
+ {
2595
+ "epoch": 2.9604736757881263,
2596
+ "grad_norm": 0.6778689026832581,
2597
+ "learning_rate": 1.920127758774466e-05,
2598
+ "loss": 0.8119,
2599
+ "step": 18500
2600
+ },
2601
+ {
2602
+ "epoch": 2.968474955992959,
2603
+ "grad_norm": 0.7225350737571716,
2604
+ "learning_rate": 1.8926999483424313e-05,
2605
+ "loss": 0.8504,
2606
+ "step": 18550
2607
+ },
2608
+ {
2609
+ "epoch": 2.976476236197792,
2610
+ "grad_norm": 0.8543927073478699,
2611
+ "learning_rate": 1.8654236371925727e-05,
2612
+ "loss": 0.8124,
2613
+ "step": 18600
2614
+ },
2615
+ {
2616
+ "epoch": 2.9844775164026243,
2617
+ "grad_norm": 0.6733004450798035,
2618
+ "learning_rate": 1.8383001552066164e-05,
2619
+ "loss": 0.8299,
2620
+ "step": 18650
2621
+ },
2622
+ {
2623
+ "epoch": 2.992478796607457,
2624
+ "grad_norm": 0.7595524787902832,
2625
+ "learning_rate": 1.8113308248149635e-05,
2626
+ "loss": 0.8177,
2627
+ "step": 18700
2628
+ },
2629
+ {
2630
+ "epoch": 3.00048007681229,
2631
+ "grad_norm": 0.6430355310440063,
2632
+ "learning_rate": 1.784516960932211e-05,
2633
+ "loss": 0.8311,
2634
+ "step": 18750
2635
+ },
2636
+ {
2637
+ "epoch": 3.0084813570171227,
2638
+ "grad_norm": 0.6314593553543091,
2639
+ "learning_rate": 1.7578598708930428e-05,
2640
+ "loss": 0.7241,
2641
+ "step": 18800
2642
+ },
2643
+ {
2644
+ "epoch": 3.0164826372219555,
2645
+ "grad_norm": 0.6709548234939575,
2646
+ "learning_rate": 1.7313608543884868e-05,
2647
+ "loss": 0.7459,
2648
+ "step": 18850
2649
+ },
2650
+ {
2651
+ "epoch": 3.0244839174267883,
2652
+ "grad_norm": 0.6981055736541748,
2653
+ "learning_rate": 1.7050212034025575e-05,
2654
+ "loss": 0.7399,
2655
+ "step": 18900
2656
+ },
2657
+ {
2658
+ "epoch": 3.032485197631621,
2659
+ "grad_norm": 0.7344752550125122,
2660
+ "learning_rate": 1.6788422021492472e-05,
2661
+ "loss": 0.7197,
2662
+ "step": 18950
2663
+ },
2664
+ {
2665
+ "epoch": 3.040486477836454,
2666
+ "grad_norm": 0.7181177139282227,
2667
+ "learning_rate": 1.6528251270099256e-05,
2668
+ "loss": 0.7161,
2669
+ "step": 19000
2670
+ },
2671
+ {
2672
+ "epoch": 3.048487758041287,
2673
+ "grad_norm": 0.5588538646697998,
2674
+ "learning_rate": 1.6269712464711105e-05,
2675
+ "loss": 0.7488,
2676
+ "step": 19050
2677
+ },
2678
+ {
2679
+ "epoch": 3.056489038246119,
2680
+ "grad_norm": 0.7480596303939819,
2681
+ "learning_rate": 1.6012818210626075e-05,
2682
+ "loss": 0.712,
2683
+ "step": 19100
2684
+ },
2685
+ {
2686
+ "epoch": 3.064490318450952,
2687
+ "grad_norm": 0.5872476696968079,
2688
+ "learning_rate": 1.5757581032960638e-05,
2689
+ "loss": 0.7154,
2690
+ "step": 19150
2691
+ },
2692
+ {
2693
+ "epoch": 3.072491598655785,
2694
+ "grad_norm": 0.6517592072486877,
2695
+ "learning_rate": 1.550401337603902e-05,
2696
+ "loss": 0.7134,
2697
+ "step": 19200
2698
+ },
2699
+ {
2700
+ "epoch": 3.0804928788606176,
2701
+ "grad_norm": 0.6740624308586121,
2702
+ "learning_rate": 1.5252127602786397e-05,
2703
+ "loss": 0.7446,
2704
+ "step": 19250
2705
+ },
2706
+ {
2707
+ "epoch": 3.0884941590654504,
2708
+ "grad_norm": 0.6558243632316589,
2709
+ "learning_rate": 1.5001935994126104e-05,
2710
+ "loss": 0.7354,
2711
+ "step": 19300
2712
+ },
2713
+ {
2714
+ "epoch": 3.0964954392702833,
2715
+ "grad_norm": 0.6562448740005493,
2716
+ "learning_rate": 1.4753450748380953e-05,
2717
+ "loss": 0.7035,
2718
+ "step": 19350
2719
+ },
2720
+ {
2721
+ "epoch": 3.104496719475116,
2722
+ "grad_norm": 0.7197704315185547,
2723
+ "learning_rate": 1.4506683980678503e-05,
2724
+ "loss": 0.7313,
2725
+ "step": 19400
2726
+ },
2727
+ {
2728
+ "epoch": 3.112497999679949,
2729
+ "grad_norm": 0.7322149872779846,
2730
+ "learning_rate": 1.4261647722360278e-05,
2731
+ "loss": 0.7357,
2732
+ "step": 19450
2733
+ },
2734
+ {
2735
+ "epoch": 3.1204992798847817,
2736
+ "grad_norm": 0.7477754354476929,
2737
+ "learning_rate": 1.4018353920395193e-05,
2738
+ "loss": 0.7334,
2739
+ "step": 19500
2740
+ },
2741
+ {
2742
+ "epoch": 3.1285005600896145,
2743
+ "grad_norm": 0.5789663791656494,
2744
+ "learning_rate": 1.3776814436797176e-05,
2745
+ "loss": 0.7435,
2746
+ "step": 19550
2747
+ },
2748
+ {
2749
+ "epoch": 3.1365018402944473,
2750
+ "grad_norm": 0.6711790561676025,
2751
+ "learning_rate": 1.3537041048046695e-05,
2752
+ "loss": 0.713,
2753
+ "step": 19600
2754
+ },
2755
+ {
2756
+ "epoch": 3.1445031204992797,
2757
+ "grad_norm": 0.6365526914596558,
2758
+ "learning_rate": 1.32990454445166e-05,
2759
+ "loss": 0.7679,
2760
+ "step": 19650
2761
+ },
2762
+ {
2763
+ "epoch": 3.1525044007041125,
2764
+ "grad_norm": 0.6711440682411194,
2765
+ "learning_rate": 1.3062839229902263e-05,
2766
+ "loss": 0.7199,
2767
+ "step": 19700
2768
+ },
2769
+ {
2770
+ "epoch": 3.1605056809089453,
2771
+ "grad_norm": 0.7575156688690186,
2772
+ "learning_rate": 1.2828433920655687e-05,
2773
+ "loss": 0.7052,
2774
+ "step": 19750
2775
+ },
2776
+ {
2777
+ "epoch": 3.168506961113778,
2778
+ "grad_norm": 0.6248161792755127,
2779
+ "learning_rate": 1.2595840945424093e-05,
2780
+ "loss": 0.7129,
2781
+ "step": 19800
2782
+ },
2783
+ {
2784
+ "epoch": 3.176508241318611,
2785
+ "grad_norm": 0.7342621684074402,
2786
+ "learning_rate": 1.2365071644492682e-05,
2787
+ "loss": 0.7187,
2788
+ "step": 19850
2789
+ },
2790
+ {
2791
+ "epoch": 3.184509521523444,
2792
+ "grad_norm": 0.6555837988853455,
2793
+ "learning_rate": 1.2136137269231723e-05,
2794
+ "loss": 0.7378,
2795
+ "step": 19900
2796
+ },
2797
+ {
2798
+ "epoch": 3.1925108017282766,
2799
+ "grad_norm": 0.7092923521995544,
2800
+ "learning_rate": 1.1909048981547998e-05,
2801
+ "loss": 0.7259,
2802
+ "step": 19950
2803
+ },
2804
+ {
2805
+ "epoch": 3.2005120819331094,
2806
+ "grad_norm": 0.6612015962600708,
2807
+ "learning_rate": 1.1683817853340595e-05,
2808
+ "loss": 0.7168,
2809
+ "step": 20000
2810
+ },
2811
+ {
2812
+ "epoch": 3.2085133621379422,
2813
+ "grad_norm": 0.7098072171211243,
2814
+ "learning_rate": 1.1460454865961056e-05,
2815
+ "loss": 0.7226,
2816
+ "step": 20050
2817
+ },
2818
+ {
2819
+ "epoch": 3.2165146423427746,
2820
+ "grad_norm": 0.7153401970863342,
2821
+ "learning_rate": 1.1238970909677993e-05,
2822
+ "loss": 0.7304,
2823
+ "step": 20100
2824
+ },
2825
+ {
2826
+ "epoch": 3.2245159225476074,
2827
+ "grad_norm": 0.6184985637664795,
2828
+ "learning_rate": 1.1019376783146174e-05,
2829
+ "loss": 0.7113,
2830
+ "step": 20150
2831
+ },
2832
+ {
2833
+ "epoch": 3.2325172027524403,
2834
+ "grad_norm": 0.658746063709259,
2835
+ "learning_rate": 1.080168319287989e-05,
2836
+ "loss": 0.7545,
2837
+ "step": 20200
2838
+ },
2839
+ {
2840
+ "epoch": 3.240518482957273,
2841
+ "grad_norm": 0.6574704647064209,
2842
+ "learning_rate": 1.0585900752731077e-05,
2843
+ "loss": 0.7103,
2844
+ "step": 20250
2845
+ },
2846
+ {
2847
+ "epoch": 3.248519763162106,
2848
+ "grad_norm": 0.7436890006065369,
2849
+ "learning_rate": 1.0372039983371818e-05,
2850
+ "loss": 0.7335,
2851
+ "step": 20300
2852
+ },
2853
+ {
2854
+ "epoch": 3.2565210433669387,
2855
+ "grad_norm": 0.7010487914085388,
2856
+ "learning_rate": 1.0160111311781284e-05,
2857
+ "loss": 0.7463,
2858
+ "step": 20350
2859
+ },
2860
+ {
2861
+ "epoch": 3.2645223235717715,
2862
+ "grad_norm": 0.7422741651535034,
2863
+ "learning_rate": 9.950125070737476e-06,
2864
+ "loss": 0.7253,
2865
+ "step": 20400
2866
+ },
2867
+ {
2868
+ "epoch": 3.2725236037766043,
2869
+ "grad_norm": 0.6463279724121094,
2870
+ "learning_rate": 9.742091498313426e-06,
2871
+ "loss": 0.7334,
2872
+ "step": 20450
2873
+ },
2874
+ {
2875
+ "epoch": 3.280524883981437,
2876
+ "grad_norm": 0.7407013177871704,
2877
+ "learning_rate": 9.536020737377993e-06,
2878
+ "loss": 0.7104,
2879
+ "step": 20500
2880
+ },
2881
+ {
2882
+ "epoch": 3.28852616418627,
2883
+ "grad_norm": 0.6367645263671875,
2884
+ "learning_rate": 9.331922835101282e-06,
2885
+ "loss": 0.7105,
2886
+ "step": 20550
2887
+ },
2888
+ {
2889
+ "epoch": 3.296527444391103,
2890
+ "grad_norm": 0.7848844528198242,
2891
+ "learning_rate": 9.129807742464957e-06,
2892
+ "loss": 0.7155,
2893
+ "step": 20600
2894
+ },
2895
+ {
2896
+ "epoch": 3.304528724595935,
2897
+ "grad_norm": 0.6976688504219055,
2898
+ "learning_rate": 8.929685313776903e-06,
2899
+ "loss": 0.7363,
2900
+ "step": 20650
2901
+ },
2902
+ {
2903
+ "epoch": 3.312530004800768,
2904
+ "grad_norm": 0.7478333711624146,
2905
+ "learning_rate": 8.731565306190852e-06,
2906
+ "loss": 0.7612,
2907
+ "step": 20700
2908
+ },
2909
+ {
2910
+ "epoch": 3.320531285005601,
2911
+ "grad_norm": 0.6891793012619019,
2912
+ "learning_rate": 8.535457379230649e-06,
2913
+ "loss": 0.7221,
2914
+ "step": 20750
2915
+ },
2916
+ {
2917
+ "epoch": 3.3285325652104336,
2918
+ "grad_norm": 0.6285429000854492,
2919
+ "learning_rate": 8.341371094319289e-06,
2920
+ "loss": 0.7554,
2921
+ "step": 20800
2922
+ },
2923
+ {
2924
+ "epoch": 3.3365338454152664,
2925
+ "grad_norm": 0.7216114401817322,
2926
+ "learning_rate": 8.149315914312733e-06,
2927
+ "loss": 0.7297,
2928
+ "step": 20850
2929
+ },
2930
+ {
2931
+ "epoch": 3.3445351256200992,
2932
+ "grad_norm": 0.6681531071662903,
2933
+ "learning_rate": 7.959301203038566e-06,
2934
+ "loss": 0.7283,
2935
+ "step": 20900
2936
+ },
2937
+ {
2938
+ "epoch": 3.352536405824932,
2939
+ "grad_norm": 0.6501981019973755,
2940
+ "learning_rate": 7.771336224839425e-06,
2941
+ "loss": 0.723,
2942
+ "step": 20950
2943
+ },
2944
+ {
2945
+ "epoch": 3.360537686029765,
2946
+ "grad_norm": 0.7048876285552979,
2947
+ "learning_rate": 7.585430144121319e-06,
2948
+ "loss": 0.7239,
2949
+ "step": 21000
2950
+ },
2951
+ {
2952
+ "epoch": 3.3685389662345977,
2953
+ "grad_norm": 0.6659078001976013,
2954
+ "learning_rate": 7.401592024906812e-06,
2955
+ "loss": 0.7417,
2956
+ "step": 21050
2957
+ },
2958
+ {
2959
+ "epoch": 3.37654024643943,
2960
+ "grad_norm": 0.632502019405365,
2961
+ "learning_rate": 7.219830830393093e-06,
2962
+ "loss": 0.7115,
2963
+ "step": 21100
2964
+ },
2965
+ {
2966
+ "epoch": 3.384541526644263,
2967
+ "grad_norm": 0.6977764964103699,
2968
+ "learning_rate": 7.040155422514977e-06,
2969
+ "loss": 0.6854,
2970
+ "step": 21150
2971
+ },
2972
+ {
2973
+ "epoch": 3.3925428068490957,
2974
+ "grad_norm": 0.6409167051315308,
2975
+ "learning_rate": 6.862574561512825e-06,
2976
+ "loss": 0.7016,
2977
+ "step": 21200
2978
+ },
2979
+ {
2980
+ "epoch": 3.4005440870539285,
2981
+ "grad_norm": 0.6645964980125427,
2982
+ "learning_rate": 6.6870969055054246e-06,
2983
+ "loss": 0.7224,
2984
+ "step": 21250
2985
+ },
2986
+ {
2987
+ "epoch": 3.4085453672587613,
2988
+ "grad_norm": 0.6525962352752686,
2989
+ "learning_rate": 6.51373101006787e-06,
2990
+ "loss": 0.7248,
2991
+ "step": 21300
2992
+ },
2993
+ {
2994
+ "epoch": 3.416546647463594,
2995
+ "grad_norm": 0.7221346497535706,
2996
+ "learning_rate": 6.3424853278144015e-06,
2997
+ "loss": 0.7159,
2998
+ "step": 21350
2999
+ },
3000
+ {
3001
+ "epoch": 3.424547927668427,
3002
+ "grad_norm": 0.7742597460746765,
3003
+ "learning_rate": 6.173368207986358e-06,
3004
+ "loss": 0.7158,
3005
+ "step": 21400
3006
+ },
3007
+ {
3008
+ "epoch": 3.43254920787326,
3009
+ "grad_norm": 0.7201706171035767,
3010
+ "learning_rate": 6.00638789604499e-06,
3011
+ "loss": 0.7351,
3012
+ "step": 21450
3013
+ },
3014
+ {
3015
+ "epoch": 3.4405504880780926,
3016
+ "grad_norm": 0.6694920063018799,
3017
+ "learning_rate": 5.841552533269534e-06,
3018
+ "loss": 0.7313,
3019
+ "step": 21500
3020
+ },
3021
+ {
3022
+ "epoch": 3.4485517682829254,
3023
+ "grad_norm": 0.773014485836029,
3024
+ "learning_rate": 5.6788701563602665e-06,
3025
+ "loss": 0.7526,
3026
+ "step": 21550
3027
+ },
3028
+ {
3029
+ "epoch": 3.4565530484877582,
3030
+ "grad_norm": 0.602942168712616,
3031
+ "learning_rate": 5.518348697046644e-06,
3032
+ "loss": 0.7304,
3033
+ "step": 21600
3034
+ },
3035
+ {
3036
+ "epoch": 3.464554328692591,
3037
+ "grad_norm": 0.7288883924484253,
3038
+ "learning_rate": 5.359995981700544e-06,
3039
+ "loss": 0.7086,
3040
+ "step": 21650
3041
+ },
3042
+ {
3043
+ "epoch": 3.4725556088974234,
3044
+ "grad_norm": 0.8319910168647766,
3045
+ "learning_rate": 5.203819730954806e-06,
3046
+ "loss": 0.7356,
3047
+ "step": 21700
3048
+ },
3049
+ {
3050
+ "epoch": 3.4805568891022562,
3051
+ "grad_norm": 0.7911546230316162,
3052
+ "learning_rate": 5.049827559326686e-06,
3053
+ "loss": 0.7192,
3054
+ "step": 21750
3055
+ },
3056
+ {
3057
+ "epoch": 3.488558169307089,
3058
+ "grad_norm": 0.704937756061554,
3059
+ "learning_rate": 4.898026974846631e-06,
3060
+ "loss": 0.7209,
3061
+ "step": 21800
3062
+ },
3063
+ {
3064
+ "epoch": 3.496559449511922,
3065
+ "grad_norm": 0.7878553867340088,
3066
+ "learning_rate": 4.748425378692278e-06,
3067
+ "loss": 0.7449,
3068
+ "step": 21850
3069
+ },
3070
+ {
3071
+ "epoch": 3.5045607297167547,
3072
+ "grad_norm": 0.7807219624519348,
3073
+ "learning_rate": 4.601030064827527e-06,
3074
+ "loss": 0.722,
3075
+ "step": 21900
3076
+ },
3077
+ {
3078
+ "epoch": 3.5125620099215875,
3079
+ "grad_norm": 0.7362565994262695,
3080
+ "learning_rate": 4.455848219646957e-06,
3081
+ "loss": 0.7069,
3082
+ "step": 21950
3083
+ },
3084
+ {
3085
+ "epoch": 3.5205632901264203,
3086
+ "grad_norm": 0.6918688416481018,
3087
+ "learning_rate": 4.3128869216254366e-06,
3088
+ "loss": 0.7198,
3089
+ "step": 22000
3090
+ },
3091
+ {
3092
+ "epoch": 3.528564570331253,
3093
+ "grad_norm": 0.6748279929161072,
3094
+ "learning_rate": 4.172153140973012e-06,
3095
+ "loss": 0.7429,
3096
+ "step": 22050
3097
+ },
3098
+ {
3099
+ "epoch": 3.5365658505360855,
3100
+ "grad_norm": 0.7261555194854736,
3101
+ "learning_rate": 4.033653739295062e-06,
3102
+ "loss": 0.7453,
3103
+ "step": 22100
3104
+ },
3105
+ {
3106
+ "epoch": 3.5445671307409183,
3107
+ "grad_norm": 0.7590264081954956,
3108
+ "learning_rate": 3.897395469257759e-06,
3109
+ "loss": 0.7435,
3110
+ "step": 22150
3111
+ },
3112
+ {
3113
+ "epoch": 3.552568410945751,
3114
+ "grad_norm": 0.6835177540779114,
3115
+ "learning_rate": 3.7633849742588213e-06,
3116
+ "loss": 0.7305,
3117
+ "step": 22200
3118
+ },
3119
+ {
3120
+ "epoch": 3.560569691150584,
3121
+ "grad_norm": 0.7218915224075317,
3122
+ "learning_rate": 3.6316287881036306e-06,
3123
+ "loss": 0.7357,
3124
+ "step": 22250
3125
+ },
3126
+ {
3127
+ "epoch": 3.568570971355417,
3128
+ "grad_norm": 0.7100145220756531,
3129
+ "learning_rate": 3.502133334686669e-06,
3130
+ "loss": 0.7244,
3131
+ "step": 22300
3132
+ },
3133
+ {
3134
+ "epoch": 3.5765722515602496,
3135
+ "grad_norm": 0.6982618570327759,
3136
+ "learning_rate": 3.374904927678285e-06,
3137
+ "loss": 0.7172,
3138
+ "step": 22350
3139
+ },
3140
+ {
3141
+ "epoch": 3.5845735317650824,
3142
+ "grad_norm": 0.6808996200561523,
3143
+ "learning_rate": 3.2499497702169035e-06,
3144
+ "loss": 0.7112,
3145
+ "step": 22400
3146
+ },
3147
+ {
3148
+ "epoch": 3.5925748119699152,
3149
+ "grad_norm": 0.6580341458320618,
3150
+ "learning_rate": 3.1272739546065746e-06,
3151
+ "loss": 0.7375,
3152
+ "step": 22450
3153
+ },
3154
+ {
3155
+ "epoch": 3.600576092174748,
3156
+ "grad_norm": 0.7925476431846619,
3157
+ "learning_rate": 3.0068834620199103e-06,
3158
+ "loss": 0.7351,
3159
+ "step": 22500
3160
+ },
3161
+ {
3162
+ "epoch": 3.608577372379581,
3163
+ "grad_norm": 0.6711053848266602,
3164
+ "learning_rate": 2.888784162206504e-06,
3165
+ "loss": 0.7281,
3166
+ "step": 22550
3167
+ },
3168
+ {
3169
+ "epoch": 3.6165786525844137,
3170
+ "grad_norm": 0.6397190690040588,
3171
+ "learning_rate": 2.7729818132067264e-06,
3172
+ "loss": 0.7277,
3173
+ "step": 22600
3174
+ },
3175
+ {
3176
+ "epoch": 3.6245799327892465,
3177
+ "grad_norm": 0.6673882007598877,
3178
+ "learning_rate": 2.6594820610710057e-06,
3179
+ "loss": 0.7045,
3180
+ "step": 22650
3181
+ },
3182
+ {
3183
+ "epoch": 3.6325812129940793,
3184
+ "grad_norm": 0.6923602223396301,
3185
+ "learning_rate": 2.5482904395845107e-06,
3186
+ "loss": 0.7435,
3187
+ "step": 22700
3188
+ },
3189
+ {
3190
+ "epoch": 3.6405824931989117,
3191
+ "grad_norm": 0.7044751048088074,
3192
+ "learning_rate": 2.439412369997374e-06,
3193
+ "loss": 0.7135,
3194
+ "step": 22750
3195
+ },
3196
+ {
3197
+ "epoch": 3.6485837734037445,
3198
+ "grad_norm": 0.7120568156242371,
3199
+ "learning_rate": 2.33285316076039e-06,
3200
+ "loss": 0.7115,
3201
+ "step": 22800
3202
+ },
3203
+ {
3204
+ "epoch": 3.6565850536085773,
3205
+ "grad_norm": 0.6994568705558777,
3206
+ "learning_rate": 2.22861800726617e-06,
3207
+ "loss": 0.7212,
3208
+ "step": 22850
3209
+ },
3210
+ {
3211
+ "epoch": 3.66458633381341,
3212
+ "grad_norm": 0.7410824298858643,
3213
+ "learning_rate": 2.1267119915958088e-06,
3214
+ "loss": 0.6973,
3215
+ "step": 22900
3216
+ },
3217
+ {
3218
+ "epoch": 3.672587614018243,
3219
+ "grad_norm": 0.7019298076629639,
3220
+ "learning_rate": 2.0271400822711894e-06,
3221
+ "loss": 0.724,
3222
+ "step": 22950
3223
+ },
3224
+ {
3225
+ "epoch": 3.680588894223076,
3226
+ "grad_norm": 0.7187603116035461,
3227
+ "learning_rate": 1.929907134012654e-06,
3228
+ "loss": 0.699,
3229
+ "step": 23000
3230
+ },
3231
+ {
3232
+ "epoch": 3.6885901744279086,
3233
+ "grad_norm": 0.7453562617301941,
3234
+ "learning_rate": 1.8350178875023272e-06,
3235
+ "loss": 0.7243,
3236
+ "step": 23050
3237
+ },
3238
+ {
3239
+ "epoch": 3.696591454632741,
3240
+ "grad_norm": 0.8272750973701477,
3241
+ "learning_rate": 1.7424769691530284e-06,
3242
+ "loss": 0.7178,
3243
+ "step": 23100
3244
+ },
3245
+ {
3246
+ "epoch": 3.704592734837574,
3247
+ "grad_norm": 0.6875506043434143,
3248
+ "learning_rate": 1.6522888908826473e-06,
3249
+ "loss": 0.7328,
3250
+ "step": 23150
3251
+ },
3252
+ {
3253
+ "epoch": 3.7125940150424066,
3254
+ "grad_norm": 0.6446670889854431,
3255
+ "learning_rate": 1.5644580498941851e-06,
3256
+ "loss": 0.7121,
3257
+ "step": 23200
3258
+ },
3259
+ {
3260
+ "epoch": 3.7205952952472394,
3261
+ "grad_norm": 0.6092432141304016,
3262
+ "learning_rate": 1.478988728461367e-06,
3263
+ "loss": 0.7045,
3264
+ "step": 23250
3265
+ },
3266
+ {
3267
+ "epoch": 3.7285965754520722,
3268
+ "grad_norm": 0.6800952553749084,
3269
+ "learning_rate": 1.3958850937198453e-06,
3270
+ "loss": 0.7275,
3271
+ "step": 23300
3272
+ },
3273
+ {
3274
+ "epoch": 3.736597855656905,
3275
+ "grad_norm": 0.684956431388855,
3276
+ "learning_rate": 1.315151197464043e-06,
3277
+ "loss": 0.7272,
3278
+ "step": 23350
3279
+ },
3280
+ {
3281
+ "epoch": 3.744599135861738,
3282
+ "grad_norm": 0.7142546772956848,
3283
+ "learning_rate": 1.236790975949592e-06,
3284
+ "loss": 0.7213,
3285
+ "step": 23400
3286
+ },
3287
+ {
3288
+ "epoch": 3.7526004160665707,
3289
+ "grad_norm": 0.7309266328811646,
3290
+ "learning_rate": 1.1608082497014228e-06,
3291
+ "loss": 0.7212,
3292
+ "step": 23450
3293
+ },
3294
+ {
3295
+ "epoch": 3.7606016962714035,
3296
+ "grad_norm": 0.7835919260978699,
3297
+ "learning_rate": 1.087206723327483e-06,
3298
+ "loss": 0.7411,
3299
+ "step": 23500
3300
+ },
3301
+ {
3302
+ "epoch": 3.7686029764762363,
3303
+ "grad_norm": 0.6577751040458679,
3304
+ "learning_rate": 1.0159899853381394e-06,
3305
+ "loss": 0.7104,
3306
+ "step": 23550
3307
+ },
3308
+ {
3309
+ "epoch": 3.776604256681069,
3310
+ "grad_norm": 0.7286819219589233,
3311
+ "learning_rate": 9.471615079711838e-07,
3312
+ "loss": 0.7284,
3313
+ "step": 23600
3314
+ },
3315
+ {
3316
+ "epoch": 3.784605536885902,
3317
+ "grad_norm": 0.7102928757667542,
3318
+ "learning_rate": 8.807246470225517e-07,
3319
+ "loss": 0.7415,
3320
+ "step": 23650
3321
+ },
3322
+ {
3323
+ "epoch": 3.7926068170907348,
3324
+ "grad_norm": 0.6017107963562012,
3325
+ "learning_rate": 8.166826416827422e-07,
3326
+ "loss": 0.7063,
3327
+ "step": 23700
3328
+ },
3329
+ {
3330
+ "epoch": 3.800608097295567,
3331
+ "grad_norm": 0.7728732824325562,
3332
+ "learning_rate": 7.550386143788224e-07,
3333
+ "loss": 0.6959,
3334
+ "step": 23750
3335
+ },
3336
+ {
3337
+ "epoch": 3.8086093775004,
3338
+ "grad_norm": 0.7075885534286499,
3339
+ "learning_rate": 6.95795570622243e-07,
3340
+ "loss": 0.6977,
3341
+ "step": 23800
3342
+ },
3343
+ {
3344
+ "epoch": 3.816610657705233,
3345
+ "grad_norm": 0.7628594636917114,
3346
+ "learning_rate": 6.389563988622948e-07,
3347
+ "loss": 0.7189,
3348
+ "step": 23850
3349
+ },
3350
+ {
3351
+ "epoch": 3.8246119379100656,
3352
+ "grad_norm": 0.6857520341873169,
3353
+ "learning_rate": 5.845238703452604e-07,
3354
+ "loss": 0.7281,
3355
+ "step": 23900
3356
+ },
3357
+ {
3358
+ "epoch": 3.8326132181148984,
3359
+ "grad_norm": 0.676717221736908,
3360
+ "learning_rate": 5.325006389793053e-07,
3361
+ "loss": 0.7275,
3362
+ "step": 23950
3363
+ },
3364
+ {
3365
+ "epoch": 3.8406144983197312,
3366
+ "grad_norm": 0.6261276602745056,
3367
+ "learning_rate": 4.828892412050978e-07,
3368
+ "loss": 0.7162,
3369
+ "step": 24000
3370
+ },
3371
+ {
3372
+ "epoch": 3.848615778524564,
3373
+ "grad_norm": 0.761638343334198,
3374
+ "learning_rate": 4.356920958721311e-07,
3375
+ "loss": 0.7405,
3376
+ "step": 24050
3377
+ },
3378
+ {
3379
+ "epoch": 3.856617058729397,
3380
+ "grad_norm": 0.697512686252594,
3381
+ "learning_rate": 3.909115041207889e-07,
3382
+ "loss": 0.7156,
3383
+ "step": 24100
3384
+ },
3385
+ {
3386
+ "epoch": 3.8646183389342292,
3387
+ "grad_norm": 0.6379271149635315,
3388
+ "learning_rate": 3.4854964927015235e-07,
3389
+ "loss": 0.7443,
3390
+ "step": 24150
3391
+ },
3392
+ {
3393
+ "epoch": 3.872619619139062,
3394
+ "grad_norm": 0.7762777209281921,
3395
+ "learning_rate": 3.086085967115626e-07,
3396
+ "loss": 0.7186,
3397
+ "step": 24200
3398
+ },
3399
+ {
3400
+ "epoch": 3.880620899343895,
3401
+ "grad_norm": 0.6799700260162354,
3402
+ "learning_rate": 2.7109029380790186e-07,
3403
+ "loss": 0.6928,
3404
+ "step": 24250
3405
+ },
3406
+ {
3407
+ "epoch": 3.8886221795487277,
3408
+ "grad_norm": 0.8152979016304016,
3409
+ "learning_rate": 2.3599656979866325e-07,
3410
+ "loss": 0.7145,
3411
+ "step": 24300
3412
+ },
3413
+ {
3414
+ "epoch": 3.8966234597535605,
3415
+ "grad_norm": 0.6055078506469727,
3416
+ "learning_rate": 2.0332913571074476e-07,
3417
+ "loss": 0.7105,
3418
+ "step": 24350
3419
+ },
3420
+ {
3421
+ "epoch": 3.9046247399583933,
3422
+ "grad_norm": 0.7122170329093933,
3423
+ "learning_rate": 1.7308958427505462e-07,
3424
+ "loss": 0.7322,
3425
+ "step": 24400
3426
+ },
3427
+ {
3428
+ "epoch": 3.912626020163226,
3429
+ "grad_norm": 0.7174406051635742,
3430
+ "learning_rate": 1.4527938984883471e-07,
3431
+ "loss": 0.7294,
3432
+ "step": 24450
3433
+ },
3434
+ {
3435
+ "epoch": 3.920627300368059,
3436
+ "grad_norm": 0.7419302463531494,
3437
+ "learning_rate": 1.1989990834378462e-07,
3438
+ "loss": 0.7272,
3439
+ "step": 24500
3440
+ },
3441
+ {
3442
+ "epoch": 3.9286285805728918,
3443
+ "grad_norm": 0.7208146452903748,
3444
+ "learning_rate": 9.695237715994788e-08,
3445
+ "loss": 0.7066,
3446
+ "step": 24550
3447
+ },
3448
+ {
3449
+ "epoch": 3.9366298607777246,
3450
+ "grad_norm": 0.8183807730674744,
3451
+ "learning_rate": 7.6437915125388e-08,
3452
+ "loss": 0.721,
3453
+ "step": 24600
3454
+ },
3455
+ {
3456
+ "epoch": 3.9446311409825574,
3457
+ "grad_norm": 0.7065560817718506,
3458
+ "learning_rate": 5.835752244164883e-08,
3459
+ "loss": 0.737,
3460
+ "step": 24650
3461
+ },
3462
+ {
3463
+ "epoch": 3.95263242118739,
3464
+ "grad_norm": 0.7247999310493469,
3465
+ "learning_rate": 4.2712080634949024e-08,
3466
+ "loss": 0.7346,
3467
+ "step": 24700
3468
+ },
3469
+ {
3470
+ "epoch": 3.9606337013922226,
3471
+ "grad_norm": 0.6564909219741821,
3472
+ "learning_rate": 2.9502352513255394e-08,
3473
+ "loss": 0.7305,
3474
+ "step": 24750
3475
+ },
3476
+ {
3477
+ "epoch": 3.9686349815970554,
3478
+ "grad_norm": 0.7844890356063843,
3479
+ "learning_rate": 1.8728982129051497e-08,
3480
+ "loss": 0.7076,
3481
+ "step": 24800
3482
+ },
3483
+ {
3484
+ "epoch": 3.9766362618018882,
3485
+ "grad_norm": 0.7181993722915649,
3486
+ "learning_rate": 1.0392494747957227e-08,
3487
+ "loss": 0.7439,
3488
+ "step": 24850
3489
+ },
3490
+ {
3491
+ "epoch": 3.984637542006721,
3492
+ "grad_norm": 0.6785070300102234,
3493
+ "learning_rate": 4.493296823104842e-09,
3494
+ "loss": 0.7222,
3495
+ "step": 24900
3496
+ },
3497
+ {
3498
+ "epoch": 3.992638822211554,
3499
+ "grad_norm": 0.6972596645355225,
3500
+ "learning_rate": 1.0316759753381534e-09,
3501
+ "loss": 0.7258,
3502
+ "step": 24950
3503
+ }
3504
+ ],
3505
+ "logging_steps": 50,
3506
+ "max_steps": 24996,
3507
+ "num_input_tokens_seen": 0,
3508
+ "num_train_epochs": 4,
3509
+ "save_steps": 2000,
3510
+ "stateful_callbacks": {
3511
+ "TrainerControl": {
3512
+ "args": {
3513
+ "should_epoch_stop": false,
3514
+ "should_evaluate": false,
3515
+ "should_log": false,
3516
+ "should_save": true,
3517
+ "should_training_stop": true
3518
+ },
3519
+ "attributes": {}
3520
+ }
3521
+ },
3522
+ "total_flos": 5.928976828545164e+19,
3523
+ "train_batch_size": 16,
3524
+ "trial_name": null,
3525
+ "trial_params": null
3526
+ }
Espresso-AI__search-llm/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97228d9c0253d23a8fc872b5cd50ed90afd31bd48b8be294073ec38b20a11664
3
+ size 5624