codezakh commited on
Commit
48830f7
·
verified ·
1 Parent(s): 2651c61

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,44 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: other
4
+ base_model: meta-llama/Llama-3.1-8B-Instruct
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: llama_factory_output_dir
11
+ results: []
12
+ ---
13
+
14
+
15
+ # llama_factory_output_dir
16
+
17
+ This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).
18
+
19
+
20
+ ### Training hyperparameters
21
+
22
+ The following hyperparameters were used during training:
23
+ - learning_rate: 0.0001
24
+ - train_batch_size: 1
25
+ - eval_batch_size: 1
26
+ - seed: 42
27
+ - distributed_type: multi-GPU
28
+ - num_devices: 4
29
+ - gradient_accumulation_steps: 2
30
+ - total_train_batch_size: 8
31
+ - total_eval_batch_size: 4
32
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
33
+ - lr_scheduler_type: cosine
34
+ - lr_scheduler_warmup_ratio: 0.1
35
+ - num_epochs: 3.0
36
+ - mixed_precision_training: Native AMP
37
+
38
+ ### Framework versions
39
+
40
+ - PEFT 0.12.0
41
+ - Transformers 4.44.2
42
+ - Pytorch 2.4.0+cu121
43
+ - Datasets 2.21.0
44
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "q_proj",
25
+ "gate_proj",
26
+ "o_proj",
27
+ "down_proj",
28
+ "up_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26fac6570bf39d2f17cd908188e0d5b28494d2b062a91c0ecc86f70ff172325d
3
+ size 83945296
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9968586387434555,
3
+ "eval_loss": 0.05348898842930794,
4
+ "eval_runtime": 97.4279,
5
+ "eval_samples_per_second": 4.362,
6
+ "eval_steps_per_second": 1.098,
7
+ "total_flos": 1.717501382279299e+18,
8
+ "train_loss": 0.0491406895828145,
9
+ "train_runtime": 12322.0896,
10
+ "train_samples_per_second": 0.93,
11
+ "train_steps_per_second": 0.116
12
+ }
checkpoint-1431/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: meta-llama/Llama-3.1-8B-Instruct
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.12.0
checkpoint-1431/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.0,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "q_proj",
25
+ "gate_proj",
26
+ "o_proj",
27
+ "down_proj",
28
+ "up_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-1431/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26fac6570bf39d2f17cd908188e0d5b28494d2b062a91c0ecc86f70ff172325d
3
+ size 83945296
checkpoint-1431/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b32500790663220983dcb4946dcbf3600c21e2a135b174040e99eb696d04fc1
3
+ size 168149074
checkpoint-1431/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c5e18f922d0af74d820247ae97bee506ab412554a58345ddf2558abc94ee3e3
3
+ size 15024
checkpoint-1431/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a2dcca6d9741f46592359768ea2212b9321da6408d1fd7d3a80b017bf37f434
3
+ size 15024
checkpoint-1431/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69420ece2c255923c5cbb3c6c9c4a6b9cb38fb57e5d3033c8b7d436a1faf6f13
3
+ size 15024
checkpoint-1431/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66f278b40a1e23b88a657c4e5d03afa8dbbbe14dfeb16f6b4beedaece6cdd0b9
3
+ size 15024
checkpoint-1431/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e502f6338cd64e05df5e84899ffc191951cfb3b39f402cbef1ae32dab2691a5d
3
+ size 1064
checkpoint-1431/special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
checkpoint-1431/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1431/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": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
checkpoint-1431/trainer_state.json ADDED
@@ -0,0 +1,1050 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9968586387434555,
5
+ "eval_steps": 500,
6
+ "global_step": 1431,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.020942408376963352,
13
+ "grad_norm": 0.5137882828712463,
14
+ "learning_rate": 6.944444444444445e-06,
15
+ "loss": 0.341,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.041884816753926704,
20
+ "grad_norm": 0.5445541739463806,
21
+ "learning_rate": 1.388888888888889e-05,
22
+ "loss": 0.3137,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06282722513089005,
27
+ "grad_norm": 0.34443390369415283,
28
+ "learning_rate": 2.0833333333333336e-05,
29
+ "loss": 0.2399,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08376963350785341,
34
+ "grad_norm": 0.36772170662879944,
35
+ "learning_rate": 2.777777777777778e-05,
36
+ "loss": 0.1832,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10471204188481675,
41
+ "grad_norm": 0.3646106719970703,
42
+ "learning_rate": 3.472222222222222e-05,
43
+ "loss": 0.151,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.1256544502617801,
48
+ "grad_norm": 0.538939356803894,
49
+ "learning_rate": 4.166666666666667e-05,
50
+ "loss": 0.129,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.14659685863874344,
55
+ "grad_norm": 0.36220353841781616,
56
+ "learning_rate": 4.8611111111111115e-05,
57
+ "loss": 0.1248,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.16753926701570682,
62
+ "grad_norm": 0.4773642420768738,
63
+ "learning_rate": 5.555555555555556e-05,
64
+ "loss": 0.1142,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.18848167539267016,
69
+ "grad_norm": 0.45749950408935547,
70
+ "learning_rate": 6.25e-05,
71
+ "loss": 0.1103,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2094240837696335,
76
+ "grad_norm": 0.4229575991630554,
77
+ "learning_rate": 6.944444444444444e-05,
78
+ "loss": 0.0985,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.23036649214659685,
83
+ "grad_norm": 0.4683126211166382,
84
+ "learning_rate": 7.638888888888889e-05,
85
+ "loss": 0.0929,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2513089005235602,
90
+ "grad_norm": 0.3871113359928131,
91
+ "learning_rate": 8.333333333333334e-05,
92
+ "loss": 0.0955,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.27225130890052357,
97
+ "grad_norm": 0.45953118801116943,
98
+ "learning_rate": 9.027777777777779e-05,
99
+ "loss": 0.0941,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2931937172774869,
104
+ "grad_norm": 0.4296354651451111,
105
+ "learning_rate": 9.722222222222223e-05,
106
+ "loss": 0.0906,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.31413612565445026,
111
+ "grad_norm": 0.4266631007194519,
112
+ "learning_rate": 9.999463737538053e-05,
113
+ "loss": 0.0815,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.33507853403141363,
118
+ "grad_norm": 0.4313138425350189,
119
+ "learning_rate": 9.996186994612176e-05,
120
+ "loss": 0.0803,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.35602094240837695,
125
+ "grad_norm": 0.36333203315734863,
126
+ "learning_rate": 9.989933382359422e-05,
127
+ "loss": 0.0797,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3769633507853403,
132
+ "grad_norm": 0.7311431765556335,
133
+ "learning_rate": 9.980706626858607e-05,
134
+ "loss": 0.0768,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.39790575916230364,
139
+ "grad_norm": 0.4651825428009033,
140
+ "learning_rate": 9.96851222567126e-05,
141
+ "loss": 0.0818,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.418848167539267,
146
+ "grad_norm": 0.5768024325370789,
147
+ "learning_rate": 9.953357444566039e-05,
148
+ "loss": 0.0717,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4397905759162304,
153
+ "grad_norm": 0.41442790627479553,
154
+ "learning_rate": 9.935251313189564e-05,
155
+ "loss": 0.0698,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4607329842931937,
160
+ "grad_norm": 0.5525192618370056,
161
+ "learning_rate": 9.914204619686314e-05,
162
+ "loss": 0.0745,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.4816753926701571,
167
+ "grad_norm": 0.4769018590450287,
168
+ "learning_rate": 9.890229904270731e-05,
169
+ "loss": 0.0719,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5026178010471204,
174
+ "grad_norm": 0.4063033163547516,
175
+ "learning_rate": 9.86334145175542e-05,
176
+ "loss": 0.0751,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5235602094240838,
181
+ "grad_norm": 0.3966362476348877,
182
+ "learning_rate": 9.833555283039842e-05,
183
+ "loss": 0.0696,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5445026178010471,
188
+ "grad_norm": 0.4347456395626068,
189
+ "learning_rate": 9.800889145564617e-05,
190
+ "loss": 0.0594,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5654450261780105,
195
+ "grad_norm": 0.3599953055381775,
196
+ "learning_rate": 9.765362502737097e-05,
197
+ "loss": 0.0732,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.5863874345549738,
202
+ "grad_norm": 0.3424774706363678,
203
+ "learning_rate": 9.730960252267743e-05,
204
+ "loss": 0.0649,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6073298429319371,
209
+ "grad_norm": 0.48636892437934875,
210
+ "learning_rate": 9.690058365011607e-05,
211
+ "loss": 0.0679,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6282722513089005,
216
+ "grad_norm": 0.5237702131271362,
217
+ "learning_rate": 9.646362008512602e-05,
218
+ "loss": 0.0787,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6492146596858639,
223
+ "grad_norm": 0.3805506229400635,
224
+ "learning_rate": 9.599897218294122e-05,
225
+ "loss": 0.072,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.6701570680628273,
230
+ "grad_norm": 0.4530421197414398,
231
+ "learning_rate": 9.550691679390558e-05,
232
+ "loss": 0.065,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.6910994764397905,
237
+ "grad_norm": 0.4006820321083069,
238
+ "learning_rate": 9.498774709851779e-05,
239
+ "loss": 0.0644,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7120418848167539,
244
+ "grad_norm": 0.3857646584510803,
245
+ "learning_rate": 9.444177243274618e-05,
246
+ "loss": 0.0624,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7329842931937173,
251
+ "grad_norm": 0.4317072331905365,
252
+ "learning_rate": 9.386931810371742e-05,
253
+ "loss": 0.066,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7539267015706806,
258
+ "grad_norm": 0.3598201274871826,
259
+ "learning_rate": 9.327072519588954e-05,
260
+ "loss": 0.0642,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.774869109947644,
265
+ "grad_norm": 0.39206311106681824,
266
+ "learning_rate": 9.264635036782405e-05,
267
+ "loss": 0.064,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.7958115183246073,
272
+ "grad_norm": 0.40854617953300476,
273
+ "learning_rate": 9.199656563967875e-05,
274
+ "loss": 0.0635,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8167539267015707,
279
+ "grad_norm": 0.4052296578884125,
280
+ "learning_rate": 9.132175817154763e-05,
281
+ "loss": 0.0617,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.837696335078534,
286
+ "grad_norm": 0.5453737378120422,
287
+ "learning_rate": 9.062233003277983e-05,
288
+ "loss": 0.0612,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.8586387434554974,
293
+ "grad_norm": 0.4285629391670227,
294
+ "learning_rate": 8.989869796241559e-05,
295
+ "loss": 0.0609,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.8795811518324608,
300
+ "grad_norm": 0.42577216029167175,
301
+ "learning_rate": 8.915129312088112e-05,
302
+ "loss": 0.0634,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.900523560209424,
307
+ "grad_norm": 0.44957348704338074,
308
+ "learning_rate": 8.838056083309118e-05,
309
+ "loss": 0.0569,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9214659685863874,
314
+ "grad_norm": 0.3643034100532532,
315
+ "learning_rate": 8.758696032311192e-05,
316
+ "loss": 0.0583,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.9424083769633508,
321
+ "grad_norm": 0.5593224167823792,
322
+ "learning_rate": 8.677096444054213e-05,
323
+ "loss": 0.0637,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9633507853403142,
328
+ "grad_norm": 0.4963381886482239,
329
+ "learning_rate": 8.593305937877614e-05,
330
+ "loss": 0.0607,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.9842931937172775,
335
+ "grad_norm": 0.5490202307701111,
336
+ "learning_rate": 8.507374438531607e-05,
337
+ "loss": 0.0617,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 1.0052356020942408,
342
+ "grad_norm": 0.33712923526763916,
343
+ "learning_rate": 8.419353146430609e-05,
344
+ "loss": 0.0563,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 1.0261780104712042,
349
+ "grad_norm": 0.4473194181919098,
350
+ "learning_rate": 8.329294507146579e-05,
351
+ "loss": 0.0415,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 1.0471204188481675,
356
+ "grad_norm": 0.43435972929000854,
357
+ "learning_rate": 8.23725218016048e-05,
358
+ "loss": 0.0402,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 1.0471204188481675,
363
+ "eval_loss": 0.058112796396017075,
364
+ "eval_runtime": 97.7069,
365
+ "eval_samples_per_second": 4.35,
366
+ "eval_steps_per_second": 1.095,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.068062827225131,
371
+ "grad_norm": 0.41959723830223083,
372
+ "learning_rate": 8.143281006890433e-05,
373
+ "loss": 0.0388,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.0890052356020943,
378
+ "grad_norm": 0.46331778168678284,
379
+ "learning_rate": 8.047436978015649e-05,
380
+ "loss": 0.0467,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1099476439790577,
385
+ "grad_norm": 0.4408092200756073,
386
+ "learning_rate": 7.949777200115616e-05,
387
+ "loss": 0.0414,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.130890052356021,
392
+ "grad_norm": 0.5561596751213074,
393
+ "learning_rate": 7.850359861644368e-05,
394
+ "loss": 0.0413,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.1518324607329844,
399
+ "grad_norm": 0.6036704778671265,
400
+ "learning_rate": 7.749244198260175e-05,
401
+ "loss": 0.0448,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.1727748691099475,
406
+ "grad_norm": 0.333761602640152,
407
+ "learning_rate": 7.646490457531257e-05,
408
+ "loss": 0.0379,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.193717277486911,
413
+ "grad_norm": 0.4401955306529999,
414
+ "learning_rate": 7.54215986303858e-05,
415
+ "loss": 0.0375,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2146596858638743,
420
+ "grad_norm": 0.3552649915218353,
421
+ "learning_rate": 7.436314577897126e-05,
422
+ "loss": 0.0373,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.2356020942408377,
427
+ "grad_norm": 0.2970343828201294,
428
+ "learning_rate": 7.329017667717339e-05,
429
+ "loss": 0.042,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.256544502617801,
434
+ "grad_norm": 0.45380938053131104,
435
+ "learning_rate": 7.220333063028872e-05,
436
+ "loss": 0.0379,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.2774869109947644,
441
+ "grad_norm": 0.4114688038825989,
442
+ "learning_rate": 7.110325521188949e-05,
443
+ "loss": 0.0444,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.2984293193717278,
448
+ "grad_norm": 0.37951603531837463,
449
+ "learning_rate": 6.999060587798128e-05,
450
+ "loss": 0.0422,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.3193717277486912,
455
+ "grad_norm": 0.5121111869812012,
456
+ "learning_rate": 6.886604557646356e-05,
457
+ "loss": 0.0384,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.3403141361256545,
462
+ "grad_norm": 0.3808182179927826,
463
+ "learning_rate": 6.773024435212678e-05,
464
+ "loss": 0.0352,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.3612565445026177,
469
+ "grad_norm": 0.3297405540943146,
470
+ "learning_rate": 6.658387894742071e-05,
471
+ "loss": 0.0397,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.3821989528795813,
476
+ "grad_norm": 0.41979941725730896,
477
+ "learning_rate": 6.542763239923215e-05,
478
+ "loss": 0.0375,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.4031413612565444,
483
+ "grad_norm": 0.5469591021537781,
484
+ "learning_rate": 6.426219363191224e-05,
485
+ "loss": 0.0443,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.4240837696335078,
490
+ "grad_norm": 0.3828868865966797,
491
+ "learning_rate": 6.308825704679596e-05,
492
+ "loss": 0.0334,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.4450261780104712,
497
+ "grad_norm": 0.49810731410980225,
498
+ "learning_rate": 6.190652210845815e-05,
499
+ "loss": 0.0401,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.4659685863874345,
504
+ "grad_norm": 0.4368995130062103,
505
+ "learning_rate": 6.0717692927952744e-05,
506
+ "loss": 0.0367,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.486910994764398,
511
+ "grad_norm": 0.4042227566242218,
512
+ "learning_rate": 5.952247784328351e-05,
513
+ "loss": 0.0375,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.5078534031413613,
518
+ "grad_norm": 0.49127721786499023,
519
+ "learning_rate": 5.8321588997356326e-05,
520
+ "loss": 0.0339,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.5287958115183247,
525
+ "grad_norm": 0.3174681067466736,
526
+ "learning_rate": 5.7115741913664264e-05,
527
+ "loss": 0.0381,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.5497382198952878,
532
+ "grad_norm": 0.4839365780353546,
533
+ "learning_rate": 5.59056550699585e-05,
534
+ "loss": 0.0355,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.5706806282722514,
539
+ "grad_norm": 0.30561134219169617,
540
+ "learning_rate": 5.469204947015897e-05,
541
+ "loss": 0.0374,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.5916230366492146,
546
+ "grad_norm": 0.3758664131164551,
547
+ "learning_rate": 5.3475648214759896e-05,
548
+ "loss": 0.0327,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.6125654450261782,
553
+ "grad_norm": 0.3118516206741333,
554
+ "learning_rate": 5.2257176069986036e-05,
555
+ "loss": 0.0403,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.6335078534031413,
560
+ "grad_norm": 0.33437207341194153,
561
+ "learning_rate": 5.103735903595658e-05,
562
+ "loss": 0.0364,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.6544502617801047,
567
+ "grad_norm": 0.54002845287323,
568
+ "learning_rate": 4.981692391411366e-05,
569
+ "loss": 0.0371,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.675392670157068,
574
+ "grad_norm": 0.2974444031715393,
575
+ "learning_rate": 4.859659787417362e-05,
576
+ "loss": 0.0406,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.6963350785340314,
581
+ "grad_norm": 0.3456689417362213,
582
+ "learning_rate": 4.737710802085875e-05,
583
+ "loss": 0.0353,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.7172774869109948,
588
+ "grad_norm": 0.4571535885334015,
589
+ "learning_rate": 4.615918096066766e-05,
590
+ "loss": 0.0325,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.738219895287958,
595
+ "grad_norm": 0.3281984031200409,
596
+ "learning_rate": 4.4943542368942746e-05,
597
+ "loss": 0.0318,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.7591623036649215,
602
+ "grad_norm": 0.2916335165500641,
603
+ "learning_rate": 4.373091655749225e-05,
604
+ "loss": 0.0374,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.7801047120418847,
609
+ "grad_norm": 0.4069044888019562,
610
+ "learning_rate": 4.252202604302476e-05,
611
+ "loss": 0.0362,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.8010471204188483,
616
+ "grad_norm": 0.39771515130996704,
617
+ "learning_rate": 4.131759111665349e-05,
618
+ "loss": 0.038,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.8219895287958114,
623
+ "grad_norm": 0.38277313113212585,
624
+ "learning_rate": 4.011832941472641e-05,
625
+ "loss": 0.0393,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.8429319371727748,
630
+ "grad_norm": 0.2795620560646057,
631
+ "learning_rate": 3.8924955491238216e-05,
632
+ "loss": 0.0336,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.8638743455497382,
637
+ "grad_norm": 0.3264184594154358,
638
+ "learning_rate": 3.7738180392078937e-05,
639
+ "loss": 0.033,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.8848167539267016,
644
+ "grad_norm": 0.5280706286430359,
645
+ "learning_rate": 3.6558711231372704e-05,
646
+ "loss": 0.035,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.905759162303665,
651
+ "grad_norm": 0.3607095181941986,
652
+ "learning_rate": 3.538725077015915e-05,
653
+ "loss": 0.0357,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.9267015706806283,
658
+ "grad_norm": 0.3703671991825104,
659
+ "learning_rate": 3.422449699766851e-05,
660
+ "loss": 0.0313,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.9476439790575917,
665
+ "grad_norm": 0.4830826222896576,
666
+ "learning_rate": 3.307114271543999e-05,
667
+ "loss": 0.0345,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.9685863874345548,
672
+ "grad_norm": 0.42555513978004456,
673
+ "learning_rate": 3.192787512453105e-05,
674
+ "loss": 0.0333,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.9895287958115184,
679
+ "grad_norm": 0.3647818863391876,
680
+ "learning_rate": 3.079537541606349e-05,
681
+ "loss": 0.0317,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 2.0104712041884816,
686
+ "grad_norm": 0.27432000637054443,
687
+ "learning_rate": 2.9674318365350685e-05,
688
+ "loss": 0.0235,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 2.031413612565445,
693
+ "grad_norm": 0.2879980802536011,
694
+ "learning_rate": 2.8565371929847284e-05,
695
+ "loss": 0.0158,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 2.0523560209424083,
700
+ "grad_norm": 0.30074015259742737,
701
+ "learning_rate": 2.7469196851161373e-05,
702
+ "loss": 0.0179,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 2.073298429319372,
707
+ "grad_norm": 0.48433229327201843,
708
+ "learning_rate": 2.638644626136587e-05,
709
+ "loss": 0.0174,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 2.094240837696335,
714
+ "grad_norm": 0.3053944706916809,
715
+ "learning_rate": 2.531776529384407e-05,
716
+ "loss": 0.0204,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 2.094240837696335,
721
+ "eval_loss": 0.05247209593653679,
722
+ "eval_runtime": 97.7528,
723
+ "eval_samples_per_second": 4.348,
724
+ "eval_steps_per_second": 1.095,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.115183246073298,
729
+ "grad_norm": 0.3178795576095581,
730
+ "learning_rate": 2.426379069890098e-05,
731
+ "loss": 0.0178,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.136125654450262,
736
+ "grad_norm": 0.30507609248161316,
737
+ "learning_rate": 2.3225150464369312e-05,
738
+ "loss": 0.0145,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.157068062827225,
743
+ "grad_norm": 0.3095521330833435,
744
+ "learning_rate": 2.2202463441436884e-05,
745
+ "loss": 0.0186,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.1780104712041886,
750
+ "grad_norm": 0.40178781747817993,
751
+ "learning_rate": 2.1196338975917358e-05,
752
+ "loss": 0.0185,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.1989528795811517,
757
+ "grad_norm": 0.3371562063694,
758
+ "learning_rate": 2.0207376545184893e-05,
759
+ "loss": 0.0148,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.2198952879581153,
764
+ "grad_norm": 0.5400903820991516,
765
+ "learning_rate": 1.9236165400988638e-05,
766
+ "loss": 0.0188,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.2408376963350785,
771
+ "grad_norm": 0.1960514336824417,
772
+ "learning_rate": 1.8283284218359782e-05,
773
+ "loss": 0.0167,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.261780104712042,
778
+ "grad_norm": 0.29054176807403564,
779
+ "learning_rate": 1.734930075082076e-05,
780
+ "loss": 0.0156,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.282722513089005,
785
+ "grad_norm": 0.31542539596557617,
786
+ "learning_rate": 1.6434771492101485e-05,
787
+ "loss": 0.0168,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.303664921465969,
792
+ "grad_norm": 0.30312708020210266,
793
+ "learning_rate": 1.5540241344564915e-05,
794
+ "loss": 0.0178,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.324607329842932,
799
+ "grad_norm": 0.22572675347328186,
800
+ "learning_rate": 1.46662432945386e-05,
801
+ "loss": 0.0159,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.345549738219895,
806
+ "grad_norm": 0.32737213373184204,
807
+ "learning_rate": 1.3813298094746491e-05,
808
+ "loss": 0.0155,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.3664921465968587,
813
+ "grad_norm": 0.29300010204315186,
814
+ "learning_rate": 1.2981913954029784e-05,
815
+ "loss": 0.0158,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.387434554973822,
820
+ "grad_norm": 0.3531718850135803,
821
+ "learning_rate": 1.2172586234541644e-05,
822
+ "loss": 0.0162,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.4083769633507854,
827
+ "grad_norm": 0.3117247521877289,
828
+ "learning_rate": 1.1385797156596506e-05,
829
+ "loss": 0.0157,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.4293193717277486,
834
+ "grad_norm": 0.3147590756416321,
835
+ "learning_rate": 1.062201551134957e-05,
836
+ "loss": 0.0146,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.450261780104712,
841
+ "grad_norm": 0.3247630298137665,
842
+ "learning_rate": 9.88169638147784e-06,
843
+ "loss": 0.0143,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.4712041884816753,
848
+ "grad_norm": 0.3280116319656372,
849
+ "learning_rate": 9.16528087002892e-06,
850
+ "loss": 0.017,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.492146596858639,
855
+ "grad_norm": 0.30790087580680847,
856
+ "learning_rate": 8.473195837599418e-06,
857
+ "loss": 0.0155,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.513089005235602,
862
+ "grad_norm": 0.4461917579174042,
863
+ "learning_rate": 7.805853647999362e-06,
864
+ "loss": 0.0176,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.5340314136125652,
869
+ "grad_norm": 0.3395947515964508,
870
+ "learning_rate": 7.163651922554149e-06,
871
+ "loss": 0.0194,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.554973821989529,
876
+ "grad_norm": 0.30847620964050293,
877
+ "learning_rate": 6.5469733031905515e-06,
878
+ "loss": 0.0147,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.5759162303664924,
883
+ "grad_norm": 0.2089480310678482,
884
+ "learning_rate": 5.956185224447841e-06,
885
+ "loss": 0.0146,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.5968586387434556,
890
+ "grad_norm": 0.36750879883766174,
891
+ "learning_rate": 5.391639694549943e-06,
892
+ "loss": 0.0164,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.6178010471204187,
897
+ "grad_norm": 0.41677984595298767,
898
+ "learning_rate": 4.853673085668947e-06,
899
+ "loss": 0.0148,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.6387434554973823,
904
+ "grad_norm": 0.32629698514938354,
905
+ "learning_rate": 4.342605933505084e-06,
906
+ "loss": 0.0154,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.6596858638743455,
911
+ "grad_norm": 0.34532350301742554,
912
+ "learning_rate": 3.858742746302535e-06,
913
+ "loss": 0.0153,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.680628272251309,
918
+ "grad_norm": 0.21778731048107147,
919
+ "learning_rate": 3.402371823414774e-06,
920
+ "loss": 0.0136,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.701570680628272,
925
+ "grad_norm": 0.28639301657676697,
926
+ "learning_rate": 2.9737650835276853e-06,
927
+ "loss": 0.0137,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.7225130890052354,
932
+ "grad_norm": 0.44888314604759216,
933
+ "learning_rate": 2.573177902642726e-06,
934
+ "loss": 0.0204,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.743455497382199,
939
+ "grad_norm": 0.3165195882320404,
940
+ "learning_rate": 2.200848961916718e-06,
941
+ "loss": 0.0147,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.7643979057591626,
946
+ "grad_norm": 0.3899117112159729,
947
+ "learning_rate": 1.8570001054488362e-06,
948
+ "loss": 0.0175,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.7853403141361257,
953
+ "grad_norm": 0.2718731164932251,
954
+ "learning_rate": 1.5418362080996507e-06,
955
+ "loss": 0.0153,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.806282722513089,
960
+ "grad_norm": 0.4670896828174591,
961
+ "learning_rate": 1.2555450534208978e-06,
962
+ "loss": 0.0138,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.8272251308900525,
967
+ "grad_norm": 0.26648226380348206,
968
+ "learning_rate": 9.98297221768718e-07,
969
+ "loss": 0.0142,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.8481675392670156,
974
+ "grad_norm": 0.3085860311985016,
975
+ "learning_rate": 7.702459886670788e-07,
976
+ "loss": 0.0141,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.869109947643979,
981
+ "grad_norm": 0.46135184168815613,
982
+ "learning_rate": 5.715272334818944e-07,
983
+ "loss": 0.0162,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.8900523560209423,
988
+ "grad_norm": 0.3128398060798645,
989
+ "learning_rate": 4.02259358460233e-07,
990
+ "loss": 0.0159,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.9109947643979055,
995
+ "grad_norm": 0.44724029302597046,
996
+ "learning_rate": 2.6254321818295345e-07,
997
+ "loss": 0.0178,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.931937172774869,
1002
+ "grad_norm": 0.35600796341896057,
1003
+ "learning_rate": 1.5246205947265779e-07,
1004
+ "loss": 0.0151,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.9528795811518327,
1009
+ "grad_norm": 0.2872493863105774,
1010
+ "learning_rate": 7.208147179291192e-08,
1011
+ "loss": 0.0156,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.973821989528796,
1016
+ "grad_norm": 0.27174440026283264,
1017
+ "learning_rate": 2.1449348168167682e-08,
1018
+ "loss": 0.0162,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.994764397905759,
1023
+ "grad_norm": 0.42477887868881226,
1024
+ "learning_rate": 5.95856647772619e-10,
1025
+ "loss": 0.0136,
1026
+ "step": 1430
1027
+ }
1028
+ ],
1029
+ "logging_steps": 10,
1030
+ "max_steps": 1431,
1031
+ "num_input_tokens_seen": 0,
1032
+ "num_train_epochs": 3,
1033
+ "save_steps": 500,
1034
+ "stateful_callbacks": {
1035
+ "TrainerControl": {
1036
+ "args": {
1037
+ "should_epoch_stop": false,
1038
+ "should_evaluate": false,
1039
+ "should_log": false,
1040
+ "should_save": true,
1041
+ "should_training_stop": true
1042
+ },
1043
+ "attributes": {}
1044
+ }
1045
+ },
1046
+ "total_flos": 1.717501382279299e+18,
1047
+ "train_batch_size": 1,
1048
+ "trial_name": null,
1049
+ "trial_params": null
1050
+ }
checkpoint-1431/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daccc80b18eb9d7799bde94f4978ce1c3db384a0b077499322436ae29d6d2f44
3
+ size 5496
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9968586387434555,
3
+ "eval_loss": 0.05348898842930794,
4
+ "eval_runtime": 97.4279,
5
+ "eval_samples_per_second": 4.362,
6
+ "eval_steps_per_second": 1.098
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|eot_id|>"
17
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": "{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>\n\n' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 131072,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9968586387434555,
3
+ "total_flos": 1.717501382279299e+18,
4
+ "train_loss": 0.0491406895828145,
5
+ "train_runtime": 12322.0896,
6
+ "train_samples_per_second": 0.93,
7
+ "train_steps_per_second": 0.116
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 1431, "loss": 0.341, "learning_rate": 6.944444444444445e-06, "epoch": 0.020942408376963352, "percentage": 0.7, "elapsed_time": "0:01:27", "remaining_time": "3:26:57"}
2
+ {"current_steps": 20, "total_steps": 1431, "loss": 0.3137, "learning_rate": 1.388888888888889e-05, "epoch": 0.041884816753926704, "percentage": 1.4, "elapsed_time": "0:02:54", "remaining_time": "3:25:29"}
3
+ {"current_steps": 30, "total_steps": 1431, "loss": 0.2399, "learning_rate": 2.0833333333333336e-05, "epoch": 0.06282722513089005, "percentage": 2.1, "elapsed_time": "0:04:21", "remaining_time": "3:23:32"}
4
+ {"current_steps": 40, "total_steps": 1431, "loss": 0.1832, "learning_rate": 2.777777777777778e-05, "epoch": 0.08376963350785341, "percentage": 2.8, "elapsed_time": "0:05:46", "remaining_time": "3:20:44"}
5
+ {"current_steps": 50, "total_steps": 1431, "loss": 0.151, "learning_rate": 3.472222222222222e-05, "epoch": 0.10471204188481675, "percentage": 3.49, "elapsed_time": "0:07:09", "remaining_time": "3:17:38"}
6
+ {"current_steps": 60, "total_steps": 1431, "loss": 0.129, "learning_rate": 4.166666666666667e-05, "epoch": 0.1256544502617801, "percentage": 4.19, "elapsed_time": "0:08:33", "remaining_time": "3:15:23"}
7
+ {"current_steps": 70, "total_steps": 1431, "loss": 0.1248, "learning_rate": 4.8611111111111115e-05, "epoch": 0.14659685863874344, "percentage": 4.89, "elapsed_time": "0:10:00", "remaining_time": "3:14:26"}
8
+ {"current_steps": 80, "total_steps": 1431, "loss": 0.1142, "learning_rate": 5.555555555555556e-05, "epoch": 0.16753926701570682, "percentage": 5.59, "elapsed_time": "0:11:25", "remaining_time": "3:12:56"}
9
+ {"current_steps": 90, "total_steps": 1431, "loss": 0.1103, "learning_rate": 6.25e-05, "epoch": 0.18848167539267016, "percentage": 6.29, "elapsed_time": "0:12:48", "remaining_time": "3:10:48"}
10
+ {"current_steps": 100, "total_steps": 1431, "loss": 0.0985, "learning_rate": 6.944444444444444e-05, "epoch": 0.2094240837696335, "percentage": 6.99, "elapsed_time": "0:14:12", "remaining_time": "3:09:05"}
11
+ {"current_steps": 110, "total_steps": 1431, "loss": 0.0929, "learning_rate": 7.638888888888889e-05, "epoch": 0.23036649214659685, "percentage": 7.69, "elapsed_time": "0:15:37", "remaining_time": "3:07:34"}
12
+ {"current_steps": 120, "total_steps": 1431, "loss": 0.0955, "learning_rate": 8.333333333333334e-05, "epoch": 0.2513089005235602, "percentage": 8.39, "elapsed_time": "0:17:03", "remaining_time": "3:06:22"}
13
+ {"current_steps": 130, "total_steps": 1431, "loss": 0.0941, "learning_rate": 9.027777777777779e-05, "epoch": 0.27225130890052357, "percentage": 9.08, "elapsed_time": "0:18:30", "remaining_time": "3:05:13"}
14
+ {"current_steps": 140, "total_steps": 1431, "loss": 0.0906, "learning_rate": 9.722222222222223e-05, "epoch": 0.2931937172774869, "percentage": 9.78, "elapsed_time": "0:19:51", "remaining_time": "3:03:10"}
15
+ {"current_steps": 150, "total_steps": 1431, "loss": 0.0815, "learning_rate": 9.999463737538053e-05, "epoch": 0.31413612565445026, "percentage": 10.48, "elapsed_time": "0:21:15", "remaining_time": "3:01:29"}
16
+ {"current_steps": 160, "total_steps": 1431, "loss": 0.0803, "learning_rate": 9.996186994612176e-05, "epoch": 0.33507853403141363, "percentage": 11.18, "elapsed_time": "0:22:41", "remaining_time": "3:00:14"}
17
+ {"current_steps": 170, "total_steps": 1431, "loss": 0.0797, "learning_rate": 9.989933382359422e-05, "epoch": 0.35602094240837695, "percentage": 11.88, "elapsed_time": "0:24:06", "remaining_time": "2:58:47"}
18
+ {"current_steps": 180, "total_steps": 1431, "loss": 0.0768, "learning_rate": 9.980706626858607e-05, "epoch": 0.3769633507853403, "percentage": 12.58, "elapsed_time": "0:25:29", "remaining_time": "2:57:09"}
19
+ {"current_steps": 190, "total_steps": 1431, "loss": 0.0818, "learning_rate": 9.96851222567126e-05, "epoch": 0.39790575916230364, "percentage": 13.28, "elapsed_time": "0:26:54", "remaining_time": "2:55:44"}
20
+ {"current_steps": 200, "total_steps": 1431, "loss": 0.0717, "learning_rate": 9.953357444566039e-05, "epoch": 0.418848167539267, "percentage": 13.98, "elapsed_time": "0:28:19", "remaining_time": "2:54:20"}
21
+ {"current_steps": 210, "total_steps": 1431, "loss": 0.0698, "learning_rate": 9.935251313189564e-05, "epoch": 0.4397905759162304, "percentage": 14.68, "elapsed_time": "0:29:46", "remaining_time": "2:53:08"}
22
+ {"current_steps": 220, "total_steps": 1431, "loss": 0.0745, "learning_rate": 9.914204619686314e-05, "epoch": 0.4607329842931937, "percentage": 15.37, "elapsed_time": "0:31:11", "remaining_time": "2:51:41"}
23
+ {"current_steps": 230, "total_steps": 1431, "loss": 0.0719, "learning_rate": 9.890229904270731e-05, "epoch": 0.4816753926701571, "percentage": 16.07, "elapsed_time": "0:32:35", "remaining_time": "2:50:11"}
24
+ {"current_steps": 240, "total_steps": 1431, "loss": 0.0751, "learning_rate": 9.86334145175542e-05, "epoch": 0.5026178010471204, "percentage": 16.77, "elapsed_time": "0:33:57", "remaining_time": "2:48:31"}
25
+ {"current_steps": 250, "total_steps": 1431, "loss": 0.0696, "learning_rate": 9.833555283039842e-05, "epoch": 0.5235602094240838, "percentage": 17.47, "elapsed_time": "0:35:21", "remaining_time": "2:47:03"}
26
+ {"current_steps": 260, "total_steps": 1431, "loss": 0.0594, "learning_rate": 9.800889145564617e-05, "epoch": 0.5445026178010471, "percentage": 18.17, "elapsed_time": "0:36:44", "remaining_time": "2:45:26"}
27
+ {"current_steps": 270, "total_steps": 1431, "loss": 0.0732, "learning_rate": 9.765362502737097e-05, "epoch": 0.5654450261780105, "percentage": 18.87, "elapsed_time": "0:38:09", "remaining_time": "2:44:03"}
28
+ {"current_steps": 280, "total_steps": 1431, "loss": 0.0649, "learning_rate": 9.730960252267743e-05, "epoch": 0.5863874345549738, "percentage": 19.57, "elapsed_time": "0:39:34", "remaining_time": "2:42:39"}
29
+ {"current_steps": 290, "total_steps": 1431, "loss": 0.0679, "learning_rate": 9.690058365011607e-05, "epoch": 0.6073298429319371, "percentage": 20.27, "elapsed_time": "0:40:57", "remaining_time": "2:41:07"}
30
+ {"current_steps": 300, "total_steps": 1431, "loss": 0.0787, "learning_rate": 9.646362008512602e-05, "epoch": 0.6282722513089005, "percentage": 20.96, "elapsed_time": "0:42:22", "remaining_time": "2:39:46"}
31
+ {"current_steps": 310, "total_steps": 1431, "loss": 0.072, "learning_rate": 9.599897218294122e-05, "epoch": 0.6492146596858639, "percentage": 21.66, "elapsed_time": "0:43:50", "remaining_time": "2:38:31"}
32
+ {"current_steps": 320, "total_steps": 1431, "loss": 0.065, "learning_rate": 9.550691679390558e-05, "epoch": 0.6701570680628273, "percentage": 22.36, "elapsed_time": "0:45:12", "remaining_time": "2:36:58"}
33
+ {"current_steps": 330, "total_steps": 1431, "loss": 0.0644, "learning_rate": 9.498774709851779e-05, "epoch": 0.6910994764397905, "percentage": 23.06, "elapsed_time": "0:46:39", "remaining_time": "2:35:40"}
34
+ {"current_steps": 340, "total_steps": 1431, "loss": 0.0624, "learning_rate": 9.444177243274618e-05, "epoch": 0.7120418848167539, "percentage": 23.76, "elapsed_time": "0:48:02", "remaining_time": "2:34:10"}
35
+ {"current_steps": 350, "total_steps": 1431, "loss": 0.066, "learning_rate": 9.386931810371742e-05, "epoch": 0.7329842931937173, "percentage": 24.46, "elapsed_time": "0:49:28", "remaining_time": "2:32:49"}
36
+ {"current_steps": 360, "total_steps": 1431, "loss": 0.0642, "learning_rate": 9.327072519588954e-05, "epoch": 0.7539267015706806, "percentage": 25.16, "elapsed_time": "0:50:51", "remaining_time": "2:31:17"}
37
+ {"current_steps": 370, "total_steps": 1431, "loss": 0.064, "learning_rate": 9.264635036782405e-05, "epoch": 0.774869109947644, "percentage": 25.86, "elapsed_time": "0:52:16", "remaining_time": "2:29:55"}
38
+ {"current_steps": 380, "total_steps": 1431, "loss": 0.0635, "learning_rate": 9.199656563967875e-05, "epoch": 0.7958115183246073, "percentage": 26.55, "elapsed_time": "0:53:43", "remaining_time": "2:28:34"}
39
+ {"current_steps": 390, "total_steps": 1431, "loss": 0.0617, "learning_rate": 9.132175817154763e-05, "epoch": 0.8167539267015707, "percentage": 27.25, "elapsed_time": "0:55:06", "remaining_time": "2:27:04"}
40
+ {"current_steps": 400, "total_steps": 1431, "loss": 0.0612, "learning_rate": 9.062233003277983e-05, "epoch": 0.837696335078534, "percentage": 27.95, "elapsed_time": "0:56:31", "remaining_time": "2:25:40"}
41
+ {"current_steps": 410, "total_steps": 1431, "loss": 0.0609, "learning_rate": 8.989869796241559e-05, "epoch": 0.8586387434554974, "percentage": 28.65, "elapsed_time": "0:57:55", "remaining_time": "2:24:14"}
42
+ {"current_steps": 420, "total_steps": 1431, "loss": 0.0634, "learning_rate": 8.915129312088112e-05, "epoch": 0.8795811518324608, "percentage": 29.35, "elapsed_time": "0:59:18", "remaining_time": "2:22:46"}
43
+ {"current_steps": 430, "total_steps": 1431, "loss": 0.0569, "learning_rate": 8.838056083309118e-05, "epoch": 0.900523560209424, "percentage": 30.05, "elapsed_time": "1:00:41", "remaining_time": "2:21:16"}
44
+ {"current_steps": 440, "total_steps": 1431, "loss": 0.0583, "learning_rate": 8.758696032311192e-05, "epoch": 0.9214659685863874, "percentage": 30.75, "elapsed_time": "1:02:06", "remaining_time": "2:19:53"}
45
+ {"current_steps": 450, "total_steps": 1431, "loss": 0.0637, "learning_rate": 8.677096444054213e-05, "epoch": 0.9424083769633508, "percentage": 31.45, "elapsed_time": "1:03:32", "remaining_time": "2:18:31"}
46
+ {"current_steps": 460, "total_steps": 1431, "loss": 0.0607, "learning_rate": 8.593305937877614e-05, "epoch": 0.9633507853403142, "percentage": 32.15, "elapsed_time": "1:04:58", "remaining_time": "2:17:09"}
47
+ {"current_steps": 470, "total_steps": 1431, "loss": 0.0617, "learning_rate": 8.507374438531607e-05, "epoch": 0.9842931937172775, "percentage": 32.84, "elapsed_time": "1:06:21", "remaining_time": "2:15:41"}
48
+ {"current_steps": 480, "total_steps": 1431, "loss": 0.0563, "learning_rate": 8.419353146430609e-05, "epoch": 1.0052356020942408, "percentage": 33.54, "elapsed_time": "1:07:48", "remaining_time": "2:14:19"}
49
+ {"current_steps": 490, "total_steps": 1431, "loss": 0.0415, "learning_rate": 8.329294507146579e-05, "epoch": 1.0261780104712042, "percentage": 34.24, "elapsed_time": "1:09:14", "remaining_time": "2:12:57"}
50
+ {"current_steps": 500, "total_steps": 1431, "loss": 0.0402, "learning_rate": 8.23725218016048e-05, "epoch": 1.0471204188481675, "percentage": 34.94, "elapsed_time": "1:10:38", "remaining_time": "2:11:31"}
51
+ {"current_steps": 500, "total_steps": 1431, "eval_loss": 0.058112796396017075, "epoch": 1.0471204188481675, "percentage": 34.94, "elapsed_time": "1:12:16", "remaining_time": "2:14:33"}
52
+ {"current_steps": 510, "total_steps": 1431, "loss": 0.0388, "learning_rate": 8.143281006890433e-05, "epoch": 1.068062827225131, "percentage": 35.64, "elapsed_time": "1:13:39", "remaining_time": "2:13:01"}
53
+ {"current_steps": 520, "total_steps": 1431, "loss": 0.0467, "learning_rate": 8.047436978015649e-05, "epoch": 1.0890052356020943, "percentage": 36.34, "elapsed_time": "1:15:03", "remaining_time": "2:11:29"}
54
+ {"current_steps": 530, "total_steps": 1431, "loss": 0.0414, "learning_rate": 7.949777200115616e-05, "epoch": 1.1099476439790577, "percentage": 37.04, "elapsed_time": "1:16:27", "remaining_time": "2:09:58"}
55
+ {"current_steps": 540, "total_steps": 1431, "loss": 0.0413, "learning_rate": 7.850359861644368e-05, "epoch": 1.130890052356021, "percentage": 37.74, "elapsed_time": "1:17:51", "remaining_time": "2:08:28"}
56
+ {"current_steps": 550, "total_steps": 1431, "loss": 0.0448, "learning_rate": 7.749244198260175e-05, "epoch": 1.1518324607329844, "percentage": 38.43, "elapsed_time": "1:19:16", "remaining_time": "2:06:58"}
57
+ {"current_steps": 560, "total_steps": 1431, "loss": 0.0379, "learning_rate": 7.646490457531257e-05, "epoch": 1.1727748691099475, "percentage": 39.13, "elapsed_time": "1:20:37", "remaining_time": "2:05:23"}
58
+ {"current_steps": 570, "total_steps": 1431, "loss": 0.0375, "learning_rate": 7.54215986303858e-05, "epoch": 1.193717277486911, "percentage": 39.83, "elapsed_time": "1:21:59", "remaining_time": "2:03:50"}
59
+ {"current_steps": 580, "total_steps": 1431, "loss": 0.0373, "learning_rate": 7.436314577897126e-05, "epoch": 1.2146596858638743, "percentage": 40.53, "elapsed_time": "1:23:21", "remaining_time": "2:02:19"}
60
+ {"current_steps": 590, "total_steps": 1431, "loss": 0.042, "learning_rate": 7.329017667717339e-05, "epoch": 1.2356020942408377, "percentage": 41.23, "elapsed_time": "1:24:48", "remaining_time": "2:00:53"}
61
+ {"current_steps": 600, "total_steps": 1431, "loss": 0.0379, "learning_rate": 7.220333063028872e-05, "epoch": 1.256544502617801, "percentage": 41.93, "elapsed_time": "1:26:14", "remaining_time": "1:59:26"}
62
+ {"current_steps": 610, "total_steps": 1431, "loss": 0.0444, "learning_rate": 7.110325521188949e-05, "epoch": 1.2774869109947644, "percentage": 42.63, "elapsed_time": "1:27:37", "remaining_time": "1:57:56"}
63
+ {"current_steps": 620, "total_steps": 1431, "loss": 0.0422, "learning_rate": 6.999060587798128e-05, "epoch": 1.2984293193717278, "percentage": 43.33, "elapsed_time": "1:29:00", "remaining_time": "1:56:26"}
64
+ {"current_steps": 630, "total_steps": 1431, "loss": 0.0384, "learning_rate": 6.886604557646356e-05, "epoch": 1.3193717277486912, "percentage": 44.03, "elapsed_time": "1:30:25", "remaining_time": "1:54:57"}
65
+ {"current_steps": 640, "total_steps": 1431, "loss": 0.0352, "learning_rate": 6.773024435212678e-05, "epoch": 1.3403141361256545, "percentage": 44.72, "elapsed_time": "1:31:49", "remaining_time": "1:53:29"}
66
+ {"current_steps": 650, "total_steps": 1431, "loss": 0.0397, "learning_rate": 6.658387894742071e-05, "epoch": 1.3612565445026177, "percentage": 45.42, "elapsed_time": "1:33:15", "remaining_time": "1:52:03"}
67
+ {"current_steps": 660, "total_steps": 1431, "loss": 0.0375, "learning_rate": 6.542763239923215e-05, "epoch": 1.3821989528795813, "percentage": 46.12, "elapsed_time": "1:34:40", "remaining_time": "1:50:35"}
68
+ {"current_steps": 670, "total_steps": 1431, "loss": 0.0443, "learning_rate": 6.426219363191224e-05, "epoch": 1.4031413612565444, "percentage": 46.82, "elapsed_time": "1:36:02", "remaining_time": "1:49:05"}
69
+ {"current_steps": 680, "total_steps": 1431, "loss": 0.0334, "learning_rate": 6.308825704679596e-05, "epoch": 1.4240837696335078, "percentage": 47.52, "elapsed_time": "1:37:27", "remaining_time": "1:47:37"}
70
+ {"current_steps": 690, "total_steps": 1431, "loss": 0.0401, "learning_rate": 6.190652210845815e-05, "epoch": 1.4450261780104712, "percentage": 48.22, "elapsed_time": "1:38:53", "remaining_time": "1:46:11"}
71
+ {"current_steps": 700, "total_steps": 1431, "loss": 0.0367, "learning_rate": 6.0717692927952744e-05, "epoch": 1.4659685863874345, "percentage": 48.92, "elapsed_time": "1:40:18", "remaining_time": "1:44:45"}
72
+ {"current_steps": 710, "total_steps": 1431, "loss": 0.0375, "learning_rate": 5.952247784328351e-05, "epoch": 1.486910994764398, "percentage": 49.62, "elapsed_time": "1:41:44", "remaining_time": "1:43:18"}
73
+ {"current_steps": 720, "total_steps": 1431, "loss": 0.0339, "learning_rate": 5.8321588997356326e-05, "epoch": 1.5078534031413613, "percentage": 50.31, "elapsed_time": "1:43:10", "remaining_time": "1:41:53"}
74
+ {"current_steps": 730, "total_steps": 1431, "loss": 0.0381, "learning_rate": 5.7115741913664264e-05, "epoch": 1.5287958115183247, "percentage": 51.01, "elapsed_time": "1:44:33", "remaining_time": "1:40:24"}
75
+ {"current_steps": 740, "total_steps": 1431, "loss": 0.0355, "learning_rate": 5.59056550699585e-05, "epoch": 1.5497382198952878, "percentage": 51.71, "elapsed_time": "1:45:59", "remaining_time": "1:38:58"}
76
+ {"current_steps": 750, "total_steps": 1431, "loss": 0.0374, "learning_rate": 5.469204947015897e-05, "epoch": 1.5706806282722514, "percentage": 52.41, "elapsed_time": "1:47:23", "remaining_time": "1:37:30"}
77
+ {"current_steps": 760, "total_steps": 1431, "loss": 0.0327, "learning_rate": 5.3475648214759896e-05, "epoch": 1.5916230366492146, "percentage": 53.11, "elapsed_time": "1:48:48", "remaining_time": "1:36:03"}
78
+ {"current_steps": 770, "total_steps": 1431, "loss": 0.0403, "learning_rate": 5.2257176069986036e-05, "epoch": 1.6125654450261782, "percentage": 53.81, "elapsed_time": "1:50:14", "remaining_time": "1:34:38"}
79
+ {"current_steps": 780, "total_steps": 1431, "loss": 0.0364, "learning_rate": 5.103735903595658e-05, "epoch": 1.6335078534031413, "percentage": 54.51, "elapsed_time": "1:51:41", "remaining_time": "1:33:13"}
80
+ {"current_steps": 790, "total_steps": 1431, "loss": 0.0371, "learning_rate": 4.981692391411366e-05, "epoch": 1.6544502617801047, "percentage": 55.21, "elapsed_time": "1:53:04", "remaining_time": "1:31:44"}
81
+ {"current_steps": 800, "total_steps": 1431, "loss": 0.0406, "learning_rate": 4.859659787417362e-05, "epoch": 1.675392670157068, "percentage": 55.9, "elapsed_time": "1:54:29", "remaining_time": "1:30:18"}
82
+ {"current_steps": 810, "total_steps": 1431, "loss": 0.0353, "learning_rate": 4.737710802085875e-05, "epoch": 1.6963350785340314, "percentage": 56.6, "elapsed_time": "1:55:55", "remaining_time": "1:28:52"}
83
+ {"current_steps": 820, "total_steps": 1431, "loss": 0.0325, "learning_rate": 4.615918096066766e-05, "epoch": 1.7172774869109948, "percentage": 57.3, "elapsed_time": "1:57:20", "remaining_time": "1:27:26"}
84
+ {"current_steps": 830, "total_steps": 1431, "loss": 0.0318, "learning_rate": 4.4943542368942746e-05, "epoch": 1.738219895287958, "percentage": 58.0, "elapsed_time": "1:58:48", "remaining_time": "1:26:01"}
85
+ {"current_steps": 840, "total_steps": 1431, "loss": 0.0374, "learning_rate": 4.373091655749225e-05, "epoch": 1.7591623036649215, "percentage": 58.7, "elapsed_time": "2:00:12", "remaining_time": "1:24:34"}
86
+ {"current_steps": 850, "total_steps": 1431, "loss": 0.0362, "learning_rate": 4.252202604302476e-05, "epoch": 1.7801047120418847, "percentage": 59.4, "elapsed_time": "2:01:35", "remaining_time": "1:23:06"}
87
+ {"current_steps": 860, "total_steps": 1431, "loss": 0.038, "learning_rate": 4.131759111665349e-05, "epoch": 1.8010471204188483, "percentage": 60.1, "elapsed_time": "2:03:00", "remaining_time": "1:21:40"}
88
+ {"current_steps": 870, "total_steps": 1431, "loss": 0.0393, "learning_rate": 4.011832941472641e-05, "epoch": 1.8219895287958114, "percentage": 60.8, "elapsed_time": "2:04:24", "remaining_time": "1:20:13"}
89
+ {"current_steps": 880, "total_steps": 1431, "loss": 0.0336, "learning_rate": 3.8924955491238216e-05, "epoch": 1.8429319371727748, "percentage": 61.5, "elapsed_time": "2:05:48", "remaining_time": "1:18:46"}
90
+ {"current_steps": 890, "total_steps": 1431, "loss": 0.033, "learning_rate": 3.7738180392078937e-05, "epoch": 1.8638743455497382, "percentage": 62.19, "elapsed_time": "2:07:13", "remaining_time": "1:17:19"}
91
+ {"current_steps": 900, "total_steps": 1431, "loss": 0.035, "learning_rate": 3.6558711231372704e-05, "epoch": 1.8848167539267016, "percentage": 62.89, "elapsed_time": "2:08:38", "remaining_time": "1:15:54"}
92
+ {"current_steps": 910, "total_steps": 1431, "loss": 0.0357, "learning_rate": 3.538725077015915e-05, "epoch": 1.905759162303665, "percentage": 63.59, "elapsed_time": "2:10:05", "remaining_time": "1:14:28"}
93
+ {"current_steps": 920, "total_steps": 1431, "loss": 0.0313, "learning_rate": 3.422449699766851e-05, "epoch": 1.9267015706806283, "percentage": 64.29, "elapsed_time": "2:11:30", "remaining_time": "1:13:02"}
94
+ {"current_steps": 930, "total_steps": 1431, "loss": 0.0345, "learning_rate": 3.307114271543999e-05, "epoch": 1.9476439790575917, "percentage": 64.99, "elapsed_time": "2:12:55", "remaining_time": "1:11:36"}
95
+ {"current_steps": 940, "total_steps": 1431, "loss": 0.0333, "learning_rate": 3.192787512453105e-05, "epoch": 1.9685863874345548, "percentage": 65.69, "elapsed_time": "2:14:23", "remaining_time": "1:10:11"}
96
+ {"current_steps": 950, "total_steps": 1431, "loss": 0.0317, "learning_rate": 3.079537541606349e-05, "epoch": 1.9895287958115184, "percentage": 66.39, "elapsed_time": "2:15:46", "remaining_time": "1:08:44"}
97
+ {"current_steps": 960, "total_steps": 1431, "loss": 0.0235, "learning_rate": 2.9674318365350685e-05, "epoch": 2.0104712041884816, "percentage": 67.09, "elapsed_time": "2:17:12", "remaining_time": "1:07:19"}
98
+ {"current_steps": 970, "total_steps": 1431, "loss": 0.0158, "learning_rate": 2.8565371929847284e-05, "epoch": 2.031413612565445, "percentage": 67.78, "elapsed_time": "2:18:37", "remaining_time": "1:05:53"}
99
+ {"current_steps": 980, "total_steps": 1431, "loss": 0.0179, "learning_rate": 2.7469196851161373e-05, "epoch": 2.0523560209424083, "percentage": 68.48, "elapsed_time": "2:20:00", "remaining_time": "1:04:26"}
100
+ {"current_steps": 990, "total_steps": 1431, "loss": 0.0174, "learning_rate": 2.638644626136587e-05, "epoch": 2.073298429319372, "percentage": 69.18, "elapsed_time": "2:21:27", "remaining_time": "1:03:00"}
101
+ {"current_steps": 1000, "total_steps": 1431, "loss": 0.0204, "learning_rate": 2.531776529384407e-05, "epoch": 2.094240837696335, "percentage": 69.88, "elapsed_time": "2:22:52", "remaining_time": "1:01:34"}
102
+ {"current_steps": 1000, "total_steps": 1431, "eval_loss": 0.05247209593653679, "epoch": 2.094240837696335, "percentage": 69.88, "elapsed_time": "2:24:30", "remaining_time": "1:02:16"}
103
+ {"current_steps": 1010, "total_steps": 1431, "loss": 0.0178, "learning_rate": 2.426379069890098e-05, "epoch": 2.115183246073298, "percentage": 70.58, "elapsed_time": "2:25:57", "remaining_time": "1:00:50"}
104
+ {"current_steps": 1020, "total_steps": 1431, "loss": 0.0145, "learning_rate": 2.3225150464369312e-05, "epoch": 2.136125654450262, "percentage": 71.28, "elapsed_time": "2:27:22", "remaining_time": "0:59:22"}
105
+ {"current_steps": 1030, "total_steps": 1431, "loss": 0.0186, "learning_rate": 2.2202463441436884e-05, "epoch": 2.157068062827225, "percentage": 71.98, "elapsed_time": "2:28:48", "remaining_time": "0:57:56"}
106
+ {"current_steps": 1040, "total_steps": 1431, "loss": 0.0185, "learning_rate": 2.1196338975917358e-05, "epoch": 2.1780104712041886, "percentage": 72.68, "elapsed_time": "2:30:10", "remaining_time": "0:56:27"}
107
+ {"current_steps": 1050, "total_steps": 1431, "loss": 0.0148, "learning_rate": 2.0207376545184893e-05, "epoch": 2.1989528795811517, "percentage": 73.38, "elapsed_time": "2:31:31", "remaining_time": "0:54:59"}
108
+ {"current_steps": 1060, "total_steps": 1431, "loss": 0.0188, "learning_rate": 1.9236165400988638e-05, "epoch": 2.2198952879581153, "percentage": 74.07, "elapsed_time": "2:32:56", "remaining_time": "0:53:31"}
109
+ {"current_steps": 1070, "total_steps": 1431, "loss": 0.0167, "learning_rate": 1.8283284218359782e-05, "epoch": 2.2408376963350785, "percentage": 74.77, "elapsed_time": "2:34:20", "remaining_time": "0:52:04"}
110
+ {"current_steps": 1080, "total_steps": 1431, "loss": 0.0156, "learning_rate": 1.734930075082076e-05, "epoch": 2.261780104712042, "percentage": 75.47, "elapsed_time": "2:35:47", "remaining_time": "0:50:37"}
111
+ {"current_steps": 1090, "total_steps": 1431, "loss": 0.0168, "learning_rate": 1.6434771492101485e-05, "epoch": 2.282722513089005, "percentage": 76.17, "elapsed_time": "2:37:10", "remaining_time": "0:49:10"}
112
+ {"current_steps": 1100, "total_steps": 1431, "loss": 0.0178, "learning_rate": 1.5540241344564915e-05, "epoch": 2.303664921465969, "percentage": 76.87, "elapsed_time": "2:38:36", "remaining_time": "0:47:43"}
113
+ {"current_steps": 1110, "total_steps": 1431, "loss": 0.0159, "learning_rate": 1.46662432945386e-05, "epoch": 2.324607329842932, "percentage": 77.57, "elapsed_time": "2:40:01", "remaining_time": "0:46:16"}
114
+ {"current_steps": 1120, "total_steps": 1431, "loss": 0.0155, "learning_rate": 1.3813298094746491e-05, "epoch": 2.345549738219895, "percentage": 78.27, "elapsed_time": "2:41:24", "remaining_time": "0:44:49"}
115
+ {"current_steps": 1130, "total_steps": 1431, "loss": 0.0158, "learning_rate": 1.2981913954029784e-05, "epoch": 2.3664921465968587, "percentage": 78.97, "elapsed_time": "2:42:49", "remaining_time": "0:43:22"}
116
+ {"current_steps": 1140, "total_steps": 1431, "loss": 0.0162, "learning_rate": 1.2172586234541644e-05, "epoch": 2.387434554973822, "percentage": 79.66, "elapsed_time": "2:44:13", "remaining_time": "0:41:55"}
117
+ {"current_steps": 1150, "total_steps": 1431, "loss": 0.0157, "learning_rate": 1.1385797156596506e-05, "epoch": 2.4083769633507854, "percentage": 80.36, "elapsed_time": "2:45:35", "remaining_time": "0:40:27"}
118
+ {"current_steps": 1160, "total_steps": 1431, "loss": 0.0146, "learning_rate": 1.062201551134957e-05, "epoch": 2.4293193717277486, "percentage": 81.06, "elapsed_time": "2:46:59", "remaining_time": "0:39:00"}
119
+ {"current_steps": 1170, "total_steps": 1431, "loss": 0.0143, "learning_rate": 9.88169638147784e-06, "epoch": 2.450261780104712, "percentage": 81.76, "elapsed_time": "2:48:21", "remaining_time": "0:37:33"}
120
+ {"current_steps": 1180, "total_steps": 1431, "loss": 0.017, "learning_rate": 9.16528087002892e-06, "epoch": 2.4712041884816753, "percentage": 82.46, "elapsed_time": "2:49:46", "remaining_time": "0:36:06"}
121
+ {"current_steps": 1190, "total_steps": 1431, "loss": 0.0155, "learning_rate": 8.473195837599418e-06, "epoch": 2.492146596858639, "percentage": 83.16, "elapsed_time": "2:51:11", "remaining_time": "0:34:40"}
122
+ {"current_steps": 1200, "total_steps": 1431, "loss": 0.0176, "learning_rate": 7.805853647999362e-06, "epoch": 2.513089005235602, "percentage": 83.86, "elapsed_time": "2:52:35", "remaining_time": "0:33:13"}
123
+ {"current_steps": 1210, "total_steps": 1431, "loss": 0.0194, "learning_rate": 7.163651922554149e-06, "epoch": 2.5340314136125652, "percentage": 84.56, "elapsed_time": "2:53:58", "remaining_time": "0:31:46"}
124
+ {"current_steps": 1220, "total_steps": 1431, "loss": 0.0147, "learning_rate": 6.5469733031905515e-06, "epoch": 2.554973821989529, "percentage": 85.26, "elapsed_time": "2:55:22", "remaining_time": "0:30:19"}
125
+ {"current_steps": 1230, "total_steps": 1431, "loss": 0.0146, "learning_rate": 5.956185224447841e-06, "epoch": 2.5759162303664924, "percentage": 85.95, "elapsed_time": "2:56:48", "remaining_time": "0:28:53"}
126
+ {"current_steps": 1240, "total_steps": 1431, "loss": 0.0164, "learning_rate": 5.391639694549943e-06, "epoch": 2.5968586387434556, "percentage": 86.65, "elapsed_time": "2:58:12", "remaining_time": "0:27:27"}
127
+ {"current_steps": 1250, "total_steps": 1431, "loss": 0.0148, "learning_rate": 4.853673085668947e-06, "epoch": 2.6178010471204187, "percentage": 87.35, "elapsed_time": "2:59:37", "remaining_time": "0:26:00"}
128
+ {"current_steps": 1260, "total_steps": 1431, "loss": 0.0154, "learning_rate": 4.342605933505084e-06, "epoch": 2.6387434554973823, "percentage": 88.05, "elapsed_time": "3:01:01", "remaining_time": "0:24:34"}
129
+ {"current_steps": 1270, "total_steps": 1431, "loss": 0.0153, "learning_rate": 3.858742746302535e-06, "epoch": 2.6596858638743455, "percentage": 88.75, "elapsed_time": "3:02:27", "remaining_time": "0:23:07"}
130
+ {"current_steps": 1280, "total_steps": 1431, "loss": 0.0136, "learning_rate": 3.402371823414774e-06, "epoch": 2.680628272251309, "percentage": 89.45, "elapsed_time": "3:03:50", "remaining_time": "0:21:41"}
131
+ {"current_steps": 1290, "total_steps": 1431, "loss": 0.0137, "learning_rate": 2.9737650835276853e-06, "epoch": 2.701570680628272, "percentage": 90.15, "elapsed_time": "3:05:15", "remaining_time": "0:20:14"}
132
+ {"current_steps": 1300, "total_steps": 1431, "loss": 0.0204, "learning_rate": 2.573177902642726e-06, "epoch": 2.7225130890052354, "percentage": 90.85, "elapsed_time": "3:06:41", "remaining_time": "0:18:48"}
133
+ {"current_steps": 1310, "total_steps": 1431, "loss": 0.0147, "learning_rate": 2.200848961916718e-06, "epoch": 2.743455497382199, "percentage": 91.54, "elapsed_time": "3:08:07", "remaining_time": "0:17:22"}
134
+ {"current_steps": 1320, "total_steps": 1431, "loss": 0.0175, "learning_rate": 1.8570001054488362e-06, "epoch": 2.7643979057591626, "percentage": 92.24, "elapsed_time": "3:09:32", "remaining_time": "0:15:56"}
135
+ {"current_steps": 1330, "total_steps": 1431, "loss": 0.0153, "learning_rate": 1.5418362080996507e-06, "epoch": 2.7853403141361257, "percentage": 92.94, "elapsed_time": "3:10:58", "remaining_time": "0:14:30"}
136
+ {"current_steps": 1340, "total_steps": 1431, "loss": 0.0138, "learning_rate": 1.2555450534208978e-06, "epoch": 2.806282722513089, "percentage": 93.64, "elapsed_time": "3:12:21", "remaining_time": "0:13:03"}
137
+ {"current_steps": 1350, "total_steps": 1431, "loss": 0.0142, "learning_rate": 9.98297221768718e-07, "epoch": 2.8272251308900525, "percentage": 94.34, "elapsed_time": "3:13:44", "remaining_time": "0:11:37"}
138
+ {"current_steps": 1360, "total_steps": 1431, "loss": 0.0141, "learning_rate": 7.702459886670788e-07, "epoch": 2.8481675392670156, "percentage": 95.04, "elapsed_time": "3:15:09", "remaining_time": "0:10:11"}
139
+ {"current_steps": 1370, "total_steps": 1431, "loss": 0.0162, "learning_rate": 5.715272334818944e-07, "epoch": 2.869109947643979, "percentage": 95.74, "elapsed_time": "3:16:34", "remaining_time": "0:08:45"}
140
+ {"current_steps": 1380, "total_steps": 1431, "loss": 0.0159, "learning_rate": 4.02259358460233e-07, "epoch": 2.8900523560209423, "percentage": 96.44, "elapsed_time": "3:17:59", "remaining_time": "0:07:19"}
141
+ {"current_steps": 1390, "total_steps": 1431, "loss": 0.0178, "learning_rate": 2.6254321818295345e-07, "epoch": 2.9109947643979055, "percentage": 97.13, "elapsed_time": "3:19:24", "remaining_time": "0:05:52"}
142
+ {"current_steps": 1400, "total_steps": 1431, "loss": 0.0151, "learning_rate": 1.5246205947265779e-07, "epoch": 2.931937172774869, "percentage": 97.83, "elapsed_time": "3:20:48", "remaining_time": "0:04:26"}
143
+ {"current_steps": 1410, "total_steps": 1431, "loss": 0.0156, "learning_rate": 7.208147179291192e-08, "epoch": 2.9528795811518327, "percentage": 98.53, "elapsed_time": "3:22:13", "remaining_time": "0:03:00"}
144
+ {"current_steps": 1420, "total_steps": 1431, "loss": 0.0162, "learning_rate": 2.1449348168167682e-08, "epoch": 2.973821989528796, "percentage": 99.23, "elapsed_time": "3:23:38", "remaining_time": "0:01:34"}
145
+ {"current_steps": 1430, "total_steps": 1431, "loss": 0.0136, "learning_rate": 5.95856647772619e-10, "epoch": 2.994764397905759, "percentage": 99.93, "elapsed_time": "3:25:02", "remaining_time": "0:00:08"}
146
+ {"current_steps": 1431, "total_steps": 1431, "epoch": 2.9968586387434555, "percentage": 100.0, "elapsed_time": "3:25:12", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,1059 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9968586387434555,
5
+ "eval_steps": 500,
6
+ "global_step": 1431,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.020942408376963352,
13
+ "grad_norm": 0.5137882828712463,
14
+ "learning_rate": 6.944444444444445e-06,
15
+ "loss": 0.341,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.041884816753926704,
20
+ "grad_norm": 0.5445541739463806,
21
+ "learning_rate": 1.388888888888889e-05,
22
+ "loss": 0.3137,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.06282722513089005,
27
+ "grad_norm": 0.34443390369415283,
28
+ "learning_rate": 2.0833333333333336e-05,
29
+ "loss": 0.2399,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.08376963350785341,
34
+ "grad_norm": 0.36772170662879944,
35
+ "learning_rate": 2.777777777777778e-05,
36
+ "loss": 0.1832,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.10471204188481675,
41
+ "grad_norm": 0.3646106719970703,
42
+ "learning_rate": 3.472222222222222e-05,
43
+ "loss": 0.151,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.1256544502617801,
48
+ "grad_norm": 0.538939356803894,
49
+ "learning_rate": 4.166666666666667e-05,
50
+ "loss": 0.129,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.14659685863874344,
55
+ "grad_norm": 0.36220353841781616,
56
+ "learning_rate": 4.8611111111111115e-05,
57
+ "loss": 0.1248,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.16753926701570682,
62
+ "grad_norm": 0.4773642420768738,
63
+ "learning_rate": 5.555555555555556e-05,
64
+ "loss": 0.1142,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.18848167539267016,
69
+ "grad_norm": 0.45749950408935547,
70
+ "learning_rate": 6.25e-05,
71
+ "loss": 0.1103,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.2094240837696335,
76
+ "grad_norm": 0.4229575991630554,
77
+ "learning_rate": 6.944444444444444e-05,
78
+ "loss": 0.0985,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.23036649214659685,
83
+ "grad_norm": 0.4683126211166382,
84
+ "learning_rate": 7.638888888888889e-05,
85
+ "loss": 0.0929,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.2513089005235602,
90
+ "grad_norm": 0.3871113359928131,
91
+ "learning_rate": 8.333333333333334e-05,
92
+ "loss": 0.0955,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.27225130890052357,
97
+ "grad_norm": 0.45953118801116943,
98
+ "learning_rate": 9.027777777777779e-05,
99
+ "loss": 0.0941,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.2931937172774869,
104
+ "grad_norm": 0.4296354651451111,
105
+ "learning_rate": 9.722222222222223e-05,
106
+ "loss": 0.0906,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.31413612565445026,
111
+ "grad_norm": 0.4266631007194519,
112
+ "learning_rate": 9.999463737538053e-05,
113
+ "loss": 0.0815,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.33507853403141363,
118
+ "grad_norm": 0.4313138425350189,
119
+ "learning_rate": 9.996186994612176e-05,
120
+ "loss": 0.0803,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.35602094240837695,
125
+ "grad_norm": 0.36333203315734863,
126
+ "learning_rate": 9.989933382359422e-05,
127
+ "loss": 0.0797,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.3769633507853403,
132
+ "grad_norm": 0.7311431765556335,
133
+ "learning_rate": 9.980706626858607e-05,
134
+ "loss": 0.0768,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.39790575916230364,
139
+ "grad_norm": 0.4651825428009033,
140
+ "learning_rate": 9.96851222567126e-05,
141
+ "loss": 0.0818,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.418848167539267,
146
+ "grad_norm": 0.5768024325370789,
147
+ "learning_rate": 9.953357444566039e-05,
148
+ "loss": 0.0717,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.4397905759162304,
153
+ "grad_norm": 0.41442790627479553,
154
+ "learning_rate": 9.935251313189564e-05,
155
+ "loss": 0.0698,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.4607329842931937,
160
+ "grad_norm": 0.5525192618370056,
161
+ "learning_rate": 9.914204619686314e-05,
162
+ "loss": 0.0745,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.4816753926701571,
167
+ "grad_norm": 0.4769018590450287,
168
+ "learning_rate": 9.890229904270731e-05,
169
+ "loss": 0.0719,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.5026178010471204,
174
+ "grad_norm": 0.4063033163547516,
175
+ "learning_rate": 9.86334145175542e-05,
176
+ "loss": 0.0751,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.5235602094240838,
181
+ "grad_norm": 0.3966362476348877,
182
+ "learning_rate": 9.833555283039842e-05,
183
+ "loss": 0.0696,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.5445026178010471,
188
+ "grad_norm": 0.4347456395626068,
189
+ "learning_rate": 9.800889145564617e-05,
190
+ "loss": 0.0594,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.5654450261780105,
195
+ "grad_norm": 0.3599953055381775,
196
+ "learning_rate": 9.765362502737097e-05,
197
+ "loss": 0.0732,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.5863874345549738,
202
+ "grad_norm": 0.3424774706363678,
203
+ "learning_rate": 9.730960252267743e-05,
204
+ "loss": 0.0649,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.6073298429319371,
209
+ "grad_norm": 0.48636892437934875,
210
+ "learning_rate": 9.690058365011607e-05,
211
+ "loss": 0.0679,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.6282722513089005,
216
+ "grad_norm": 0.5237702131271362,
217
+ "learning_rate": 9.646362008512602e-05,
218
+ "loss": 0.0787,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.6492146596858639,
223
+ "grad_norm": 0.3805506229400635,
224
+ "learning_rate": 9.599897218294122e-05,
225
+ "loss": 0.072,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.6701570680628273,
230
+ "grad_norm": 0.4530421197414398,
231
+ "learning_rate": 9.550691679390558e-05,
232
+ "loss": 0.065,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.6910994764397905,
237
+ "grad_norm": 0.4006820321083069,
238
+ "learning_rate": 9.498774709851779e-05,
239
+ "loss": 0.0644,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.7120418848167539,
244
+ "grad_norm": 0.3857646584510803,
245
+ "learning_rate": 9.444177243274618e-05,
246
+ "loss": 0.0624,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.7329842931937173,
251
+ "grad_norm": 0.4317072331905365,
252
+ "learning_rate": 9.386931810371742e-05,
253
+ "loss": 0.066,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.7539267015706806,
258
+ "grad_norm": 0.3598201274871826,
259
+ "learning_rate": 9.327072519588954e-05,
260
+ "loss": 0.0642,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.774869109947644,
265
+ "grad_norm": 0.39206311106681824,
266
+ "learning_rate": 9.264635036782405e-05,
267
+ "loss": 0.064,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.7958115183246073,
272
+ "grad_norm": 0.40854617953300476,
273
+ "learning_rate": 9.199656563967875e-05,
274
+ "loss": 0.0635,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.8167539267015707,
279
+ "grad_norm": 0.4052296578884125,
280
+ "learning_rate": 9.132175817154763e-05,
281
+ "loss": 0.0617,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.837696335078534,
286
+ "grad_norm": 0.5453737378120422,
287
+ "learning_rate": 9.062233003277983e-05,
288
+ "loss": 0.0612,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.8586387434554974,
293
+ "grad_norm": 0.4285629391670227,
294
+ "learning_rate": 8.989869796241559e-05,
295
+ "loss": 0.0609,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.8795811518324608,
300
+ "grad_norm": 0.42577216029167175,
301
+ "learning_rate": 8.915129312088112e-05,
302
+ "loss": 0.0634,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.900523560209424,
307
+ "grad_norm": 0.44957348704338074,
308
+ "learning_rate": 8.838056083309118e-05,
309
+ "loss": 0.0569,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.9214659685863874,
314
+ "grad_norm": 0.3643034100532532,
315
+ "learning_rate": 8.758696032311192e-05,
316
+ "loss": 0.0583,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.9424083769633508,
321
+ "grad_norm": 0.5593224167823792,
322
+ "learning_rate": 8.677096444054213e-05,
323
+ "loss": 0.0637,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.9633507853403142,
328
+ "grad_norm": 0.4963381886482239,
329
+ "learning_rate": 8.593305937877614e-05,
330
+ "loss": 0.0607,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.9842931937172775,
335
+ "grad_norm": 0.5490202307701111,
336
+ "learning_rate": 8.507374438531607e-05,
337
+ "loss": 0.0617,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 1.0052356020942408,
342
+ "grad_norm": 0.33712923526763916,
343
+ "learning_rate": 8.419353146430609e-05,
344
+ "loss": 0.0563,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 1.0261780104712042,
349
+ "grad_norm": 0.4473194181919098,
350
+ "learning_rate": 8.329294507146579e-05,
351
+ "loss": 0.0415,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 1.0471204188481675,
356
+ "grad_norm": 0.43435972929000854,
357
+ "learning_rate": 8.23725218016048e-05,
358
+ "loss": 0.0402,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 1.0471204188481675,
363
+ "eval_loss": 0.058112796396017075,
364
+ "eval_runtime": 97.7069,
365
+ "eval_samples_per_second": 4.35,
366
+ "eval_steps_per_second": 1.095,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.068062827225131,
371
+ "grad_norm": 0.41959723830223083,
372
+ "learning_rate": 8.143281006890433e-05,
373
+ "loss": 0.0388,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.0890052356020943,
378
+ "grad_norm": 0.46331778168678284,
379
+ "learning_rate": 8.047436978015649e-05,
380
+ "loss": 0.0467,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.1099476439790577,
385
+ "grad_norm": 0.4408092200756073,
386
+ "learning_rate": 7.949777200115616e-05,
387
+ "loss": 0.0414,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.130890052356021,
392
+ "grad_norm": 0.5561596751213074,
393
+ "learning_rate": 7.850359861644368e-05,
394
+ "loss": 0.0413,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.1518324607329844,
399
+ "grad_norm": 0.6036704778671265,
400
+ "learning_rate": 7.749244198260175e-05,
401
+ "loss": 0.0448,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.1727748691099475,
406
+ "grad_norm": 0.333761602640152,
407
+ "learning_rate": 7.646490457531257e-05,
408
+ "loss": 0.0379,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.193717277486911,
413
+ "grad_norm": 0.4401955306529999,
414
+ "learning_rate": 7.54215986303858e-05,
415
+ "loss": 0.0375,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.2146596858638743,
420
+ "grad_norm": 0.3552649915218353,
421
+ "learning_rate": 7.436314577897126e-05,
422
+ "loss": 0.0373,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.2356020942408377,
427
+ "grad_norm": 0.2970343828201294,
428
+ "learning_rate": 7.329017667717339e-05,
429
+ "loss": 0.042,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.256544502617801,
434
+ "grad_norm": 0.45380938053131104,
435
+ "learning_rate": 7.220333063028872e-05,
436
+ "loss": 0.0379,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.2774869109947644,
441
+ "grad_norm": 0.4114688038825989,
442
+ "learning_rate": 7.110325521188949e-05,
443
+ "loss": 0.0444,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.2984293193717278,
448
+ "grad_norm": 0.37951603531837463,
449
+ "learning_rate": 6.999060587798128e-05,
450
+ "loss": 0.0422,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.3193717277486912,
455
+ "grad_norm": 0.5121111869812012,
456
+ "learning_rate": 6.886604557646356e-05,
457
+ "loss": 0.0384,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.3403141361256545,
462
+ "grad_norm": 0.3808182179927826,
463
+ "learning_rate": 6.773024435212678e-05,
464
+ "loss": 0.0352,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.3612565445026177,
469
+ "grad_norm": 0.3297405540943146,
470
+ "learning_rate": 6.658387894742071e-05,
471
+ "loss": 0.0397,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.3821989528795813,
476
+ "grad_norm": 0.41979941725730896,
477
+ "learning_rate": 6.542763239923215e-05,
478
+ "loss": 0.0375,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.4031413612565444,
483
+ "grad_norm": 0.5469591021537781,
484
+ "learning_rate": 6.426219363191224e-05,
485
+ "loss": 0.0443,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.4240837696335078,
490
+ "grad_norm": 0.3828868865966797,
491
+ "learning_rate": 6.308825704679596e-05,
492
+ "loss": 0.0334,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.4450261780104712,
497
+ "grad_norm": 0.49810731410980225,
498
+ "learning_rate": 6.190652210845815e-05,
499
+ "loss": 0.0401,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.4659685863874345,
504
+ "grad_norm": 0.4368995130062103,
505
+ "learning_rate": 6.0717692927952744e-05,
506
+ "loss": 0.0367,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.486910994764398,
511
+ "grad_norm": 0.4042227566242218,
512
+ "learning_rate": 5.952247784328351e-05,
513
+ "loss": 0.0375,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.5078534031413613,
518
+ "grad_norm": 0.49127721786499023,
519
+ "learning_rate": 5.8321588997356326e-05,
520
+ "loss": 0.0339,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.5287958115183247,
525
+ "grad_norm": 0.3174681067466736,
526
+ "learning_rate": 5.7115741913664264e-05,
527
+ "loss": 0.0381,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.5497382198952878,
532
+ "grad_norm": 0.4839365780353546,
533
+ "learning_rate": 5.59056550699585e-05,
534
+ "loss": 0.0355,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.5706806282722514,
539
+ "grad_norm": 0.30561134219169617,
540
+ "learning_rate": 5.469204947015897e-05,
541
+ "loss": 0.0374,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.5916230366492146,
546
+ "grad_norm": 0.3758664131164551,
547
+ "learning_rate": 5.3475648214759896e-05,
548
+ "loss": 0.0327,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.6125654450261782,
553
+ "grad_norm": 0.3118516206741333,
554
+ "learning_rate": 5.2257176069986036e-05,
555
+ "loss": 0.0403,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.6335078534031413,
560
+ "grad_norm": 0.33437207341194153,
561
+ "learning_rate": 5.103735903595658e-05,
562
+ "loss": 0.0364,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.6544502617801047,
567
+ "grad_norm": 0.54002845287323,
568
+ "learning_rate": 4.981692391411366e-05,
569
+ "loss": 0.0371,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.675392670157068,
574
+ "grad_norm": 0.2974444031715393,
575
+ "learning_rate": 4.859659787417362e-05,
576
+ "loss": 0.0406,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.6963350785340314,
581
+ "grad_norm": 0.3456689417362213,
582
+ "learning_rate": 4.737710802085875e-05,
583
+ "loss": 0.0353,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.7172774869109948,
588
+ "grad_norm": 0.4571535885334015,
589
+ "learning_rate": 4.615918096066766e-05,
590
+ "loss": 0.0325,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.738219895287958,
595
+ "grad_norm": 0.3281984031200409,
596
+ "learning_rate": 4.4943542368942746e-05,
597
+ "loss": 0.0318,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.7591623036649215,
602
+ "grad_norm": 0.2916335165500641,
603
+ "learning_rate": 4.373091655749225e-05,
604
+ "loss": 0.0374,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.7801047120418847,
609
+ "grad_norm": 0.4069044888019562,
610
+ "learning_rate": 4.252202604302476e-05,
611
+ "loss": 0.0362,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.8010471204188483,
616
+ "grad_norm": 0.39771515130996704,
617
+ "learning_rate": 4.131759111665349e-05,
618
+ "loss": 0.038,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.8219895287958114,
623
+ "grad_norm": 0.38277313113212585,
624
+ "learning_rate": 4.011832941472641e-05,
625
+ "loss": 0.0393,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.8429319371727748,
630
+ "grad_norm": 0.2795620560646057,
631
+ "learning_rate": 3.8924955491238216e-05,
632
+ "loss": 0.0336,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.8638743455497382,
637
+ "grad_norm": 0.3264184594154358,
638
+ "learning_rate": 3.7738180392078937e-05,
639
+ "loss": 0.033,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.8848167539267016,
644
+ "grad_norm": 0.5280706286430359,
645
+ "learning_rate": 3.6558711231372704e-05,
646
+ "loss": 0.035,
647
+ "step": 900
648
+ },
649
+ {
650
+ "epoch": 1.905759162303665,
651
+ "grad_norm": 0.3607095181941986,
652
+ "learning_rate": 3.538725077015915e-05,
653
+ "loss": 0.0357,
654
+ "step": 910
655
+ },
656
+ {
657
+ "epoch": 1.9267015706806283,
658
+ "grad_norm": 0.3703671991825104,
659
+ "learning_rate": 3.422449699766851e-05,
660
+ "loss": 0.0313,
661
+ "step": 920
662
+ },
663
+ {
664
+ "epoch": 1.9476439790575917,
665
+ "grad_norm": 0.4830826222896576,
666
+ "learning_rate": 3.307114271543999e-05,
667
+ "loss": 0.0345,
668
+ "step": 930
669
+ },
670
+ {
671
+ "epoch": 1.9685863874345548,
672
+ "grad_norm": 0.42555513978004456,
673
+ "learning_rate": 3.192787512453105e-05,
674
+ "loss": 0.0333,
675
+ "step": 940
676
+ },
677
+ {
678
+ "epoch": 1.9895287958115184,
679
+ "grad_norm": 0.3647818863391876,
680
+ "learning_rate": 3.079537541606349e-05,
681
+ "loss": 0.0317,
682
+ "step": 950
683
+ },
684
+ {
685
+ "epoch": 2.0104712041884816,
686
+ "grad_norm": 0.27432000637054443,
687
+ "learning_rate": 2.9674318365350685e-05,
688
+ "loss": 0.0235,
689
+ "step": 960
690
+ },
691
+ {
692
+ "epoch": 2.031413612565445,
693
+ "grad_norm": 0.2879980802536011,
694
+ "learning_rate": 2.8565371929847284e-05,
695
+ "loss": 0.0158,
696
+ "step": 970
697
+ },
698
+ {
699
+ "epoch": 2.0523560209424083,
700
+ "grad_norm": 0.30074015259742737,
701
+ "learning_rate": 2.7469196851161373e-05,
702
+ "loss": 0.0179,
703
+ "step": 980
704
+ },
705
+ {
706
+ "epoch": 2.073298429319372,
707
+ "grad_norm": 0.48433229327201843,
708
+ "learning_rate": 2.638644626136587e-05,
709
+ "loss": 0.0174,
710
+ "step": 990
711
+ },
712
+ {
713
+ "epoch": 2.094240837696335,
714
+ "grad_norm": 0.3053944706916809,
715
+ "learning_rate": 2.531776529384407e-05,
716
+ "loss": 0.0204,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 2.094240837696335,
721
+ "eval_loss": 0.05247209593653679,
722
+ "eval_runtime": 97.7528,
723
+ "eval_samples_per_second": 4.348,
724
+ "eval_steps_per_second": 1.095,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.115183246073298,
729
+ "grad_norm": 0.3178795576095581,
730
+ "learning_rate": 2.426379069890098e-05,
731
+ "loss": 0.0178,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.136125654450262,
736
+ "grad_norm": 0.30507609248161316,
737
+ "learning_rate": 2.3225150464369312e-05,
738
+ "loss": 0.0145,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.157068062827225,
743
+ "grad_norm": 0.3095521330833435,
744
+ "learning_rate": 2.2202463441436884e-05,
745
+ "loss": 0.0186,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.1780104712041886,
750
+ "grad_norm": 0.40178781747817993,
751
+ "learning_rate": 2.1196338975917358e-05,
752
+ "loss": 0.0185,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.1989528795811517,
757
+ "grad_norm": 0.3371562063694,
758
+ "learning_rate": 2.0207376545184893e-05,
759
+ "loss": 0.0148,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.2198952879581153,
764
+ "grad_norm": 0.5400903820991516,
765
+ "learning_rate": 1.9236165400988638e-05,
766
+ "loss": 0.0188,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.2408376963350785,
771
+ "grad_norm": 0.1960514336824417,
772
+ "learning_rate": 1.8283284218359782e-05,
773
+ "loss": 0.0167,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.261780104712042,
778
+ "grad_norm": 0.29054176807403564,
779
+ "learning_rate": 1.734930075082076e-05,
780
+ "loss": 0.0156,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.282722513089005,
785
+ "grad_norm": 0.31542539596557617,
786
+ "learning_rate": 1.6434771492101485e-05,
787
+ "loss": 0.0168,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.303664921465969,
792
+ "grad_norm": 0.30312708020210266,
793
+ "learning_rate": 1.5540241344564915e-05,
794
+ "loss": 0.0178,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.324607329842932,
799
+ "grad_norm": 0.22572675347328186,
800
+ "learning_rate": 1.46662432945386e-05,
801
+ "loss": 0.0159,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.345549738219895,
806
+ "grad_norm": 0.32737213373184204,
807
+ "learning_rate": 1.3813298094746491e-05,
808
+ "loss": 0.0155,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.3664921465968587,
813
+ "grad_norm": 0.29300010204315186,
814
+ "learning_rate": 1.2981913954029784e-05,
815
+ "loss": 0.0158,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.387434554973822,
820
+ "grad_norm": 0.3531718850135803,
821
+ "learning_rate": 1.2172586234541644e-05,
822
+ "loss": 0.0162,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.4083769633507854,
827
+ "grad_norm": 0.3117247521877289,
828
+ "learning_rate": 1.1385797156596506e-05,
829
+ "loss": 0.0157,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.4293193717277486,
834
+ "grad_norm": 0.3147590756416321,
835
+ "learning_rate": 1.062201551134957e-05,
836
+ "loss": 0.0146,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.450261780104712,
841
+ "grad_norm": 0.3247630298137665,
842
+ "learning_rate": 9.88169638147784e-06,
843
+ "loss": 0.0143,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.4712041884816753,
848
+ "grad_norm": 0.3280116319656372,
849
+ "learning_rate": 9.16528087002892e-06,
850
+ "loss": 0.017,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.492146596858639,
855
+ "grad_norm": 0.30790087580680847,
856
+ "learning_rate": 8.473195837599418e-06,
857
+ "loss": 0.0155,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.513089005235602,
862
+ "grad_norm": 0.4461917579174042,
863
+ "learning_rate": 7.805853647999362e-06,
864
+ "loss": 0.0176,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.5340314136125652,
869
+ "grad_norm": 0.3395947515964508,
870
+ "learning_rate": 7.163651922554149e-06,
871
+ "loss": 0.0194,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.554973821989529,
876
+ "grad_norm": 0.30847620964050293,
877
+ "learning_rate": 6.5469733031905515e-06,
878
+ "loss": 0.0147,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.5759162303664924,
883
+ "grad_norm": 0.2089480310678482,
884
+ "learning_rate": 5.956185224447841e-06,
885
+ "loss": 0.0146,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.5968586387434556,
890
+ "grad_norm": 0.36750879883766174,
891
+ "learning_rate": 5.391639694549943e-06,
892
+ "loss": 0.0164,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.6178010471204187,
897
+ "grad_norm": 0.41677984595298767,
898
+ "learning_rate": 4.853673085668947e-06,
899
+ "loss": 0.0148,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.6387434554973823,
904
+ "grad_norm": 0.32629698514938354,
905
+ "learning_rate": 4.342605933505084e-06,
906
+ "loss": 0.0154,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.6596858638743455,
911
+ "grad_norm": 0.34532350301742554,
912
+ "learning_rate": 3.858742746302535e-06,
913
+ "loss": 0.0153,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.680628272251309,
918
+ "grad_norm": 0.21778731048107147,
919
+ "learning_rate": 3.402371823414774e-06,
920
+ "loss": 0.0136,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.701570680628272,
925
+ "grad_norm": 0.28639301657676697,
926
+ "learning_rate": 2.9737650835276853e-06,
927
+ "loss": 0.0137,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.7225130890052354,
932
+ "grad_norm": 0.44888314604759216,
933
+ "learning_rate": 2.573177902642726e-06,
934
+ "loss": 0.0204,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.743455497382199,
939
+ "grad_norm": 0.3165195882320404,
940
+ "learning_rate": 2.200848961916718e-06,
941
+ "loss": 0.0147,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.7643979057591626,
946
+ "grad_norm": 0.3899117112159729,
947
+ "learning_rate": 1.8570001054488362e-06,
948
+ "loss": 0.0175,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.7853403141361257,
953
+ "grad_norm": 0.2718731164932251,
954
+ "learning_rate": 1.5418362080996507e-06,
955
+ "loss": 0.0153,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.806282722513089,
960
+ "grad_norm": 0.4670896828174591,
961
+ "learning_rate": 1.2555450534208978e-06,
962
+ "loss": 0.0138,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.8272251308900525,
967
+ "grad_norm": 0.26648226380348206,
968
+ "learning_rate": 9.98297221768718e-07,
969
+ "loss": 0.0142,
970
+ "step": 1350
971
+ },
972
+ {
973
+ "epoch": 2.8481675392670156,
974
+ "grad_norm": 0.3085860311985016,
975
+ "learning_rate": 7.702459886670788e-07,
976
+ "loss": 0.0141,
977
+ "step": 1360
978
+ },
979
+ {
980
+ "epoch": 2.869109947643979,
981
+ "grad_norm": 0.46135184168815613,
982
+ "learning_rate": 5.715272334818944e-07,
983
+ "loss": 0.0162,
984
+ "step": 1370
985
+ },
986
+ {
987
+ "epoch": 2.8900523560209423,
988
+ "grad_norm": 0.3128398060798645,
989
+ "learning_rate": 4.02259358460233e-07,
990
+ "loss": 0.0159,
991
+ "step": 1380
992
+ },
993
+ {
994
+ "epoch": 2.9109947643979055,
995
+ "grad_norm": 0.44724029302597046,
996
+ "learning_rate": 2.6254321818295345e-07,
997
+ "loss": 0.0178,
998
+ "step": 1390
999
+ },
1000
+ {
1001
+ "epoch": 2.931937172774869,
1002
+ "grad_norm": 0.35600796341896057,
1003
+ "learning_rate": 1.5246205947265779e-07,
1004
+ "loss": 0.0151,
1005
+ "step": 1400
1006
+ },
1007
+ {
1008
+ "epoch": 2.9528795811518327,
1009
+ "grad_norm": 0.2872493863105774,
1010
+ "learning_rate": 7.208147179291192e-08,
1011
+ "loss": 0.0156,
1012
+ "step": 1410
1013
+ },
1014
+ {
1015
+ "epoch": 2.973821989528796,
1016
+ "grad_norm": 0.27174440026283264,
1017
+ "learning_rate": 2.1449348168167682e-08,
1018
+ "loss": 0.0162,
1019
+ "step": 1420
1020
+ },
1021
+ {
1022
+ "epoch": 2.994764397905759,
1023
+ "grad_norm": 0.42477887868881226,
1024
+ "learning_rate": 5.95856647772619e-10,
1025
+ "loss": 0.0136,
1026
+ "step": 1430
1027
+ },
1028
+ {
1029
+ "epoch": 2.9968586387434555,
1030
+ "step": 1431,
1031
+ "total_flos": 1.717501382279299e+18,
1032
+ "train_loss": 0.0491406895828145,
1033
+ "train_runtime": 12322.0896,
1034
+ "train_samples_per_second": 0.93,
1035
+ "train_steps_per_second": 0.116
1036
+ }
1037
+ ],
1038
+ "logging_steps": 10,
1039
+ "max_steps": 1431,
1040
+ "num_input_tokens_seen": 0,
1041
+ "num_train_epochs": 3,
1042
+ "save_steps": 500,
1043
+ "stateful_callbacks": {
1044
+ "TrainerControl": {
1045
+ "args": {
1046
+ "should_epoch_stop": false,
1047
+ "should_evaluate": false,
1048
+ "should_log": false,
1049
+ "should_save": true,
1050
+ "should_training_stop": true
1051
+ },
1052
+ "attributes": {}
1053
+ }
1054
+ },
1055
+ "total_flos": 1.717501382279299e+18,
1056
+ "train_batch_size": 1,
1057
+ "trial_name": null,
1058
+ "trial_params": null
1059
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:daccc80b18eb9d7799bde94f4978ce1c3db384a0b077499322436ae29d6d2f44
3
+ size 5496
training_eval_loss.png ADDED
training_loss.png ADDED