sam2ai commited on
Commit
a7cf583
·
verified ·
1 Parent(s): 1c88fb1

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: OdiaGenAI-LLM/llama_3_8b_odia_pt
3
+ library_name: peft
4
+ license: other
5
+ tags:
6
+ - llama-factory
7
+ - lora
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/sambitsekharai/huggingface/runs/v5hy5x4t)
18
+ # sft
19
+
20
+ This model is a fine-tuned version of [OdiaGenAI-LLM/llama_3_8b_odia_pt](https://huggingface.co/OdiaGenAI-LLM/llama_3_8b_odia_pt) on the odia_sft dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.3962
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 0.0001
42
+ - train_batch_size: 2
43
+ - eval_batch_size: 1
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 8
46
+ - total_train_batch_size: 16
47
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 10.0
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.1145 | 8.8889 | 500 | 0.3873 |
57
+
58
+
59
+ ### Framework versions
60
+
61
+ - PEFT 0.11.1
62
+ - Transformers 4.42.3
63
+ - Pytorch 2.3.1+rocm6.0
64
+ - Datasets 2.20.0
65
+ - 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": "OdiaGenAI-LLM/llama_3_8b_odia_pt",
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
+ "down_proj",
24
+ "up_proj",
25
+ "k_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "o_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 sha256:7755f3281134f8bf1a862da826b309934503ff9270d29a7a522900287e073ad8
3
+ size 83945296
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.955555555555556,
3
+ "eval_loss": 0.39617523550987244,
4
+ "eval_runtime": 44.4947,
5
+ "eval_samples_per_second": 2.247,
6
+ "eval_steps_per_second": 2.247,
7
+ "total_flos": 9.116617776876749e+17,
8
+ "train_loss": 0.2247792588014688,
9
+ "train_runtime": 17934.4708,
10
+ "train_samples_per_second": 0.502,
11
+ "train_steps_per_second": 0.031
12
+ }
checkpoint-500/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: OdiaGenAI-LLM/llama_3_8b_odia_pt
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 0.11.1
checkpoint-500/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "OdiaGenAI-LLM/llama_3_8b_odia_pt",
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
+ "down_proj",
24
+ "up_proj",
25
+ "k_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "o_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-500/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e50540424814e7c567d1aabdeab4e7c50dde8ff9b816f5cbb3d1b813200ef66d
3
+ size 83945296
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12206bf357b2c0ed243255542c95b677f6c4368b0251f184aac5ee605af26ea
3
+ size 168149074
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
3
+ size 14244
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f768249205f00f63008d98fcbae06acf00fff23c306eaaa8861925b1f5b07444
3
+ size 1064
checkpoint-500/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
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 system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in 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": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,3541 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.88888888888889,
5
+ "eval_steps": 500,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.017777777777777778,
13
+ "grad_norm": 1.7422537803649902,
14
+ "learning_rate": 1.7857142857142857e-06,
15
+ "loss": 0.7247,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.035555555555555556,
20
+ "grad_norm": 1.5862261056900024,
21
+ "learning_rate": 3.5714285714285714e-06,
22
+ "loss": 0.6432,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.05333333333333334,
27
+ "grad_norm": 1.3740944862365723,
28
+ "learning_rate": 5.357142857142857e-06,
29
+ "loss": 0.6158,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.07111111111111111,
34
+ "grad_norm": 1.5012167692184448,
35
+ "learning_rate": 7.142857142857143e-06,
36
+ "loss": 0.6322,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.08888888888888889,
41
+ "grad_norm": 1.4912959337234497,
42
+ "learning_rate": 8.92857142857143e-06,
43
+ "loss": 0.5955,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.10666666666666667,
48
+ "grad_norm": 1.462948203086853,
49
+ "learning_rate": 1.0714285714285714e-05,
50
+ "loss": 0.6794,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.12444444444444444,
55
+ "grad_norm": 1.226659893989563,
56
+ "learning_rate": 1.25e-05,
57
+ "loss": 0.5716,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.14222222222222222,
62
+ "grad_norm": 1.1903551816940308,
63
+ "learning_rate": 1.4285714285714285e-05,
64
+ "loss": 0.6785,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.16,
69
+ "grad_norm": 1.4021542072296143,
70
+ "learning_rate": 1.6071428571428572e-05,
71
+ "loss": 0.5768,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.17777777777777778,
76
+ "grad_norm": 1.4458407163619995,
77
+ "learning_rate": 1.785714285714286e-05,
78
+ "loss": 0.653,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.19555555555555557,
83
+ "grad_norm": 1.669067144393921,
84
+ "learning_rate": 1.9642857142857145e-05,
85
+ "loss": 0.608,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.21333333333333335,
90
+ "grad_norm": 1.5338914394378662,
91
+ "learning_rate": 2.1428571428571428e-05,
92
+ "loss": 0.6273,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.2311111111111111,
97
+ "grad_norm": 1.299443006515503,
98
+ "learning_rate": 2.3214285714285715e-05,
99
+ "loss": 0.5894,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.24888888888888888,
104
+ "grad_norm": 1.3132046461105347,
105
+ "learning_rate": 2.5e-05,
106
+ "loss": 0.6952,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.26666666666666666,
111
+ "grad_norm": 1.780645728111267,
112
+ "learning_rate": 2.6785714285714288e-05,
113
+ "loss": 0.695,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.28444444444444444,
118
+ "grad_norm": 1.391330361366272,
119
+ "learning_rate": 2.857142857142857e-05,
120
+ "loss": 0.5933,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.3022222222222222,
125
+ "grad_norm": 1.3170968294143677,
126
+ "learning_rate": 3.0357142857142857e-05,
127
+ "loss": 0.5422,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.32,
132
+ "grad_norm": 1.0980342626571655,
133
+ "learning_rate": 3.2142857142857144e-05,
134
+ "loss": 0.5283,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.3377777777777778,
139
+ "grad_norm": 1.122798204421997,
140
+ "learning_rate": 3.392857142857143e-05,
141
+ "loss": 0.5295,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.35555555555555557,
146
+ "grad_norm": 1.741687297821045,
147
+ "learning_rate": 3.571428571428572e-05,
148
+ "loss": 0.4891,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.37333333333333335,
153
+ "grad_norm": 1.3390421867370605,
154
+ "learning_rate": 3.7500000000000003e-05,
155
+ "loss": 0.5169,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.39111111111111113,
160
+ "grad_norm": 1.5962032079696655,
161
+ "learning_rate": 3.928571428571429e-05,
162
+ "loss": 0.5211,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.4088888888888889,
167
+ "grad_norm": 1.4163485765457153,
168
+ "learning_rate": 4.107142857142857e-05,
169
+ "loss": 0.4661,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.4266666666666667,
174
+ "grad_norm": 1.2807841300964355,
175
+ "learning_rate": 4.2857142857142856e-05,
176
+ "loss": 0.4794,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.4444444444444444,
181
+ "grad_norm": 1.7780894041061401,
182
+ "learning_rate": 4.464285714285715e-05,
183
+ "loss": 0.4965,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.4622222222222222,
188
+ "grad_norm": 3.661797285079956,
189
+ "learning_rate": 4.642857142857143e-05,
190
+ "loss": 0.8358,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.48,
195
+ "grad_norm": 1.6696407794952393,
196
+ "learning_rate": 4.8214285714285716e-05,
197
+ "loss": 0.4957,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.49777777777777776,
202
+ "grad_norm": 1.1838289499282837,
203
+ "learning_rate": 5e-05,
204
+ "loss": 0.5393,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.5155555555555555,
209
+ "grad_norm": 1.532225489616394,
210
+ "learning_rate": 5.1785714285714296e-05,
211
+ "loss": 0.5784,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.5333333333333333,
216
+ "grad_norm": 2.2218728065490723,
217
+ "learning_rate": 5.3571428571428575e-05,
218
+ "loss": 0.4446,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.5511111111111111,
223
+ "grad_norm": 1.4392008781433105,
224
+ "learning_rate": 5.535714285714286e-05,
225
+ "loss": 0.3995,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.5688888888888889,
230
+ "grad_norm": 0.8953332901000977,
231
+ "learning_rate": 5.714285714285714e-05,
232
+ "loss": 0.3399,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.5866666666666667,
237
+ "grad_norm": 1.1794021129608154,
238
+ "learning_rate": 5.8928571428571435e-05,
239
+ "loss": 0.3983,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.6044444444444445,
244
+ "grad_norm": 0.9146949052810669,
245
+ "learning_rate": 6.0714285714285715e-05,
246
+ "loss": 0.3831,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.6222222222222222,
251
+ "grad_norm": 0.4634794294834137,
252
+ "learning_rate": 6.25e-05,
253
+ "loss": 0.3359,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.64,
258
+ "grad_norm": 0.5568346977233887,
259
+ "learning_rate": 6.428571428571429e-05,
260
+ "loss": 0.3597,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.6577777777777778,
265
+ "grad_norm": 0.6084932684898376,
266
+ "learning_rate": 6.607142857142857e-05,
267
+ "loss": 0.4061,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.6755555555555556,
272
+ "grad_norm": 0.6706041693687439,
273
+ "learning_rate": 6.785714285714286e-05,
274
+ "loss": 0.3533,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.6933333333333334,
279
+ "grad_norm": 0.9489718079566956,
280
+ "learning_rate": 6.964285714285715e-05,
281
+ "loss": 0.3598,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.7111111111111111,
286
+ "grad_norm": 1.2667860984802246,
287
+ "learning_rate": 7.142857142857143e-05,
288
+ "loss": 0.3796,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.7288888888888889,
293
+ "grad_norm": 1.1869858503341675,
294
+ "learning_rate": 7.321428571428571e-05,
295
+ "loss": 0.4386,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.7466666666666667,
300
+ "grad_norm": 0.5942434668540955,
301
+ "learning_rate": 7.500000000000001e-05,
302
+ "loss": 0.3265,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.7644444444444445,
307
+ "grad_norm": 0.7414906620979309,
308
+ "learning_rate": 7.67857142857143e-05,
309
+ "loss": 0.3344,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.7822222222222223,
314
+ "grad_norm": 0.6775667071342468,
315
+ "learning_rate": 7.857142857142858e-05,
316
+ "loss": 0.3514,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.8,
321
+ "grad_norm": 0.5995815992355347,
322
+ "learning_rate": 8.035714285714287e-05,
323
+ "loss": 0.3258,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.8177777777777778,
328
+ "grad_norm": 0.42830514907836914,
329
+ "learning_rate": 8.214285714285714e-05,
330
+ "loss": 0.3228,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.8355555555555556,
335
+ "grad_norm": 0.5796249508857727,
336
+ "learning_rate": 8.392857142857144e-05,
337
+ "loss": 0.3752,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.8533333333333334,
342
+ "grad_norm": 0.5575869083404541,
343
+ "learning_rate": 8.571428571428571e-05,
344
+ "loss": 0.3656,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.8711111111111111,
349
+ "grad_norm": 0.3702499270439148,
350
+ "learning_rate": 8.75e-05,
351
+ "loss": 0.3254,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.8888888888888888,
356
+ "grad_norm": 0.3036387860774994,
357
+ "learning_rate": 8.92857142857143e-05,
358
+ "loss": 0.2911,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.9066666666666666,
363
+ "grad_norm": 0.6176546216011047,
364
+ "learning_rate": 9.107142857142857e-05,
365
+ "loss": 0.3641,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.9244444444444444,
370
+ "grad_norm": 0.46132686734199524,
371
+ "learning_rate": 9.285714285714286e-05,
372
+ "loss": 0.3164,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.9422222222222222,
377
+ "grad_norm": 0.42897599935531616,
378
+ "learning_rate": 9.464285714285715e-05,
379
+ "loss": 0.3216,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.96,
384
+ "grad_norm": 1.1321483850479126,
385
+ "learning_rate": 9.642857142857143e-05,
386
+ "loss": 0.4645,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.9777777777777777,
391
+ "grad_norm": 0.345939576625824,
392
+ "learning_rate": 9.821428571428572e-05,
393
+ "loss": 0.341,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.9955555555555555,
398
+ "grad_norm": 0.2705654203891754,
399
+ "learning_rate": 0.0001,
400
+ "loss": 0.3029,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 1.0133333333333334,
405
+ "grad_norm": 0.38632267713546753,
406
+ "learning_rate": 9.999902864657691e-05,
407
+ "loss": 0.3005,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 1.031111111111111,
412
+ "grad_norm": 0.3401973247528076,
413
+ "learning_rate": 9.999611462404875e-05,
414
+ "loss": 0.3182,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 1.048888888888889,
419
+ "grad_norm": 1.9517568349838257,
420
+ "learning_rate": 9.999125804563732e-05,
421
+ "loss": 0.4438,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 1.0666666666666667,
426
+ "grad_norm": 0.3414149582386017,
427
+ "learning_rate": 9.998445910004082e-05,
428
+ "loss": 0.3115,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 1.0844444444444445,
433
+ "grad_norm": 0.655548095703125,
434
+ "learning_rate": 9.997571805142639e-05,
435
+ "loss": 0.4094,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 1.1022222222222222,
440
+ "grad_norm": 0.49635574221611023,
441
+ "learning_rate": 9.996503523941994e-05,
442
+ "loss": 0.3135,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 1.12,
447
+ "grad_norm": 0.34827786684036255,
448
+ "learning_rate": 9.99524110790929e-05,
449
+ "loss": 0.2901,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 1.1377777777777778,
454
+ "grad_norm": 0.4313528835773468,
455
+ "learning_rate": 9.993784606094612e-05,
456
+ "loss": 0.3178,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 1.1555555555555554,
461
+ "grad_norm": 0.5291451215744019,
462
+ "learning_rate": 9.992134075089084e-05,
463
+ "loss": 0.3534,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 1.1733333333333333,
468
+ "grad_norm": 0.4702828526496887,
469
+ "learning_rate": 9.99028957902266e-05,
470
+ "loss": 0.3155,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 1.1911111111111112,
475
+ "grad_norm": 0.5662183165550232,
476
+ "learning_rate": 9.988251189561645e-05,
477
+ "loss": 0.3555,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 1.208888888888889,
482
+ "grad_norm": 0.3226587772369385,
483
+ "learning_rate": 9.986018985905901e-05,
484
+ "loss": 0.33,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 1.2266666666666666,
489
+ "grad_norm": 0.7809450030326843,
490
+ "learning_rate": 9.983593054785776e-05,
491
+ "loss": 0.3499,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 1.2444444444444445,
496
+ "grad_norm": 0.6240183115005493,
497
+ "learning_rate": 9.980973490458728e-05,
498
+ "loss": 0.353,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 1.2622222222222224,
503
+ "grad_norm": 0.34356218576431274,
504
+ "learning_rate": 9.978160394705668e-05,
505
+ "loss": 0.2993,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 1.28,
510
+ "grad_norm": 0.33020302653312683,
511
+ "learning_rate": 9.975153876827008e-05,
512
+ "loss": 0.3122,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 1.2977777777777777,
517
+ "grad_norm": 0.4314161241054535,
518
+ "learning_rate": 9.971954053638399e-05,
519
+ "loss": 0.3258,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 1.3155555555555556,
524
+ "grad_norm": 0.5286882519721985,
525
+ "learning_rate": 9.968561049466214e-05,
526
+ "loss": 0.3835,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 1.3333333333333333,
531
+ "grad_norm": 0.2787860929965973,
532
+ "learning_rate": 9.964974996142698e-05,
533
+ "loss": 0.2817,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 1.3511111111111112,
538
+ "grad_norm": 0.29439663887023926,
539
+ "learning_rate": 9.961196033000861e-05,
540
+ "loss": 0.2828,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 1.3688888888888888,
545
+ "grad_norm": 0.27987906336784363,
546
+ "learning_rate": 9.957224306869053e-05,
547
+ "loss": 0.3253,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 1.3866666666666667,
552
+ "grad_norm": 0.3439163863658905,
553
+ "learning_rate": 9.953059972065265e-05,
554
+ "loss": 0.3215,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 1.4044444444444444,
559
+ "grad_norm": 0.32061126828193665,
560
+ "learning_rate": 9.948703190391131e-05,
561
+ "loss": 0.323,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 1.4222222222222223,
566
+ "grad_norm": 0.4793407917022705,
567
+ "learning_rate": 9.944154131125642e-05,
568
+ "loss": 0.2962,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 1.44,
573
+ "grad_norm": 0.2514803111553192,
574
+ "learning_rate": 9.939412971018574e-05,
575
+ "loss": 0.314,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 1.4577777777777778,
580
+ "grad_norm": 0.4879082143306732,
581
+ "learning_rate": 9.934479894283606e-05,
582
+ "loss": 0.2828,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 1.4755555555555555,
587
+ "grad_norm": 0.41817083954811096,
588
+ "learning_rate": 9.92935509259118e-05,
589
+ "loss": 0.3124,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 1.4933333333333334,
594
+ "grad_norm": 0.3143192529678345,
595
+ "learning_rate": 9.924038765061042e-05,
596
+ "loss": 0.2861,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 1.511111111111111,
601
+ "grad_norm": 0.33786436915397644,
602
+ "learning_rate": 9.918531118254507e-05,
603
+ "loss": 0.286,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 1.528888888888889,
608
+ "grad_norm": 0.3116290867328644,
609
+ "learning_rate": 9.912832366166442e-05,
610
+ "loss": 0.307,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 1.5466666666666666,
615
+ "grad_norm": 0.5235384106636047,
616
+ "learning_rate": 9.906942730216939e-05,
617
+ "loss": 0.3053,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 1.5644444444444443,
622
+ "grad_norm": 0.3879358172416687,
623
+ "learning_rate": 9.900862439242719e-05,
624
+ "loss": 0.3108,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 1.5822222222222222,
629
+ "grad_norm": 0.4028690755367279,
630
+ "learning_rate": 9.894591729488242e-05,
631
+ "loss": 0.3178,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 1.6,
636
+ "grad_norm": 0.3827480375766754,
637
+ "learning_rate": 9.888130844596524e-05,
638
+ "loss": 0.303,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 1.6177777777777778,
643
+ "grad_norm": 0.48203060030937195,
644
+ "learning_rate": 9.881480035599667e-05,
645
+ "loss": 0.3503,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 1.6355555555555554,
650
+ "grad_norm": 0.30467236042022705,
651
+ "learning_rate": 9.874639560909117e-05,
652
+ "loss": 0.2876,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 1.6533333333333333,
657
+ "grad_norm": 0.4495410621166229,
658
+ "learning_rate": 9.867609686305617e-05,
659
+ "loss": 0.2937,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 1.6711111111111112,
664
+ "grad_norm": 0.29854950308799744,
665
+ "learning_rate": 9.860390684928873e-05,
666
+ "loss": 0.3155,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 1.6888888888888889,
671
+ "grad_norm": 0.4602304995059967,
672
+ "learning_rate": 9.852982837266955e-05,
673
+ "loss": 0.276,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 1.7066666666666666,
678
+ "grad_norm": 0.34135401248931885,
679
+ "learning_rate": 9.84538643114539e-05,
680
+ "loss": 0.2831,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 1.7244444444444444,
685
+ "grad_norm": 0.26776087284088135,
686
+ "learning_rate": 9.837601761715983e-05,
687
+ "loss": 0.2964,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 1.7422222222222223,
692
+ "grad_norm": 0.3476792573928833,
693
+ "learning_rate": 9.829629131445342e-05,
694
+ "loss": 0.2814,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 1.76,
699
+ "grad_norm": 0.2479284703731537,
700
+ "learning_rate": 9.82146885010314e-05,
701
+ "loss": 0.2806,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 1.7777777777777777,
706
+ "grad_norm": 0.32680875062942505,
707
+ "learning_rate": 9.81312123475006e-05,
708
+ "loss": 0.3065,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 1.7955555555555556,
713
+ "grad_norm": 0.28494346141815186,
714
+ "learning_rate": 9.804586609725499e-05,
715
+ "loss": 0.311,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 1.8133333333333335,
720
+ "grad_norm": 0.444627583026886,
721
+ "learning_rate": 9.79586530663494e-05,
722
+ "loss": 0.3003,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 1.8311111111111111,
727
+ "grad_norm": 0.35969412326812744,
728
+ "learning_rate": 9.78695766433709e-05,
729
+ "loss": 0.2727,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 1.8488888888888888,
734
+ "grad_norm": 0.378616064786911,
735
+ "learning_rate": 9.777864028930705e-05,
736
+ "loss": 0.2834,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 1.8666666666666667,
741
+ "grad_norm": 0.2953629493713379,
742
+ "learning_rate": 9.768584753741134e-05,
743
+ "loss": 0.2806,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 1.8844444444444446,
748
+ "grad_norm": 0.44163236021995544,
749
+ "learning_rate": 9.759120199306613e-05,
750
+ "loss": 0.2951,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 1.9022222222222223,
755
+ "grad_norm": 0.26908189058303833,
756
+ "learning_rate": 9.74947073336423e-05,
757
+ "loss": 0.2975,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 1.92,
762
+ "grad_norm": 0.2417159080505371,
763
+ "learning_rate": 9.73963673083566e-05,
764
+ "loss": 0.2677,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 1.9377777777777778,
769
+ "grad_norm": 0.3327369689941406,
770
+ "learning_rate": 9.72961857381258e-05,
771
+ "loss": 0.3219,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 1.9555555555555557,
776
+ "grad_norm": 0.27677884697914124,
777
+ "learning_rate": 9.719416651541839e-05,
778
+ "loss": 0.2631,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 1.9733333333333334,
783
+ "grad_norm": 0.41239938139915466,
784
+ "learning_rate": 9.709031360410318e-05,
785
+ "loss": 0.2788,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 1.991111111111111,
790
+ "grad_norm": 0.28369349241256714,
791
+ "learning_rate": 9.698463103929542e-05,
792
+ "loss": 0.2723,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 2.008888888888889,
797
+ "grad_norm": 0.3098125457763672,
798
+ "learning_rate": 9.687712292719997e-05,
799
+ "loss": 0.3279,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 2.026666666666667,
804
+ "grad_norm": 0.35817790031433105,
805
+ "learning_rate": 9.67677934449517e-05,
806
+ "loss": 0.2708,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 2.0444444444444443,
811
+ "grad_norm": 0.32206666469573975,
812
+ "learning_rate": 9.665664684045333e-05,
813
+ "loss": 0.2801,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 2.062222222222222,
818
+ "grad_norm": 0.2292087823152542,
819
+ "learning_rate": 9.654368743221022e-05,
820
+ "loss": 0.218,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 2.08,
825
+ "grad_norm": 0.30288153886795044,
826
+ "learning_rate": 9.642891960916268e-05,
827
+ "loss": 0.2865,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 2.097777777777778,
832
+ "grad_norm": 0.33361321687698364,
833
+ "learning_rate": 9.631234783051544e-05,
834
+ "loss": 0.2866,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 2.1155555555555554,
839
+ "grad_norm": 0.2744784951210022,
840
+ "learning_rate": 9.619397662556435e-05,
841
+ "loss": 0.2776,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 2.1333333333333333,
846
+ "grad_norm": 0.29272395372390747,
847
+ "learning_rate": 9.607381059352038e-05,
848
+ "loss": 0.2655,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 2.151111111111111,
853
+ "grad_norm": 1.0778076648712158,
854
+ "learning_rate": 9.595185440333103e-05,
855
+ "loss": 0.3282,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 2.168888888888889,
860
+ "grad_norm": 0.48110413551330566,
861
+ "learning_rate": 9.582811279349882e-05,
862
+ "loss": 0.3087,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 2.1866666666666665,
867
+ "grad_norm": 0.28637051582336426,
868
+ "learning_rate": 9.570259057189717e-05,
869
+ "loss": 0.2924,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 2.2044444444444444,
874
+ "grad_norm": 0.27911806106567383,
875
+ "learning_rate": 9.557529261558367e-05,
876
+ "loss": 0.2613,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 2.2222222222222223,
881
+ "grad_norm": 0.34397801756858826,
882
+ "learning_rate": 9.544622387061055e-05,
883
+ "loss": 0.2574,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 2.24,
888
+ "grad_norm": 0.2947402000427246,
889
+ "learning_rate": 9.53153893518325e-05,
890
+ "loss": 0.2883,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 2.2577777777777777,
895
+ "grad_norm": 0.39530470967292786,
896
+ "learning_rate": 9.518279414271183e-05,
897
+ "loss": 0.3131,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 2.2755555555555556,
902
+ "grad_norm": 0.24501116573810577,
903
+ "learning_rate": 9.504844339512095e-05,
904
+ "loss": 0.3184,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 2.2933333333333334,
909
+ "grad_norm": 0.25899410247802734,
910
+ "learning_rate": 9.491234232914221e-05,
911
+ "loss": 0.2794,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 2.311111111111111,
916
+ "grad_norm": 0.41601303219795227,
917
+ "learning_rate": 9.477449623286505e-05,
918
+ "loss": 0.2884,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 2.328888888888889,
923
+ "grad_norm": 0.3597092628479004,
924
+ "learning_rate": 9.463491046218058e-05,
925
+ "loss": 0.2655,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 2.3466666666666667,
930
+ "grad_norm": 0.361904501914978,
931
+ "learning_rate": 9.449359044057345e-05,
932
+ "loss": 0.2611,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 2.3644444444444446,
937
+ "grad_norm": 0.4677833020687103,
938
+ "learning_rate": 9.435054165891109e-05,
939
+ "loss": 0.2589,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 2.3822222222222225,
944
+ "grad_norm": 0.5052748918533325,
945
+ "learning_rate": 9.420576967523049e-05,
946
+ "loss": 0.3022,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 2.4,
951
+ "grad_norm": 0.2593027651309967,
952
+ "learning_rate": 9.405928011452211e-05,
953
+ "loss": 0.2498,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 2.417777777777778,
958
+ "grad_norm": 0.2840777337551117,
959
+ "learning_rate": 9.391107866851143e-05,
960
+ "loss": 0.2636,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 2.4355555555555557,
965
+ "grad_norm": 0.3062927722930908,
966
+ "learning_rate": 9.376117109543769e-05,
967
+ "loss": 0.25,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 2.453333333333333,
972
+ "grad_norm": 0.31112948060035706,
973
+ "learning_rate": 9.360956321983028e-05,
974
+ "loss": 0.2435,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 2.471111111111111,
979
+ "grad_norm": 0.4025621712207794,
980
+ "learning_rate": 9.345626093228233e-05,
981
+ "loss": 0.2427,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 2.488888888888889,
986
+ "grad_norm": 0.39693212509155273,
987
+ "learning_rate": 9.330127018922194e-05,
988
+ "loss": 0.2897,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 2.506666666666667,
993
+ "grad_norm": 0.30706965923309326,
994
+ "learning_rate": 9.314459701268065e-05,
995
+ "loss": 0.2833,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 2.5244444444444447,
1000
+ "grad_norm": 0.45809707045555115,
1001
+ "learning_rate": 9.298624749005951e-05,
1002
+ "loss": 0.2698,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 2.542222222222222,
1007
+ "grad_norm": 0.295108824968338,
1008
+ "learning_rate": 9.282622777389258e-05,
1009
+ "loss": 0.2372,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 2.56,
1014
+ "grad_norm": 0.35757213830947876,
1015
+ "learning_rate": 9.266454408160779e-05,
1016
+ "loss": 0.2756,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 2.5777777777777775,
1021
+ "grad_norm": 0.2958184778690338,
1022
+ "learning_rate": 9.250120269528546e-05,
1023
+ "loss": 0.2661,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 2.5955555555555554,
1028
+ "grad_norm": 0.36897847056388855,
1029
+ "learning_rate": 9.233620996141421e-05,
1030
+ "loss": 0.2945,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 2.6133333333333333,
1035
+ "grad_norm": 0.2986817955970764,
1036
+ "learning_rate": 9.21695722906443e-05,
1037
+ "loss": 0.2391,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 2.631111111111111,
1042
+ "grad_norm": 0.28577160835266113,
1043
+ "learning_rate": 9.200129615753859e-05,
1044
+ "loss": 0.2664,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 2.648888888888889,
1049
+ "grad_norm": 0.363800585269928,
1050
+ "learning_rate": 9.183138810032099e-05,
1051
+ "loss": 0.2371,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 2.6666666666666665,
1056
+ "grad_norm": 0.34674468636512756,
1057
+ "learning_rate": 9.165985472062246e-05,
1058
+ "loss": 0.2883,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 2.6844444444444444,
1063
+ "grad_norm": 0.35801827907562256,
1064
+ "learning_rate": 9.148670268322438e-05,
1065
+ "loss": 0.2572,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 2.7022222222222223,
1070
+ "grad_norm": 0.24792705476284027,
1071
+ "learning_rate": 9.131193871579975e-05,
1072
+ "loss": 0.2423,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 2.7199999999999998,
1077
+ "grad_norm": 0.31966882944107056,
1078
+ "learning_rate": 9.113556960865167e-05,
1079
+ "loss": 0.2453,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 2.7377777777777776,
1084
+ "grad_norm": 0.27944958209991455,
1085
+ "learning_rate": 9.09576022144496e-05,
1086
+ "loss": 0.2297,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 2.7555555555555555,
1091
+ "grad_norm": 0.34474286437034607,
1092
+ "learning_rate": 9.077804344796302e-05,
1093
+ "loss": 0.2865,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 2.7733333333333334,
1098
+ "grad_norm": 0.36895522475242615,
1099
+ "learning_rate": 9.059690028579284e-05,
1100
+ "loss": 0.2567,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 2.7911111111111113,
1105
+ "grad_norm": 0.26620030403137207,
1106
+ "learning_rate": 9.041417976610027e-05,
1107
+ "loss": 0.2537,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 2.8088888888888888,
1112
+ "grad_norm": 0.24772542715072632,
1113
+ "learning_rate": 9.022988898833342e-05,
1114
+ "loss": 0.2212,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 2.8266666666666667,
1119
+ "grad_norm": 0.3265734016895294,
1120
+ "learning_rate": 9.004403511295141e-05,
1121
+ "loss": 0.2514,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 2.8444444444444446,
1126
+ "grad_norm": 0.44243156909942627,
1127
+ "learning_rate": 8.985662536114613e-05,
1128
+ "loss": 0.2857,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 2.862222222222222,
1133
+ "grad_norm": 0.27827122807502747,
1134
+ "learning_rate": 8.966766701456177e-05,
1135
+ "loss": 0.2507,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 2.88,
1140
+ "grad_norm": 0.47080013155937195,
1141
+ "learning_rate": 8.947716741501177e-05,
1142
+ "loss": 0.2875,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 2.897777777777778,
1147
+ "grad_norm": 0.37070050835609436,
1148
+ "learning_rate": 8.928513396419368e-05,
1149
+ "loss": 0.2601,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 2.9155555555555557,
1154
+ "grad_norm": 0.3937135338783264,
1155
+ "learning_rate": 8.90915741234015e-05,
1156
+ "loss": 0.2624,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 2.9333333333333336,
1161
+ "grad_norm": 0.3232908844947815,
1162
+ "learning_rate": 8.889649541323574e-05,
1163
+ "loss": 0.2578,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 2.951111111111111,
1168
+ "grad_norm": 0.29915979504585266,
1169
+ "learning_rate": 8.869990541331138e-05,
1170
+ "loss": 0.2354,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 2.968888888888889,
1175
+ "grad_norm": 0.4688418209552765,
1176
+ "learning_rate": 8.850181176196315e-05,
1177
+ "loss": 0.3058,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 2.986666666666667,
1182
+ "grad_norm": 0.21794776618480682,
1183
+ "learning_rate": 8.83022221559489e-05,
1184
+ "loss": 0.2424,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 3.0044444444444443,
1189
+ "grad_norm": 0.20859044790267944,
1190
+ "learning_rate": 8.810114435015054e-05,
1191
+ "loss": 0.2527,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 3.022222222222222,
1196
+ "grad_norm": 0.329470157623291,
1197
+ "learning_rate": 8.789858615727265e-05,
1198
+ "loss": 0.2644,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 3.04,
1203
+ "grad_norm": 0.2836751341819763,
1204
+ "learning_rate": 8.7694555447539e-05,
1205
+ "loss": 0.2419,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 3.057777777777778,
1210
+ "grad_norm": 0.2949230968952179,
1211
+ "learning_rate": 8.748906014838672e-05,
1212
+ "loss": 0.2201,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 3.0755555555555554,
1217
+ "grad_norm": 0.4008142054080963,
1218
+ "learning_rate": 8.728210824415827e-05,
1219
+ "loss": 0.2479,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 3.0933333333333333,
1224
+ "grad_norm": 0.25974419713020325,
1225
+ "learning_rate": 8.707370777579133e-05,
1226
+ "loss": 0.2311,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 3.111111111111111,
1231
+ "grad_norm": 0.2546006143093109,
1232
+ "learning_rate": 8.68638668405062e-05,
1233
+ "loss": 0.2239,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 3.128888888888889,
1238
+ "grad_norm": 0.5272888541221619,
1239
+ "learning_rate": 8.665259359149132e-05,
1240
+ "loss": 0.2798,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 3.1466666666666665,
1245
+ "grad_norm": 0.4749833047389984,
1246
+ "learning_rate": 8.643989623758643e-05,
1247
+ "loss": 0.2376,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 3.1644444444444444,
1252
+ "grad_norm": 0.3421812653541565,
1253
+ "learning_rate": 8.622578304296364e-05,
1254
+ "loss": 0.2672,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 3.1822222222222223,
1259
+ "grad_norm": 0.3668532073497772,
1260
+ "learning_rate": 8.601026232680634e-05,
1261
+ "loss": 0.2463,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 3.2,
1266
+ "grad_norm": 0.2934477925300598,
1267
+ "learning_rate": 8.579334246298593e-05,
1268
+ "loss": 0.2367,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 3.2177777777777776,
1273
+ "grad_norm": 0.26318293809890747,
1274
+ "learning_rate": 8.557503187973651e-05,
1275
+ "loss": 0.2362,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 3.2355555555555555,
1280
+ "grad_norm": 0.3571169972419739,
1281
+ "learning_rate": 8.535533905932738e-05,
1282
+ "loss": 0.2331,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 3.2533333333333334,
1287
+ "grad_norm": 0.39406391978263855,
1288
+ "learning_rate": 8.513427253773346e-05,
1289
+ "loss": 0.2775,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 3.2711111111111113,
1294
+ "grad_norm": 0.39618298411369324,
1295
+ "learning_rate": 8.491184090430364e-05,
1296
+ "loss": 0.2239,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 3.2888888888888888,
1301
+ "grad_norm": 0.30980485677719116,
1302
+ "learning_rate": 8.468805280142709e-05,
1303
+ "loss": 0.2395,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 3.3066666666666666,
1308
+ "grad_norm": 0.3459194004535675,
1309
+ "learning_rate": 8.446291692419736e-05,
1310
+ "loss": 0.2222,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 3.3244444444444445,
1315
+ "grad_norm": 0.2490205019712448,
1316
+ "learning_rate": 8.423644202007467e-05,
1317
+ "loss": 0.2151,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 3.3422222222222224,
1322
+ "grad_norm": 0.4106178879737854,
1323
+ "learning_rate": 8.400863688854597e-05,
1324
+ "loss": 0.2501,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 3.36,
1329
+ "grad_norm": 0.5236695408821106,
1330
+ "learning_rate": 8.377951038078302e-05,
1331
+ "loss": 0.2801,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 3.3777777777777778,
1336
+ "grad_norm": 0.39424973726272583,
1337
+ "learning_rate": 8.354907139929851e-05,
1338
+ "loss": 0.2216,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 3.3955555555555557,
1343
+ "grad_norm": 0.38971391320228577,
1344
+ "learning_rate": 8.33173288976002e-05,
1345
+ "loss": 0.228,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 3.413333333333333,
1350
+ "grad_norm": 0.48786965012550354,
1351
+ "learning_rate": 8.308429187984297e-05,
1352
+ "loss": 0.2521,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 3.431111111111111,
1357
+ "grad_norm": 0.37168943881988525,
1358
+ "learning_rate": 8.284996940047903e-05,
1359
+ "loss": 0.2397,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 3.448888888888889,
1364
+ "grad_norm": 0.36831504106521606,
1365
+ "learning_rate": 8.261437056390606e-05,
1366
+ "loss": 0.2204,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 3.466666666666667,
1371
+ "grad_norm": 0.32543519139289856,
1372
+ "learning_rate": 8.237750452411353e-05,
1373
+ "loss": 0.2291,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 3.4844444444444447,
1378
+ "grad_norm": 0.3227090835571289,
1379
+ "learning_rate": 8.213938048432697e-05,
1380
+ "loss": 0.2218,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 3.502222222222222,
1385
+ "grad_norm": 0.623389720916748,
1386
+ "learning_rate": 8.190000769665044e-05,
1387
+ "loss": 0.249,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 3.52,
1392
+ "grad_norm": 0.35425952076911926,
1393
+ "learning_rate": 8.1659395461707e-05,
1394
+ "loss": 0.2749,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 3.537777777777778,
1399
+ "grad_norm": 0.33658289909362793,
1400
+ "learning_rate": 8.141755312827736e-05,
1401
+ "loss": 0.2134,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 3.5555555555555554,
1406
+ "grad_norm": 0.34356260299682617,
1407
+ "learning_rate": 8.117449009293668e-05,
1408
+ "loss": 0.2216,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 3.5733333333333333,
1413
+ "grad_norm": 0.32880356907844543,
1414
+ "learning_rate": 8.093021579968941e-05,
1415
+ "loss": 0.2369,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 3.591111111111111,
1420
+ "grad_norm": 0.47223803400993347,
1421
+ "learning_rate": 8.068473973960238e-05,
1422
+ "loss": 0.2433,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 3.608888888888889,
1427
+ "grad_norm": 0.37927350401878357,
1428
+ "learning_rate": 8.043807145043604e-05,
1429
+ "loss": 0.2405,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 3.626666666666667,
1434
+ "grad_norm": 0.28793418407440186,
1435
+ "learning_rate": 8.019022051627388e-05,
1436
+ "loss": 0.2345,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 3.6444444444444444,
1441
+ "grad_norm": 0.3489110767841339,
1442
+ "learning_rate": 7.994119656715002e-05,
1443
+ "loss": 0.2574,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 3.6622222222222223,
1448
+ "grad_norm": 0.3693983554840088,
1449
+ "learning_rate": 7.969100927867507e-05,
1450
+ "loss": 0.2445,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 3.68,
1455
+ "grad_norm": 0.3646757900714874,
1456
+ "learning_rate": 7.943966837166023e-05,
1457
+ "loss": 0.2099,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 3.6977777777777776,
1462
+ "grad_norm": 0.31038224697113037,
1463
+ "learning_rate": 7.91871836117395e-05,
1464
+ "loss": 0.2051,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 3.7155555555555555,
1469
+ "grad_norm": 0.2764589786529541,
1470
+ "learning_rate": 7.89335648089903e-05,
1471
+ "loss": 0.2132,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 3.7333333333333334,
1476
+ "grad_norm": 0.3864257037639618,
1477
+ "learning_rate": 7.86788218175523e-05,
1478
+ "loss": 0.2284,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 3.7511111111111113,
1483
+ "grad_norm": 0.8009142279624939,
1484
+ "learning_rate": 7.842296453524463e-05,
1485
+ "loss": 0.3221,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 3.7688888888888887,
1490
+ "grad_norm": 0.3626723885536194,
1491
+ "learning_rate": 7.81660029031811e-05,
1492
+ "loss": 0.2558,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 3.7866666666666666,
1497
+ "grad_norm": 0.4381621778011322,
1498
+ "learning_rate": 7.79079469053842e-05,
1499
+ "loss": 0.228,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 3.8044444444444445,
1504
+ "grad_norm": 0.38796478509902954,
1505
+ "learning_rate": 7.764880656839696e-05,
1506
+ "loss": 0.2025,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 3.822222222222222,
1511
+ "grad_norm": 0.27901729941368103,
1512
+ "learning_rate": 7.738859196089358e-05,
1513
+ "loss": 0.2142,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 3.84,
1518
+ "grad_norm": 0.4677048623561859,
1519
+ "learning_rate": 7.712731319328798e-05,
1520
+ "loss": 0.2614,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 3.8577777777777778,
1525
+ "grad_norm": 0.2969120740890503,
1526
+ "learning_rate": 7.68649804173412e-05,
1527
+ "loss": 0.24,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 3.8755555555555556,
1532
+ "grad_norm": 0.42577284574508667,
1533
+ "learning_rate": 7.660160382576683e-05,
1534
+ "loss": 0.2054,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 3.8933333333333335,
1539
+ "grad_norm": 0.40695130825042725,
1540
+ "learning_rate": 7.633719365183504e-05,
1541
+ "loss": 0.2464,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 3.911111111111111,
1546
+ "grad_norm": 0.5424155592918396,
1547
+ "learning_rate": 7.60717601689749e-05,
1548
+ "loss": 0.2583,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 3.928888888888889,
1553
+ "grad_norm": 0.683966338634491,
1554
+ "learning_rate": 7.580531369037533e-05,
1555
+ "loss": 0.2387,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 3.9466666666666668,
1560
+ "grad_norm": 0.37036415934562683,
1561
+ "learning_rate": 7.553786456858429e-05,
1562
+ "loss": 0.2333,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 3.964444444444444,
1567
+ "grad_norm": 0.5287876129150391,
1568
+ "learning_rate": 7.526942319510655e-05,
1569
+ "loss": 0.2353,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 3.982222222222222,
1574
+ "grad_norm": 0.31925442814826965,
1575
+ "learning_rate": 7.500000000000001e-05,
1576
+ "loss": 0.2411,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 4.0,
1581
+ "grad_norm": 0.5316102504730225,
1582
+ "learning_rate": 7.472960545147038e-05,
1583
+ "loss": 0.2472,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 4.017777777777778,
1588
+ "grad_norm": 0.24691040813922882,
1589
+ "learning_rate": 7.445825005546448e-05,
1590
+ "loss": 0.217,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 4.035555555555556,
1595
+ "grad_norm": 0.3662887215614319,
1596
+ "learning_rate": 7.4185944355262e-05,
1597
+ "loss": 0.2026,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 4.053333333333334,
1602
+ "grad_norm": 0.36757993698120117,
1603
+ "learning_rate": 7.391269893106592e-05,
1604
+ "loss": 0.2364,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 4.071111111111111,
1609
+ "grad_norm": 0.29429471492767334,
1610
+ "learning_rate": 7.363852439959135e-05,
1611
+ "loss": 0.1774,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 4.088888888888889,
1616
+ "grad_norm": 0.48565641045570374,
1617
+ "learning_rate": 7.33634314136531e-05,
1618
+ "loss": 0.2156,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 4.1066666666666665,
1623
+ "grad_norm": 0.3768898844718933,
1624
+ "learning_rate": 7.308743066175172e-05,
1625
+ "loss": 0.2006,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 4.124444444444444,
1630
+ "grad_norm": 0.32797563076019287,
1631
+ "learning_rate": 7.281053286765815e-05,
1632
+ "loss": 0.2195,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 4.142222222222222,
1637
+ "grad_norm": 0.3106316030025482,
1638
+ "learning_rate": 7.253274878999727e-05,
1639
+ "loss": 0.2268,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 4.16,
1644
+ "grad_norm": 0.43699216842651367,
1645
+ "learning_rate": 7.225408922182961e-05,
1646
+ "loss": 0.2186,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 4.177777777777778,
1651
+ "grad_norm": 0.569455623626709,
1652
+ "learning_rate": 7.197456499023225e-05,
1653
+ "loss": 0.2039,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 4.195555555555556,
1658
+ "grad_norm": 0.49764353036880493,
1659
+ "learning_rate": 7.169418695587791e-05,
1660
+ "loss": 0.2107,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 4.213333333333333,
1665
+ "grad_norm": 0.5107737183570862,
1666
+ "learning_rate": 7.141296601261314e-05,
1667
+ "loss": 0.2387,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 4.231111111111111,
1672
+ "grad_norm": 0.531856119632721,
1673
+ "learning_rate": 7.113091308703498e-05,
1674
+ "loss": 0.1914,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 4.248888888888889,
1679
+ "grad_norm": 0.3557555377483368,
1680
+ "learning_rate": 7.084803913806641e-05,
1681
+ "loss": 0.2192,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 4.266666666666667,
1686
+ "grad_norm": 0.520222544670105,
1687
+ "learning_rate": 7.056435515653059e-05,
1688
+ "loss": 0.2406,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 4.2844444444444445,
1693
+ "grad_norm": 0.5725359916687012,
1694
+ "learning_rate": 7.027987216472377e-05,
1695
+ "loss": 0.2102,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 4.302222222222222,
1700
+ "grad_norm": 0.39855217933654785,
1701
+ "learning_rate": 6.999460121598704e-05,
1702
+ "loss": 0.1943,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 4.32,
1707
+ "grad_norm": 0.47654294967651367,
1708
+ "learning_rate": 6.970855339427698e-05,
1709
+ "loss": 0.1955,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 4.337777777777778,
1714
+ "grad_norm": 0.6176052093505859,
1715
+ "learning_rate": 6.942173981373474e-05,
1716
+ "loss": 0.2316,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 4.355555555555555,
1721
+ "grad_norm": 0.446646511554718,
1722
+ "learning_rate": 6.91341716182545e-05,
1723
+ "loss": 0.2038,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 4.373333333333333,
1728
+ "grad_norm": 0.4111061692237854,
1729
+ "learning_rate": 6.884585998105026e-05,
1730
+ "loss": 0.2137,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 4.391111111111111,
1735
+ "grad_norm": 0.5625485777854919,
1736
+ "learning_rate": 6.855681610422189e-05,
1737
+ "loss": 0.2059,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 4.408888888888889,
1742
+ "grad_norm": 0.30589085817337036,
1743
+ "learning_rate": 6.826705121831976e-05,
1744
+ "loss": 0.2213,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 4.426666666666667,
1749
+ "grad_norm": 0.766379177570343,
1750
+ "learning_rate": 6.797657658190839e-05,
1751
+ "loss": 0.2061,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 4.444444444444445,
1756
+ "grad_norm": 0.3027375340461731,
1757
+ "learning_rate": 6.768540348112907e-05,
1758
+ "loss": 0.2185,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 4.4622222222222225,
1763
+ "grad_norm": 0.49446240067481995,
1764
+ "learning_rate": 6.739354322926136e-05,
1765
+ "loss": 0.1946,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 4.48,
1770
+ "grad_norm": 0.5550069212913513,
1771
+ "learning_rate": 6.710100716628344e-05,
1772
+ "loss": 0.2716,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 4.497777777777777,
1777
+ "grad_norm": 0.4387371838092804,
1778
+ "learning_rate": 6.680780665843155e-05,
1779
+ "loss": 0.1893,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 4.515555555555555,
1784
+ "grad_norm": 0.3026201128959656,
1785
+ "learning_rate": 6.651395309775837e-05,
1786
+ "loss": 0.216,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 4.533333333333333,
1791
+ "grad_norm": 0.4486079216003418,
1792
+ "learning_rate": 6.621945790169036e-05,
1793
+ "loss": 0.1849,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 4.551111111111111,
1798
+ "grad_norm": 0.4118870496749878,
1799
+ "learning_rate": 6.592433251258423e-05,
1800
+ "loss": 0.1977,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 4.568888888888889,
1805
+ "grad_norm": 0.5137110352516174,
1806
+ "learning_rate": 6.562858839728223e-05,
1807
+ "loss": 0.2167,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 4.586666666666667,
1812
+ "grad_norm": 0.34046244621276855,
1813
+ "learning_rate": 6.533223704666672e-05,
1814
+ "loss": 0.2128,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 4.604444444444445,
1819
+ "grad_norm": 0.44516146183013916,
1820
+ "learning_rate": 6.503528997521366e-05,
1821
+ "loss": 0.1932,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 4.622222222222222,
1826
+ "grad_norm": 0.2885585427284241,
1827
+ "learning_rate": 6.473775872054521e-05,
1828
+ "loss": 0.1991,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 4.64,
1833
+ "grad_norm": 0.37257564067840576,
1834
+ "learning_rate": 6.44396548429815e-05,
1835
+ "loss": 0.179,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 4.657777777777778,
1840
+ "grad_norm": 0.43277639150619507,
1841
+ "learning_rate": 6.414098992509138e-05,
1842
+ "loss": 0.2154,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 4.6755555555555555,
1847
+ "grad_norm": 0.4736541509628296,
1848
+ "learning_rate": 6.384177557124247e-05,
1849
+ "loss": 0.2024,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 4.693333333333333,
1854
+ "grad_norm": 0.3058260381221771,
1855
+ "learning_rate": 6.354202340715026e-05,
1856
+ "loss": 0.2264,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 4.711111111111111,
1861
+ "grad_norm": 0.33973225951194763,
1862
+ "learning_rate": 6.324174507942637e-05,
1863
+ "loss": 0.2175,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 4.728888888888889,
1868
+ "grad_norm": 0.370286762714386,
1869
+ "learning_rate": 6.294095225512603e-05,
1870
+ "loss": 0.1969,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 4.746666666666667,
1875
+ "grad_norm": 0.5065796375274658,
1876
+ "learning_rate": 6.263965662129487e-05,
1877
+ "loss": 0.2322,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 4.764444444444445,
1882
+ "grad_norm": 0.2974378764629364,
1883
+ "learning_rate": 6.233786988451468e-05,
1884
+ "loss": 0.1617,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 4.782222222222222,
1889
+ "grad_norm": 0.37753137946128845,
1890
+ "learning_rate": 6.203560377044866e-05,
1891
+ "loss": 0.2324,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 4.8,
1896
+ "grad_norm": 0.5713666677474976,
1897
+ "learning_rate": 6.173287002338577e-05,
1898
+ "loss": 0.2213,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 4.817777777777778,
1903
+ "grad_norm": 0.5500757694244385,
1904
+ "learning_rate": 6.142968040578449e-05,
1905
+ "loss": 0.2163,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 4.835555555555556,
1910
+ "grad_norm": 0.3870888948440552,
1911
+ "learning_rate": 6.112604669781572e-05,
1912
+ "loss": 0.2014,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 4.8533333333333335,
1917
+ "grad_norm": 0.4181479811668396,
1918
+ "learning_rate": 6.0821980696905146e-05,
1919
+ "loss": 0.2123,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 4.871111111111111,
1924
+ "grad_norm": 0.3824799656867981,
1925
+ "learning_rate": 6.0517494217274794e-05,
1926
+ "loss": 0.2008,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 4.888888888888889,
1931
+ "grad_norm": 0.3899323642253876,
1932
+ "learning_rate": 6.021259908948402e-05,
1933
+ "loss": 0.2011,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 4.906666666666666,
1938
+ "grad_norm": 0.4690476059913635,
1939
+ "learning_rate": 5.9907307159969884e-05,
1940
+ "loss": 0.2215,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 4.924444444444444,
1945
+ "grad_norm": 0.3852761387825012,
1946
+ "learning_rate": 5.960163029058682e-05,
1947
+ "loss": 0.1943,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 4.942222222222222,
1952
+ "grad_norm": 0.40581774711608887,
1953
+ "learning_rate": 5.9295580358145744e-05,
1954
+ "loss": 0.2132,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 4.96,
1959
+ "grad_norm": 0.7496148943901062,
1960
+ "learning_rate": 5.898916925395264e-05,
1961
+ "loss": 0.2227,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 4.977777777777778,
1966
+ "grad_norm": 0.3892797529697418,
1967
+ "learning_rate": 5.868240888334653e-05,
1968
+ "loss": 0.2165,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 4.995555555555556,
1973
+ "grad_norm": 0.284811794757843,
1974
+ "learning_rate": 5.837531116523682e-05,
1975
+ "loss": 0.1669,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 5.013333333333334,
1980
+ "grad_norm": 0.416891872882843,
1981
+ "learning_rate": 5.806788803164034e-05,
1982
+ "loss": 0.1828,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 5.0311111111111115,
1987
+ "grad_norm": 0.4431915283203125,
1988
+ "learning_rate": 5.7760151427217576e-05,
1989
+ "loss": 0.1957,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 5.0488888888888885,
1994
+ "grad_norm": 0.5158615708351135,
1995
+ "learning_rate": 5.745211330880872e-05,
1996
+ "loss": 0.2331,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 5.066666666666666,
2001
+ "grad_norm": 0.3418184220790863,
2002
+ "learning_rate": 5.714378564496901e-05,
2003
+ "loss": 0.2065,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 5.084444444444444,
2008
+ "grad_norm": 0.5028918981552124,
2009
+ "learning_rate": 5.683518041550368e-05,
2010
+ "loss": 0.1657,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 5.102222222222222,
2015
+ "grad_norm": 0.4428432285785675,
2016
+ "learning_rate": 5.6526309611002594e-05,
2017
+ "loss": 0.1948,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 5.12,
2022
+ "grad_norm": 0.3536894917488098,
2023
+ "learning_rate": 5.621718523237427e-05,
2024
+ "loss": 0.1709,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 5.137777777777778,
2029
+ "grad_norm": 0.4637707769870758,
2030
+ "learning_rate": 5.590781929037965e-05,
2031
+ "loss": 0.1662,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 5.155555555555556,
2036
+ "grad_norm": 0.5988882780075073,
2037
+ "learning_rate": 5.559822380516539e-05,
2038
+ "loss": 0.1477,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 5.173333333333334,
2043
+ "grad_norm": 0.45593711733818054,
2044
+ "learning_rate": 5.5288410805796895e-05,
2045
+ "loss": 0.1802,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 5.191111111111111,
2050
+ "grad_norm": 0.46239393949508667,
2051
+ "learning_rate": 5.497839232979084e-05,
2052
+ "loss": 0.178,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 5.208888888888889,
2057
+ "grad_norm": 0.5151268839836121,
2058
+ "learning_rate": 5.466818042264753e-05,
2059
+ "loss": 0.1453,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 5.226666666666667,
2064
+ "grad_norm": 0.5723825097084045,
2065
+ "learning_rate": 5.435778713738292e-05,
2066
+ "loss": 0.212,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 5.2444444444444445,
2071
+ "grad_norm": 0.5398524403572083,
2072
+ "learning_rate": 5.404722453406017e-05,
2073
+ "loss": 0.1773,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 5.262222222222222,
2078
+ "grad_norm": 0.5362580418586731,
2079
+ "learning_rate": 5.373650467932122e-05,
2080
+ "loss": 0.1816,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 5.28,
2085
+ "grad_norm": 0.5614521503448486,
2086
+ "learning_rate": 5.3425639645917834e-05,
2087
+ "loss": 0.1544,
2088
+ "step": 297
2089
+ },
2090
+ {
2091
+ "epoch": 5.297777777777778,
2092
+ "grad_norm": 0.44896313548088074,
2093
+ "learning_rate": 5.311464151224261e-05,
2094
+ "loss": 0.1381,
2095
+ "step": 298
2096
+ },
2097
+ {
2098
+ "epoch": 5.315555555555555,
2099
+ "grad_norm": 0.35840409994125366,
2100
+ "learning_rate": 5.2803522361859594e-05,
2101
+ "loss": 0.1653,
2102
+ "step": 299
2103
+ },
2104
+ {
2105
+ "epoch": 5.333333333333333,
2106
+ "grad_norm": 0.6827304363250732,
2107
+ "learning_rate": 5.249229428303486e-05,
2108
+ "loss": 0.167,
2109
+ "step": 300
2110
+ },
2111
+ {
2112
+ "epoch": 5.351111111111111,
2113
+ "grad_norm": 0.3499818444252014,
2114
+ "learning_rate": 5.218096936826681e-05,
2115
+ "loss": 0.2221,
2116
+ "step": 301
2117
+ },
2118
+ {
2119
+ "epoch": 5.368888888888889,
2120
+ "grad_norm": 0.48628711700439453,
2121
+ "learning_rate": 5.18695597138163e-05,
2122
+ "loss": 0.1932,
2123
+ "step": 302
2124
+ },
2125
+ {
2126
+ "epoch": 5.386666666666667,
2127
+ "grad_norm": 0.5208820104598999,
2128
+ "learning_rate": 5.155807741923666e-05,
2129
+ "loss": 0.1818,
2130
+ "step": 303
2131
+ },
2132
+ {
2133
+ "epoch": 5.404444444444445,
2134
+ "grad_norm": 0.4346122741699219,
2135
+ "learning_rate": 5.124653458690365e-05,
2136
+ "loss": 0.1924,
2137
+ "step": 304
2138
+ },
2139
+ {
2140
+ "epoch": 5.4222222222222225,
2141
+ "grad_norm": 0.45820167660713196,
2142
+ "learning_rate": 5.0934943321545115e-05,
2143
+ "loss": 0.1922,
2144
+ "step": 305
2145
+ },
2146
+ {
2147
+ "epoch": 5.44,
2148
+ "grad_norm": 0.5644346475601196,
2149
+ "learning_rate": 5.062331572977076e-05,
2150
+ "loss": 0.1828,
2151
+ "step": 306
2152
+ },
2153
+ {
2154
+ "epoch": 5.457777777777777,
2155
+ "grad_norm": 0.507893979549408,
2156
+ "learning_rate": 5.031166391960168e-05,
2157
+ "loss": 0.2173,
2158
+ "step": 307
2159
+ },
2160
+ {
2161
+ "epoch": 5.475555555555555,
2162
+ "grad_norm": 0.4621982276439667,
2163
+ "learning_rate": 5e-05,
2164
+ "loss": 0.1703,
2165
+ "step": 308
2166
+ },
2167
+ {
2168
+ "epoch": 5.493333333333333,
2169
+ "grad_norm": 0.4117422103881836,
2170
+ "learning_rate": 4.968833608039832e-05,
2171
+ "loss": 0.1751,
2172
+ "step": 309
2173
+ },
2174
+ {
2175
+ "epoch": 5.511111111111111,
2176
+ "grad_norm": 0.4004817605018616,
2177
+ "learning_rate": 4.9376684270229254e-05,
2178
+ "loss": 0.1835,
2179
+ "step": 310
2180
+ },
2181
+ {
2182
+ "epoch": 5.528888888888889,
2183
+ "grad_norm": 0.4063107669353485,
2184
+ "learning_rate": 4.9065056678454904e-05,
2185
+ "loss": 0.1892,
2186
+ "step": 311
2187
+ },
2188
+ {
2189
+ "epoch": 5.546666666666667,
2190
+ "grad_norm": 0.45984384417533875,
2191
+ "learning_rate": 4.875346541309637e-05,
2192
+ "loss": 0.181,
2193
+ "step": 312
2194
+ },
2195
+ {
2196
+ "epoch": 5.564444444444445,
2197
+ "grad_norm": 0.48440927267074585,
2198
+ "learning_rate": 4.844192258076336e-05,
2199
+ "loss": 0.1723,
2200
+ "step": 313
2201
+ },
2202
+ {
2203
+ "epoch": 5.582222222222223,
2204
+ "grad_norm": 0.6084842681884766,
2205
+ "learning_rate": 4.813044028618373e-05,
2206
+ "loss": 0.1875,
2207
+ "step": 314
2208
+ },
2209
+ {
2210
+ "epoch": 5.6,
2211
+ "grad_norm": 0.5340481996536255,
2212
+ "learning_rate": 4.781903063173321e-05,
2213
+ "loss": 0.1903,
2214
+ "step": 315
2215
+ },
2216
+ {
2217
+ "epoch": 5.6177777777777775,
2218
+ "grad_norm": 0.3680734634399414,
2219
+ "learning_rate": 4.750770571696514e-05,
2220
+ "loss": 0.1742,
2221
+ "step": 316
2222
+ },
2223
+ {
2224
+ "epoch": 5.635555555555555,
2225
+ "grad_norm": 0.4389323592185974,
2226
+ "learning_rate": 4.7196477638140404e-05,
2227
+ "loss": 0.1604,
2228
+ "step": 317
2229
+ },
2230
+ {
2231
+ "epoch": 5.653333333333333,
2232
+ "grad_norm": 0.5682416558265686,
2233
+ "learning_rate": 4.68853584877574e-05,
2234
+ "loss": 0.2142,
2235
+ "step": 318
2236
+ },
2237
+ {
2238
+ "epoch": 5.671111111111111,
2239
+ "grad_norm": 0.5514141321182251,
2240
+ "learning_rate": 4.657436035408217e-05,
2241
+ "loss": 0.1902,
2242
+ "step": 319
2243
+ },
2244
+ {
2245
+ "epoch": 5.688888888888889,
2246
+ "grad_norm": 0.5815438032150269,
2247
+ "learning_rate": 4.626349532067879e-05,
2248
+ "loss": 0.1604,
2249
+ "step": 320
2250
+ },
2251
+ {
2252
+ "epoch": 5.706666666666667,
2253
+ "grad_norm": 0.3311176598072052,
2254
+ "learning_rate": 4.595277546593984e-05,
2255
+ "loss": 0.2049,
2256
+ "step": 321
2257
+ },
2258
+ {
2259
+ "epoch": 5.724444444444444,
2260
+ "grad_norm": 0.4205529987812042,
2261
+ "learning_rate": 4.564221286261709e-05,
2262
+ "loss": 0.1715,
2263
+ "step": 322
2264
+ },
2265
+ {
2266
+ "epoch": 5.742222222222222,
2267
+ "grad_norm": 0.6624743342399597,
2268
+ "learning_rate": 4.5331819577352474e-05,
2269
+ "loss": 0.1601,
2270
+ "step": 323
2271
+ },
2272
+ {
2273
+ "epoch": 5.76,
2274
+ "grad_norm": 0.5203994512557983,
2275
+ "learning_rate": 4.502160767020918e-05,
2276
+ "loss": 0.1589,
2277
+ "step": 324
2278
+ },
2279
+ {
2280
+ "epoch": 5.777777777777778,
2281
+ "grad_norm": 0.4620148241519928,
2282
+ "learning_rate": 4.471158919420312e-05,
2283
+ "loss": 0.1656,
2284
+ "step": 325
2285
+ },
2286
+ {
2287
+ "epoch": 5.795555555555556,
2288
+ "grad_norm": 0.5596708655357361,
2289
+ "learning_rate": 4.4401776194834613e-05,
2290
+ "loss": 0.1821,
2291
+ "step": 326
2292
+ },
2293
+ {
2294
+ "epoch": 5.8133333333333335,
2295
+ "grad_norm": 0.4360620975494385,
2296
+ "learning_rate": 4.409218070962036e-05,
2297
+ "loss": 0.1752,
2298
+ "step": 327
2299
+ },
2300
+ {
2301
+ "epoch": 5.831111111111111,
2302
+ "grad_norm": 0.4674508571624756,
2303
+ "learning_rate": 4.378281476762576e-05,
2304
+ "loss": 0.204,
2305
+ "step": 328
2306
+ },
2307
+ {
2308
+ "epoch": 5.848888888888889,
2309
+ "grad_norm": 0.9109951853752136,
2310
+ "learning_rate": 4.347369038899744e-05,
2311
+ "loss": 0.1562,
2312
+ "step": 329
2313
+ },
2314
+ {
2315
+ "epoch": 5.866666666666667,
2316
+ "grad_norm": 0.8667967915534973,
2317
+ "learning_rate": 4.316481958449634e-05,
2318
+ "loss": 0.2376,
2319
+ "step": 330
2320
+ },
2321
+ {
2322
+ "epoch": 5.884444444444444,
2323
+ "grad_norm": 0.6173791289329529,
2324
+ "learning_rate": 4.285621435503101e-05,
2325
+ "loss": 0.1699,
2326
+ "step": 331
2327
+ },
2328
+ {
2329
+ "epoch": 5.902222222222222,
2330
+ "grad_norm": 0.6599533557891846,
2331
+ "learning_rate": 4.254788669119127e-05,
2332
+ "loss": 0.1652,
2333
+ "step": 332
2334
+ },
2335
+ {
2336
+ "epoch": 5.92,
2337
+ "grad_norm": 0.39456817507743835,
2338
+ "learning_rate": 4.223984857278242e-05,
2339
+ "loss": 0.1695,
2340
+ "step": 333
2341
+ },
2342
+ {
2343
+ "epoch": 5.937777777777778,
2344
+ "grad_norm": 0.7024866342544556,
2345
+ "learning_rate": 4.1932111968359664e-05,
2346
+ "loss": 0.1673,
2347
+ "step": 334
2348
+ },
2349
+ {
2350
+ "epoch": 5.955555555555556,
2351
+ "grad_norm": 0.5477570295333862,
2352
+ "learning_rate": 4.162468883476319e-05,
2353
+ "loss": 0.1852,
2354
+ "step": 335
2355
+ },
2356
+ {
2357
+ "epoch": 5.973333333333334,
2358
+ "grad_norm": 0.5014763474464417,
2359
+ "learning_rate": 4.131759111665349e-05,
2360
+ "loss": 0.1847,
2361
+ "step": 336
2362
+ },
2363
+ {
2364
+ "epoch": 5.9911111111111115,
2365
+ "grad_norm": 0.334262877702713,
2366
+ "learning_rate": 4.101083074604737e-05,
2367
+ "loss": 0.1709,
2368
+ "step": 337
2369
+ },
2370
+ {
2371
+ "epoch": 6.0088888888888885,
2372
+ "grad_norm": 0.5552971959114075,
2373
+ "learning_rate": 4.0704419641854274e-05,
2374
+ "loss": 0.1476,
2375
+ "step": 338
2376
+ },
2377
+ {
2378
+ "epoch": 6.026666666666666,
2379
+ "grad_norm": 0.35900405049324036,
2380
+ "learning_rate": 4.03983697094132e-05,
2381
+ "loss": 0.1731,
2382
+ "step": 339
2383
+ },
2384
+ {
2385
+ "epoch": 6.044444444444444,
2386
+ "grad_norm": 0.3748185634613037,
2387
+ "learning_rate": 4.0092692840030134e-05,
2388
+ "loss": 0.1625,
2389
+ "step": 340
2390
+ },
2391
+ {
2392
+ "epoch": 6.062222222222222,
2393
+ "grad_norm": 0.5626404285430908,
2394
+ "learning_rate": 3.978740091051599e-05,
2395
+ "loss": 0.1718,
2396
+ "step": 341
2397
+ },
2398
+ {
2399
+ "epoch": 6.08,
2400
+ "grad_norm": 0.5533756017684937,
2401
+ "learning_rate": 3.9482505782725224e-05,
2402
+ "loss": 0.1793,
2403
+ "step": 342
2404
+ },
2405
+ {
2406
+ "epoch": 6.097777777777778,
2407
+ "grad_norm": 0.45061609148979187,
2408
+ "learning_rate": 3.917801930309486e-05,
2409
+ "loss": 0.1675,
2410
+ "step": 343
2411
+ },
2412
+ {
2413
+ "epoch": 6.115555555555556,
2414
+ "grad_norm": 0.6766936182975769,
2415
+ "learning_rate": 3.887395330218429e-05,
2416
+ "loss": 0.1528,
2417
+ "step": 344
2418
+ },
2419
+ {
2420
+ "epoch": 6.133333333333334,
2421
+ "grad_norm": 0.4249931573867798,
2422
+ "learning_rate": 3.857031959421553e-05,
2423
+ "loss": 0.1437,
2424
+ "step": 345
2425
+ },
2426
+ {
2427
+ "epoch": 6.151111111111111,
2428
+ "grad_norm": 0.4025160074234009,
2429
+ "learning_rate": 3.8267129976614254e-05,
2430
+ "loss": 0.1647,
2431
+ "step": 346
2432
+ },
2433
+ {
2434
+ "epoch": 6.168888888888889,
2435
+ "grad_norm": 0.42490458488464355,
2436
+ "learning_rate": 3.7964396229551364e-05,
2437
+ "loss": 0.1436,
2438
+ "step": 347
2439
+ },
2440
+ {
2441
+ "epoch": 6.1866666666666665,
2442
+ "grad_norm": 0.6905245184898376,
2443
+ "learning_rate": 3.7662130115485314e-05,
2444
+ "loss": 0.148,
2445
+ "step": 348
2446
+ },
2447
+ {
2448
+ "epoch": 6.204444444444444,
2449
+ "grad_norm": 0.608650267124176,
2450
+ "learning_rate": 3.7360343378705124e-05,
2451
+ "loss": 0.1413,
2452
+ "step": 349
2453
+ },
2454
+ {
2455
+ "epoch": 6.222222222222222,
2456
+ "grad_norm": 0.560066819190979,
2457
+ "learning_rate": 3.705904774487396e-05,
2458
+ "loss": 0.1528,
2459
+ "step": 350
2460
+ },
2461
+ {
2462
+ "epoch": 6.24,
2463
+ "grad_norm": 0.5189685821533203,
2464
+ "learning_rate": 3.675825492057364e-05,
2465
+ "loss": 0.1639,
2466
+ "step": 351
2467
+ },
2468
+ {
2469
+ "epoch": 6.257777777777778,
2470
+ "grad_norm": 0.92945796251297,
2471
+ "learning_rate": 3.6457976592849754e-05,
2472
+ "loss": 0.2024,
2473
+ "step": 352
2474
+ },
2475
+ {
2476
+ "epoch": 6.275555555555556,
2477
+ "grad_norm": 0.544842541217804,
2478
+ "learning_rate": 3.6158224428757535e-05,
2479
+ "loss": 0.1443,
2480
+ "step": 353
2481
+ },
2482
+ {
2483
+ "epoch": 6.293333333333333,
2484
+ "grad_norm": 0.4329567849636078,
2485
+ "learning_rate": 3.585901007490863e-05,
2486
+ "loss": 0.1314,
2487
+ "step": 354
2488
+ },
2489
+ {
2490
+ "epoch": 6.311111111111111,
2491
+ "grad_norm": 0.5567479729652405,
2492
+ "learning_rate": 3.556034515701852e-05,
2493
+ "loss": 0.1495,
2494
+ "step": 355
2495
+ },
2496
+ {
2497
+ "epoch": 6.328888888888889,
2498
+ "grad_norm": 0.45176929235458374,
2499
+ "learning_rate": 3.5262241279454785e-05,
2500
+ "loss": 0.1571,
2501
+ "step": 356
2502
+ },
2503
+ {
2504
+ "epoch": 6.346666666666667,
2505
+ "grad_norm": 0.4304347634315491,
2506
+ "learning_rate": 3.4964710024786354e-05,
2507
+ "loss": 0.1413,
2508
+ "step": 357
2509
+ },
2510
+ {
2511
+ "epoch": 6.364444444444445,
2512
+ "grad_norm": 0.5478505492210388,
2513
+ "learning_rate": 3.4667762953333295e-05,
2514
+ "loss": 0.1643,
2515
+ "step": 358
2516
+ },
2517
+ {
2518
+ "epoch": 6.3822222222222225,
2519
+ "grad_norm": 0.5922195911407471,
2520
+ "learning_rate": 3.4371411602717784e-05,
2521
+ "loss": 0.1716,
2522
+ "step": 359
2523
+ },
2524
+ {
2525
+ "epoch": 6.4,
2526
+ "grad_norm": 0.4263589084148407,
2527
+ "learning_rate": 3.4075667487415785e-05,
2528
+ "loss": 0.1671,
2529
+ "step": 360
2530
+ },
2531
+ {
2532
+ "epoch": 6.417777777777777,
2533
+ "grad_norm": 0.44783204793930054,
2534
+ "learning_rate": 3.3780542098309654e-05,
2535
+ "loss": 0.167,
2536
+ "step": 361
2537
+ },
2538
+ {
2539
+ "epoch": 6.435555555555555,
2540
+ "grad_norm": 0.5761044025421143,
2541
+ "learning_rate": 3.3486046902241664e-05,
2542
+ "loss": 0.1518,
2543
+ "step": 362
2544
+ },
2545
+ {
2546
+ "epoch": 6.453333333333333,
2547
+ "grad_norm": 0.4984096884727478,
2548
+ "learning_rate": 3.319219334156847e-05,
2549
+ "loss": 0.1888,
2550
+ "step": 363
2551
+ },
2552
+ {
2553
+ "epoch": 6.471111111111111,
2554
+ "grad_norm": 0.5709213614463806,
2555
+ "learning_rate": 3.289899283371657e-05,
2556
+ "loss": 0.1374,
2557
+ "step": 364
2558
+ },
2559
+ {
2560
+ "epoch": 6.488888888888889,
2561
+ "grad_norm": 0.45197322964668274,
2562
+ "learning_rate": 3.2606456770738636e-05,
2563
+ "loss": 0.1823,
2564
+ "step": 365
2565
+ },
2566
+ {
2567
+ "epoch": 6.506666666666667,
2568
+ "grad_norm": 0.3853418231010437,
2569
+ "learning_rate": 3.231459651887093e-05,
2570
+ "loss": 0.1424,
2571
+ "step": 366
2572
+ },
2573
+ {
2574
+ "epoch": 6.524444444444445,
2575
+ "grad_norm": 0.6892653107643127,
2576
+ "learning_rate": 3.2023423418091626e-05,
2577
+ "loss": 0.1354,
2578
+ "step": 367
2579
+ },
2580
+ {
2581
+ "epoch": 6.542222222222223,
2582
+ "grad_norm": 0.8659518957138062,
2583
+ "learning_rate": 3.173294878168025e-05,
2584
+ "loss": 0.1658,
2585
+ "step": 368
2586
+ },
2587
+ {
2588
+ "epoch": 6.5600000000000005,
2589
+ "grad_norm": 0.6673440933227539,
2590
+ "learning_rate": 3.1443183895778105e-05,
2591
+ "loss": 0.1341,
2592
+ "step": 369
2593
+ },
2594
+ {
2595
+ "epoch": 6.5777777777777775,
2596
+ "grad_norm": 0.49865254759788513,
2597
+ "learning_rate": 3.115414001894974e-05,
2598
+ "loss": 0.1746,
2599
+ "step": 370
2600
+ },
2601
+ {
2602
+ "epoch": 6.595555555555555,
2603
+ "grad_norm": 0.5364950299263,
2604
+ "learning_rate": 3.086582838174551e-05,
2605
+ "loss": 0.1655,
2606
+ "step": 371
2607
+ },
2608
+ {
2609
+ "epoch": 6.613333333333333,
2610
+ "grad_norm": 0.6427706480026245,
2611
+ "learning_rate": 3.0578260186265265e-05,
2612
+ "loss": 0.1489,
2613
+ "step": 372
2614
+ },
2615
+ {
2616
+ "epoch": 6.631111111111111,
2617
+ "grad_norm": 0.5947421193122864,
2618
+ "learning_rate": 3.029144660572304e-05,
2619
+ "loss": 0.1327,
2620
+ "step": 373
2621
+ },
2622
+ {
2623
+ "epoch": 6.648888888888889,
2624
+ "grad_norm": 0.5604392886161804,
2625
+ "learning_rate": 3.000539878401296e-05,
2626
+ "loss": 0.1593,
2627
+ "step": 374
2628
+ },
2629
+ {
2630
+ "epoch": 6.666666666666667,
2631
+ "grad_norm": 0.4848502576351166,
2632
+ "learning_rate": 2.9720127835276256e-05,
2633
+ "loss": 0.1551,
2634
+ "step": 375
2635
+ },
2636
+ {
2637
+ "epoch": 6.684444444444445,
2638
+ "grad_norm": 0.5442904829978943,
2639
+ "learning_rate": 2.9435644843469436e-05,
2640
+ "loss": 0.1526,
2641
+ "step": 376
2642
+ },
2643
+ {
2644
+ "epoch": 6.702222222222222,
2645
+ "grad_norm": 0.4855183959007263,
2646
+ "learning_rate": 2.9151960861933614e-05,
2647
+ "loss": 0.183,
2648
+ "step": 377
2649
+ },
2650
+ {
2651
+ "epoch": 6.72,
2652
+ "grad_norm": 0.8890539407730103,
2653
+ "learning_rate": 2.886908691296504e-05,
2654
+ "loss": 0.1624,
2655
+ "step": 378
2656
+ },
2657
+ {
2658
+ "epoch": 6.737777777777778,
2659
+ "grad_norm": 0.47631746530532837,
2660
+ "learning_rate": 2.858703398738686e-05,
2661
+ "loss": 0.1373,
2662
+ "step": 379
2663
+ },
2664
+ {
2665
+ "epoch": 6.7555555555555555,
2666
+ "grad_norm": 0.46250614523887634,
2667
+ "learning_rate": 2.8305813044122097e-05,
2668
+ "loss": 0.1786,
2669
+ "step": 380
2670
+ },
2671
+ {
2672
+ "epoch": 6.773333333333333,
2673
+ "grad_norm": 0.5734685063362122,
2674
+ "learning_rate": 2.8025435009767747e-05,
2675
+ "loss": 0.1432,
2676
+ "step": 381
2677
+ },
2678
+ {
2679
+ "epoch": 6.791111111111111,
2680
+ "grad_norm": 0.7250308394432068,
2681
+ "learning_rate": 2.774591077817038e-05,
2682
+ "loss": 0.1483,
2683
+ "step": 382
2684
+ },
2685
+ {
2686
+ "epoch": 6.808888888888889,
2687
+ "grad_norm": 0.4598230719566345,
2688
+ "learning_rate": 2.746725121000273e-05,
2689
+ "loss": 0.1709,
2690
+ "step": 383
2691
+ },
2692
+ {
2693
+ "epoch": 6.826666666666666,
2694
+ "grad_norm": 0.5403770208358765,
2695
+ "learning_rate": 2.718946713234185e-05,
2696
+ "loss": 0.1944,
2697
+ "step": 384
2698
+ },
2699
+ {
2700
+ "epoch": 6.844444444444444,
2701
+ "grad_norm": 0.43435898423194885,
2702
+ "learning_rate": 2.6912569338248315e-05,
2703
+ "loss": 0.1471,
2704
+ "step": 385
2705
+ },
2706
+ {
2707
+ "epoch": 6.862222222222222,
2708
+ "grad_norm": 0.7569040656089783,
2709
+ "learning_rate": 2.66365685863469e-05,
2710
+ "loss": 0.1755,
2711
+ "step": 386
2712
+ },
2713
+ {
2714
+ "epoch": 6.88,
2715
+ "grad_norm": 0.4488949775695801,
2716
+ "learning_rate": 2.636147560040866e-05,
2717
+ "loss": 0.1354,
2718
+ "step": 387
2719
+ },
2720
+ {
2721
+ "epoch": 6.897777777777778,
2722
+ "grad_norm": 0.43409401178359985,
2723
+ "learning_rate": 2.6087301068934106e-05,
2724
+ "loss": 0.1803,
2725
+ "step": 388
2726
+ },
2727
+ {
2728
+ "epoch": 6.915555555555556,
2729
+ "grad_norm": 0.38693767786026,
2730
+ "learning_rate": 2.581405564473801e-05,
2731
+ "loss": 0.1762,
2732
+ "step": 389
2733
+ },
2734
+ {
2735
+ "epoch": 6.933333333333334,
2736
+ "grad_norm": 0.3770747780799866,
2737
+ "learning_rate": 2.5541749944535554e-05,
2738
+ "loss": 0.1644,
2739
+ "step": 390
2740
+ },
2741
+ {
2742
+ "epoch": 6.9511111111111115,
2743
+ "grad_norm": 0.5996742844581604,
2744
+ "learning_rate": 2.527039454852963e-05,
2745
+ "loss": 0.1719,
2746
+ "step": 391
2747
+ },
2748
+ {
2749
+ "epoch": 6.968888888888889,
2750
+ "grad_norm": 0.54173743724823,
2751
+ "learning_rate": 2.500000000000001e-05,
2752
+ "loss": 0.1366,
2753
+ "step": 392
2754
+ },
2755
+ {
2756
+ "epoch": 6.986666666666666,
2757
+ "grad_norm": 0.5965537428855896,
2758
+ "learning_rate": 2.473057680489348e-05,
2759
+ "loss": 0.155,
2760
+ "step": 393
2761
+ },
2762
+ {
2763
+ "epoch": 7.004444444444444,
2764
+ "grad_norm": 0.3956046998500824,
2765
+ "learning_rate": 2.4462135431415733e-05,
2766
+ "loss": 0.1627,
2767
+ "step": 394
2768
+ },
2769
+ {
2770
+ "epoch": 7.022222222222222,
2771
+ "grad_norm": 0.530720055103302,
2772
+ "learning_rate": 2.4194686309624663e-05,
2773
+ "loss": 0.1384,
2774
+ "step": 395
2775
+ },
2776
+ {
2777
+ "epoch": 7.04,
2778
+ "grad_norm": 0.4579175114631653,
2779
+ "learning_rate": 2.39282398310251e-05,
2780
+ "loss": 0.1731,
2781
+ "step": 396
2782
+ },
2783
+ {
2784
+ "epoch": 7.057777777777778,
2785
+ "grad_norm": 0.807518720626831,
2786
+ "learning_rate": 2.366280634816496e-05,
2787
+ "loss": 0.1471,
2788
+ "step": 397
2789
+ },
2790
+ {
2791
+ "epoch": 7.075555555555556,
2792
+ "grad_norm": 0.5390831232070923,
2793
+ "learning_rate": 2.3398396174233178e-05,
2794
+ "loss": 0.1066,
2795
+ "step": 398
2796
+ },
2797
+ {
2798
+ "epoch": 7.093333333333334,
2799
+ "grad_norm": 0.4245457649230957,
2800
+ "learning_rate": 2.3135019582658802e-05,
2801
+ "loss": 0.1201,
2802
+ "step": 399
2803
+ },
2804
+ {
2805
+ "epoch": 7.111111111111111,
2806
+ "grad_norm": 0.40093037486076355,
2807
+ "learning_rate": 2.2872686806712035e-05,
2808
+ "loss": 0.1401,
2809
+ "step": 400
2810
+ },
2811
+ {
2812
+ "epoch": 7.128888888888889,
2813
+ "grad_norm": 0.8866329789161682,
2814
+ "learning_rate": 2.261140803910644e-05,
2815
+ "loss": 0.1096,
2816
+ "step": 401
2817
+ },
2818
+ {
2819
+ "epoch": 7.1466666666666665,
2820
+ "grad_norm": 0.45840370655059814,
2821
+ "learning_rate": 2.235119343160303e-05,
2822
+ "loss": 0.1555,
2823
+ "step": 402
2824
+ },
2825
+ {
2826
+ "epoch": 7.164444444444444,
2827
+ "grad_norm": 0.478550523519516,
2828
+ "learning_rate": 2.2092053094615813e-05,
2829
+ "loss": 0.1301,
2830
+ "step": 403
2831
+ },
2832
+ {
2833
+ "epoch": 7.182222222222222,
2834
+ "grad_norm": 0.4727082848548889,
2835
+ "learning_rate": 2.1833997096818898e-05,
2836
+ "loss": 0.1345,
2837
+ "step": 404
2838
+ },
2839
+ {
2840
+ "epoch": 7.2,
2841
+ "grad_norm": 0.5048395991325378,
2842
+ "learning_rate": 2.157703546475539e-05,
2843
+ "loss": 0.1733,
2844
+ "step": 405
2845
+ },
2846
+ {
2847
+ "epoch": 7.217777777777778,
2848
+ "grad_norm": 0.40645188093185425,
2849
+ "learning_rate": 2.132117818244771e-05,
2850
+ "loss": 0.1491,
2851
+ "step": 406
2852
+ },
2853
+ {
2854
+ "epoch": 7.235555555555556,
2855
+ "grad_norm": 0.560034990310669,
2856
+ "learning_rate": 2.1066435191009715e-05,
2857
+ "loss": 0.1226,
2858
+ "step": 407
2859
+ },
2860
+ {
2861
+ "epoch": 7.253333333333333,
2862
+ "grad_norm": 0.7475597262382507,
2863
+ "learning_rate": 2.0812816388260518e-05,
2864
+ "loss": 0.1455,
2865
+ "step": 408
2866
+ },
2867
+ {
2868
+ "epoch": 7.271111111111111,
2869
+ "grad_norm": 0.4967871904373169,
2870
+ "learning_rate": 2.056033162833977e-05,
2871
+ "loss": 0.1176,
2872
+ "step": 409
2873
+ },
2874
+ {
2875
+ "epoch": 7.288888888888889,
2876
+ "grad_norm": 1.1265000104904175,
2877
+ "learning_rate": 2.0308990721324927e-05,
2878
+ "loss": 0.1654,
2879
+ "step": 410
2880
+ },
2881
+ {
2882
+ "epoch": 7.306666666666667,
2883
+ "grad_norm": 1.0787440538406372,
2884
+ "learning_rate": 2.0058803432849987e-05,
2885
+ "loss": 0.1741,
2886
+ "step": 411
2887
+ },
2888
+ {
2889
+ "epoch": 7.3244444444444445,
2890
+ "grad_norm": 0.7019418478012085,
2891
+ "learning_rate": 1.980977948372612e-05,
2892
+ "loss": 0.1198,
2893
+ "step": 412
2894
+ },
2895
+ {
2896
+ "epoch": 7.342222222222222,
2897
+ "grad_norm": 0.5232211947441101,
2898
+ "learning_rate": 1.9561928549563968e-05,
2899
+ "loss": 0.1176,
2900
+ "step": 413
2901
+ },
2902
+ {
2903
+ "epoch": 7.36,
2904
+ "grad_norm": 0.4455171823501587,
2905
+ "learning_rate": 1.931526026039764e-05,
2906
+ "loss": 0.1487,
2907
+ "step": 414
2908
+ },
2909
+ {
2910
+ "epoch": 7.377777777777778,
2911
+ "grad_norm": 0.8757272362709045,
2912
+ "learning_rate": 1.906978420031059e-05,
2913
+ "loss": 0.1809,
2914
+ "step": 415
2915
+ },
2916
+ {
2917
+ "epoch": 7.395555555555555,
2918
+ "grad_norm": 0.4900935888290405,
2919
+ "learning_rate": 1.8825509907063327e-05,
2920
+ "loss": 0.1134,
2921
+ "step": 416
2922
+ },
2923
+ {
2924
+ "epoch": 7.413333333333333,
2925
+ "grad_norm": 0.4308149218559265,
2926
+ "learning_rate": 1.8582446871722636e-05,
2927
+ "loss": 0.1467,
2928
+ "step": 417
2929
+ },
2930
+ {
2931
+ "epoch": 7.431111111111111,
2932
+ "grad_norm": 0.42540425062179565,
2933
+ "learning_rate": 1.8340604538293015e-05,
2934
+ "loss": 0.1813,
2935
+ "step": 418
2936
+ },
2937
+ {
2938
+ "epoch": 7.448888888888889,
2939
+ "grad_norm": 0.9641832113265991,
2940
+ "learning_rate": 1.8099992303349577e-05,
2941
+ "loss": 0.1514,
2942
+ "step": 419
2943
+ },
2944
+ {
2945
+ "epoch": 7.466666666666667,
2946
+ "grad_norm": 0.47594931721687317,
2947
+ "learning_rate": 1.7860619515673033e-05,
2948
+ "loss": 0.1348,
2949
+ "step": 420
2950
+ },
2951
+ {
2952
+ "epoch": 7.484444444444445,
2953
+ "grad_norm": 0.7819913625717163,
2954
+ "learning_rate": 1.7622495475886487e-05,
2955
+ "loss": 0.127,
2956
+ "step": 421
2957
+ },
2958
+ {
2959
+ "epoch": 7.502222222222223,
2960
+ "grad_norm": 0.4303249418735504,
2961
+ "learning_rate": 1.738562943609396e-05,
2962
+ "loss": 0.1081,
2963
+ "step": 422
2964
+ },
2965
+ {
2966
+ "epoch": 7.52,
2967
+ "grad_norm": 0.8481171131134033,
2968
+ "learning_rate": 1.7150030599520984e-05,
2969
+ "loss": 0.1875,
2970
+ "step": 423
2971
+ },
2972
+ {
2973
+ "epoch": 7.5377777777777775,
2974
+ "grad_norm": 0.5441702008247375,
2975
+ "learning_rate": 1.691570812015704e-05,
2976
+ "loss": 0.1278,
2977
+ "step": 424
2978
+ },
2979
+ {
2980
+ "epoch": 7.555555555555555,
2981
+ "grad_norm": 0.6104997992515564,
2982
+ "learning_rate": 1.6682671102399805e-05,
2983
+ "loss": 0.1391,
2984
+ "step": 425
2985
+ },
2986
+ {
2987
+ "epoch": 7.573333333333333,
2988
+ "grad_norm": 0.4054010212421417,
2989
+ "learning_rate": 1.6450928600701504e-05,
2990
+ "loss": 0.1568,
2991
+ "step": 426
2992
+ },
2993
+ {
2994
+ "epoch": 7.591111111111111,
2995
+ "grad_norm": 0.4448254108428955,
2996
+ "learning_rate": 1.622048961921699e-05,
2997
+ "loss": 0.1352,
2998
+ "step": 427
2999
+ },
3000
+ {
3001
+ "epoch": 7.608888888888889,
3002
+ "grad_norm": 0.5302364826202393,
3003
+ "learning_rate": 1.599136311145402e-05,
3004
+ "loss": 0.1635,
3005
+ "step": 428
3006
+ },
3007
+ {
3008
+ "epoch": 7.626666666666667,
3009
+ "grad_norm": 0.42252257466316223,
3010
+ "learning_rate": 1.5763557979925324e-05,
3011
+ "loss": 0.1637,
3012
+ "step": 429
3013
+ },
3014
+ {
3015
+ "epoch": 7.644444444444445,
3016
+ "grad_norm": 0.508930504322052,
3017
+ "learning_rate": 1.553708307580265e-05,
3018
+ "loss": 0.1537,
3019
+ "step": 430
3020
+ },
3021
+ {
3022
+ "epoch": 7.662222222222223,
3023
+ "grad_norm": 0.6009820103645325,
3024
+ "learning_rate": 1.531194719857292e-05,
3025
+ "loss": 0.1205,
3026
+ "step": 431
3027
+ },
3028
+ {
3029
+ "epoch": 7.68,
3030
+ "grad_norm": 0.4471452236175537,
3031
+ "learning_rate": 1.5088159095696363e-05,
3032
+ "loss": 0.128,
3033
+ "step": 432
3034
+ },
3035
+ {
3036
+ "epoch": 7.697777777777778,
3037
+ "grad_norm": 0.6378930807113647,
3038
+ "learning_rate": 1.4865727462266543e-05,
3039
+ "loss": 0.1254,
3040
+ "step": 433
3041
+ },
3042
+ {
3043
+ "epoch": 7.7155555555555555,
3044
+ "grad_norm": 0.627171516418457,
3045
+ "learning_rate": 1.4644660940672627e-05,
3046
+ "loss": 0.1451,
3047
+ "step": 434
3048
+ },
3049
+ {
3050
+ "epoch": 7.733333333333333,
3051
+ "grad_norm": 0.4755552411079407,
3052
+ "learning_rate": 1.4424968120263504e-05,
3053
+ "loss": 0.1285,
3054
+ "step": 435
3055
+ },
3056
+ {
3057
+ "epoch": 7.751111111111111,
3058
+ "grad_norm": 0.6819527745246887,
3059
+ "learning_rate": 1.4206657537014079e-05,
3060
+ "loss": 0.1817,
3061
+ "step": 436
3062
+ },
3063
+ {
3064
+ "epoch": 7.768888888888889,
3065
+ "grad_norm": 0.5436893701553345,
3066
+ "learning_rate": 1.398973767319368e-05,
3067
+ "loss": 0.1569,
3068
+ "step": 437
3069
+ },
3070
+ {
3071
+ "epoch": 7.786666666666667,
3072
+ "grad_norm": 0.506430447101593,
3073
+ "learning_rate": 1.3774216957036367e-05,
3074
+ "loss": 0.1493,
3075
+ "step": 438
3076
+ },
3077
+ {
3078
+ "epoch": 7.804444444444444,
3079
+ "grad_norm": 0.8908332586288452,
3080
+ "learning_rate": 1.3560103762413584e-05,
3081
+ "loss": 0.1215,
3082
+ "step": 439
3083
+ },
3084
+ {
3085
+ "epoch": 7.822222222222222,
3086
+ "grad_norm": 0.38750067353248596,
3087
+ "learning_rate": 1.3347406408508695e-05,
3088
+ "loss": 0.1389,
3089
+ "step": 440
3090
+ },
3091
+ {
3092
+ "epoch": 7.84,
3093
+ "grad_norm": 0.44923001527786255,
3094
+ "learning_rate": 1.3136133159493802e-05,
3095
+ "loss": 0.113,
3096
+ "step": 441
3097
+ },
3098
+ {
3099
+ "epoch": 7.857777777777778,
3100
+ "grad_norm": 0.4674062132835388,
3101
+ "learning_rate": 1.2926292224208664e-05,
3102
+ "loss": 0.1344,
3103
+ "step": 442
3104
+ },
3105
+ {
3106
+ "epoch": 7.875555555555556,
3107
+ "grad_norm": 0.47324058413505554,
3108
+ "learning_rate": 1.2717891755841722e-05,
3109
+ "loss": 0.1363,
3110
+ "step": 443
3111
+ },
3112
+ {
3113
+ "epoch": 7.8933333333333335,
3114
+ "grad_norm": 0.6032904386520386,
3115
+ "learning_rate": 1.2510939851613285e-05,
3116
+ "loss": 0.1293,
3117
+ "step": 444
3118
+ },
3119
+ {
3120
+ "epoch": 7.911111111111111,
3121
+ "grad_norm": 0.4771234393119812,
3122
+ "learning_rate": 1.230544455246101e-05,
3123
+ "loss": 0.161,
3124
+ "step": 445
3125
+ },
3126
+ {
3127
+ "epoch": 7.928888888888888,
3128
+ "grad_norm": 0.48323342204093933,
3129
+ "learning_rate": 1.2101413842727345e-05,
3130
+ "loss": 0.1336,
3131
+ "step": 446
3132
+ },
3133
+ {
3134
+ "epoch": 7.946666666666666,
3135
+ "grad_norm": 0.34565791487693787,
3136
+ "learning_rate": 1.1898855649849461e-05,
3137
+ "loss": 0.177,
3138
+ "step": 447
3139
+ },
3140
+ {
3141
+ "epoch": 7.964444444444444,
3142
+ "grad_norm": 0.39549532532691956,
3143
+ "learning_rate": 1.1697777844051105e-05,
3144
+ "loss": 0.1431,
3145
+ "step": 448
3146
+ },
3147
+ {
3148
+ "epoch": 7.982222222222222,
3149
+ "grad_norm": 0.45379385352134705,
3150
+ "learning_rate": 1.1498188238036861e-05,
3151
+ "loss": 0.1503,
3152
+ "step": 449
3153
+ },
3154
+ {
3155
+ "epoch": 8.0,
3156
+ "grad_norm": 0.5633464455604553,
3157
+ "learning_rate": 1.130009458668863e-05,
3158
+ "loss": 0.1328,
3159
+ "step": 450
3160
+ },
3161
+ {
3162
+ "epoch": 8.017777777777777,
3163
+ "grad_norm": 0.42473697662353516,
3164
+ "learning_rate": 1.1103504586764263e-05,
3165
+ "loss": 0.1182,
3166
+ "step": 451
3167
+ },
3168
+ {
3169
+ "epoch": 8.035555555555556,
3170
+ "grad_norm": 0.34909459948539734,
3171
+ "learning_rate": 1.090842587659851e-05,
3172
+ "loss": 0.1369,
3173
+ "step": 452
3174
+ },
3175
+ {
3176
+ "epoch": 8.053333333333333,
3177
+ "grad_norm": 0.49491363763809204,
3178
+ "learning_rate": 1.0714866035806326e-05,
3179
+ "loss": 0.1346,
3180
+ "step": 453
3181
+ },
3182
+ {
3183
+ "epoch": 8.071111111111112,
3184
+ "grad_norm": 0.39719170331954956,
3185
+ "learning_rate": 1.0522832584988234e-05,
3186
+ "loss": 0.144,
3187
+ "step": 454
3188
+ },
3189
+ {
3190
+ "epoch": 8.088888888888889,
3191
+ "grad_norm": 0.530826210975647,
3192
+ "learning_rate": 1.0332332985438248e-05,
3193
+ "loss": 0.1522,
3194
+ "step": 455
3195
+ },
3196
+ {
3197
+ "epoch": 8.106666666666667,
3198
+ "grad_norm": 0.44326362013816833,
3199
+ "learning_rate": 1.0143374638853891e-05,
3200
+ "loss": 0.1347,
3201
+ "step": 456
3202
+ },
3203
+ {
3204
+ "epoch": 8.124444444444444,
3205
+ "grad_norm": 0.47626104950904846,
3206
+ "learning_rate": 9.955964887048607e-06,
3207
+ "loss": 0.1371,
3208
+ "step": 457
3209
+ },
3210
+ {
3211
+ "epoch": 8.142222222222221,
3212
+ "grad_norm": 0.532647430896759,
3213
+ "learning_rate": 9.770111011666583e-06,
3214
+ "loss": 0.1247,
3215
+ "step": 458
3216
+ },
3217
+ {
3218
+ "epoch": 8.16,
3219
+ "grad_norm": 0.6383976340293884,
3220
+ "learning_rate": 9.58582023389974e-06,
3221
+ "loss": 0.1328,
3222
+ "step": 459
3223
+ },
3224
+ {
3225
+ "epoch": 8.177777777777777,
3226
+ "grad_norm": 0.6057294011116028,
3227
+ "learning_rate": 9.403099714207175e-06,
3228
+ "loss": 0.1485,
3229
+ "step": 460
3230
+ },
3231
+ {
3232
+ "epoch": 8.195555555555556,
3233
+ "grad_norm": 0.3655204474925995,
3234
+ "learning_rate": 9.221956552036992e-06,
3235
+ "loss": 0.1226,
3236
+ "step": 461
3237
+ },
3238
+ {
3239
+ "epoch": 8.213333333333333,
3240
+ "grad_norm": 0.3895055055618286,
3241
+ "learning_rate": 9.042397785550405e-06,
3242
+ "loss": 0.1297,
3243
+ "step": 462
3244
+ },
3245
+ {
3246
+ "epoch": 8.231111111111112,
3247
+ "grad_norm": 0.42906251549720764,
3248
+ "learning_rate": 8.864430391348332e-06,
3249
+ "loss": 0.1209,
3250
+ "step": 463
3251
+ },
3252
+ {
3253
+ "epoch": 8.248888888888889,
3254
+ "grad_norm": 0.6001704335212708,
3255
+ "learning_rate": 8.688061284200266e-06,
3256
+ "loss": 0.0914,
3257
+ "step": 464
3258
+ },
3259
+ {
3260
+ "epoch": 8.266666666666667,
3261
+ "grad_norm": 0.5638251304626465,
3262
+ "learning_rate": 8.513297316775625e-06,
3263
+ "loss": 0.1514,
3264
+ "step": 465
3265
+ },
3266
+ {
3267
+ "epoch": 8.284444444444444,
3268
+ "grad_norm": 0.6026332378387451,
3269
+ "learning_rate": 8.34014527937756e-06,
3270
+ "loss": 0.1336,
3271
+ "step": 466
3272
+ },
3273
+ {
3274
+ "epoch": 8.302222222222222,
3275
+ "grad_norm": 0.4549403190612793,
3276
+ "learning_rate": 8.168611899679013e-06,
3277
+ "loss": 0.1287,
3278
+ "step": 467
3279
+ },
3280
+ {
3281
+ "epoch": 8.32,
3282
+ "grad_norm": 0.48877498507499695,
3283
+ "learning_rate": 7.998703842461431e-06,
3284
+ "loss": 0.1336,
3285
+ "step": 468
3286
+ },
3287
+ {
3288
+ "epoch": 8.337777777777777,
3289
+ "grad_norm": 0.7382359504699707,
3290
+ "learning_rate": 7.830427709355725e-06,
3291
+ "loss": 0.1321,
3292
+ "step": 469
3293
+ },
3294
+ {
3295
+ "epoch": 8.355555555555556,
3296
+ "grad_norm": 0.6301836371421814,
3297
+ "learning_rate": 7.663790038585793e-06,
3298
+ "loss": 0.1072,
3299
+ "step": 470
3300
+ },
3301
+ {
3302
+ "epoch": 8.373333333333333,
3303
+ "grad_norm": 0.45454826951026917,
3304
+ "learning_rate": 7.498797304714544e-06,
3305
+ "loss": 0.1336,
3306
+ "step": 471
3307
+ },
3308
+ {
3309
+ "epoch": 8.391111111111112,
3310
+ "grad_norm": 0.5664876103401184,
3311
+ "learning_rate": 7.33545591839222e-06,
3312
+ "loss": 0.1141,
3313
+ "step": 472
3314
+ },
3315
+ {
3316
+ "epoch": 8.408888888888889,
3317
+ "grad_norm": 0.45692479610443115,
3318
+ "learning_rate": 7.173772226107434e-06,
3319
+ "loss": 0.1143,
3320
+ "step": 473
3321
+ },
3322
+ {
3323
+ "epoch": 8.426666666666666,
3324
+ "grad_norm": 0.3842525780200958,
3325
+ "learning_rate": 7.013752509940485e-06,
3326
+ "loss": 0.1242,
3327
+ "step": 474
3328
+ },
3329
+ {
3330
+ "epoch": 8.444444444444445,
3331
+ "grad_norm": 0.5034791827201843,
3332
+ "learning_rate": 6.855402987319348e-06,
3333
+ "loss": 0.1302,
3334
+ "step": 475
3335
+ },
3336
+ {
3337
+ "epoch": 8.462222222222222,
3338
+ "grad_norm": 1.0054627656936646,
3339
+ "learning_rate": 6.698729810778065e-06,
3340
+ "loss": 0.1245,
3341
+ "step": 476
3342
+ },
3343
+ {
3344
+ "epoch": 8.48,
3345
+ "grad_norm": 0.5008876919746399,
3346
+ "learning_rate": 6.54373906771768e-06,
3347
+ "loss": 0.134,
3348
+ "step": 477
3349
+ },
3350
+ {
3351
+ "epoch": 8.497777777777777,
3352
+ "grad_norm": 0.6585814356803894,
3353
+ "learning_rate": 6.390436780169734e-06,
3354
+ "loss": 0.1106,
3355
+ "step": 478
3356
+ },
3357
+ {
3358
+ "epoch": 8.515555555555556,
3359
+ "grad_norm": 0.40638384222984314,
3360
+ "learning_rate": 6.238828904562316e-06,
3361
+ "loss": 0.1309,
3362
+ "step": 479
3363
+ },
3364
+ {
3365
+ "epoch": 8.533333333333333,
3366
+ "grad_norm": 0.6327247619628906,
3367
+ "learning_rate": 6.088921331488568e-06,
3368
+ "loss": 0.1263,
3369
+ "step": 480
3370
+ },
3371
+ {
3372
+ "epoch": 8.551111111111112,
3373
+ "grad_norm": 0.4367387592792511,
3374
+ "learning_rate": 5.94071988547788e-06,
3375
+ "loss": 0.1018,
3376
+ "step": 481
3377
+ },
3378
+ {
3379
+ "epoch": 8.568888888888889,
3380
+ "grad_norm": 0.5796259641647339,
3381
+ "learning_rate": 5.794230324769517e-06,
3382
+ "loss": 0.1568,
3383
+ "step": 482
3384
+ },
3385
+ {
3386
+ "epoch": 8.586666666666666,
3387
+ "grad_norm": 0.485882043838501,
3388
+ "learning_rate": 5.649458341088915e-06,
3389
+ "loss": 0.1537,
3390
+ "step": 483
3391
+ },
3392
+ {
3393
+ "epoch": 8.604444444444445,
3394
+ "grad_norm": 0.38468489050865173,
3395
+ "learning_rate": 5.506409559426573e-06,
3396
+ "loss": 0.1364,
3397
+ "step": 484
3398
+ },
3399
+ {
3400
+ "epoch": 8.622222222222222,
3401
+ "grad_norm": 2.784595012664795,
3402
+ "learning_rate": 5.365089537819434e-06,
3403
+ "loss": 0.1214,
3404
+ "step": 485
3405
+ },
3406
+ {
3407
+ "epoch": 8.64,
3408
+ "grad_norm": 0.40455055236816406,
3409
+ "learning_rate": 5.2255037671349535e-06,
3410
+ "loss": 0.1029,
3411
+ "step": 486
3412
+ },
3413
+ {
3414
+ "epoch": 8.657777777777778,
3415
+ "grad_norm": 0.5025741457939148,
3416
+ "learning_rate": 5.087657670857798e-06,
3417
+ "loss": 0.1279,
3418
+ "step": 487
3419
+ },
3420
+ {
3421
+ "epoch": 8.675555555555556,
3422
+ "grad_norm": 0.5535502433776855,
3423
+ "learning_rate": 4.951556604879048e-06,
3424
+ "loss": 0.1055,
3425
+ "step": 488
3426
+ },
3427
+ {
3428
+ "epoch": 8.693333333333333,
3429
+ "grad_norm": 0.47892096638679504,
3430
+ "learning_rate": 4.8172058572881765e-06,
3431
+ "loss": 0.1115,
3432
+ "step": 489
3433
+ },
3434
+ {
3435
+ "epoch": 8.71111111111111,
3436
+ "grad_norm": 0.6920176148414612,
3437
+ "learning_rate": 4.684610648167503e-06,
3438
+ "loss": 0.1337,
3439
+ "step": 490
3440
+ },
3441
+ {
3442
+ "epoch": 8.72888888888889,
3443
+ "grad_norm": 0.41214314103126526,
3444
+ "learning_rate": 4.5537761293894535e-06,
3445
+ "loss": 0.1677,
3446
+ "step": 491
3447
+ },
3448
+ {
3449
+ "epoch": 8.746666666666666,
3450
+ "grad_norm": 0.4349137544631958,
3451
+ "learning_rate": 4.424707384416344e-06,
3452
+ "loss": 0.1281,
3453
+ "step": 492
3454
+ },
3455
+ {
3456
+ "epoch": 8.764444444444445,
3457
+ "grad_norm": 0.5308365225791931,
3458
+ "learning_rate": 4.29740942810285e-06,
3459
+ "loss": 0.1464,
3460
+ "step": 493
3461
+ },
3462
+ {
3463
+ "epoch": 8.782222222222222,
3464
+ "grad_norm": 0.5176928043365479,
3465
+ "learning_rate": 4.1718872065011904e-06,
3466
+ "loss": 0.1266,
3467
+ "step": 494
3468
+ },
3469
+ {
3470
+ "epoch": 8.8,
3471
+ "grad_norm": 0.4264501631259918,
3472
+ "learning_rate": 4.048145596668967e-06,
3473
+ "loss": 0.1355,
3474
+ "step": 495
3475
+ },
3476
+ {
3477
+ "epoch": 8.817777777777778,
3478
+ "grad_norm": 0.5254343152046204,
3479
+ "learning_rate": 3.9261894064796135e-06,
3480
+ "loss": 0.144,
3481
+ "step": 496
3482
+ },
3483
+ {
3484
+ "epoch": 8.835555555555555,
3485
+ "grad_norm": 0.400968998670578,
3486
+ "learning_rate": 3.8060233744356633e-06,
3487
+ "loss": 0.1422,
3488
+ "step": 497
3489
+ },
3490
+ {
3491
+ "epoch": 8.853333333333333,
3492
+ "grad_norm": 0.7004261016845703,
3493
+ "learning_rate": 3.687652169484568e-06,
3494
+ "loss": 0.1472,
3495
+ "step": 498
3496
+ },
3497
+ {
3498
+ "epoch": 8.87111111111111,
3499
+ "grad_norm": 0.42059558629989624,
3500
+ "learning_rate": 3.5710803908373224e-06,
3501
+ "loss": 0.1145,
3502
+ "step": 499
3503
+ },
3504
+ {
3505
+ "epoch": 8.88888888888889,
3506
+ "grad_norm": 0.5794507265090942,
3507
+ "learning_rate": 3.4563125677897932e-06,
3508
+ "loss": 0.1145,
3509
+ "step": 500
3510
+ },
3511
+ {
3512
+ "epoch": 8.88888888888889,
3513
+ "eval_loss": 0.3872971832752228,
3514
+ "eval_runtime": 44.5374,
3515
+ "eval_samples_per_second": 2.245,
3516
+ "eval_steps_per_second": 2.245,
3517
+ "step": 500
3518
+ }
3519
+ ],
3520
+ "logging_steps": 1,
3521
+ "max_steps": 560,
3522
+ "num_input_tokens_seen": 0,
3523
+ "num_train_epochs": 10,
3524
+ "save_steps": 500,
3525
+ "stateful_callbacks": {
3526
+ "TrainerControl": {
3527
+ "args": {
3528
+ "should_epoch_stop": false,
3529
+ "should_evaluate": false,
3530
+ "should_log": false,
3531
+ "should_save": true,
3532
+ "should_training_stop": false
3533
+ },
3534
+ "attributes": {}
3535
+ }
3536
+ },
3537
+ "total_flos": 8.141377228159058e+17,
3538
+ "train_batch_size": 2,
3539
+ "trial_name": null,
3540
+ "trial_params": null
3541
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81376cdd08e4423e634cf2f773917ef87ef1b08af1ab1340738fb6d1caed3ec5
3
+ size 5304
checkpoint-560/README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: OdiaGenAI-LLM/llama_3_8b_odia_pt
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 0.11.1
checkpoint-560/adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "OdiaGenAI-LLM/llama_3_8b_odia_pt",
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
+ "down_proj",
24
+ "up_proj",
25
+ "k_proj",
26
+ "gate_proj",
27
+ "q_proj",
28
+ "o_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
checkpoint-560/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7755f3281134f8bf1a862da826b309934503ff9270d29a7a522900287e073ad8
3
+ size 83945296
checkpoint-560/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6076a3010a5a47ca49a81ae82fbfcbb757d3faf9dbc55dda491bdd580b1c22d
3
+ size 168149074
checkpoint-560/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5edb34d031c0c2b447f3eaadb401a4c1e7e7e6d8c096e28b7092e01a8bd48c92
3
+ size 14244
checkpoint-560/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20715e03e6f2f2744bc1fba8c744854dc7b82c89d8238b57676982792c428010
3
+ size 1064
checkpoint-560/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
checkpoint-560/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-560/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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
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 system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in 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": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
checkpoint-560/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-560/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81376cdd08e4423e634cf2f773917ef87ef1b08af1ab1340738fb6d1caed3ec5
3
+ size 5304
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 9.955555555555556,
3
+ "eval_loss": 0.39617523550987244,
4
+ "eval_runtime": 44.4947,
5
+ "eval_samples_per_second": 2.247,
6
+ "eval_steps_per_second": 2.247
7
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|end_of_text|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
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": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
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": "<|reserved_special_token_4|>",
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": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
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 system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>\n\n' + system_message + '<|eot_id|>' }}{% endif %}{% for message in 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": 1000000000000000019884624838656,
2061
+ "pad_token": "<|end_of_text|>",
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": 9.955555555555556,
3
+ "total_flos": 9.116617776876749e+17,
4
+ "train_loss": 0.2247792588014688,
5
+ "train_runtime": 17934.4708,
6
+ "train_samples_per_second": 0.502,
7
+ "train_steps_per_second": 0.031
8
+ }
trainer_log.jsonl ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81376cdd08e4423e634cf2f773917ef87ef1b08af1ab1340738fb6d1caed3ec5
3
+ size 5304
training_eval_loss.png ADDED
training_loss.png ADDED