Upload folder using huggingface_hub
Browse files- .gitattributes +4 -0
- README.md +202 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- checkpoint-1000/README.md +202 -0
- checkpoint-1000/adapter_config.json +39 -0
- checkpoint-1000/adapter_model.safetensors +3 -0
- checkpoint-1000/optimizer.pt +3 -0
- checkpoint-1000/rng_state.pth +3 -0
- checkpoint-1000/scaler.pt +3 -0
- checkpoint-1000/scheduler.pt +3 -0
- checkpoint-1000/special_tokens_map.json +23 -0
- checkpoint-1000/tokenizer.json +3 -0
- checkpoint-1000/tokenizer_config.json +2067 -0
- checkpoint-1000/trainer_state.json +1014 -0
- checkpoint-1000/training_args.bin +3 -0
- checkpoint-800/README.md +202 -0
- checkpoint-800/adapter_config.json +39 -0
- checkpoint-800/adapter_model.safetensors +3 -0
- checkpoint-800/optimizer.pt +3 -0
- checkpoint-800/rng_state.pth +3 -0
- checkpoint-800/scaler.pt +3 -0
- checkpoint-800/scheduler.pt +3 -0
- checkpoint-800/special_tokens_map.json +23 -0
- checkpoint-800/tokenizer.json +3 -0
- checkpoint-800/tokenizer_config.json +2067 -0
- checkpoint-800/trainer_state.json +818 -0
- checkpoint-800/training_args.bin +3 -0
- checkpoint-900/README.md +202 -0
- checkpoint-900/adapter_config.json +39 -0
- checkpoint-900/adapter_model.safetensors +3 -0
- checkpoint-900/optimizer.pt +3 -0
- checkpoint-900/rng_state.pth +3 -0
- checkpoint-900/scaler.pt +3 -0
- checkpoint-900/scheduler.pt +3 -0
- checkpoint-900/special_tokens_map.json +23 -0
- checkpoint-900/tokenizer.json +3 -0
- checkpoint-900/tokenizer_config.json +2067 -0
- checkpoint-900/trainer_state.json +916 -0
- checkpoint-900/training_args.bin +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2067 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
checkpoint-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
checkpoint-900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
|
| 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 0.15.2
|
adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 16,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"v_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"up_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"q_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1202581478277adf0388c8cb761fb6f9cbe9436e088a6de175aff9a010001ceb
|
| 3 |
+
size 167832240
|
checkpoint-1000/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
|
| 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 0.15.2
|
checkpoint-1000/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 16,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"v_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"up_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"q_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-1000/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1202581478277adf0388c8cb761fb6f9cbe9436e088a6de175aff9a010001ceb
|
| 3 |
+
size 167832240
|
checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8b2f7bae405db88f1f56d538907ed350d5f1dbb770ee2c28dd23b9de9e23ae1
|
| 3 |
+
size 335922851
|
checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2aea247fc522d0f1028f2c86776996597eb6a1f2631824241edbe69b4ac9ed83
|
| 3 |
+
size 14645
|
checkpoint-1000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
|
| 3 |
+
size 1383
|
checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55ed4d9fa7502fc9a7179d50fdbbfdf7f05207514568d8410679a326d6e91876
|
| 3 |
+
size 1465
|
checkpoint-1000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin▁of▁sentence|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end▁of▁sentence|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|end▁of▁sentence|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-1000/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
|
| 3 |
+
size 17209530
|
checkpoint-1000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2067 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"128000": {
|
| 7 |
+
"content": "<|begin▁of▁sentence|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"128001": {
|
| 15 |
+
"content": "<|end▁of▁sentence|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"128002": {
|
| 23 |
+
"content": "<|reserved_special_token_0|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"128003": {
|
| 31 |
+
"content": "<|reserved_special_token_1|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"128004": {
|
| 39 |
+
"content": "<|finetune_right_pad_id|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"128005": {
|
| 47 |
+
"content": "<|reserved_special_token_2|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"128006": {
|
| 55 |
+
"content": "<|start_header_id|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"128007": {
|
| 63 |
+
"content": "<|end_header_id|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"128008": {
|
| 71 |
+
"content": "<|eom_id|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"128009": {
|
| 79 |
+
"content": "<|eot_id|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"128010": {
|
| 87 |
+
"content": "<|python_tag|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"128011": {
|
| 95 |
+
"content": "<|User|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"128012": {
|
| 103 |
+
"content": "<|Assistant|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"128013": {
|
| 111 |
+
"content": "<think>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"128014": {
|
| 119 |
+
"content": "</think>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"128015": {
|
| 127 |
+
"content": "<|▁pad▁|>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": true
|
| 133 |
+
},
|
| 134 |
+
"128016": {
|
| 135 |
+
"content": "<|reserved_special_token_8|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": true
|
| 141 |
+
},
|
| 142 |
+
"128017": {
|
| 143 |
+
"content": "<|reserved_special_token_9|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
"128018": {
|
| 151 |
+
"content": "<|reserved_special_token_10|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": true
|
| 157 |
+
},
|
| 158 |
+
"128019": {
|
| 159 |
+
"content": "<|reserved_special_token_11|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": true
|
| 165 |
+
},
|
| 166 |
+
"128020": {
|
| 167 |
+
"content": "<|reserved_special_token_12|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": true
|
| 173 |
+
},
|
| 174 |
+
"128021": {
|
| 175 |
+
"content": "<|reserved_special_token_13|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
},
|
| 182 |
+
"128022": {
|
| 183 |
+
"content": "<|reserved_special_token_14|>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": true
|
| 189 |
+
},
|
| 190 |
+
"128023": {
|
| 191 |
+
"content": "<|reserved_special_token_15|>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": true
|
| 197 |
+
},
|
| 198 |
+
"128024": {
|
| 199 |
+
"content": "<|reserved_special_token_16|>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": true
|
| 205 |
+
},
|
| 206 |
+
"128025": {
|
| 207 |
+
"content": "<|reserved_special_token_17|>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": true
|
| 213 |
+
},
|
| 214 |
+
"128026": {
|
| 215 |
+
"content": "<|reserved_special_token_18|>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
"128027": {
|
| 223 |
+
"content": "<|reserved_special_token_19|>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
},
|
| 230 |
+
"128028": {
|
| 231 |
+
"content": "<|reserved_special_token_20|>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
"128029": {
|
| 239 |
+
"content": "<|reserved_special_token_21|>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"128030": {
|
| 247 |
+
"content": "<|reserved_special_token_22|>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"128031": {
|
| 255 |
+
"content": "<|reserved_special_token_23|>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": true
|
| 261 |
+
},
|
| 262 |
+
"128032": {
|
| 263 |
+
"content": "<|reserved_special_token_24|>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": true
|
| 269 |
+
},
|
| 270 |
+
"128033": {
|
| 271 |
+
"content": "<|reserved_special_token_25|>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": true
|
| 277 |
+
},
|
| 278 |
+
"128034": {
|
| 279 |
+
"content": "<|reserved_special_token_26|>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": true
|
| 285 |
+
},
|
| 286 |
+
"128035": {
|
| 287 |
+
"content": "<|reserved_special_token_27|>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
"128036": {
|
| 295 |
+
"content": "<|reserved_special_token_28|>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
},
|
| 302 |
+
"128037": {
|
| 303 |
+
"content": "<|reserved_special_token_29|>",
|
| 304 |
+
"lstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"rstrip": false,
|
| 307 |
+
"single_word": false,
|
| 308 |
+
"special": true
|
| 309 |
+
},
|
| 310 |
+
"128038": {
|
| 311 |
+
"content": "<|reserved_special_token_30|>",
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"normalized": false,
|
| 314 |
+
"rstrip": false,
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"special": true
|
| 317 |
+
},
|
| 318 |
+
"128039": {
|
| 319 |
+
"content": "<|reserved_special_token_31|>",
|
| 320 |
+
"lstrip": false,
|
| 321 |
+
"normalized": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false,
|
| 324 |
+
"special": true
|
| 325 |
+
},
|
| 326 |
+
"128040": {
|
| 327 |
+
"content": "<|reserved_special_token_32|>",
|
| 328 |
+
"lstrip": false,
|
| 329 |
+
"normalized": false,
|
| 330 |
+
"rstrip": false,
|
| 331 |
+
"single_word": false,
|
| 332 |
+
"special": true
|
| 333 |
+
},
|
| 334 |
+
"128041": {
|
| 335 |
+
"content": "<|reserved_special_token_33|>",
|
| 336 |
+
"lstrip": false,
|
| 337 |
+
"normalized": false,
|
| 338 |
+
"rstrip": false,
|
| 339 |
+
"single_word": false,
|
| 340 |
+
"special": true
|
| 341 |
+
},
|
| 342 |
+
"128042": {
|
| 343 |
+
"content": "<|reserved_special_token_34|>",
|
| 344 |
+
"lstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"rstrip": false,
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"special": true
|
| 349 |
+
},
|
| 350 |
+
"128043": {
|
| 351 |
+
"content": "<|reserved_special_token_35|>",
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"normalized": false,
|
| 354 |
+
"rstrip": false,
|
| 355 |
+
"single_word": false,
|
| 356 |
+
"special": true
|
| 357 |
+
},
|
| 358 |
+
"128044": {
|
| 359 |
+
"content": "<|reserved_special_token_36|>",
|
| 360 |
+
"lstrip": false,
|
| 361 |
+
"normalized": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"single_word": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
"128045": {
|
| 367 |
+
"content": "<|reserved_special_token_37|>",
|
| 368 |
+
"lstrip": false,
|
| 369 |
+
"normalized": false,
|
| 370 |
+
"rstrip": false,
|
| 371 |
+
"single_word": false,
|
| 372 |
+
"special": true
|
| 373 |
+
},
|
| 374 |
+
"128046": {
|
| 375 |
+
"content": "<|reserved_special_token_38|>",
|
| 376 |
+
"lstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"single_word": false,
|
| 380 |
+
"special": true
|
| 381 |
+
},
|
| 382 |
+
"128047": {
|
| 383 |
+
"content": "<|reserved_special_token_39|>",
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"normalized": false,
|
| 386 |
+
"rstrip": false,
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"special": true
|
| 389 |
+
},
|
| 390 |
+
"128048": {
|
| 391 |
+
"content": "<|reserved_special_token_40|>",
|
| 392 |
+
"lstrip": false,
|
| 393 |
+
"normalized": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"single_word": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
"128049": {
|
| 399 |
+
"content": "<|reserved_special_token_41|>",
|
| 400 |
+
"lstrip": false,
|
| 401 |
+
"normalized": false,
|
| 402 |
+
"rstrip": false,
|
| 403 |
+
"single_word": false,
|
| 404 |
+
"special": true
|
| 405 |
+
},
|
| 406 |
+
"128050": {
|
| 407 |
+
"content": "<|reserved_special_token_42|>",
|
| 408 |
+
"lstrip": false,
|
| 409 |
+
"normalized": false,
|
| 410 |
+
"rstrip": false,
|
| 411 |
+
"single_word": false,
|
| 412 |
+
"special": true
|
| 413 |
+
},
|
| 414 |
+
"128051": {
|
| 415 |
+
"content": "<|reserved_special_token_43|>",
|
| 416 |
+
"lstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"rstrip": false,
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"special": true
|
| 421 |
+
},
|
| 422 |
+
"128052": {
|
| 423 |
+
"content": "<|reserved_special_token_44|>",
|
| 424 |
+
"lstrip": false,
|
| 425 |
+
"normalized": false,
|
| 426 |
+
"rstrip": false,
|
| 427 |
+
"single_word": false,
|
| 428 |
+
"special": true
|
| 429 |
+
},
|
| 430 |
+
"128053": {
|
| 431 |
+
"content": "<|reserved_special_token_45|>",
|
| 432 |
+
"lstrip": false,
|
| 433 |
+
"normalized": false,
|
| 434 |
+
"rstrip": false,
|
| 435 |
+
"single_word": false,
|
| 436 |
+
"special": true
|
| 437 |
+
},
|
| 438 |
+
"128054": {
|
| 439 |
+
"content": "<|reserved_special_token_46|>",
|
| 440 |
+
"lstrip": false,
|
| 441 |
+
"normalized": false,
|
| 442 |
+
"rstrip": false,
|
| 443 |
+
"single_word": false,
|
| 444 |
+
"special": true
|
| 445 |
+
},
|
| 446 |
+
"128055": {
|
| 447 |
+
"content": "<|reserved_special_token_47|>",
|
| 448 |
+
"lstrip": false,
|
| 449 |
+
"normalized": false,
|
| 450 |
+
"rstrip": false,
|
| 451 |
+
"single_word": false,
|
| 452 |
+
"special": true
|
| 453 |
+
},
|
| 454 |
+
"128056": {
|
| 455 |
+
"content": "<|reserved_special_token_48|>",
|
| 456 |
+
"lstrip": false,
|
| 457 |
+
"normalized": false,
|
| 458 |
+
"rstrip": false,
|
| 459 |
+
"single_word": false,
|
| 460 |
+
"special": true
|
| 461 |
+
},
|
| 462 |
+
"128057": {
|
| 463 |
+
"content": "<|reserved_special_token_49|>",
|
| 464 |
+
"lstrip": false,
|
| 465 |
+
"normalized": false,
|
| 466 |
+
"rstrip": false,
|
| 467 |
+
"single_word": false,
|
| 468 |
+
"special": true
|
| 469 |
+
},
|
| 470 |
+
"128058": {
|
| 471 |
+
"content": "<|reserved_special_token_50|>",
|
| 472 |
+
"lstrip": false,
|
| 473 |
+
"normalized": false,
|
| 474 |
+
"rstrip": false,
|
| 475 |
+
"single_word": false,
|
| 476 |
+
"special": true
|
| 477 |
+
},
|
| 478 |
+
"128059": {
|
| 479 |
+
"content": "<|reserved_special_token_51|>",
|
| 480 |
+
"lstrip": false,
|
| 481 |
+
"normalized": false,
|
| 482 |
+
"rstrip": false,
|
| 483 |
+
"single_word": false,
|
| 484 |
+
"special": true
|
| 485 |
+
},
|
| 486 |
+
"128060": {
|
| 487 |
+
"content": "<|reserved_special_token_52|>",
|
| 488 |
+
"lstrip": false,
|
| 489 |
+
"normalized": false,
|
| 490 |
+
"rstrip": false,
|
| 491 |
+
"single_word": false,
|
| 492 |
+
"special": true
|
| 493 |
+
},
|
| 494 |
+
"128061": {
|
| 495 |
+
"content": "<|reserved_special_token_53|>",
|
| 496 |
+
"lstrip": false,
|
| 497 |
+
"normalized": false,
|
| 498 |
+
"rstrip": false,
|
| 499 |
+
"single_word": false,
|
| 500 |
+
"special": true
|
| 501 |
+
},
|
| 502 |
+
"128062": {
|
| 503 |
+
"content": "<|reserved_special_token_54|>",
|
| 504 |
+
"lstrip": false,
|
| 505 |
+
"normalized": false,
|
| 506 |
+
"rstrip": false,
|
| 507 |
+
"single_word": false,
|
| 508 |
+
"special": true
|
| 509 |
+
},
|
| 510 |
+
"128063": {
|
| 511 |
+
"content": "<|reserved_special_token_55|>",
|
| 512 |
+
"lstrip": false,
|
| 513 |
+
"normalized": false,
|
| 514 |
+
"rstrip": false,
|
| 515 |
+
"single_word": false,
|
| 516 |
+
"special": true
|
| 517 |
+
},
|
| 518 |
+
"128064": {
|
| 519 |
+
"content": "<|reserved_special_token_56|>",
|
| 520 |
+
"lstrip": false,
|
| 521 |
+
"normalized": false,
|
| 522 |
+
"rstrip": false,
|
| 523 |
+
"single_word": false,
|
| 524 |
+
"special": true
|
| 525 |
+
},
|
| 526 |
+
"128065": {
|
| 527 |
+
"content": "<|reserved_special_token_57|>",
|
| 528 |
+
"lstrip": false,
|
| 529 |
+
"normalized": false,
|
| 530 |
+
"rstrip": false,
|
| 531 |
+
"single_word": false,
|
| 532 |
+
"special": true
|
| 533 |
+
},
|
| 534 |
+
"128066": {
|
| 535 |
+
"content": "<|reserved_special_token_58|>",
|
| 536 |
+
"lstrip": false,
|
| 537 |
+
"normalized": false,
|
| 538 |
+
"rstrip": false,
|
| 539 |
+
"single_word": false,
|
| 540 |
+
"special": true
|
| 541 |
+
},
|
| 542 |
+
"128067": {
|
| 543 |
+
"content": "<|reserved_special_token_59|>",
|
| 544 |
+
"lstrip": false,
|
| 545 |
+
"normalized": false,
|
| 546 |
+
"rstrip": false,
|
| 547 |
+
"single_word": false,
|
| 548 |
+
"special": true
|
| 549 |
+
},
|
| 550 |
+
"128068": {
|
| 551 |
+
"content": "<|reserved_special_token_60|>",
|
| 552 |
+
"lstrip": false,
|
| 553 |
+
"normalized": false,
|
| 554 |
+
"rstrip": false,
|
| 555 |
+
"single_word": false,
|
| 556 |
+
"special": true
|
| 557 |
+
},
|
| 558 |
+
"128069": {
|
| 559 |
+
"content": "<|reserved_special_token_61|>",
|
| 560 |
+
"lstrip": false,
|
| 561 |
+
"normalized": false,
|
| 562 |
+
"rstrip": false,
|
| 563 |
+
"single_word": false,
|
| 564 |
+
"special": true
|
| 565 |
+
},
|
| 566 |
+
"128070": {
|
| 567 |
+
"content": "<|reserved_special_token_62|>",
|
| 568 |
+
"lstrip": false,
|
| 569 |
+
"normalized": false,
|
| 570 |
+
"rstrip": false,
|
| 571 |
+
"single_word": false,
|
| 572 |
+
"special": true
|
| 573 |
+
},
|
| 574 |
+
"128071": {
|
| 575 |
+
"content": "<|reserved_special_token_63|>",
|
| 576 |
+
"lstrip": false,
|
| 577 |
+
"normalized": false,
|
| 578 |
+
"rstrip": false,
|
| 579 |
+
"single_word": false,
|
| 580 |
+
"special": true
|
| 581 |
+
},
|
| 582 |
+
"128072": {
|
| 583 |
+
"content": "<|reserved_special_token_64|>",
|
| 584 |
+
"lstrip": false,
|
| 585 |
+
"normalized": false,
|
| 586 |
+
"rstrip": false,
|
| 587 |
+
"single_word": false,
|
| 588 |
+
"special": true
|
| 589 |
+
},
|
| 590 |
+
"128073": {
|
| 591 |
+
"content": "<|reserved_special_token_65|>",
|
| 592 |
+
"lstrip": false,
|
| 593 |
+
"normalized": false,
|
| 594 |
+
"rstrip": false,
|
| 595 |
+
"single_word": false,
|
| 596 |
+
"special": true
|
| 597 |
+
},
|
| 598 |
+
"128074": {
|
| 599 |
+
"content": "<|reserved_special_token_66|>",
|
| 600 |
+
"lstrip": false,
|
| 601 |
+
"normalized": false,
|
| 602 |
+
"rstrip": false,
|
| 603 |
+
"single_word": false,
|
| 604 |
+
"special": true
|
| 605 |
+
},
|
| 606 |
+
"128075": {
|
| 607 |
+
"content": "<|reserved_special_token_67|>",
|
| 608 |
+
"lstrip": false,
|
| 609 |
+
"normalized": false,
|
| 610 |
+
"rstrip": false,
|
| 611 |
+
"single_word": false,
|
| 612 |
+
"special": true
|
| 613 |
+
},
|
| 614 |
+
"128076": {
|
| 615 |
+
"content": "<|reserved_special_token_68|>",
|
| 616 |
+
"lstrip": false,
|
| 617 |
+
"normalized": false,
|
| 618 |
+
"rstrip": false,
|
| 619 |
+
"single_word": false,
|
| 620 |
+
"special": true
|
| 621 |
+
},
|
| 622 |
+
"128077": {
|
| 623 |
+
"content": "<|reserved_special_token_69|>",
|
| 624 |
+
"lstrip": false,
|
| 625 |
+
"normalized": false,
|
| 626 |
+
"rstrip": false,
|
| 627 |
+
"single_word": false,
|
| 628 |
+
"special": true
|
| 629 |
+
},
|
| 630 |
+
"128078": {
|
| 631 |
+
"content": "<|reserved_special_token_70|>",
|
| 632 |
+
"lstrip": false,
|
| 633 |
+
"normalized": false,
|
| 634 |
+
"rstrip": false,
|
| 635 |
+
"single_word": false,
|
| 636 |
+
"special": true
|
| 637 |
+
},
|
| 638 |
+
"128079": {
|
| 639 |
+
"content": "<|reserved_special_token_71|>",
|
| 640 |
+
"lstrip": false,
|
| 641 |
+
"normalized": false,
|
| 642 |
+
"rstrip": false,
|
| 643 |
+
"single_word": false,
|
| 644 |
+
"special": true
|
| 645 |
+
},
|
| 646 |
+
"128080": {
|
| 647 |
+
"content": "<|reserved_special_token_72|>",
|
| 648 |
+
"lstrip": false,
|
| 649 |
+
"normalized": false,
|
| 650 |
+
"rstrip": false,
|
| 651 |
+
"single_word": false,
|
| 652 |
+
"special": true
|
| 653 |
+
},
|
| 654 |
+
"128081": {
|
| 655 |
+
"content": "<|reserved_special_token_73|>",
|
| 656 |
+
"lstrip": false,
|
| 657 |
+
"normalized": false,
|
| 658 |
+
"rstrip": false,
|
| 659 |
+
"single_word": false,
|
| 660 |
+
"special": true
|
| 661 |
+
},
|
| 662 |
+
"128082": {
|
| 663 |
+
"content": "<|reserved_special_token_74|>",
|
| 664 |
+
"lstrip": false,
|
| 665 |
+
"normalized": false,
|
| 666 |
+
"rstrip": false,
|
| 667 |
+
"single_word": false,
|
| 668 |
+
"special": true
|
| 669 |
+
},
|
| 670 |
+
"128083": {
|
| 671 |
+
"content": "<|reserved_special_token_75|>",
|
| 672 |
+
"lstrip": false,
|
| 673 |
+
"normalized": false,
|
| 674 |
+
"rstrip": false,
|
| 675 |
+
"single_word": false,
|
| 676 |
+
"special": true
|
| 677 |
+
},
|
| 678 |
+
"128084": {
|
| 679 |
+
"content": "<|reserved_special_token_76|>",
|
| 680 |
+
"lstrip": false,
|
| 681 |
+
"normalized": false,
|
| 682 |
+
"rstrip": false,
|
| 683 |
+
"single_word": false,
|
| 684 |
+
"special": true
|
| 685 |
+
},
|
| 686 |
+
"128085": {
|
| 687 |
+
"content": "<|reserved_special_token_77|>",
|
| 688 |
+
"lstrip": false,
|
| 689 |
+
"normalized": false,
|
| 690 |
+
"rstrip": false,
|
| 691 |
+
"single_word": false,
|
| 692 |
+
"special": true
|
| 693 |
+
},
|
| 694 |
+
"128086": {
|
| 695 |
+
"content": "<|reserved_special_token_78|>",
|
| 696 |
+
"lstrip": false,
|
| 697 |
+
"normalized": false,
|
| 698 |
+
"rstrip": false,
|
| 699 |
+
"single_word": false,
|
| 700 |
+
"special": true
|
| 701 |
+
},
|
| 702 |
+
"128087": {
|
| 703 |
+
"content": "<|reserved_special_token_79|>",
|
| 704 |
+
"lstrip": false,
|
| 705 |
+
"normalized": false,
|
| 706 |
+
"rstrip": false,
|
| 707 |
+
"single_word": false,
|
| 708 |
+
"special": true
|
| 709 |
+
},
|
| 710 |
+
"128088": {
|
| 711 |
+
"content": "<|reserved_special_token_80|>",
|
| 712 |
+
"lstrip": false,
|
| 713 |
+
"normalized": false,
|
| 714 |
+
"rstrip": false,
|
| 715 |
+
"single_word": false,
|
| 716 |
+
"special": true
|
| 717 |
+
},
|
| 718 |
+
"128089": {
|
| 719 |
+
"content": "<|reserved_special_token_81|>",
|
| 720 |
+
"lstrip": false,
|
| 721 |
+
"normalized": false,
|
| 722 |
+
"rstrip": false,
|
| 723 |
+
"single_word": false,
|
| 724 |
+
"special": true
|
| 725 |
+
},
|
| 726 |
+
"128090": {
|
| 727 |
+
"content": "<|reserved_special_token_82|>",
|
| 728 |
+
"lstrip": false,
|
| 729 |
+
"normalized": false,
|
| 730 |
+
"rstrip": false,
|
| 731 |
+
"single_word": false,
|
| 732 |
+
"special": true
|
| 733 |
+
},
|
| 734 |
+
"128091": {
|
| 735 |
+
"content": "<|reserved_special_token_83|>",
|
| 736 |
+
"lstrip": false,
|
| 737 |
+
"normalized": false,
|
| 738 |
+
"rstrip": false,
|
| 739 |
+
"single_word": false,
|
| 740 |
+
"special": true
|
| 741 |
+
},
|
| 742 |
+
"128092": {
|
| 743 |
+
"content": "<|reserved_special_token_84|>",
|
| 744 |
+
"lstrip": false,
|
| 745 |
+
"normalized": false,
|
| 746 |
+
"rstrip": false,
|
| 747 |
+
"single_word": false,
|
| 748 |
+
"special": true
|
| 749 |
+
},
|
| 750 |
+
"128093": {
|
| 751 |
+
"content": "<|reserved_special_token_85|>",
|
| 752 |
+
"lstrip": false,
|
| 753 |
+
"normalized": false,
|
| 754 |
+
"rstrip": false,
|
| 755 |
+
"single_word": false,
|
| 756 |
+
"special": true
|
| 757 |
+
},
|
| 758 |
+
"128094": {
|
| 759 |
+
"content": "<|reserved_special_token_86|>",
|
| 760 |
+
"lstrip": false,
|
| 761 |
+
"normalized": false,
|
| 762 |
+
"rstrip": false,
|
| 763 |
+
"single_word": false,
|
| 764 |
+
"special": true
|
| 765 |
+
},
|
| 766 |
+
"128095": {
|
| 767 |
+
"content": "<|reserved_special_token_87|>",
|
| 768 |
+
"lstrip": false,
|
| 769 |
+
"normalized": false,
|
| 770 |
+
"rstrip": false,
|
| 771 |
+
"single_word": false,
|
| 772 |
+
"special": true
|
| 773 |
+
},
|
| 774 |
+
"128096": {
|
| 775 |
+
"content": "<|reserved_special_token_88|>",
|
| 776 |
+
"lstrip": false,
|
| 777 |
+
"normalized": false,
|
| 778 |
+
"rstrip": false,
|
| 779 |
+
"single_word": false,
|
| 780 |
+
"special": true
|
| 781 |
+
},
|
| 782 |
+
"128097": {
|
| 783 |
+
"content": "<|reserved_special_token_89|>",
|
| 784 |
+
"lstrip": false,
|
| 785 |
+
"normalized": false,
|
| 786 |
+
"rstrip": false,
|
| 787 |
+
"single_word": false,
|
| 788 |
+
"special": true
|
| 789 |
+
},
|
| 790 |
+
"128098": {
|
| 791 |
+
"content": "<|reserved_special_token_90|>",
|
| 792 |
+
"lstrip": false,
|
| 793 |
+
"normalized": false,
|
| 794 |
+
"rstrip": false,
|
| 795 |
+
"single_word": false,
|
| 796 |
+
"special": true
|
| 797 |
+
},
|
| 798 |
+
"128099": {
|
| 799 |
+
"content": "<|reserved_special_token_91|>",
|
| 800 |
+
"lstrip": false,
|
| 801 |
+
"normalized": false,
|
| 802 |
+
"rstrip": false,
|
| 803 |
+
"single_word": false,
|
| 804 |
+
"special": true
|
| 805 |
+
},
|
| 806 |
+
"128100": {
|
| 807 |
+
"content": "<|reserved_special_token_92|>",
|
| 808 |
+
"lstrip": false,
|
| 809 |
+
"normalized": false,
|
| 810 |
+
"rstrip": false,
|
| 811 |
+
"single_word": false,
|
| 812 |
+
"special": true
|
| 813 |
+
},
|
| 814 |
+
"128101": {
|
| 815 |
+
"content": "<|reserved_special_token_93|>",
|
| 816 |
+
"lstrip": false,
|
| 817 |
+
"normalized": false,
|
| 818 |
+
"rstrip": false,
|
| 819 |
+
"single_word": false,
|
| 820 |
+
"special": true
|
| 821 |
+
},
|
| 822 |
+
"128102": {
|
| 823 |
+
"content": "<|reserved_special_token_94|>",
|
| 824 |
+
"lstrip": false,
|
| 825 |
+
"normalized": false,
|
| 826 |
+
"rstrip": false,
|
| 827 |
+
"single_word": false,
|
| 828 |
+
"special": true
|
| 829 |
+
},
|
| 830 |
+
"128103": {
|
| 831 |
+
"content": "<|reserved_special_token_95|>",
|
| 832 |
+
"lstrip": false,
|
| 833 |
+
"normalized": false,
|
| 834 |
+
"rstrip": false,
|
| 835 |
+
"single_word": false,
|
| 836 |
+
"special": true
|
| 837 |
+
},
|
| 838 |
+
"128104": {
|
| 839 |
+
"content": "<|reserved_special_token_96|>",
|
| 840 |
+
"lstrip": false,
|
| 841 |
+
"normalized": false,
|
| 842 |
+
"rstrip": false,
|
| 843 |
+
"single_word": false,
|
| 844 |
+
"special": true
|
| 845 |
+
},
|
| 846 |
+
"128105": {
|
| 847 |
+
"content": "<|reserved_special_token_97|>",
|
| 848 |
+
"lstrip": false,
|
| 849 |
+
"normalized": false,
|
| 850 |
+
"rstrip": false,
|
| 851 |
+
"single_word": false,
|
| 852 |
+
"special": true
|
| 853 |
+
},
|
| 854 |
+
"128106": {
|
| 855 |
+
"content": "<|reserved_special_token_98|>",
|
| 856 |
+
"lstrip": false,
|
| 857 |
+
"normalized": false,
|
| 858 |
+
"rstrip": false,
|
| 859 |
+
"single_word": false,
|
| 860 |
+
"special": true
|
| 861 |
+
},
|
| 862 |
+
"128107": {
|
| 863 |
+
"content": "<|reserved_special_token_99|>",
|
| 864 |
+
"lstrip": false,
|
| 865 |
+
"normalized": false,
|
| 866 |
+
"rstrip": false,
|
| 867 |
+
"single_word": false,
|
| 868 |
+
"special": true
|
| 869 |
+
},
|
| 870 |
+
"128108": {
|
| 871 |
+
"content": "<|reserved_special_token_100|>",
|
| 872 |
+
"lstrip": false,
|
| 873 |
+
"normalized": false,
|
| 874 |
+
"rstrip": false,
|
| 875 |
+
"single_word": false,
|
| 876 |
+
"special": true
|
| 877 |
+
},
|
| 878 |
+
"128109": {
|
| 879 |
+
"content": "<|reserved_special_token_101|>",
|
| 880 |
+
"lstrip": false,
|
| 881 |
+
"normalized": false,
|
| 882 |
+
"rstrip": false,
|
| 883 |
+
"single_word": false,
|
| 884 |
+
"special": true
|
| 885 |
+
},
|
| 886 |
+
"128110": {
|
| 887 |
+
"content": "<|reserved_special_token_102|>",
|
| 888 |
+
"lstrip": false,
|
| 889 |
+
"normalized": false,
|
| 890 |
+
"rstrip": false,
|
| 891 |
+
"single_word": false,
|
| 892 |
+
"special": true
|
| 893 |
+
},
|
| 894 |
+
"128111": {
|
| 895 |
+
"content": "<|reserved_special_token_103|>",
|
| 896 |
+
"lstrip": false,
|
| 897 |
+
"normalized": false,
|
| 898 |
+
"rstrip": false,
|
| 899 |
+
"single_word": false,
|
| 900 |
+
"special": true
|
| 901 |
+
},
|
| 902 |
+
"128112": {
|
| 903 |
+
"content": "<|reserved_special_token_104|>",
|
| 904 |
+
"lstrip": false,
|
| 905 |
+
"normalized": false,
|
| 906 |
+
"rstrip": false,
|
| 907 |
+
"single_word": false,
|
| 908 |
+
"special": true
|
| 909 |
+
},
|
| 910 |
+
"128113": {
|
| 911 |
+
"content": "<|reserved_special_token_105|>",
|
| 912 |
+
"lstrip": false,
|
| 913 |
+
"normalized": false,
|
| 914 |
+
"rstrip": false,
|
| 915 |
+
"single_word": false,
|
| 916 |
+
"special": true
|
| 917 |
+
},
|
| 918 |
+
"128114": {
|
| 919 |
+
"content": "<|reserved_special_token_106|>",
|
| 920 |
+
"lstrip": false,
|
| 921 |
+
"normalized": false,
|
| 922 |
+
"rstrip": false,
|
| 923 |
+
"single_word": false,
|
| 924 |
+
"special": true
|
| 925 |
+
},
|
| 926 |
+
"128115": {
|
| 927 |
+
"content": "<|reserved_special_token_107|>",
|
| 928 |
+
"lstrip": false,
|
| 929 |
+
"normalized": false,
|
| 930 |
+
"rstrip": false,
|
| 931 |
+
"single_word": false,
|
| 932 |
+
"special": true
|
| 933 |
+
},
|
| 934 |
+
"128116": {
|
| 935 |
+
"content": "<|reserved_special_token_108|>",
|
| 936 |
+
"lstrip": false,
|
| 937 |
+
"normalized": false,
|
| 938 |
+
"rstrip": false,
|
| 939 |
+
"single_word": false,
|
| 940 |
+
"special": true
|
| 941 |
+
},
|
| 942 |
+
"128117": {
|
| 943 |
+
"content": "<|reserved_special_token_109|>",
|
| 944 |
+
"lstrip": false,
|
| 945 |
+
"normalized": false,
|
| 946 |
+
"rstrip": false,
|
| 947 |
+
"single_word": false,
|
| 948 |
+
"special": true
|
| 949 |
+
},
|
| 950 |
+
"128118": {
|
| 951 |
+
"content": "<|reserved_special_token_110|>",
|
| 952 |
+
"lstrip": false,
|
| 953 |
+
"normalized": false,
|
| 954 |
+
"rstrip": false,
|
| 955 |
+
"single_word": false,
|
| 956 |
+
"special": true
|
| 957 |
+
},
|
| 958 |
+
"128119": {
|
| 959 |
+
"content": "<|reserved_special_token_111|>",
|
| 960 |
+
"lstrip": false,
|
| 961 |
+
"normalized": false,
|
| 962 |
+
"rstrip": false,
|
| 963 |
+
"single_word": false,
|
| 964 |
+
"special": true
|
| 965 |
+
},
|
| 966 |
+
"128120": {
|
| 967 |
+
"content": "<|reserved_special_token_112|>",
|
| 968 |
+
"lstrip": false,
|
| 969 |
+
"normalized": false,
|
| 970 |
+
"rstrip": false,
|
| 971 |
+
"single_word": false,
|
| 972 |
+
"special": true
|
| 973 |
+
},
|
| 974 |
+
"128121": {
|
| 975 |
+
"content": "<|reserved_special_token_113|>",
|
| 976 |
+
"lstrip": false,
|
| 977 |
+
"normalized": false,
|
| 978 |
+
"rstrip": false,
|
| 979 |
+
"single_word": false,
|
| 980 |
+
"special": true
|
| 981 |
+
},
|
| 982 |
+
"128122": {
|
| 983 |
+
"content": "<|reserved_special_token_114|>",
|
| 984 |
+
"lstrip": false,
|
| 985 |
+
"normalized": false,
|
| 986 |
+
"rstrip": false,
|
| 987 |
+
"single_word": false,
|
| 988 |
+
"special": true
|
| 989 |
+
},
|
| 990 |
+
"128123": {
|
| 991 |
+
"content": "<|reserved_special_token_115|>",
|
| 992 |
+
"lstrip": false,
|
| 993 |
+
"normalized": false,
|
| 994 |
+
"rstrip": false,
|
| 995 |
+
"single_word": false,
|
| 996 |
+
"special": true
|
| 997 |
+
},
|
| 998 |
+
"128124": {
|
| 999 |
+
"content": "<|reserved_special_token_116|>",
|
| 1000 |
+
"lstrip": false,
|
| 1001 |
+
"normalized": false,
|
| 1002 |
+
"rstrip": false,
|
| 1003 |
+
"single_word": false,
|
| 1004 |
+
"special": true
|
| 1005 |
+
},
|
| 1006 |
+
"128125": {
|
| 1007 |
+
"content": "<|reserved_special_token_117|>",
|
| 1008 |
+
"lstrip": false,
|
| 1009 |
+
"normalized": false,
|
| 1010 |
+
"rstrip": false,
|
| 1011 |
+
"single_word": false,
|
| 1012 |
+
"special": true
|
| 1013 |
+
},
|
| 1014 |
+
"128126": {
|
| 1015 |
+
"content": "<|reserved_special_token_118|>",
|
| 1016 |
+
"lstrip": false,
|
| 1017 |
+
"normalized": false,
|
| 1018 |
+
"rstrip": false,
|
| 1019 |
+
"single_word": false,
|
| 1020 |
+
"special": true
|
| 1021 |
+
},
|
| 1022 |
+
"128127": {
|
| 1023 |
+
"content": "<|reserved_special_token_119|>",
|
| 1024 |
+
"lstrip": false,
|
| 1025 |
+
"normalized": false,
|
| 1026 |
+
"rstrip": false,
|
| 1027 |
+
"single_word": false,
|
| 1028 |
+
"special": true
|
| 1029 |
+
},
|
| 1030 |
+
"128128": {
|
| 1031 |
+
"content": "<|reserved_special_token_120|>",
|
| 1032 |
+
"lstrip": false,
|
| 1033 |
+
"normalized": false,
|
| 1034 |
+
"rstrip": false,
|
| 1035 |
+
"single_word": false,
|
| 1036 |
+
"special": true
|
| 1037 |
+
},
|
| 1038 |
+
"128129": {
|
| 1039 |
+
"content": "<|reserved_special_token_121|>",
|
| 1040 |
+
"lstrip": false,
|
| 1041 |
+
"normalized": false,
|
| 1042 |
+
"rstrip": false,
|
| 1043 |
+
"single_word": false,
|
| 1044 |
+
"special": true
|
| 1045 |
+
},
|
| 1046 |
+
"128130": {
|
| 1047 |
+
"content": "<|reserved_special_token_122|>",
|
| 1048 |
+
"lstrip": false,
|
| 1049 |
+
"normalized": false,
|
| 1050 |
+
"rstrip": false,
|
| 1051 |
+
"single_word": false,
|
| 1052 |
+
"special": true
|
| 1053 |
+
},
|
| 1054 |
+
"128131": {
|
| 1055 |
+
"content": "<|reserved_special_token_123|>",
|
| 1056 |
+
"lstrip": false,
|
| 1057 |
+
"normalized": false,
|
| 1058 |
+
"rstrip": false,
|
| 1059 |
+
"single_word": false,
|
| 1060 |
+
"special": true
|
| 1061 |
+
},
|
| 1062 |
+
"128132": {
|
| 1063 |
+
"content": "<|reserved_special_token_124|>",
|
| 1064 |
+
"lstrip": false,
|
| 1065 |
+
"normalized": false,
|
| 1066 |
+
"rstrip": false,
|
| 1067 |
+
"single_word": false,
|
| 1068 |
+
"special": true
|
| 1069 |
+
},
|
| 1070 |
+
"128133": {
|
| 1071 |
+
"content": "<|reserved_special_token_125|>",
|
| 1072 |
+
"lstrip": false,
|
| 1073 |
+
"normalized": false,
|
| 1074 |
+
"rstrip": false,
|
| 1075 |
+
"single_word": false,
|
| 1076 |
+
"special": true
|
| 1077 |
+
},
|
| 1078 |
+
"128134": {
|
| 1079 |
+
"content": "<|reserved_special_token_126|>",
|
| 1080 |
+
"lstrip": false,
|
| 1081 |
+
"normalized": false,
|
| 1082 |
+
"rstrip": false,
|
| 1083 |
+
"single_word": false,
|
| 1084 |
+
"special": true
|
| 1085 |
+
},
|
| 1086 |
+
"128135": {
|
| 1087 |
+
"content": "<|reserved_special_token_127|>",
|
| 1088 |
+
"lstrip": false,
|
| 1089 |
+
"normalized": false,
|
| 1090 |
+
"rstrip": false,
|
| 1091 |
+
"single_word": false,
|
| 1092 |
+
"special": true
|
| 1093 |
+
},
|
| 1094 |
+
"128136": {
|
| 1095 |
+
"content": "<|reserved_special_token_128|>",
|
| 1096 |
+
"lstrip": false,
|
| 1097 |
+
"normalized": false,
|
| 1098 |
+
"rstrip": false,
|
| 1099 |
+
"single_word": false,
|
| 1100 |
+
"special": true
|
| 1101 |
+
},
|
| 1102 |
+
"128137": {
|
| 1103 |
+
"content": "<|reserved_special_token_129|>",
|
| 1104 |
+
"lstrip": false,
|
| 1105 |
+
"normalized": false,
|
| 1106 |
+
"rstrip": false,
|
| 1107 |
+
"single_word": false,
|
| 1108 |
+
"special": true
|
| 1109 |
+
},
|
| 1110 |
+
"128138": {
|
| 1111 |
+
"content": "<|reserved_special_token_130|>",
|
| 1112 |
+
"lstrip": false,
|
| 1113 |
+
"normalized": false,
|
| 1114 |
+
"rstrip": false,
|
| 1115 |
+
"single_word": false,
|
| 1116 |
+
"special": true
|
| 1117 |
+
},
|
| 1118 |
+
"128139": {
|
| 1119 |
+
"content": "<|reserved_special_token_131|>",
|
| 1120 |
+
"lstrip": false,
|
| 1121 |
+
"normalized": false,
|
| 1122 |
+
"rstrip": false,
|
| 1123 |
+
"single_word": false,
|
| 1124 |
+
"special": true
|
| 1125 |
+
},
|
| 1126 |
+
"128140": {
|
| 1127 |
+
"content": "<|reserved_special_token_132|>",
|
| 1128 |
+
"lstrip": false,
|
| 1129 |
+
"normalized": false,
|
| 1130 |
+
"rstrip": false,
|
| 1131 |
+
"single_word": false,
|
| 1132 |
+
"special": true
|
| 1133 |
+
},
|
| 1134 |
+
"128141": {
|
| 1135 |
+
"content": "<|reserved_special_token_133|>",
|
| 1136 |
+
"lstrip": false,
|
| 1137 |
+
"normalized": false,
|
| 1138 |
+
"rstrip": false,
|
| 1139 |
+
"single_word": false,
|
| 1140 |
+
"special": true
|
| 1141 |
+
},
|
| 1142 |
+
"128142": {
|
| 1143 |
+
"content": "<|reserved_special_token_134|>",
|
| 1144 |
+
"lstrip": false,
|
| 1145 |
+
"normalized": false,
|
| 1146 |
+
"rstrip": false,
|
| 1147 |
+
"single_word": false,
|
| 1148 |
+
"special": true
|
| 1149 |
+
},
|
| 1150 |
+
"128143": {
|
| 1151 |
+
"content": "<|reserved_special_token_135|>",
|
| 1152 |
+
"lstrip": false,
|
| 1153 |
+
"normalized": false,
|
| 1154 |
+
"rstrip": false,
|
| 1155 |
+
"single_word": false,
|
| 1156 |
+
"special": true
|
| 1157 |
+
},
|
| 1158 |
+
"128144": {
|
| 1159 |
+
"content": "<|reserved_special_token_136|>",
|
| 1160 |
+
"lstrip": false,
|
| 1161 |
+
"normalized": false,
|
| 1162 |
+
"rstrip": false,
|
| 1163 |
+
"single_word": false,
|
| 1164 |
+
"special": true
|
| 1165 |
+
},
|
| 1166 |
+
"128145": {
|
| 1167 |
+
"content": "<|reserved_special_token_137|>",
|
| 1168 |
+
"lstrip": false,
|
| 1169 |
+
"normalized": false,
|
| 1170 |
+
"rstrip": false,
|
| 1171 |
+
"single_word": false,
|
| 1172 |
+
"special": true
|
| 1173 |
+
},
|
| 1174 |
+
"128146": {
|
| 1175 |
+
"content": "<|reserved_special_token_138|>",
|
| 1176 |
+
"lstrip": false,
|
| 1177 |
+
"normalized": false,
|
| 1178 |
+
"rstrip": false,
|
| 1179 |
+
"single_word": false,
|
| 1180 |
+
"special": true
|
| 1181 |
+
},
|
| 1182 |
+
"128147": {
|
| 1183 |
+
"content": "<|reserved_special_token_139|>",
|
| 1184 |
+
"lstrip": false,
|
| 1185 |
+
"normalized": false,
|
| 1186 |
+
"rstrip": false,
|
| 1187 |
+
"single_word": false,
|
| 1188 |
+
"special": true
|
| 1189 |
+
},
|
| 1190 |
+
"128148": {
|
| 1191 |
+
"content": "<|reserved_special_token_140|>",
|
| 1192 |
+
"lstrip": false,
|
| 1193 |
+
"normalized": false,
|
| 1194 |
+
"rstrip": false,
|
| 1195 |
+
"single_word": false,
|
| 1196 |
+
"special": true
|
| 1197 |
+
},
|
| 1198 |
+
"128149": {
|
| 1199 |
+
"content": "<|reserved_special_token_141|>",
|
| 1200 |
+
"lstrip": false,
|
| 1201 |
+
"normalized": false,
|
| 1202 |
+
"rstrip": false,
|
| 1203 |
+
"single_word": false,
|
| 1204 |
+
"special": true
|
| 1205 |
+
},
|
| 1206 |
+
"128150": {
|
| 1207 |
+
"content": "<|reserved_special_token_142|>",
|
| 1208 |
+
"lstrip": false,
|
| 1209 |
+
"normalized": false,
|
| 1210 |
+
"rstrip": false,
|
| 1211 |
+
"single_word": false,
|
| 1212 |
+
"special": true
|
| 1213 |
+
},
|
| 1214 |
+
"128151": {
|
| 1215 |
+
"content": "<|reserved_special_token_143|>",
|
| 1216 |
+
"lstrip": false,
|
| 1217 |
+
"normalized": false,
|
| 1218 |
+
"rstrip": false,
|
| 1219 |
+
"single_word": false,
|
| 1220 |
+
"special": true
|
| 1221 |
+
},
|
| 1222 |
+
"128152": {
|
| 1223 |
+
"content": "<|reserved_special_token_144|>",
|
| 1224 |
+
"lstrip": false,
|
| 1225 |
+
"normalized": false,
|
| 1226 |
+
"rstrip": false,
|
| 1227 |
+
"single_word": false,
|
| 1228 |
+
"special": true
|
| 1229 |
+
},
|
| 1230 |
+
"128153": {
|
| 1231 |
+
"content": "<|reserved_special_token_145|>",
|
| 1232 |
+
"lstrip": false,
|
| 1233 |
+
"normalized": false,
|
| 1234 |
+
"rstrip": false,
|
| 1235 |
+
"single_word": false,
|
| 1236 |
+
"special": true
|
| 1237 |
+
},
|
| 1238 |
+
"128154": {
|
| 1239 |
+
"content": "<|reserved_special_token_146|>",
|
| 1240 |
+
"lstrip": false,
|
| 1241 |
+
"normalized": false,
|
| 1242 |
+
"rstrip": false,
|
| 1243 |
+
"single_word": false,
|
| 1244 |
+
"special": true
|
| 1245 |
+
},
|
| 1246 |
+
"128155": {
|
| 1247 |
+
"content": "<|reserved_special_token_147|>",
|
| 1248 |
+
"lstrip": false,
|
| 1249 |
+
"normalized": false,
|
| 1250 |
+
"rstrip": false,
|
| 1251 |
+
"single_word": false,
|
| 1252 |
+
"special": true
|
| 1253 |
+
},
|
| 1254 |
+
"128156": {
|
| 1255 |
+
"content": "<|reserved_special_token_148|>",
|
| 1256 |
+
"lstrip": false,
|
| 1257 |
+
"normalized": false,
|
| 1258 |
+
"rstrip": false,
|
| 1259 |
+
"single_word": false,
|
| 1260 |
+
"special": true
|
| 1261 |
+
},
|
| 1262 |
+
"128157": {
|
| 1263 |
+
"content": "<|reserved_special_token_149|>",
|
| 1264 |
+
"lstrip": false,
|
| 1265 |
+
"normalized": false,
|
| 1266 |
+
"rstrip": false,
|
| 1267 |
+
"single_word": false,
|
| 1268 |
+
"special": true
|
| 1269 |
+
},
|
| 1270 |
+
"128158": {
|
| 1271 |
+
"content": "<|reserved_special_token_150|>",
|
| 1272 |
+
"lstrip": false,
|
| 1273 |
+
"normalized": false,
|
| 1274 |
+
"rstrip": false,
|
| 1275 |
+
"single_word": false,
|
| 1276 |
+
"special": true
|
| 1277 |
+
},
|
| 1278 |
+
"128159": {
|
| 1279 |
+
"content": "<|reserved_special_token_151|>",
|
| 1280 |
+
"lstrip": false,
|
| 1281 |
+
"normalized": false,
|
| 1282 |
+
"rstrip": false,
|
| 1283 |
+
"single_word": false,
|
| 1284 |
+
"special": true
|
| 1285 |
+
},
|
| 1286 |
+
"128160": {
|
| 1287 |
+
"content": "<|reserved_special_token_152|>",
|
| 1288 |
+
"lstrip": false,
|
| 1289 |
+
"normalized": false,
|
| 1290 |
+
"rstrip": false,
|
| 1291 |
+
"single_word": false,
|
| 1292 |
+
"special": true
|
| 1293 |
+
},
|
| 1294 |
+
"128161": {
|
| 1295 |
+
"content": "<|reserved_special_token_153|>",
|
| 1296 |
+
"lstrip": false,
|
| 1297 |
+
"normalized": false,
|
| 1298 |
+
"rstrip": false,
|
| 1299 |
+
"single_word": false,
|
| 1300 |
+
"special": true
|
| 1301 |
+
},
|
| 1302 |
+
"128162": {
|
| 1303 |
+
"content": "<|reserved_special_token_154|>",
|
| 1304 |
+
"lstrip": false,
|
| 1305 |
+
"normalized": false,
|
| 1306 |
+
"rstrip": false,
|
| 1307 |
+
"single_word": false,
|
| 1308 |
+
"special": true
|
| 1309 |
+
},
|
| 1310 |
+
"128163": {
|
| 1311 |
+
"content": "<|reserved_special_token_155|>",
|
| 1312 |
+
"lstrip": false,
|
| 1313 |
+
"normalized": false,
|
| 1314 |
+
"rstrip": false,
|
| 1315 |
+
"single_word": false,
|
| 1316 |
+
"special": true
|
| 1317 |
+
},
|
| 1318 |
+
"128164": {
|
| 1319 |
+
"content": "<|reserved_special_token_156|>",
|
| 1320 |
+
"lstrip": false,
|
| 1321 |
+
"normalized": false,
|
| 1322 |
+
"rstrip": false,
|
| 1323 |
+
"single_word": false,
|
| 1324 |
+
"special": true
|
| 1325 |
+
},
|
| 1326 |
+
"128165": {
|
| 1327 |
+
"content": "<|reserved_special_token_157|>",
|
| 1328 |
+
"lstrip": false,
|
| 1329 |
+
"normalized": false,
|
| 1330 |
+
"rstrip": false,
|
| 1331 |
+
"single_word": false,
|
| 1332 |
+
"special": true
|
| 1333 |
+
},
|
| 1334 |
+
"128166": {
|
| 1335 |
+
"content": "<|reserved_special_token_158|>",
|
| 1336 |
+
"lstrip": false,
|
| 1337 |
+
"normalized": false,
|
| 1338 |
+
"rstrip": false,
|
| 1339 |
+
"single_word": false,
|
| 1340 |
+
"special": true
|
| 1341 |
+
},
|
| 1342 |
+
"128167": {
|
| 1343 |
+
"content": "<|reserved_special_token_159|>",
|
| 1344 |
+
"lstrip": false,
|
| 1345 |
+
"normalized": false,
|
| 1346 |
+
"rstrip": false,
|
| 1347 |
+
"single_word": false,
|
| 1348 |
+
"special": true
|
| 1349 |
+
},
|
| 1350 |
+
"128168": {
|
| 1351 |
+
"content": "<|reserved_special_token_160|>",
|
| 1352 |
+
"lstrip": false,
|
| 1353 |
+
"normalized": false,
|
| 1354 |
+
"rstrip": false,
|
| 1355 |
+
"single_word": false,
|
| 1356 |
+
"special": true
|
| 1357 |
+
},
|
| 1358 |
+
"128169": {
|
| 1359 |
+
"content": "<|reserved_special_token_161|>",
|
| 1360 |
+
"lstrip": false,
|
| 1361 |
+
"normalized": false,
|
| 1362 |
+
"rstrip": false,
|
| 1363 |
+
"single_word": false,
|
| 1364 |
+
"special": true
|
| 1365 |
+
},
|
| 1366 |
+
"128170": {
|
| 1367 |
+
"content": "<|reserved_special_token_162|>",
|
| 1368 |
+
"lstrip": false,
|
| 1369 |
+
"normalized": false,
|
| 1370 |
+
"rstrip": false,
|
| 1371 |
+
"single_word": false,
|
| 1372 |
+
"special": true
|
| 1373 |
+
},
|
| 1374 |
+
"128171": {
|
| 1375 |
+
"content": "<|reserved_special_token_163|>",
|
| 1376 |
+
"lstrip": false,
|
| 1377 |
+
"normalized": false,
|
| 1378 |
+
"rstrip": false,
|
| 1379 |
+
"single_word": false,
|
| 1380 |
+
"special": true
|
| 1381 |
+
},
|
| 1382 |
+
"128172": {
|
| 1383 |
+
"content": "<|reserved_special_token_164|>",
|
| 1384 |
+
"lstrip": false,
|
| 1385 |
+
"normalized": false,
|
| 1386 |
+
"rstrip": false,
|
| 1387 |
+
"single_word": false,
|
| 1388 |
+
"special": true
|
| 1389 |
+
},
|
| 1390 |
+
"128173": {
|
| 1391 |
+
"content": "<|reserved_special_token_165|>",
|
| 1392 |
+
"lstrip": false,
|
| 1393 |
+
"normalized": false,
|
| 1394 |
+
"rstrip": false,
|
| 1395 |
+
"single_word": false,
|
| 1396 |
+
"special": true
|
| 1397 |
+
},
|
| 1398 |
+
"128174": {
|
| 1399 |
+
"content": "<|reserved_special_token_166|>",
|
| 1400 |
+
"lstrip": false,
|
| 1401 |
+
"normalized": false,
|
| 1402 |
+
"rstrip": false,
|
| 1403 |
+
"single_word": false,
|
| 1404 |
+
"special": true
|
| 1405 |
+
},
|
| 1406 |
+
"128175": {
|
| 1407 |
+
"content": "<|reserved_special_token_167|>",
|
| 1408 |
+
"lstrip": false,
|
| 1409 |
+
"normalized": false,
|
| 1410 |
+
"rstrip": false,
|
| 1411 |
+
"single_word": false,
|
| 1412 |
+
"special": true
|
| 1413 |
+
},
|
| 1414 |
+
"128176": {
|
| 1415 |
+
"content": "<|reserved_special_token_168|>",
|
| 1416 |
+
"lstrip": false,
|
| 1417 |
+
"normalized": false,
|
| 1418 |
+
"rstrip": false,
|
| 1419 |
+
"single_word": false,
|
| 1420 |
+
"special": true
|
| 1421 |
+
},
|
| 1422 |
+
"128177": {
|
| 1423 |
+
"content": "<|reserved_special_token_169|>",
|
| 1424 |
+
"lstrip": false,
|
| 1425 |
+
"normalized": false,
|
| 1426 |
+
"rstrip": false,
|
| 1427 |
+
"single_word": false,
|
| 1428 |
+
"special": true
|
| 1429 |
+
},
|
| 1430 |
+
"128178": {
|
| 1431 |
+
"content": "<|reserved_special_token_170|>",
|
| 1432 |
+
"lstrip": false,
|
| 1433 |
+
"normalized": false,
|
| 1434 |
+
"rstrip": false,
|
| 1435 |
+
"single_word": false,
|
| 1436 |
+
"special": true
|
| 1437 |
+
},
|
| 1438 |
+
"128179": {
|
| 1439 |
+
"content": "<|reserved_special_token_171|>",
|
| 1440 |
+
"lstrip": false,
|
| 1441 |
+
"normalized": false,
|
| 1442 |
+
"rstrip": false,
|
| 1443 |
+
"single_word": false,
|
| 1444 |
+
"special": true
|
| 1445 |
+
},
|
| 1446 |
+
"128180": {
|
| 1447 |
+
"content": "<|reserved_special_token_172|>",
|
| 1448 |
+
"lstrip": false,
|
| 1449 |
+
"normalized": false,
|
| 1450 |
+
"rstrip": false,
|
| 1451 |
+
"single_word": false,
|
| 1452 |
+
"special": true
|
| 1453 |
+
},
|
| 1454 |
+
"128181": {
|
| 1455 |
+
"content": "<|reserved_special_token_173|>",
|
| 1456 |
+
"lstrip": false,
|
| 1457 |
+
"normalized": false,
|
| 1458 |
+
"rstrip": false,
|
| 1459 |
+
"single_word": false,
|
| 1460 |
+
"special": true
|
| 1461 |
+
},
|
| 1462 |
+
"128182": {
|
| 1463 |
+
"content": "<|reserved_special_token_174|>",
|
| 1464 |
+
"lstrip": false,
|
| 1465 |
+
"normalized": false,
|
| 1466 |
+
"rstrip": false,
|
| 1467 |
+
"single_word": false,
|
| 1468 |
+
"special": true
|
| 1469 |
+
},
|
| 1470 |
+
"128183": {
|
| 1471 |
+
"content": "<|reserved_special_token_175|>",
|
| 1472 |
+
"lstrip": false,
|
| 1473 |
+
"normalized": false,
|
| 1474 |
+
"rstrip": false,
|
| 1475 |
+
"single_word": false,
|
| 1476 |
+
"special": true
|
| 1477 |
+
},
|
| 1478 |
+
"128184": {
|
| 1479 |
+
"content": "<|reserved_special_token_176|>",
|
| 1480 |
+
"lstrip": false,
|
| 1481 |
+
"normalized": false,
|
| 1482 |
+
"rstrip": false,
|
| 1483 |
+
"single_word": false,
|
| 1484 |
+
"special": true
|
| 1485 |
+
},
|
| 1486 |
+
"128185": {
|
| 1487 |
+
"content": "<|reserved_special_token_177|>",
|
| 1488 |
+
"lstrip": false,
|
| 1489 |
+
"normalized": false,
|
| 1490 |
+
"rstrip": false,
|
| 1491 |
+
"single_word": false,
|
| 1492 |
+
"special": true
|
| 1493 |
+
},
|
| 1494 |
+
"128186": {
|
| 1495 |
+
"content": "<|reserved_special_token_178|>",
|
| 1496 |
+
"lstrip": false,
|
| 1497 |
+
"normalized": false,
|
| 1498 |
+
"rstrip": false,
|
| 1499 |
+
"single_word": false,
|
| 1500 |
+
"special": true
|
| 1501 |
+
},
|
| 1502 |
+
"128187": {
|
| 1503 |
+
"content": "<|reserved_special_token_179|>",
|
| 1504 |
+
"lstrip": false,
|
| 1505 |
+
"normalized": false,
|
| 1506 |
+
"rstrip": false,
|
| 1507 |
+
"single_word": false,
|
| 1508 |
+
"special": true
|
| 1509 |
+
},
|
| 1510 |
+
"128188": {
|
| 1511 |
+
"content": "<|reserved_special_token_180|>",
|
| 1512 |
+
"lstrip": false,
|
| 1513 |
+
"normalized": false,
|
| 1514 |
+
"rstrip": false,
|
| 1515 |
+
"single_word": false,
|
| 1516 |
+
"special": true
|
| 1517 |
+
},
|
| 1518 |
+
"128189": {
|
| 1519 |
+
"content": "<|reserved_special_token_181|>",
|
| 1520 |
+
"lstrip": false,
|
| 1521 |
+
"normalized": false,
|
| 1522 |
+
"rstrip": false,
|
| 1523 |
+
"single_word": false,
|
| 1524 |
+
"special": true
|
| 1525 |
+
},
|
| 1526 |
+
"128190": {
|
| 1527 |
+
"content": "<|reserved_special_token_182|>",
|
| 1528 |
+
"lstrip": false,
|
| 1529 |
+
"normalized": false,
|
| 1530 |
+
"rstrip": false,
|
| 1531 |
+
"single_word": false,
|
| 1532 |
+
"special": true
|
| 1533 |
+
},
|
| 1534 |
+
"128191": {
|
| 1535 |
+
"content": "<|reserved_special_token_183|>",
|
| 1536 |
+
"lstrip": false,
|
| 1537 |
+
"normalized": false,
|
| 1538 |
+
"rstrip": false,
|
| 1539 |
+
"single_word": false,
|
| 1540 |
+
"special": true
|
| 1541 |
+
},
|
| 1542 |
+
"128192": {
|
| 1543 |
+
"content": "<|reserved_special_token_184|>",
|
| 1544 |
+
"lstrip": false,
|
| 1545 |
+
"normalized": false,
|
| 1546 |
+
"rstrip": false,
|
| 1547 |
+
"single_word": false,
|
| 1548 |
+
"special": true
|
| 1549 |
+
},
|
| 1550 |
+
"128193": {
|
| 1551 |
+
"content": "<|reserved_special_token_185|>",
|
| 1552 |
+
"lstrip": false,
|
| 1553 |
+
"normalized": false,
|
| 1554 |
+
"rstrip": false,
|
| 1555 |
+
"single_word": false,
|
| 1556 |
+
"special": true
|
| 1557 |
+
},
|
| 1558 |
+
"128194": {
|
| 1559 |
+
"content": "<|reserved_special_token_186|>",
|
| 1560 |
+
"lstrip": false,
|
| 1561 |
+
"normalized": false,
|
| 1562 |
+
"rstrip": false,
|
| 1563 |
+
"single_word": false,
|
| 1564 |
+
"special": true
|
| 1565 |
+
},
|
| 1566 |
+
"128195": {
|
| 1567 |
+
"content": "<|reserved_special_token_187|>",
|
| 1568 |
+
"lstrip": false,
|
| 1569 |
+
"normalized": false,
|
| 1570 |
+
"rstrip": false,
|
| 1571 |
+
"single_word": false,
|
| 1572 |
+
"special": true
|
| 1573 |
+
},
|
| 1574 |
+
"128196": {
|
| 1575 |
+
"content": "<|reserved_special_token_188|>",
|
| 1576 |
+
"lstrip": false,
|
| 1577 |
+
"normalized": false,
|
| 1578 |
+
"rstrip": false,
|
| 1579 |
+
"single_word": false,
|
| 1580 |
+
"special": true
|
| 1581 |
+
},
|
| 1582 |
+
"128197": {
|
| 1583 |
+
"content": "<|reserved_special_token_189|>",
|
| 1584 |
+
"lstrip": false,
|
| 1585 |
+
"normalized": false,
|
| 1586 |
+
"rstrip": false,
|
| 1587 |
+
"single_word": false,
|
| 1588 |
+
"special": true
|
| 1589 |
+
},
|
| 1590 |
+
"128198": {
|
| 1591 |
+
"content": "<|reserved_special_token_190|>",
|
| 1592 |
+
"lstrip": false,
|
| 1593 |
+
"normalized": false,
|
| 1594 |
+
"rstrip": false,
|
| 1595 |
+
"single_word": false,
|
| 1596 |
+
"special": true
|
| 1597 |
+
},
|
| 1598 |
+
"128199": {
|
| 1599 |
+
"content": "<|reserved_special_token_191|>",
|
| 1600 |
+
"lstrip": false,
|
| 1601 |
+
"normalized": false,
|
| 1602 |
+
"rstrip": false,
|
| 1603 |
+
"single_word": false,
|
| 1604 |
+
"special": true
|
| 1605 |
+
},
|
| 1606 |
+
"128200": {
|
| 1607 |
+
"content": "<|reserved_special_token_192|>",
|
| 1608 |
+
"lstrip": false,
|
| 1609 |
+
"normalized": false,
|
| 1610 |
+
"rstrip": false,
|
| 1611 |
+
"single_word": false,
|
| 1612 |
+
"special": true
|
| 1613 |
+
},
|
| 1614 |
+
"128201": {
|
| 1615 |
+
"content": "<|reserved_special_token_193|>",
|
| 1616 |
+
"lstrip": false,
|
| 1617 |
+
"normalized": false,
|
| 1618 |
+
"rstrip": false,
|
| 1619 |
+
"single_word": false,
|
| 1620 |
+
"special": true
|
| 1621 |
+
},
|
| 1622 |
+
"128202": {
|
| 1623 |
+
"content": "<|reserved_special_token_194|>",
|
| 1624 |
+
"lstrip": false,
|
| 1625 |
+
"normalized": false,
|
| 1626 |
+
"rstrip": false,
|
| 1627 |
+
"single_word": false,
|
| 1628 |
+
"special": true
|
| 1629 |
+
},
|
| 1630 |
+
"128203": {
|
| 1631 |
+
"content": "<|reserved_special_token_195|>",
|
| 1632 |
+
"lstrip": false,
|
| 1633 |
+
"normalized": false,
|
| 1634 |
+
"rstrip": false,
|
| 1635 |
+
"single_word": false,
|
| 1636 |
+
"special": true
|
| 1637 |
+
},
|
| 1638 |
+
"128204": {
|
| 1639 |
+
"content": "<|reserved_special_token_196|>",
|
| 1640 |
+
"lstrip": false,
|
| 1641 |
+
"normalized": false,
|
| 1642 |
+
"rstrip": false,
|
| 1643 |
+
"single_word": false,
|
| 1644 |
+
"special": true
|
| 1645 |
+
},
|
| 1646 |
+
"128205": {
|
| 1647 |
+
"content": "<|reserved_special_token_197|>",
|
| 1648 |
+
"lstrip": false,
|
| 1649 |
+
"normalized": false,
|
| 1650 |
+
"rstrip": false,
|
| 1651 |
+
"single_word": false,
|
| 1652 |
+
"special": true
|
| 1653 |
+
},
|
| 1654 |
+
"128206": {
|
| 1655 |
+
"content": "<|reserved_special_token_198|>",
|
| 1656 |
+
"lstrip": false,
|
| 1657 |
+
"normalized": false,
|
| 1658 |
+
"rstrip": false,
|
| 1659 |
+
"single_word": false,
|
| 1660 |
+
"special": true
|
| 1661 |
+
},
|
| 1662 |
+
"128207": {
|
| 1663 |
+
"content": "<|reserved_special_token_199|>",
|
| 1664 |
+
"lstrip": false,
|
| 1665 |
+
"normalized": false,
|
| 1666 |
+
"rstrip": false,
|
| 1667 |
+
"single_word": false,
|
| 1668 |
+
"special": true
|
| 1669 |
+
},
|
| 1670 |
+
"128208": {
|
| 1671 |
+
"content": "<|reserved_special_token_200|>",
|
| 1672 |
+
"lstrip": false,
|
| 1673 |
+
"normalized": false,
|
| 1674 |
+
"rstrip": false,
|
| 1675 |
+
"single_word": false,
|
| 1676 |
+
"special": true
|
| 1677 |
+
},
|
| 1678 |
+
"128209": {
|
| 1679 |
+
"content": "<|reserved_special_token_201|>",
|
| 1680 |
+
"lstrip": false,
|
| 1681 |
+
"normalized": false,
|
| 1682 |
+
"rstrip": false,
|
| 1683 |
+
"single_word": false,
|
| 1684 |
+
"special": true
|
| 1685 |
+
},
|
| 1686 |
+
"128210": {
|
| 1687 |
+
"content": "<|reserved_special_token_202|>",
|
| 1688 |
+
"lstrip": false,
|
| 1689 |
+
"normalized": false,
|
| 1690 |
+
"rstrip": false,
|
| 1691 |
+
"single_word": false,
|
| 1692 |
+
"special": true
|
| 1693 |
+
},
|
| 1694 |
+
"128211": {
|
| 1695 |
+
"content": "<|reserved_special_token_203|>",
|
| 1696 |
+
"lstrip": false,
|
| 1697 |
+
"normalized": false,
|
| 1698 |
+
"rstrip": false,
|
| 1699 |
+
"single_word": false,
|
| 1700 |
+
"special": true
|
| 1701 |
+
},
|
| 1702 |
+
"128212": {
|
| 1703 |
+
"content": "<|reserved_special_token_204|>",
|
| 1704 |
+
"lstrip": false,
|
| 1705 |
+
"normalized": false,
|
| 1706 |
+
"rstrip": false,
|
| 1707 |
+
"single_word": false,
|
| 1708 |
+
"special": true
|
| 1709 |
+
},
|
| 1710 |
+
"128213": {
|
| 1711 |
+
"content": "<|reserved_special_token_205|>",
|
| 1712 |
+
"lstrip": false,
|
| 1713 |
+
"normalized": false,
|
| 1714 |
+
"rstrip": false,
|
| 1715 |
+
"single_word": false,
|
| 1716 |
+
"special": true
|
| 1717 |
+
},
|
| 1718 |
+
"128214": {
|
| 1719 |
+
"content": "<|reserved_special_token_206|>",
|
| 1720 |
+
"lstrip": false,
|
| 1721 |
+
"normalized": false,
|
| 1722 |
+
"rstrip": false,
|
| 1723 |
+
"single_word": false,
|
| 1724 |
+
"special": true
|
| 1725 |
+
},
|
| 1726 |
+
"128215": {
|
| 1727 |
+
"content": "<|reserved_special_token_207|>",
|
| 1728 |
+
"lstrip": false,
|
| 1729 |
+
"normalized": false,
|
| 1730 |
+
"rstrip": false,
|
| 1731 |
+
"single_word": false,
|
| 1732 |
+
"special": true
|
| 1733 |
+
},
|
| 1734 |
+
"128216": {
|
| 1735 |
+
"content": "<|reserved_special_token_208|>",
|
| 1736 |
+
"lstrip": false,
|
| 1737 |
+
"normalized": false,
|
| 1738 |
+
"rstrip": false,
|
| 1739 |
+
"single_word": false,
|
| 1740 |
+
"special": true
|
| 1741 |
+
},
|
| 1742 |
+
"128217": {
|
| 1743 |
+
"content": "<|reserved_special_token_209|>",
|
| 1744 |
+
"lstrip": false,
|
| 1745 |
+
"normalized": false,
|
| 1746 |
+
"rstrip": false,
|
| 1747 |
+
"single_word": false,
|
| 1748 |
+
"special": true
|
| 1749 |
+
},
|
| 1750 |
+
"128218": {
|
| 1751 |
+
"content": "<|reserved_special_token_210|>",
|
| 1752 |
+
"lstrip": false,
|
| 1753 |
+
"normalized": false,
|
| 1754 |
+
"rstrip": false,
|
| 1755 |
+
"single_word": false,
|
| 1756 |
+
"special": true
|
| 1757 |
+
},
|
| 1758 |
+
"128219": {
|
| 1759 |
+
"content": "<|reserved_special_token_211|>",
|
| 1760 |
+
"lstrip": false,
|
| 1761 |
+
"normalized": false,
|
| 1762 |
+
"rstrip": false,
|
| 1763 |
+
"single_word": false,
|
| 1764 |
+
"special": true
|
| 1765 |
+
},
|
| 1766 |
+
"128220": {
|
| 1767 |
+
"content": "<|reserved_special_token_212|>",
|
| 1768 |
+
"lstrip": false,
|
| 1769 |
+
"normalized": false,
|
| 1770 |
+
"rstrip": false,
|
| 1771 |
+
"single_word": false,
|
| 1772 |
+
"special": true
|
| 1773 |
+
},
|
| 1774 |
+
"128221": {
|
| 1775 |
+
"content": "<|reserved_special_token_213|>",
|
| 1776 |
+
"lstrip": false,
|
| 1777 |
+
"normalized": false,
|
| 1778 |
+
"rstrip": false,
|
| 1779 |
+
"single_word": false,
|
| 1780 |
+
"special": true
|
| 1781 |
+
},
|
| 1782 |
+
"128222": {
|
| 1783 |
+
"content": "<|reserved_special_token_214|>",
|
| 1784 |
+
"lstrip": false,
|
| 1785 |
+
"normalized": false,
|
| 1786 |
+
"rstrip": false,
|
| 1787 |
+
"single_word": false,
|
| 1788 |
+
"special": true
|
| 1789 |
+
},
|
| 1790 |
+
"128223": {
|
| 1791 |
+
"content": "<|reserved_special_token_215|>",
|
| 1792 |
+
"lstrip": false,
|
| 1793 |
+
"normalized": false,
|
| 1794 |
+
"rstrip": false,
|
| 1795 |
+
"single_word": false,
|
| 1796 |
+
"special": true
|
| 1797 |
+
},
|
| 1798 |
+
"128224": {
|
| 1799 |
+
"content": "<|reserved_special_token_216|>",
|
| 1800 |
+
"lstrip": false,
|
| 1801 |
+
"normalized": false,
|
| 1802 |
+
"rstrip": false,
|
| 1803 |
+
"single_word": false,
|
| 1804 |
+
"special": true
|
| 1805 |
+
},
|
| 1806 |
+
"128225": {
|
| 1807 |
+
"content": "<|reserved_special_token_217|>",
|
| 1808 |
+
"lstrip": false,
|
| 1809 |
+
"normalized": false,
|
| 1810 |
+
"rstrip": false,
|
| 1811 |
+
"single_word": false,
|
| 1812 |
+
"special": true
|
| 1813 |
+
},
|
| 1814 |
+
"128226": {
|
| 1815 |
+
"content": "<|reserved_special_token_218|>",
|
| 1816 |
+
"lstrip": false,
|
| 1817 |
+
"normalized": false,
|
| 1818 |
+
"rstrip": false,
|
| 1819 |
+
"single_word": false,
|
| 1820 |
+
"special": true
|
| 1821 |
+
},
|
| 1822 |
+
"128227": {
|
| 1823 |
+
"content": "<|reserved_special_token_219|>",
|
| 1824 |
+
"lstrip": false,
|
| 1825 |
+
"normalized": false,
|
| 1826 |
+
"rstrip": false,
|
| 1827 |
+
"single_word": false,
|
| 1828 |
+
"special": true
|
| 1829 |
+
},
|
| 1830 |
+
"128228": {
|
| 1831 |
+
"content": "<|reserved_special_token_220|>",
|
| 1832 |
+
"lstrip": false,
|
| 1833 |
+
"normalized": false,
|
| 1834 |
+
"rstrip": false,
|
| 1835 |
+
"single_word": false,
|
| 1836 |
+
"special": true
|
| 1837 |
+
},
|
| 1838 |
+
"128229": {
|
| 1839 |
+
"content": "<|reserved_special_token_221|>",
|
| 1840 |
+
"lstrip": false,
|
| 1841 |
+
"normalized": false,
|
| 1842 |
+
"rstrip": false,
|
| 1843 |
+
"single_word": false,
|
| 1844 |
+
"special": true
|
| 1845 |
+
},
|
| 1846 |
+
"128230": {
|
| 1847 |
+
"content": "<|reserved_special_token_222|>",
|
| 1848 |
+
"lstrip": false,
|
| 1849 |
+
"normalized": false,
|
| 1850 |
+
"rstrip": false,
|
| 1851 |
+
"single_word": false,
|
| 1852 |
+
"special": true
|
| 1853 |
+
},
|
| 1854 |
+
"128231": {
|
| 1855 |
+
"content": "<|reserved_special_token_223|>",
|
| 1856 |
+
"lstrip": false,
|
| 1857 |
+
"normalized": false,
|
| 1858 |
+
"rstrip": false,
|
| 1859 |
+
"single_word": false,
|
| 1860 |
+
"special": true
|
| 1861 |
+
},
|
| 1862 |
+
"128232": {
|
| 1863 |
+
"content": "<|reserved_special_token_224|>",
|
| 1864 |
+
"lstrip": false,
|
| 1865 |
+
"normalized": false,
|
| 1866 |
+
"rstrip": false,
|
| 1867 |
+
"single_word": false,
|
| 1868 |
+
"special": true
|
| 1869 |
+
},
|
| 1870 |
+
"128233": {
|
| 1871 |
+
"content": "<|reserved_special_token_225|>",
|
| 1872 |
+
"lstrip": false,
|
| 1873 |
+
"normalized": false,
|
| 1874 |
+
"rstrip": false,
|
| 1875 |
+
"single_word": false,
|
| 1876 |
+
"special": true
|
| 1877 |
+
},
|
| 1878 |
+
"128234": {
|
| 1879 |
+
"content": "<|reserved_special_token_226|>",
|
| 1880 |
+
"lstrip": false,
|
| 1881 |
+
"normalized": false,
|
| 1882 |
+
"rstrip": false,
|
| 1883 |
+
"single_word": false,
|
| 1884 |
+
"special": true
|
| 1885 |
+
},
|
| 1886 |
+
"128235": {
|
| 1887 |
+
"content": "<|reserved_special_token_227|>",
|
| 1888 |
+
"lstrip": false,
|
| 1889 |
+
"normalized": false,
|
| 1890 |
+
"rstrip": false,
|
| 1891 |
+
"single_word": false,
|
| 1892 |
+
"special": true
|
| 1893 |
+
},
|
| 1894 |
+
"128236": {
|
| 1895 |
+
"content": "<|reserved_special_token_228|>",
|
| 1896 |
+
"lstrip": false,
|
| 1897 |
+
"normalized": false,
|
| 1898 |
+
"rstrip": false,
|
| 1899 |
+
"single_word": false,
|
| 1900 |
+
"special": true
|
| 1901 |
+
},
|
| 1902 |
+
"128237": {
|
| 1903 |
+
"content": "<|reserved_special_token_229|>",
|
| 1904 |
+
"lstrip": false,
|
| 1905 |
+
"normalized": false,
|
| 1906 |
+
"rstrip": false,
|
| 1907 |
+
"single_word": false,
|
| 1908 |
+
"special": true
|
| 1909 |
+
},
|
| 1910 |
+
"128238": {
|
| 1911 |
+
"content": "<|reserved_special_token_230|>",
|
| 1912 |
+
"lstrip": false,
|
| 1913 |
+
"normalized": false,
|
| 1914 |
+
"rstrip": false,
|
| 1915 |
+
"single_word": false,
|
| 1916 |
+
"special": true
|
| 1917 |
+
},
|
| 1918 |
+
"128239": {
|
| 1919 |
+
"content": "<|reserved_special_token_231|>",
|
| 1920 |
+
"lstrip": false,
|
| 1921 |
+
"normalized": false,
|
| 1922 |
+
"rstrip": false,
|
| 1923 |
+
"single_word": false,
|
| 1924 |
+
"special": true
|
| 1925 |
+
},
|
| 1926 |
+
"128240": {
|
| 1927 |
+
"content": "<|reserved_special_token_232|>",
|
| 1928 |
+
"lstrip": false,
|
| 1929 |
+
"normalized": false,
|
| 1930 |
+
"rstrip": false,
|
| 1931 |
+
"single_word": false,
|
| 1932 |
+
"special": true
|
| 1933 |
+
},
|
| 1934 |
+
"128241": {
|
| 1935 |
+
"content": "<|reserved_special_token_233|>",
|
| 1936 |
+
"lstrip": false,
|
| 1937 |
+
"normalized": false,
|
| 1938 |
+
"rstrip": false,
|
| 1939 |
+
"single_word": false,
|
| 1940 |
+
"special": true
|
| 1941 |
+
},
|
| 1942 |
+
"128242": {
|
| 1943 |
+
"content": "<|reserved_special_token_234|>",
|
| 1944 |
+
"lstrip": false,
|
| 1945 |
+
"normalized": false,
|
| 1946 |
+
"rstrip": false,
|
| 1947 |
+
"single_word": false,
|
| 1948 |
+
"special": true
|
| 1949 |
+
},
|
| 1950 |
+
"128243": {
|
| 1951 |
+
"content": "<|reserved_special_token_235|>",
|
| 1952 |
+
"lstrip": false,
|
| 1953 |
+
"normalized": false,
|
| 1954 |
+
"rstrip": false,
|
| 1955 |
+
"single_word": false,
|
| 1956 |
+
"special": true
|
| 1957 |
+
},
|
| 1958 |
+
"128244": {
|
| 1959 |
+
"content": "<|reserved_special_token_236|>",
|
| 1960 |
+
"lstrip": false,
|
| 1961 |
+
"normalized": false,
|
| 1962 |
+
"rstrip": false,
|
| 1963 |
+
"single_word": false,
|
| 1964 |
+
"special": true
|
| 1965 |
+
},
|
| 1966 |
+
"128245": {
|
| 1967 |
+
"content": "<|reserved_special_token_237|>",
|
| 1968 |
+
"lstrip": false,
|
| 1969 |
+
"normalized": false,
|
| 1970 |
+
"rstrip": false,
|
| 1971 |
+
"single_word": false,
|
| 1972 |
+
"special": true
|
| 1973 |
+
},
|
| 1974 |
+
"128246": {
|
| 1975 |
+
"content": "<|reserved_special_token_238|>",
|
| 1976 |
+
"lstrip": false,
|
| 1977 |
+
"normalized": false,
|
| 1978 |
+
"rstrip": false,
|
| 1979 |
+
"single_word": false,
|
| 1980 |
+
"special": true
|
| 1981 |
+
},
|
| 1982 |
+
"128247": {
|
| 1983 |
+
"content": "<|reserved_special_token_239|>",
|
| 1984 |
+
"lstrip": false,
|
| 1985 |
+
"normalized": false,
|
| 1986 |
+
"rstrip": false,
|
| 1987 |
+
"single_word": false,
|
| 1988 |
+
"special": true
|
| 1989 |
+
},
|
| 1990 |
+
"128248": {
|
| 1991 |
+
"content": "<|reserved_special_token_240|>",
|
| 1992 |
+
"lstrip": false,
|
| 1993 |
+
"normalized": false,
|
| 1994 |
+
"rstrip": false,
|
| 1995 |
+
"single_word": false,
|
| 1996 |
+
"special": true
|
| 1997 |
+
},
|
| 1998 |
+
"128249": {
|
| 1999 |
+
"content": "<|reserved_special_token_241|>",
|
| 2000 |
+
"lstrip": false,
|
| 2001 |
+
"normalized": false,
|
| 2002 |
+
"rstrip": false,
|
| 2003 |
+
"single_word": false,
|
| 2004 |
+
"special": true
|
| 2005 |
+
},
|
| 2006 |
+
"128250": {
|
| 2007 |
+
"content": "<|reserved_special_token_242|>",
|
| 2008 |
+
"lstrip": false,
|
| 2009 |
+
"normalized": false,
|
| 2010 |
+
"rstrip": false,
|
| 2011 |
+
"single_word": false,
|
| 2012 |
+
"special": true
|
| 2013 |
+
},
|
| 2014 |
+
"128251": {
|
| 2015 |
+
"content": "<|reserved_special_token_243|>",
|
| 2016 |
+
"lstrip": false,
|
| 2017 |
+
"normalized": false,
|
| 2018 |
+
"rstrip": false,
|
| 2019 |
+
"single_word": false,
|
| 2020 |
+
"special": true
|
| 2021 |
+
},
|
| 2022 |
+
"128252": {
|
| 2023 |
+
"content": "<|reserved_special_token_244|>",
|
| 2024 |
+
"lstrip": false,
|
| 2025 |
+
"normalized": false,
|
| 2026 |
+
"rstrip": false,
|
| 2027 |
+
"single_word": false,
|
| 2028 |
+
"special": true
|
| 2029 |
+
},
|
| 2030 |
+
"128253": {
|
| 2031 |
+
"content": "<|reserved_special_token_245|>",
|
| 2032 |
+
"lstrip": false,
|
| 2033 |
+
"normalized": false,
|
| 2034 |
+
"rstrip": false,
|
| 2035 |
+
"single_word": false,
|
| 2036 |
+
"special": true
|
| 2037 |
+
},
|
| 2038 |
+
"128254": {
|
| 2039 |
+
"content": "<|reserved_special_token_246|>",
|
| 2040 |
+
"lstrip": false,
|
| 2041 |
+
"normalized": false,
|
| 2042 |
+
"rstrip": false,
|
| 2043 |
+
"single_word": false,
|
| 2044 |
+
"special": true
|
| 2045 |
+
},
|
| 2046 |
+
"128255": {
|
| 2047 |
+
"content": "<|reserved_special_token_247|>",
|
| 2048 |
+
"lstrip": false,
|
| 2049 |
+
"normalized": false,
|
| 2050 |
+
"rstrip": false,
|
| 2051 |
+
"single_word": false,
|
| 2052 |
+
"special": true
|
| 2053 |
+
}
|
| 2054 |
+
},
|
| 2055 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
| 2056 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\\n'}}{% endif %}",
|
| 2057 |
+
"clean_up_tokenization_spaces": false,
|
| 2058 |
+
"eos_token": "<|end▁of▁sentence|>",
|
| 2059 |
+
"extra_special_tokens": {},
|
| 2060 |
+
"legacy": true,
|
| 2061 |
+
"model_max_length": 16384,
|
| 2062 |
+
"pad_token": "<|end▁of▁sentence|>",
|
| 2063 |
+
"sp_model_kwargs": {},
|
| 2064 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 2065 |
+
"unk_token": null,
|
| 2066 |
+
"use_default_system_prompt": false
|
| 2067 |
+
}
|
checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,1014 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 1000,
|
| 3 |
+
"best_metric": 1.2503063678741455,
|
| 4 |
+
"best_model_checkpoint": "outputs/checkpoint-1000",
|
| 5 |
+
"epoch": 0.8120178643930166,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.008120178643930167,
|
| 14 |
+
"grad_norm": 0.9899182319641113,
|
| 15 |
+
"learning_rate": 1.5e-05,
|
| 16 |
+
"loss": 2.2243,
|
| 17 |
+
"mean_token_accuracy": 0.5150829579681158,
|
| 18 |
+
"num_tokens": 105884.0,
|
| 19 |
+
"step": 10
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.016240357287860333,
|
| 23 |
+
"grad_norm": 0.9635991454124451,
|
| 24 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 25 |
+
"loss": 2.0245,
|
| 26 |
+
"mean_token_accuracy": 0.5415308997035027,
|
| 27 |
+
"num_tokens": 216549.0,
|
| 28 |
+
"step": 20
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.024360535931790498,
|
| 32 |
+
"grad_norm": 0.6212347745895386,
|
| 33 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 34 |
+
"loss": 1.664,
|
| 35 |
+
"mean_token_accuracy": 0.5978568278253078,
|
| 36 |
+
"num_tokens": 326591.0,
|
| 37 |
+
"step": 30
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.032480714575720666,
|
| 41 |
+
"grad_norm": 0.39353373646736145,
|
| 42 |
+
"learning_rate": 4.998938009679042e-05,
|
| 43 |
+
"loss": 1.4829,
|
| 44 |
+
"mean_token_accuracy": 0.6291711494326592,
|
| 45 |
+
"num_tokens": 438765.0,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.04060089321965083,
|
| 50 |
+
"grad_norm": 0.3375701904296875,
|
| 51 |
+
"learning_rate": 4.9952680903753627e-05,
|
| 52 |
+
"loss": 1.4594,
|
| 53 |
+
"mean_token_accuracy": 0.6345414012670517,
|
| 54 |
+
"num_tokens": 551707.0,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.048721071863580996,
|
| 59 |
+
"grad_norm": 0.34767618775367737,
|
| 60 |
+
"learning_rate": 4.98898097941902e-05,
|
| 61 |
+
"loss": 1.4302,
|
| 62 |
+
"mean_token_accuracy": 0.6381799459457398,
|
| 63 |
+
"num_tokens": 662676.0,
|
| 64 |
+
"step": 60
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.05684125050751117,
|
| 68 |
+
"grad_norm": 0.35675737261772156,
|
| 69 |
+
"learning_rate": 4.980083271121214e-05,
|
| 70 |
+
"loss": 1.3795,
|
| 71 |
+
"mean_token_accuracy": 0.6466716401278972,
|
| 72 |
+
"num_tokens": 771289.0,
|
| 73 |
+
"step": 70
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.06496142915144133,
|
| 77 |
+
"grad_norm": 0.37088656425476074,
|
| 78 |
+
"learning_rate": 4.968584297949255e-05,
|
| 79 |
+
"loss": 1.4072,
|
| 80 |
+
"mean_token_accuracy": 0.6428142428398133,
|
| 81 |
+
"num_tokens": 882535.0,
|
| 82 |
+
"step": 80
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.0730816077953715,
|
| 86 |
+
"grad_norm": 0.40535271167755127,
|
| 87 |
+
"learning_rate": 4.954496120738094e-05,
|
| 88 |
+
"loss": 1.3712,
|
| 89 |
+
"mean_token_accuracy": 0.6488012038171291,
|
| 90 |
+
"num_tokens": 991659.0,
|
| 91 |
+
"step": 90
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.08120178643930166,
|
| 95 |
+
"grad_norm": 0.39448976516723633,
|
| 96 |
+
"learning_rate": 4.9378335160401766e-05,
|
| 97 |
+
"loss": 1.3543,
|
| 98 |
+
"step": 100
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.08120178643930166,
|
| 102 |
+
"eval_loss": 1.3557080030441284,
|
| 103 |
+
"eval_mean_token_accuracy": 0.6499481635537707,
|
| 104 |
+
"eval_num_tokens": 1102149.0,
|
| 105 |
+
"eval_runtime": 211.2938,
|
| 106 |
+
"eval_samples_per_second": 9.328,
|
| 107 |
+
"eval_steps_per_second": 1.169,
|
| 108 |
+
"step": 100
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.08932196508323183,
|
| 112 |
+
"grad_norm": 0.40397903323173523,
|
| 113 |
+
"learning_rate": 4.918613960626873e-05,
|
| 114 |
+
"loss": 1.3691,
|
| 115 |
+
"mean_token_accuracy": 0.6495238792151212,
|
| 116 |
+
"num_tokens": 1210597.0,
|
| 117 |
+
"step": 110
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09744214372716199,
|
| 121 |
+
"grad_norm": 0.4039655327796936,
|
| 122 |
+
"learning_rate": 4.896857613157765e-05,
|
| 123 |
+
"loss": 1.3264,
|
| 124 |
+
"mean_token_accuracy": 0.6550758637487888,
|
| 125 |
+
"num_tokens": 1322196.0,
|
| 126 |
+
"step": 120
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.10556232237109216,
|
| 130 |
+
"grad_norm": 0.4150333106517792,
|
| 131 |
+
"learning_rate": 4.872587293036991e-05,
|
| 132 |
+
"loss": 1.337,
|
| 133 |
+
"mean_token_accuracy": 0.655381852388382,
|
| 134 |
+
"num_tokens": 1433808.0,
|
| 135 |
+
"step": 130
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.11368250101502234,
|
| 139 |
+
"grad_norm": 0.4298645555973053,
|
| 140 |
+
"learning_rate": 4.845828456478842e-05,
|
| 141 |
+
"loss": 1.3504,
|
| 142 |
+
"mean_token_accuracy": 0.6535526886582375,
|
| 143 |
+
"num_tokens": 1547479.0,
|
| 144 |
+
"step": 140
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.1218026796589525,
|
| 148 |
+
"grad_norm": 0.46692460775375366,
|
| 149 |
+
"learning_rate": 4.8166091698077164e-05,
|
| 150 |
+
"loss": 1.3517,
|
| 151 |
+
"mean_token_accuracy": 0.6504787422716618,
|
| 152 |
+
"num_tokens": 1661034.0,
|
| 153 |
+
"step": 150
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12992285830288267,
|
| 157 |
+
"grad_norm": 0.4362328052520752,
|
| 158 |
+
"learning_rate": 4.784960080020408e-05,
|
| 159 |
+
"loss": 1.3225,
|
| 160 |
+
"mean_token_accuracy": 0.6548900716006756,
|
| 161 |
+
"num_tokens": 1771511.0,
|
| 162 |
+
"step": 160
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.13804303694681283,
|
| 166 |
+
"grad_norm": 0.4326249361038208,
|
| 167 |
+
"learning_rate": 4.750914382641648e-05,
|
| 168 |
+
"loss": 1.3482,
|
| 169 |
+
"mean_token_accuracy": 0.6529437758028507,
|
| 170 |
+
"num_tokens": 1882929.0,
|
| 171 |
+
"step": 170
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.146163215590743,
|
| 175 |
+
"grad_norm": 0.4499496519565582,
|
| 176 |
+
"learning_rate": 4.714507786906581e-05,
|
| 177 |
+
"loss": 1.3546,
|
| 178 |
+
"mean_token_accuracy": 0.651630837470293,
|
| 179 |
+
"num_tokens": 1992465.0,
|
| 180 |
+
"step": 180
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.15428339423467316,
|
| 184 |
+
"grad_norm": 0.4416871666908264,
|
| 185 |
+
"learning_rate": 4.675778478306712e-05,
|
| 186 |
+
"loss": 1.3587,
|
| 187 |
+
"mean_token_accuracy": 0.6499045781791211,
|
| 188 |
+
"num_tokens": 2104073.0,
|
| 189 |
+
"step": 190
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.16240357287860333,
|
| 193 |
+
"grad_norm": 0.4490174353122711,
|
| 194 |
+
"learning_rate": 4.6347670785385884e-05,
|
| 195 |
+
"loss": 1.3257,
|
| 196 |
+
"step": 200
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.16240357287860333,
|
| 200 |
+
"eval_loss": 1.3144221305847168,
|
| 201 |
+
"eval_mean_token_accuracy": 0.6565933012769289,
|
| 202 |
+
"eval_num_tokens": 2215310.0,
|
| 203 |
+
"eval_runtime": 210.8432,
|
| 204 |
+
"eval_samples_per_second": 9.348,
|
| 205 |
+
"eval_steps_per_second": 1.171,
|
| 206 |
+
"step": 200
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.1705237515225335,
|
| 210 |
+
"grad_norm": 0.4184815585613251,
|
| 211 |
+
"learning_rate": 4.5915166028972624e-05,
|
| 212 |
+
"loss": 1.313,
|
| 213 |
+
"mean_token_accuracy": 0.6569435287266969,
|
| 214 |
+
"num_tokens": 2326949.0,
|
| 215 |
+
"step": 210
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.17864393016646365,
|
| 219 |
+
"grad_norm": 0.46081599593162537,
|
| 220 |
+
"learning_rate": 4.546072415159179e-05,
|
| 221 |
+
"loss": 1.3162,
|
| 222 |
+
"mean_token_accuracy": 0.658608315140009,
|
| 223 |
+
"num_tokens": 2440239.0,
|
| 224 |
+
"step": 220
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.18676410881039382,
|
| 228 |
+
"grad_norm": 0.4398249685764313,
|
| 229 |
+
"learning_rate": 4.49848218000184e-05,
|
| 230 |
+
"loss": 1.3042,
|
| 231 |
+
"mean_token_accuracy": 0.6597990304231643,
|
| 232 |
+
"num_tokens": 2549360.0,
|
| 233 |
+
"step": 230
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.19488428745432398,
|
| 237 |
+
"grad_norm": 0.46249088644981384,
|
| 238 |
+
"learning_rate": 4.448795813010142e-05,
|
| 239 |
+
"loss": 1.3134,
|
| 240 |
+
"mean_token_accuracy": 0.6584605030715466,
|
| 241 |
+
"num_tokens": 2660415.0,
|
| 242 |
+
"step": 240
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.20300446609825415,
|
| 246 |
+
"grad_norm": 0.440453439950943,
|
| 247 |
+
"learning_rate": 4.397065428321817e-05,
|
| 248 |
+
"loss": 1.3029,
|
| 249 |
+
"mean_token_accuracy": 0.660743386298418,
|
| 250 |
+
"num_tokens": 2773017.0,
|
| 251 |
+
"step": 250
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.21112464474218431,
|
| 255 |
+
"grad_norm": 0.44051623344421387,
|
| 256 |
+
"learning_rate": 4.343345283966901e-05,
|
| 257 |
+
"loss": 1.305,
|
| 258 |
+
"mean_token_accuracy": 0.6578053869307041,
|
| 259 |
+
"num_tokens": 2883117.0,
|
| 260 |
+
"step": 260
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.2192448233861145,
|
| 264 |
+
"grad_norm": 0.459414005279541,
|
| 265 |
+
"learning_rate": 4.287691724958551e-05,
|
| 266 |
+
"loss": 1.2878,
|
| 267 |
+
"mean_token_accuracy": 0.662683118134737,
|
| 268 |
+
"num_tokens": 2995555.0,
|
| 269 |
+
"step": 270
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.22736500203004467,
|
| 273 |
+
"grad_norm": 0.45349356532096863,
|
| 274 |
+
"learning_rate": 4.230163124194913e-05,
|
| 275 |
+
"loss": 1.315,
|
| 276 |
+
"mean_token_accuracy": 0.6587340161204338,
|
| 277 |
+
"num_tokens": 3105636.0,
|
| 278 |
+
"step": 280
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.23548518067397484,
|
| 282 |
+
"grad_norm": 0.4721125364303589,
|
| 283 |
+
"learning_rate": 4.170819821234001e-05,
|
| 284 |
+
"loss": 1.2847,
|
| 285 |
+
"mean_token_accuracy": 0.6631687037646771,
|
| 286 |
+
"num_tokens": 3214439.0,
|
| 287 |
+
"step": 290
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.243605359317905,
|
| 291 |
+
"grad_norm": 0.4492698013782501,
|
| 292 |
+
"learning_rate": 4.109724059005844e-05,
|
| 293 |
+
"loss": 1.2992,
|
| 294 |
+
"step": 300
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.243605359317905,
|
| 298 |
+
"eval_loss": 1.2922167778015137,
|
| 299 |
+
"eval_mean_token_accuracy": 0.6602695963160712,
|
| 300 |
+
"eval_num_tokens": 3327211.0,
|
| 301 |
+
"eval_runtime": 211.0034,
|
| 302 |
+
"eval_samples_per_second": 9.341,
|
| 303 |
+
"eval_steps_per_second": 1.171,
|
| 304 |
+
"step": 300
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.25172553796183517,
|
| 308 |
+
"grad_norm": 0.4624563753604889,
|
| 309 |
+
"learning_rate": 4.046939918528243e-05,
|
| 310 |
+
"loss": 1.2965,
|
| 311 |
+
"mean_token_accuracy": 0.6618376031517983,
|
| 312 |
+
"num_tokens": 3437825.0,
|
| 313 |
+
"step": 310
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.25984571660576533,
|
| 317 |
+
"grad_norm": 0.46572402119636536,
|
| 318 |
+
"learning_rate": 3.982533251694632e-05,
|
| 319 |
+
"loss": 1.3034,
|
| 320 |
+
"mean_token_accuracy": 0.659632931649685,
|
| 321 |
+
"num_tokens": 3549948.0,
|
| 322 |
+
"step": 320
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.2679658952496955,
|
| 326 |
+
"grad_norm": 0.4801682233810425,
|
| 327 |
+
"learning_rate": 3.916571612204537e-05,
|
| 328 |
+
"loss": 1.2945,
|
| 329 |
+
"mean_token_accuracy": 0.660579564422369,
|
| 330 |
+
"num_tokens": 3659967.0,
|
| 331 |
+
"step": 330
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.27608607389362566,
|
| 335 |
+
"grad_norm": 0.4685429036617279,
|
| 336 |
+
"learning_rate": 3.849124184709073e-05,
|
| 337 |
+
"loss": 1.2818,
|
| 338 |
+
"mean_token_accuracy": 0.662060933560133,
|
| 339 |
+
"num_tokens": 3769655.0,
|
| 340 |
+
"step": 340
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.2842062525375558,
|
| 344 |
+
"grad_norm": 0.489403635263443,
|
| 345 |
+
"learning_rate": 3.7802617122457975e-05,
|
| 346 |
+
"loss": 1.2767,
|
| 347 |
+
"mean_token_accuracy": 0.664181649684906,
|
| 348 |
+
"num_tokens": 3879329.0,
|
| 349 |
+
"step": 350
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.292326431181486,
|
| 353 |
+
"grad_norm": 0.46308156847953796,
|
| 354 |
+
"learning_rate": 3.7100564220390326e-05,
|
| 355 |
+
"loss": 1.2564,
|
| 356 |
+
"mean_token_accuracy": 0.6691928833723069,
|
| 357 |
+
"num_tokens": 3991691.0,
|
| 358 |
+
"step": 360
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.30044660982541616,
|
| 362 |
+
"grad_norm": 0.4625571668148041,
|
| 363 |
+
"learning_rate": 3.6385819497434876e-05,
|
| 364 |
+
"loss": 1.3133,
|
| 365 |
+
"mean_token_accuracy": 0.6571255922317505,
|
| 366 |
+
"num_tokens": 4102451.0,
|
| 367 |
+
"step": 370
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3085667884693463,
|
| 371 |
+
"grad_norm": 0.46258220076560974,
|
| 372 |
+
"learning_rate": 3.565913262210615e-05,
|
| 373 |
+
"loss": 1.3089,
|
| 374 |
+
"mean_token_accuracy": 0.6575767800211907,
|
| 375 |
+
"num_tokens": 4211111.0,
|
| 376 |
+
"step": 380
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.3166869671132765,
|
| 380 |
+
"grad_norm": 0.48985716700553894,
|
| 381 |
+
"learning_rate": 3.4921265788587435e-05,
|
| 382 |
+
"loss": 1.2662,
|
| 383 |
+
"mean_token_accuracy": 0.6672355219721794,
|
| 384 |
+
"num_tokens": 4322281.0,
|
| 385 |
+
"step": 390
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.32480714575720665,
|
| 389 |
+
"grad_norm": 0.4666249454021454,
|
| 390 |
+
"learning_rate": 3.417299291729431e-05,
|
| 391 |
+
"loss": 1.2745,
|
| 392 |
+
"step": 400
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.32480714575720665,
|
| 396 |
+
"eval_loss": 1.278223991394043,
|
| 397 |
+
"eval_mean_token_accuracy": 0.6623295654169461,
|
| 398 |
+
"eval_num_tokens": 4435130.0,
|
| 399 |
+
"eval_runtime": 210.9199,
|
| 400 |
+
"eval_samples_per_second": 9.345,
|
| 401 |
+
"eval_steps_per_second": 1.171,
|
| 402 |
+
"step": 400
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3329273244011368,
|
| 406 |
+
"grad_norm": 0.4835776686668396,
|
| 407 |
+
"learning_rate": 3.341509884313897e-05,
|
| 408 |
+
"loss": 1.3014,
|
| 409 |
+
"mean_token_accuracy": 0.6618138968944549,
|
| 410 |
+
"num_tokens": 4545678.0,
|
| 411 |
+
"step": 410
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.341047503045067,
|
| 415 |
+
"grad_norm": 0.4572070837020874,
|
| 416 |
+
"learning_rate": 3.264837849234685e-05,
|
| 417 |
+
"loss": 1.2974,
|
| 418 |
+
"mean_token_accuracy": 0.6597278229892254,
|
| 419 |
+
"num_tokens": 4657835.0,
|
| 420 |
+
"step": 420
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.34916768168899714,
|
| 424 |
+
"grad_norm": 0.465015709400177,
|
| 425 |
+
"learning_rate": 3.187363604868872e-05,
|
| 426 |
+
"loss": 1.2718,
|
| 427 |
+
"mean_token_accuracy": 0.6638790182769299,
|
| 428 |
+
"num_tokens": 4769188.0,
|
| 429 |
+
"step": 430
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3572878603329273,
|
| 433 |
+
"grad_norm": 0.4718572199344635,
|
| 434 |
+
"learning_rate": 3.109168411000299e-05,
|
| 435 |
+
"loss": 1.2907,
|
| 436 |
+
"mean_token_accuracy": 0.6597667798399925,
|
| 437 |
+
"num_tokens": 4879176.0,
|
| 438 |
+
"step": 440
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.3654080389768575,
|
| 442 |
+
"grad_norm": 0.47551625967025757,
|
| 443 |
+
"learning_rate": 3.03033428358928e-05,
|
| 444 |
+
"loss": 1.2868,
|
| 445 |
+
"mean_token_accuracy": 0.6611412994563579,
|
| 446 |
+
"num_tokens": 4990975.0,
|
| 447 |
+
"step": 450
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.37352821762078764,
|
| 451 |
+
"grad_norm": 0.5067311525344849,
|
| 452 |
+
"learning_rate": 2.9509439087491835e-05,
|
| 453 |
+
"loss": 1.3175,
|
| 454 |
+
"mean_token_accuracy": 0.6562842346727848,
|
| 455 |
+
"num_tokens": 5102530.0,
|
| 456 |
+
"step": 460
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.3816483962647178,
|
| 460 |
+
"grad_norm": 0.4770154654979706,
|
| 461 |
+
"learning_rate": 2.871080556020118e-05,
|
| 462 |
+
"loss": 1.308,
|
| 463 |
+
"mean_token_accuracy": 0.6601759247481823,
|
| 464 |
+
"num_tokens": 5215390.0,
|
| 465 |
+
"step": 470
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.38976857490864797,
|
| 469 |
+
"grad_norm": 0.48466214537620544,
|
| 470 |
+
"learning_rate": 2.7908279910306835e-05,
|
| 471 |
+
"loss": 1.2832,
|
| 472 |
+
"mean_token_accuracy": 0.6627671822905541,
|
| 473 |
+
"num_tokens": 5327706.0,
|
| 474 |
+
"step": 480
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.39788875355257813,
|
| 478 |
+
"grad_norm": 0.4844174385070801,
|
| 479 |
+
"learning_rate": 2.7102703876393944e-05,
|
| 480 |
+
"loss": 1.3071,
|
| 481 |
+
"mean_token_accuracy": 0.6576642289757728,
|
| 482 |
+
"num_tokens": 5436538.0,
|
| 483 |
+
"step": 490
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.4060089321965083,
|
| 487 |
+
"grad_norm": 0.5532021522521973,
|
| 488 |
+
"learning_rate": 2.629492239647926e-05,
|
| 489 |
+
"loss": 1.2879,
|
| 490 |
+
"step": 500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.4060089321965083,
|
| 494 |
+
"eval_loss": 1.267868995666504,
|
| 495 |
+
"eval_mean_token_accuracy": 0.6643349033618263,
|
| 496 |
+
"eval_num_tokens": 5548090.0,
|
| 497 |
+
"eval_runtime": 210.8479,
|
| 498 |
+
"eval_samples_per_second": 9.348,
|
| 499 |
+
"eval_steps_per_second": 1.171,
|
| 500 |
+
"step": 500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.41412911084043846,
|
| 504 |
+
"grad_norm": 0.5015835762023926,
|
| 505 |
+
"learning_rate": 2.5485782721787837e-05,
|
| 506 |
+
"loss": 1.2579,
|
| 507 |
+
"mean_token_accuracy": 0.6646677803248167,
|
| 508 |
+
"num_tokens": 5660582.0,
|
| 509 |
+
"step": 510
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.42224928948436863,
|
| 513 |
+
"grad_norm": 0.5119274854660034,
|
| 514 |
+
"learning_rate": 2.4676133528103497e-05,
|
| 515 |
+
"loss": 1.2906,
|
| 516 |
+
"mean_token_accuracy": 0.660096200555563,
|
| 517 |
+
"num_tokens": 5773353.0,
|
| 518 |
+
"step": 520
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.43036946812829885,
|
| 522 |
+
"grad_norm": 0.475361168384552,
|
| 523 |
+
"learning_rate": 2.3866824025625124e-05,
|
| 524 |
+
"loss": 1.2977,
|
| 525 |
+
"mean_token_accuracy": 0.6588940002024174,
|
| 526 |
+
"num_tokens": 5887792.0,
|
| 527 |
+
"step": 530
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.438489646772229,
|
| 531 |
+
"grad_norm": 0.5254585146903992,
|
| 532 |
+
"learning_rate": 2.305870306826242e-05,
|
| 533 |
+
"loss": 1.2603,
|
| 534 |
+
"mean_token_accuracy": 0.6667217813432217,
|
| 535 |
+
"num_tokens": 5997605.0,
|
| 536 |
+
"step": 540
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.4466098254161592,
|
| 540 |
+
"grad_norm": 0.5108360052108765,
|
| 541 |
+
"learning_rate": 2.225261826330543e-05,
|
| 542 |
+
"loss": 1.291,
|
| 543 |
+
"mean_token_accuracy": 0.6622078493237495,
|
| 544 |
+
"num_tokens": 6108366.0,
|
| 545 |
+
"step": 550
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.45473000406008934,
|
| 549 |
+
"grad_norm": 0.5151691436767578,
|
| 550 |
+
"learning_rate": 2.1449415082401455e-05,
|
| 551 |
+
"loss": 1.2834,
|
| 552 |
+
"mean_token_accuracy": 0.663181109726429,
|
| 553 |
+
"num_tokens": 6218027.0,
|
| 554 |
+
"step": 560
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.4628501827040195,
|
| 558 |
+
"grad_norm": 0.4874868094921112,
|
| 559 |
+
"learning_rate": 2.0649935974772105e-05,
|
| 560 |
+
"loss": 1.297,
|
| 561 |
+
"mean_token_accuracy": 0.6599866427481175,
|
| 562 |
+
"num_tokens": 6330662.0,
|
| 563 |
+
"step": 570
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.4709703613479497,
|
| 567 |
+
"grad_norm": 0.5027274489402771,
|
| 568 |
+
"learning_rate": 1.985501948360041e-05,
|
| 569 |
+
"loss": 1.272,
|
| 570 |
+
"mean_token_accuracy": 0.6621859490871429,
|
| 571 |
+
"num_tokens": 6440999.0,
|
| 572 |
+
"step": 580
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.47909053999187984,
|
| 576 |
+
"grad_norm": 0.4950280785560608,
|
| 577 |
+
"learning_rate": 1.9065499366514757e-05,
|
| 578 |
+
"loss": 1.2779,
|
| 579 |
+
"mean_token_accuracy": 0.6634722009301186,
|
| 580 |
+
"num_tokens": 6553048.0,
|
| 581 |
+
"step": 590
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.48721071863581,
|
| 585 |
+
"grad_norm": 0.512377142906189,
|
| 586 |
+
"learning_rate": 1.828220372109232e-05,
|
| 587 |
+
"loss": 1.2728,
|
| 588 |
+
"step": 600
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.48721071863581,
|
| 592 |
+
"eval_loss": 1.260668396949768,
|
| 593 |
+
"eval_mean_token_accuracy": 0.6655809046768466,
|
| 594 |
+
"eval_num_tokens": 6664275.0,
|
| 595 |
+
"eval_runtime": 210.7964,
|
| 596 |
+
"eval_samples_per_second": 9.35,
|
| 597 |
+
"eval_steps_per_second": 1.172,
|
| 598 |
+
"step": 600
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.49533089727974017,
|
| 602 |
+
"grad_norm": 0.5057377219200134,
|
| 603 |
+
"learning_rate": 1.7505954116299063e-05,
|
| 604 |
+
"loss": 1.2752,
|
| 605 |
+
"mean_token_accuracy": 0.6648487631231547,
|
| 606 |
+
"num_tokens": 6775546.0,
|
| 607 |
+
"step": 610
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.5034510759236703,
|
| 611 |
+
"grad_norm": 0.5137090682983398,
|
| 612 |
+
"learning_rate": 1.6737564730777284e-05,
|
| 613 |
+
"loss": 1.2986,
|
| 614 |
+
"mean_token_accuracy": 0.6603142991662025,
|
| 615 |
+
"num_tokens": 6889845.0,
|
| 616 |
+
"step": 620
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.5115712545676004,
|
| 620 |
+
"grad_norm": 0.5096326470375061,
|
| 621 |
+
"learning_rate": 1.5977841498884723e-05,
|
| 622 |
+
"loss": 1.2546,
|
| 623 |
+
"mean_token_accuracy": 0.6686703085899353,
|
| 624 |
+
"num_tokens": 7000714.0,
|
| 625 |
+
"step": 630
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5196914332115307,
|
| 629 |
+
"grad_norm": 0.5050039291381836,
|
| 630 |
+
"learning_rate": 1.5227581265380685e-05,
|
| 631 |
+
"loss": 1.2688,
|
| 632 |
+
"mean_token_accuracy": 0.6652263507246972,
|
| 633 |
+
"num_tokens": 7109313.0,
|
| 634 |
+
"step": 640
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.5278116118554608,
|
| 638 |
+
"grad_norm": 0.49248260259628296,
|
| 639 |
+
"learning_rate": 1.4487570949645888e-05,
|
| 640 |
+
"loss": 1.2949,
|
| 641 |
+
"mean_token_accuracy": 0.6615142770111561,
|
| 642 |
+
"num_tokens": 7219816.0,
|
| 643 |
+
"step": 650
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.535931790499391,
|
| 647 |
+
"grad_norm": 0.49449214339256287,
|
| 648 |
+
"learning_rate": 1.375858672031276e-05,
|
| 649 |
+
"loss": 1.2692,
|
| 650 |
+
"mean_token_accuracy": 0.6655298680067062,
|
| 651 |
+
"num_tokens": 7331697.0,
|
| 652 |
+
"step": 660
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 0.5440519691433211,
|
| 656 |
+
"grad_norm": 0.5017920732498169,
|
| 657 |
+
"learning_rate": 1.3041393181171688e-05,
|
| 658 |
+
"loss": 1.2766,
|
| 659 |
+
"mean_token_accuracy": 0.6650374494493008,
|
| 660 |
+
"num_tokens": 7440661.0,
|
| 661 |
+
"step": 670
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.5521721477872513,
|
| 665 |
+
"grad_norm": 0.5125038027763367,
|
| 666 |
+
"learning_rate": 1.2336742569207235e-05,
|
| 667 |
+
"loss": 1.285,
|
| 668 |
+
"mean_token_accuracy": 0.6637549869716167,
|
| 669 |
+
"num_tokens": 7550919.0,
|
| 670 |
+
"step": 680
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.5602923264311814,
|
| 674 |
+
"grad_norm": 0.5125107765197754,
|
| 675 |
+
"learning_rate": 1.1645373965605425e-05,
|
| 676 |
+
"loss": 1.2618,
|
| 677 |
+
"mean_token_accuracy": 0.665469516068697,
|
| 678 |
+
"num_tokens": 7661194.0,
|
| 679 |
+
"step": 690
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.5684125050751117,
|
| 683 |
+
"grad_norm": 0.5296525955200195,
|
| 684 |
+
"learning_rate": 1.0968012520559634e-05,
|
| 685 |
+
"loss": 1.258,
|
| 686 |
+
"step": 700
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.5684125050751117,
|
| 690 |
+
"eval_loss": 1.2551279067993164,
|
| 691 |
+
"eval_mean_token_accuracy": 0.6664607558655835,
|
| 692 |
+
"eval_num_tokens": 7772730.0,
|
| 693 |
+
"eval_runtime": 210.9447,
|
| 694 |
+
"eval_samples_per_second": 9.344,
|
| 695 |
+
"eval_steps_per_second": 1.171,
|
| 696 |
+
"step": 700
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.5765326837190419,
|
| 700 |
+
"grad_norm": 0.5269732475280762,
|
| 701 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 702 |
+
"loss": 1.2393,
|
| 703 |
+
"mean_token_accuracy": 0.6693665731698275,
|
| 704 |
+
"num_tokens": 7880412.0,
|
| 705 |
+
"step": 710
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.584652862362972,
|
| 709 |
+
"grad_norm": 0.4768012464046478,
|
| 710 |
+
"learning_rate": 9.658137503861314e-06,
|
| 711 |
+
"loss": 1.2542,
|
| 712 |
+
"mean_token_accuracy": 0.6695502042770386,
|
| 713 |
+
"num_tokens": 7990995.0,
|
| 714 |
+
"step": 720
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.5927730410069022,
|
| 718 |
+
"grad_norm": 0.5196062326431274,
|
| 719 |
+
"learning_rate": 9.026997810219312e-06,
|
| 720 |
+
"loss": 1.2653,
|
| 721 |
+
"mean_token_accuracy": 0.6653387762606144,
|
| 722 |
+
"num_tokens": 8105125.0,
|
| 723 |
+
"step": 730
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.6008932196508323,
|
| 727 |
+
"grad_norm": 0.5181891918182373,
|
| 728 |
+
"learning_rate": 8.412611590146069e-06,
|
| 729 |
+
"loss": 1.2563,
|
| 730 |
+
"mean_token_accuracy": 0.6682513557374478,
|
| 731 |
+
"num_tokens": 8216386.0,
|
| 732 |
+
"step": 740
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.6090133982947625,
|
| 736 |
+
"grad_norm": 0.5035992860794067,
|
| 737 |
+
"learning_rate": 7.815623249945214e-06,
|
| 738 |
+
"loss": 1.274,
|
| 739 |
+
"mean_token_accuracy": 0.6650313429534436,
|
| 740 |
+
"num_tokens": 8328588.0,
|
| 741 |
+
"step": 750
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.6171335769386926,
|
| 745 |
+
"grad_norm": 0.5094414949417114,
|
| 746 |
+
"learning_rate": 7.236658947946886e-06,
|
| 747 |
+
"loss": 1.2657,
|
| 748 |
+
"mean_token_accuracy": 0.6652336426079273,
|
| 749 |
+
"num_tokens": 8440775.0,
|
| 750 |
+
"step": 760
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.6252537555826229,
|
| 754 |
+
"grad_norm": 0.5002747178077698,
|
| 755 |
+
"learning_rate": 6.676325937754102e-06,
|
| 756 |
+
"loss": 1.2878,
|
| 757 |
+
"mean_token_accuracy": 0.6618476249277592,
|
| 758 |
+
"num_tokens": 8550952.0,
|
| 759 |
+
"step": 770
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.633373934226553,
|
| 763 |
+
"grad_norm": 0.5225718021392822,
|
| 764 |
+
"learning_rate": 6.1352119313175945e-06,
|
| 765 |
+
"loss": 1.2509,
|
| 766 |
+
"mean_token_accuracy": 0.6678596146404743,
|
| 767 |
+
"num_tokens": 8660972.0,
|
| 768 |
+
"step": 780
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.6414941128704832,
|
| 772 |
+
"grad_norm": 0.5244067311286926,
|
| 773 |
+
"learning_rate": 5.613884482507123e-06,
|
| 774 |
+
"loss": 1.2952,
|
| 775 |
+
"mean_token_accuracy": 0.6590089030563832,
|
| 776 |
+
"num_tokens": 8774781.0,
|
| 777 |
+
"step": 790
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.6496142915144133,
|
| 781 |
+
"grad_norm": 0.49261534214019775,
|
| 782 |
+
"learning_rate": 5.112890391825845e-06,
|
| 783 |
+
"loss": 1.295,
|
| 784 |
+
"step": 800
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.6496142915144133,
|
| 788 |
+
"eval_loss": 1.252158284187317,
|
| 789 |
+
"eval_mean_token_accuracy": 0.6671061894671637,
|
| 790 |
+
"eval_num_tokens": 8887925.0,
|
| 791 |
+
"eval_runtime": 210.8674,
|
| 792 |
+
"eval_samples_per_second": 9.347,
|
| 793 |
+
"eval_steps_per_second": 1.171,
|
| 794 |
+
"step": 800
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.6577344701583435,
|
| 798 |
+
"grad_norm": 0.5334400534629822,
|
| 799 |
+
"learning_rate": 4.6327551328920945e-06,
|
| 800 |
+
"loss": 1.2638,
|
| 801 |
+
"mean_token_accuracy": 0.6633151285350323,
|
| 802 |
+
"num_tokens": 8997875.0,
|
| 803 |
+
"step": 810
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.6658546488022736,
|
| 807 |
+
"grad_norm": 0.5012565851211548,
|
| 808 |
+
"learning_rate": 4.173982301290122e-06,
|
| 809 |
+
"loss": 1.2781,
|
| 810 |
+
"mean_token_accuracy": 0.664675948023796,
|
| 811 |
+
"num_tokens": 9109180.0,
|
| 812 |
+
"step": 820
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.6739748274462039,
|
| 816 |
+
"grad_norm": 0.48581662774086,
|
| 817 |
+
"learning_rate": 3.737053086367873e-06,
|
| 818 |
+
"loss": 1.2822,
|
| 819 |
+
"mean_token_accuracy": 0.661733690649271,
|
| 820 |
+
"num_tokens": 9219274.0,
|
| 821 |
+
"step": 830
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.682095006090134,
|
| 825 |
+
"grad_norm": 0.5309010148048401,
|
| 826 |
+
"learning_rate": 3.322425766535778e-06,
|
| 827 |
+
"loss": 1.2587,
|
| 828 |
+
"mean_token_accuracy": 0.6681077688932419,
|
| 829 |
+
"num_tokens": 9329034.0,
|
| 830 |
+
"step": 840
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.6902151847340642,
|
| 834 |
+
"grad_norm": 0.5242215394973755,
|
| 835 |
+
"learning_rate": 2.93053522859604e-06,
|
| 836 |
+
"loss": 1.2752,
|
| 837 |
+
"mean_token_accuracy": 0.6624010242521763,
|
| 838 |
+
"num_tokens": 9442125.0,
|
| 839 |
+
"step": 850
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.6983353633779943,
|
| 843 |
+
"grad_norm": 0.5269120931625366,
|
| 844 |
+
"learning_rate": 2.5617925116063924e-06,
|
| 845 |
+
"loss": 1.2709,
|
| 846 |
+
"mean_token_accuracy": 0.6645623348653317,
|
| 847 |
+
"num_tokens": 9552075.0,
|
| 848 |
+
"step": 860
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.7064555420219245,
|
| 852 |
+
"grad_norm": 0.4972967207431793,
|
| 853 |
+
"learning_rate": 2.2165843757568805e-06,
|
| 854 |
+
"loss": 1.2963,
|
| 855 |
+
"mean_token_accuracy": 0.6616993740200996,
|
| 856 |
+
"num_tokens": 9660415.0,
|
| 857 |
+
"step": 870
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.7145757206658546,
|
| 861 |
+
"grad_norm": 0.5121223330497742,
|
| 862 |
+
"learning_rate": 1.8952728967118804e-06,
|
| 863 |
+
"loss": 1.2545,
|
| 864 |
+
"mean_token_accuracy": 0.66772101521492,
|
| 865 |
+
"num_tokens": 9768900.0,
|
| 866 |
+
"step": 880
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.7226958993097848,
|
| 870 |
+
"grad_norm": 0.49714845418930054,
|
| 871 |
+
"learning_rate": 1.5981950858426714e-06,
|
| 872 |
+
"loss": 1.2545,
|
| 873 |
+
"mean_token_accuracy": 0.6676135674118996,
|
| 874 |
+
"num_tokens": 9881161.0,
|
| 875 |
+
"step": 890
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.730816077953715,
|
| 879 |
+
"grad_norm": 0.49181970953941345,
|
| 880 |
+
"learning_rate": 1.32566253674907e-06,
|
| 881 |
+
"loss": 1.2582,
|
| 882 |
+
"step": 900
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.730816077953715,
|
| 886 |
+
"eval_loss": 1.2505640983581543,
|
| 887 |
+
"eval_mean_token_accuracy": 0.6674990793954023,
|
| 888 |
+
"eval_num_tokens": 9994374.0,
|
| 889 |
+
"eval_runtime": 210.8211,
|
| 890 |
+
"eval_samples_per_second": 9.349,
|
| 891 |
+
"eval_steps_per_second": 1.172,
|
| 892 |
+
"step": 900
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.7389362565976452,
|
| 896 |
+
"grad_norm": 0.5012276768684387,
|
| 897 |
+
"learning_rate": 1.0779610984407773e-06,
|
| 898 |
+
"loss": 1.2807,
|
| 899 |
+
"mean_token_accuracy": 0.6649035323411226,
|
| 900 |
+
"num_tokens": 10105084.0,
|
| 901 |
+
"step": 910
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.7470564352415753,
|
| 905 |
+
"grad_norm": 0.45944449305534363,
|
| 906 |
+
"learning_rate": 8.553505755212382e-07,
|
| 907 |
+
"loss": 1.2822,
|
| 908 |
+
"mean_token_accuracy": 0.6633317075669766,
|
| 909 |
+
"num_tokens": 10216642.0,
|
| 910 |
+
"step": 920
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.7551766138855055,
|
| 914 |
+
"grad_norm": 0.5188620686531067,
|
| 915 |
+
"learning_rate": 6.580644556884702e-07,
|
| 916 |
+
"loss": 1.2703,
|
| 917 |
+
"mean_token_accuracy": 0.6641688346862793,
|
| 918 |
+
"num_tokens": 10328452.0,
|
| 919 |
+
"step": 930
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.7632967925294356,
|
| 923 |
+
"grad_norm": 0.5355983972549438,
|
| 924 |
+
"learning_rate": 4.863096648387383e-07,
|
| 925 |
+
"loss": 1.2629,
|
| 926 |
+
"mean_token_accuracy": 0.6665415301918983,
|
| 927 |
+
"num_tokens": 10439017.0,
|
| 928 |
+
"step": 940
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.7714169711733658,
|
| 932 |
+
"grad_norm": 0.5319786071777344,
|
| 933 |
+
"learning_rate": 3.4026635002984977e-07,
|
| 934 |
+
"loss": 1.2973,
|
| 935 |
+
"mean_token_accuracy": 0.6609269365668297,
|
| 936 |
+
"num_tokens": 10549967.0,
|
| 937 |
+
"step": 950
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 0.7795371498172959,
|
| 941 |
+
"grad_norm": 0.5380677580833435,
|
| 942 |
+
"learning_rate": 2.2008769053176447e-07,
|
| 943 |
+
"loss": 1.2573,
|
| 944 |
+
"mean_token_accuracy": 0.6691292233765125,
|
| 945 |
+
"num_tokens": 10661974.0,
|
| 946 |
+
"step": 960
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.7876573284612262,
|
| 950 |
+
"grad_norm": 0.5304053425788879,
|
| 951 |
+
"learning_rate": 1.2589973716270188e-07,
|
| 952 |
+
"loss": 1.2715,
|
| 953 |
+
"mean_token_accuracy": 0.6645383067429066,
|
| 954 |
+
"num_tokens": 10773511.0,
|
| 955 |
+
"step": 970
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.7957775071051563,
|
| 959 |
+
"grad_norm": 0.5076190829277039,
|
| 960 |
+
"learning_rate": 5.78012800792338e-08,
|
| 961 |
+
"loss": 1.2663,
|
| 962 |
+
"mean_token_accuracy": 0.6659786835312843,
|
| 963 |
+
"num_tokens": 10884441.0,
|
| 964 |
+
"step": 980
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.8038976857490865,
|
| 968 |
+
"grad_norm": 0.5128723978996277,
|
| 969 |
+
"learning_rate": 1.5863745159055976e-08,
|
| 970 |
+
"loss": 1.2855,
|
| 971 |
+
"mean_token_accuracy": 0.6632346011698246,
|
| 972 |
+
"num_tokens": 10995473.0,
|
| 973 |
+
"step": 990
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 0.8120178643930166,
|
| 977 |
+
"grad_norm": 0.5004500150680542,
|
| 978 |
+
"learning_rate": 1.3111908510332615e-10,
|
| 979 |
+
"loss": 1.2505,
|
| 980 |
+
"step": 1000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 0.8120178643930166,
|
| 984 |
+
"eval_loss": 1.2503063678741455,
|
| 985 |
+
"eval_mean_token_accuracy": 0.6675016991040001,
|
| 986 |
+
"eval_num_tokens": 11104474.0,
|
| 987 |
+
"eval_runtime": 210.7823,
|
| 988 |
+
"eval_samples_per_second": 9.351,
|
| 989 |
+
"eval_steps_per_second": 1.172,
|
| 990 |
+
"step": 1000
|
| 991 |
+
}
|
| 992 |
+
],
|
| 993 |
+
"logging_steps": 10,
|
| 994 |
+
"max_steps": 1000,
|
| 995 |
+
"num_input_tokens_seen": 0,
|
| 996 |
+
"num_train_epochs": 1,
|
| 997 |
+
"save_steps": 100,
|
| 998 |
+
"stateful_callbacks": {
|
| 999 |
+
"TrainerControl": {
|
| 1000 |
+
"args": {
|
| 1001 |
+
"should_epoch_stop": false,
|
| 1002 |
+
"should_evaluate": false,
|
| 1003 |
+
"should_log": false,
|
| 1004 |
+
"should_save": true,
|
| 1005 |
+
"should_training_stop": true
|
| 1006 |
+
},
|
| 1007 |
+
"attributes": {}
|
| 1008 |
+
}
|
| 1009 |
+
},
|
| 1010 |
+
"total_flos": 5.561925885730652e+17,
|
| 1011 |
+
"train_batch_size": 2,
|
| 1012 |
+
"trial_name": null,
|
| 1013 |
+
"trial_params": null
|
| 1014 |
+
}
|
checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f39f026f60bf035a5ea79c75e978e7686347690f8cfd3306b305924fecaee5a
|
| 3 |
+
size 6033
|
checkpoint-800/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
|
| 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 0.15.2
|
checkpoint-800/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 16,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"v_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"up_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"q_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-800/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1adcc8b54ec16695b24d9bbb049adc29f7750d2c6a6e029e29e5c99d37a60f04
|
| 3 |
+
size 167832240
|
checkpoint-800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee5ae3b11f9ba22812ee233f2932823237d57cf54b7bd7aa4679fae508f00882
|
| 3 |
+
size 335922851
|
checkpoint-800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ebf85558ba25a31edf99f99c17d4fc5334648d4644afce10240ce9712498235
|
| 3 |
+
size 14645
|
checkpoint-800/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fef122931c86c2d2736773be787da21ac6460d41580735381e953556fb410be
|
| 3 |
+
size 1383
|
checkpoint-800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52e8e1a9e71287709927b817e8806b75be46166fbc9dd24aee241308ee71a982
|
| 3 |
+
size 1465
|
checkpoint-800/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin▁of▁sentence|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end▁of▁sentence|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|end▁of▁sentence|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-800/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
|
| 3 |
+
size 17209530
|
checkpoint-800/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2067 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"128000": {
|
| 7 |
+
"content": "<|begin▁of▁sentence|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"128001": {
|
| 15 |
+
"content": "<|end▁of▁sentence|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"128002": {
|
| 23 |
+
"content": "<|reserved_special_token_0|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"128003": {
|
| 31 |
+
"content": "<|reserved_special_token_1|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"128004": {
|
| 39 |
+
"content": "<|finetune_right_pad_id|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"128005": {
|
| 47 |
+
"content": "<|reserved_special_token_2|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"128006": {
|
| 55 |
+
"content": "<|start_header_id|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"128007": {
|
| 63 |
+
"content": "<|end_header_id|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"128008": {
|
| 71 |
+
"content": "<|eom_id|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"128009": {
|
| 79 |
+
"content": "<|eot_id|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"128010": {
|
| 87 |
+
"content": "<|python_tag|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"128011": {
|
| 95 |
+
"content": "<|User|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"128012": {
|
| 103 |
+
"content": "<|Assistant|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"128013": {
|
| 111 |
+
"content": "<think>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"128014": {
|
| 119 |
+
"content": "</think>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"128015": {
|
| 127 |
+
"content": "<|▁pad▁|>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": true
|
| 133 |
+
},
|
| 134 |
+
"128016": {
|
| 135 |
+
"content": "<|reserved_special_token_8|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": true
|
| 141 |
+
},
|
| 142 |
+
"128017": {
|
| 143 |
+
"content": "<|reserved_special_token_9|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
"128018": {
|
| 151 |
+
"content": "<|reserved_special_token_10|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": true
|
| 157 |
+
},
|
| 158 |
+
"128019": {
|
| 159 |
+
"content": "<|reserved_special_token_11|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": true
|
| 165 |
+
},
|
| 166 |
+
"128020": {
|
| 167 |
+
"content": "<|reserved_special_token_12|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": true
|
| 173 |
+
},
|
| 174 |
+
"128021": {
|
| 175 |
+
"content": "<|reserved_special_token_13|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
},
|
| 182 |
+
"128022": {
|
| 183 |
+
"content": "<|reserved_special_token_14|>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": true
|
| 189 |
+
},
|
| 190 |
+
"128023": {
|
| 191 |
+
"content": "<|reserved_special_token_15|>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": true
|
| 197 |
+
},
|
| 198 |
+
"128024": {
|
| 199 |
+
"content": "<|reserved_special_token_16|>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": true
|
| 205 |
+
},
|
| 206 |
+
"128025": {
|
| 207 |
+
"content": "<|reserved_special_token_17|>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": true
|
| 213 |
+
},
|
| 214 |
+
"128026": {
|
| 215 |
+
"content": "<|reserved_special_token_18|>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
"128027": {
|
| 223 |
+
"content": "<|reserved_special_token_19|>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
},
|
| 230 |
+
"128028": {
|
| 231 |
+
"content": "<|reserved_special_token_20|>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
"128029": {
|
| 239 |
+
"content": "<|reserved_special_token_21|>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"128030": {
|
| 247 |
+
"content": "<|reserved_special_token_22|>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"128031": {
|
| 255 |
+
"content": "<|reserved_special_token_23|>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": true
|
| 261 |
+
},
|
| 262 |
+
"128032": {
|
| 263 |
+
"content": "<|reserved_special_token_24|>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": true
|
| 269 |
+
},
|
| 270 |
+
"128033": {
|
| 271 |
+
"content": "<|reserved_special_token_25|>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": true
|
| 277 |
+
},
|
| 278 |
+
"128034": {
|
| 279 |
+
"content": "<|reserved_special_token_26|>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": true
|
| 285 |
+
},
|
| 286 |
+
"128035": {
|
| 287 |
+
"content": "<|reserved_special_token_27|>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
"128036": {
|
| 295 |
+
"content": "<|reserved_special_token_28|>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
},
|
| 302 |
+
"128037": {
|
| 303 |
+
"content": "<|reserved_special_token_29|>",
|
| 304 |
+
"lstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"rstrip": false,
|
| 307 |
+
"single_word": false,
|
| 308 |
+
"special": true
|
| 309 |
+
},
|
| 310 |
+
"128038": {
|
| 311 |
+
"content": "<|reserved_special_token_30|>",
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"normalized": false,
|
| 314 |
+
"rstrip": false,
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"special": true
|
| 317 |
+
},
|
| 318 |
+
"128039": {
|
| 319 |
+
"content": "<|reserved_special_token_31|>",
|
| 320 |
+
"lstrip": false,
|
| 321 |
+
"normalized": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false,
|
| 324 |
+
"special": true
|
| 325 |
+
},
|
| 326 |
+
"128040": {
|
| 327 |
+
"content": "<|reserved_special_token_32|>",
|
| 328 |
+
"lstrip": false,
|
| 329 |
+
"normalized": false,
|
| 330 |
+
"rstrip": false,
|
| 331 |
+
"single_word": false,
|
| 332 |
+
"special": true
|
| 333 |
+
},
|
| 334 |
+
"128041": {
|
| 335 |
+
"content": "<|reserved_special_token_33|>",
|
| 336 |
+
"lstrip": false,
|
| 337 |
+
"normalized": false,
|
| 338 |
+
"rstrip": false,
|
| 339 |
+
"single_word": false,
|
| 340 |
+
"special": true
|
| 341 |
+
},
|
| 342 |
+
"128042": {
|
| 343 |
+
"content": "<|reserved_special_token_34|>",
|
| 344 |
+
"lstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"rstrip": false,
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"special": true
|
| 349 |
+
},
|
| 350 |
+
"128043": {
|
| 351 |
+
"content": "<|reserved_special_token_35|>",
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"normalized": false,
|
| 354 |
+
"rstrip": false,
|
| 355 |
+
"single_word": false,
|
| 356 |
+
"special": true
|
| 357 |
+
},
|
| 358 |
+
"128044": {
|
| 359 |
+
"content": "<|reserved_special_token_36|>",
|
| 360 |
+
"lstrip": false,
|
| 361 |
+
"normalized": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"single_word": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
"128045": {
|
| 367 |
+
"content": "<|reserved_special_token_37|>",
|
| 368 |
+
"lstrip": false,
|
| 369 |
+
"normalized": false,
|
| 370 |
+
"rstrip": false,
|
| 371 |
+
"single_word": false,
|
| 372 |
+
"special": true
|
| 373 |
+
},
|
| 374 |
+
"128046": {
|
| 375 |
+
"content": "<|reserved_special_token_38|>",
|
| 376 |
+
"lstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"single_word": false,
|
| 380 |
+
"special": true
|
| 381 |
+
},
|
| 382 |
+
"128047": {
|
| 383 |
+
"content": "<|reserved_special_token_39|>",
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"normalized": false,
|
| 386 |
+
"rstrip": false,
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"special": true
|
| 389 |
+
},
|
| 390 |
+
"128048": {
|
| 391 |
+
"content": "<|reserved_special_token_40|>",
|
| 392 |
+
"lstrip": false,
|
| 393 |
+
"normalized": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"single_word": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
"128049": {
|
| 399 |
+
"content": "<|reserved_special_token_41|>",
|
| 400 |
+
"lstrip": false,
|
| 401 |
+
"normalized": false,
|
| 402 |
+
"rstrip": false,
|
| 403 |
+
"single_word": false,
|
| 404 |
+
"special": true
|
| 405 |
+
},
|
| 406 |
+
"128050": {
|
| 407 |
+
"content": "<|reserved_special_token_42|>",
|
| 408 |
+
"lstrip": false,
|
| 409 |
+
"normalized": false,
|
| 410 |
+
"rstrip": false,
|
| 411 |
+
"single_word": false,
|
| 412 |
+
"special": true
|
| 413 |
+
},
|
| 414 |
+
"128051": {
|
| 415 |
+
"content": "<|reserved_special_token_43|>",
|
| 416 |
+
"lstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"rstrip": false,
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"special": true
|
| 421 |
+
},
|
| 422 |
+
"128052": {
|
| 423 |
+
"content": "<|reserved_special_token_44|>",
|
| 424 |
+
"lstrip": false,
|
| 425 |
+
"normalized": false,
|
| 426 |
+
"rstrip": false,
|
| 427 |
+
"single_word": false,
|
| 428 |
+
"special": true
|
| 429 |
+
},
|
| 430 |
+
"128053": {
|
| 431 |
+
"content": "<|reserved_special_token_45|>",
|
| 432 |
+
"lstrip": false,
|
| 433 |
+
"normalized": false,
|
| 434 |
+
"rstrip": false,
|
| 435 |
+
"single_word": false,
|
| 436 |
+
"special": true
|
| 437 |
+
},
|
| 438 |
+
"128054": {
|
| 439 |
+
"content": "<|reserved_special_token_46|>",
|
| 440 |
+
"lstrip": false,
|
| 441 |
+
"normalized": false,
|
| 442 |
+
"rstrip": false,
|
| 443 |
+
"single_word": false,
|
| 444 |
+
"special": true
|
| 445 |
+
},
|
| 446 |
+
"128055": {
|
| 447 |
+
"content": "<|reserved_special_token_47|>",
|
| 448 |
+
"lstrip": false,
|
| 449 |
+
"normalized": false,
|
| 450 |
+
"rstrip": false,
|
| 451 |
+
"single_word": false,
|
| 452 |
+
"special": true
|
| 453 |
+
},
|
| 454 |
+
"128056": {
|
| 455 |
+
"content": "<|reserved_special_token_48|>",
|
| 456 |
+
"lstrip": false,
|
| 457 |
+
"normalized": false,
|
| 458 |
+
"rstrip": false,
|
| 459 |
+
"single_word": false,
|
| 460 |
+
"special": true
|
| 461 |
+
},
|
| 462 |
+
"128057": {
|
| 463 |
+
"content": "<|reserved_special_token_49|>",
|
| 464 |
+
"lstrip": false,
|
| 465 |
+
"normalized": false,
|
| 466 |
+
"rstrip": false,
|
| 467 |
+
"single_word": false,
|
| 468 |
+
"special": true
|
| 469 |
+
},
|
| 470 |
+
"128058": {
|
| 471 |
+
"content": "<|reserved_special_token_50|>",
|
| 472 |
+
"lstrip": false,
|
| 473 |
+
"normalized": false,
|
| 474 |
+
"rstrip": false,
|
| 475 |
+
"single_word": false,
|
| 476 |
+
"special": true
|
| 477 |
+
},
|
| 478 |
+
"128059": {
|
| 479 |
+
"content": "<|reserved_special_token_51|>",
|
| 480 |
+
"lstrip": false,
|
| 481 |
+
"normalized": false,
|
| 482 |
+
"rstrip": false,
|
| 483 |
+
"single_word": false,
|
| 484 |
+
"special": true
|
| 485 |
+
},
|
| 486 |
+
"128060": {
|
| 487 |
+
"content": "<|reserved_special_token_52|>",
|
| 488 |
+
"lstrip": false,
|
| 489 |
+
"normalized": false,
|
| 490 |
+
"rstrip": false,
|
| 491 |
+
"single_word": false,
|
| 492 |
+
"special": true
|
| 493 |
+
},
|
| 494 |
+
"128061": {
|
| 495 |
+
"content": "<|reserved_special_token_53|>",
|
| 496 |
+
"lstrip": false,
|
| 497 |
+
"normalized": false,
|
| 498 |
+
"rstrip": false,
|
| 499 |
+
"single_word": false,
|
| 500 |
+
"special": true
|
| 501 |
+
},
|
| 502 |
+
"128062": {
|
| 503 |
+
"content": "<|reserved_special_token_54|>",
|
| 504 |
+
"lstrip": false,
|
| 505 |
+
"normalized": false,
|
| 506 |
+
"rstrip": false,
|
| 507 |
+
"single_word": false,
|
| 508 |
+
"special": true
|
| 509 |
+
},
|
| 510 |
+
"128063": {
|
| 511 |
+
"content": "<|reserved_special_token_55|>",
|
| 512 |
+
"lstrip": false,
|
| 513 |
+
"normalized": false,
|
| 514 |
+
"rstrip": false,
|
| 515 |
+
"single_word": false,
|
| 516 |
+
"special": true
|
| 517 |
+
},
|
| 518 |
+
"128064": {
|
| 519 |
+
"content": "<|reserved_special_token_56|>",
|
| 520 |
+
"lstrip": false,
|
| 521 |
+
"normalized": false,
|
| 522 |
+
"rstrip": false,
|
| 523 |
+
"single_word": false,
|
| 524 |
+
"special": true
|
| 525 |
+
},
|
| 526 |
+
"128065": {
|
| 527 |
+
"content": "<|reserved_special_token_57|>",
|
| 528 |
+
"lstrip": false,
|
| 529 |
+
"normalized": false,
|
| 530 |
+
"rstrip": false,
|
| 531 |
+
"single_word": false,
|
| 532 |
+
"special": true
|
| 533 |
+
},
|
| 534 |
+
"128066": {
|
| 535 |
+
"content": "<|reserved_special_token_58|>",
|
| 536 |
+
"lstrip": false,
|
| 537 |
+
"normalized": false,
|
| 538 |
+
"rstrip": false,
|
| 539 |
+
"single_word": false,
|
| 540 |
+
"special": true
|
| 541 |
+
},
|
| 542 |
+
"128067": {
|
| 543 |
+
"content": "<|reserved_special_token_59|>",
|
| 544 |
+
"lstrip": false,
|
| 545 |
+
"normalized": false,
|
| 546 |
+
"rstrip": false,
|
| 547 |
+
"single_word": false,
|
| 548 |
+
"special": true
|
| 549 |
+
},
|
| 550 |
+
"128068": {
|
| 551 |
+
"content": "<|reserved_special_token_60|>",
|
| 552 |
+
"lstrip": false,
|
| 553 |
+
"normalized": false,
|
| 554 |
+
"rstrip": false,
|
| 555 |
+
"single_word": false,
|
| 556 |
+
"special": true
|
| 557 |
+
},
|
| 558 |
+
"128069": {
|
| 559 |
+
"content": "<|reserved_special_token_61|>",
|
| 560 |
+
"lstrip": false,
|
| 561 |
+
"normalized": false,
|
| 562 |
+
"rstrip": false,
|
| 563 |
+
"single_word": false,
|
| 564 |
+
"special": true
|
| 565 |
+
},
|
| 566 |
+
"128070": {
|
| 567 |
+
"content": "<|reserved_special_token_62|>",
|
| 568 |
+
"lstrip": false,
|
| 569 |
+
"normalized": false,
|
| 570 |
+
"rstrip": false,
|
| 571 |
+
"single_word": false,
|
| 572 |
+
"special": true
|
| 573 |
+
},
|
| 574 |
+
"128071": {
|
| 575 |
+
"content": "<|reserved_special_token_63|>",
|
| 576 |
+
"lstrip": false,
|
| 577 |
+
"normalized": false,
|
| 578 |
+
"rstrip": false,
|
| 579 |
+
"single_word": false,
|
| 580 |
+
"special": true
|
| 581 |
+
},
|
| 582 |
+
"128072": {
|
| 583 |
+
"content": "<|reserved_special_token_64|>",
|
| 584 |
+
"lstrip": false,
|
| 585 |
+
"normalized": false,
|
| 586 |
+
"rstrip": false,
|
| 587 |
+
"single_word": false,
|
| 588 |
+
"special": true
|
| 589 |
+
},
|
| 590 |
+
"128073": {
|
| 591 |
+
"content": "<|reserved_special_token_65|>",
|
| 592 |
+
"lstrip": false,
|
| 593 |
+
"normalized": false,
|
| 594 |
+
"rstrip": false,
|
| 595 |
+
"single_word": false,
|
| 596 |
+
"special": true
|
| 597 |
+
},
|
| 598 |
+
"128074": {
|
| 599 |
+
"content": "<|reserved_special_token_66|>",
|
| 600 |
+
"lstrip": false,
|
| 601 |
+
"normalized": false,
|
| 602 |
+
"rstrip": false,
|
| 603 |
+
"single_word": false,
|
| 604 |
+
"special": true
|
| 605 |
+
},
|
| 606 |
+
"128075": {
|
| 607 |
+
"content": "<|reserved_special_token_67|>",
|
| 608 |
+
"lstrip": false,
|
| 609 |
+
"normalized": false,
|
| 610 |
+
"rstrip": false,
|
| 611 |
+
"single_word": false,
|
| 612 |
+
"special": true
|
| 613 |
+
},
|
| 614 |
+
"128076": {
|
| 615 |
+
"content": "<|reserved_special_token_68|>",
|
| 616 |
+
"lstrip": false,
|
| 617 |
+
"normalized": false,
|
| 618 |
+
"rstrip": false,
|
| 619 |
+
"single_word": false,
|
| 620 |
+
"special": true
|
| 621 |
+
},
|
| 622 |
+
"128077": {
|
| 623 |
+
"content": "<|reserved_special_token_69|>",
|
| 624 |
+
"lstrip": false,
|
| 625 |
+
"normalized": false,
|
| 626 |
+
"rstrip": false,
|
| 627 |
+
"single_word": false,
|
| 628 |
+
"special": true
|
| 629 |
+
},
|
| 630 |
+
"128078": {
|
| 631 |
+
"content": "<|reserved_special_token_70|>",
|
| 632 |
+
"lstrip": false,
|
| 633 |
+
"normalized": false,
|
| 634 |
+
"rstrip": false,
|
| 635 |
+
"single_word": false,
|
| 636 |
+
"special": true
|
| 637 |
+
},
|
| 638 |
+
"128079": {
|
| 639 |
+
"content": "<|reserved_special_token_71|>",
|
| 640 |
+
"lstrip": false,
|
| 641 |
+
"normalized": false,
|
| 642 |
+
"rstrip": false,
|
| 643 |
+
"single_word": false,
|
| 644 |
+
"special": true
|
| 645 |
+
},
|
| 646 |
+
"128080": {
|
| 647 |
+
"content": "<|reserved_special_token_72|>",
|
| 648 |
+
"lstrip": false,
|
| 649 |
+
"normalized": false,
|
| 650 |
+
"rstrip": false,
|
| 651 |
+
"single_word": false,
|
| 652 |
+
"special": true
|
| 653 |
+
},
|
| 654 |
+
"128081": {
|
| 655 |
+
"content": "<|reserved_special_token_73|>",
|
| 656 |
+
"lstrip": false,
|
| 657 |
+
"normalized": false,
|
| 658 |
+
"rstrip": false,
|
| 659 |
+
"single_word": false,
|
| 660 |
+
"special": true
|
| 661 |
+
},
|
| 662 |
+
"128082": {
|
| 663 |
+
"content": "<|reserved_special_token_74|>",
|
| 664 |
+
"lstrip": false,
|
| 665 |
+
"normalized": false,
|
| 666 |
+
"rstrip": false,
|
| 667 |
+
"single_word": false,
|
| 668 |
+
"special": true
|
| 669 |
+
},
|
| 670 |
+
"128083": {
|
| 671 |
+
"content": "<|reserved_special_token_75|>",
|
| 672 |
+
"lstrip": false,
|
| 673 |
+
"normalized": false,
|
| 674 |
+
"rstrip": false,
|
| 675 |
+
"single_word": false,
|
| 676 |
+
"special": true
|
| 677 |
+
},
|
| 678 |
+
"128084": {
|
| 679 |
+
"content": "<|reserved_special_token_76|>",
|
| 680 |
+
"lstrip": false,
|
| 681 |
+
"normalized": false,
|
| 682 |
+
"rstrip": false,
|
| 683 |
+
"single_word": false,
|
| 684 |
+
"special": true
|
| 685 |
+
},
|
| 686 |
+
"128085": {
|
| 687 |
+
"content": "<|reserved_special_token_77|>",
|
| 688 |
+
"lstrip": false,
|
| 689 |
+
"normalized": false,
|
| 690 |
+
"rstrip": false,
|
| 691 |
+
"single_word": false,
|
| 692 |
+
"special": true
|
| 693 |
+
},
|
| 694 |
+
"128086": {
|
| 695 |
+
"content": "<|reserved_special_token_78|>",
|
| 696 |
+
"lstrip": false,
|
| 697 |
+
"normalized": false,
|
| 698 |
+
"rstrip": false,
|
| 699 |
+
"single_word": false,
|
| 700 |
+
"special": true
|
| 701 |
+
},
|
| 702 |
+
"128087": {
|
| 703 |
+
"content": "<|reserved_special_token_79|>",
|
| 704 |
+
"lstrip": false,
|
| 705 |
+
"normalized": false,
|
| 706 |
+
"rstrip": false,
|
| 707 |
+
"single_word": false,
|
| 708 |
+
"special": true
|
| 709 |
+
},
|
| 710 |
+
"128088": {
|
| 711 |
+
"content": "<|reserved_special_token_80|>",
|
| 712 |
+
"lstrip": false,
|
| 713 |
+
"normalized": false,
|
| 714 |
+
"rstrip": false,
|
| 715 |
+
"single_word": false,
|
| 716 |
+
"special": true
|
| 717 |
+
},
|
| 718 |
+
"128089": {
|
| 719 |
+
"content": "<|reserved_special_token_81|>",
|
| 720 |
+
"lstrip": false,
|
| 721 |
+
"normalized": false,
|
| 722 |
+
"rstrip": false,
|
| 723 |
+
"single_word": false,
|
| 724 |
+
"special": true
|
| 725 |
+
},
|
| 726 |
+
"128090": {
|
| 727 |
+
"content": "<|reserved_special_token_82|>",
|
| 728 |
+
"lstrip": false,
|
| 729 |
+
"normalized": false,
|
| 730 |
+
"rstrip": false,
|
| 731 |
+
"single_word": false,
|
| 732 |
+
"special": true
|
| 733 |
+
},
|
| 734 |
+
"128091": {
|
| 735 |
+
"content": "<|reserved_special_token_83|>",
|
| 736 |
+
"lstrip": false,
|
| 737 |
+
"normalized": false,
|
| 738 |
+
"rstrip": false,
|
| 739 |
+
"single_word": false,
|
| 740 |
+
"special": true
|
| 741 |
+
},
|
| 742 |
+
"128092": {
|
| 743 |
+
"content": "<|reserved_special_token_84|>",
|
| 744 |
+
"lstrip": false,
|
| 745 |
+
"normalized": false,
|
| 746 |
+
"rstrip": false,
|
| 747 |
+
"single_word": false,
|
| 748 |
+
"special": true
|
| 749 |
+
},
|
| 750 |
+
"128093": {
|
| 751 |
+
"content": "<|reserved_special_token_85|>",
|
| 752 |
+
"lstrip": false,
|
| 753 |
+
"normalized": false,
|
| 754 |
+
"rstrip": false,
|
| 755 |
+
"single_word": false,
|
| 756 |
+
"special": true
|
| 757 |
+
},
|
| 758 |
+
"128094": {
|
| 759 |
+
"content": "<|reserved_special_token_86|>",
|
| 760 |
+
"lstrip": false,
|
| 761 |
+
"normalized": false,
|
| 762 |
+
"rstrip": false,
|
| 763 |
+
"single_word": false,
|
| 764 |
+
"special": true
|
| 765 |
+
},
|
| 766 |
+
"128095": {
|
| 767 |
+
"content": "<|reserved_special_token_87|>",
|
| 768 |
+
"lstrip": false,
|
| 769 |
+
"normalized": false,
|
| 770 |
+
"rstrip": false,
|
| 771 |
+
"single_word": false,
|
| 772 |
+
"special": true
|
| 773 |
+
},
|
| 774 |
+
"128096": {
|
| 775 |
+
"content": "<|reserved_special_token_88|>",
|
| 776 |
+
"lstrip": false,
|
| 777 |
+
"normalized": false,
|
| 778 |
+
"rstrip": false,
|
| 779 |
+
"single_word": false,
|
| 780 |
+
"special": true
|
| 781 |
+
},
|
| 782 |
+
"128097": {
|
| 783 |
+
"content": "<|reserved_special_token_89|>",
|
| 784 |
+
"lstrip": false,
|
| 785 |
+
"normalized": false,
|
| 786 |
+
"rstrip": false,
|
| 787 |
+
"single_word": false,
|
| 788 |
+
"special": true
|
| 789 |
+
},
|
| 790 |
+
"128098": {
|
| 791 |
+
"content": "<|reserved_special_token_90|>",
|
| 792 |
+
"lstrip": false,
|
| 793 |
+
"normalized": false,
|
| 794 |
+
"rstrip": false,
|
| 795 |
+
"single_word": false,
|
| 796 |
+
"special": true
|
| 797 |
+
},
|
| 798 |
+
"128099": {
|
| 799 |
+
"content": "<|reserved_special_token_91|>",
|
| 800 |
+
"lstrip": false,
|
| 801 |
+
"normalized": false,
|
| 802 |
+
"rstrip": false,
|
| 803 |
+
"single_word": false,
|
| 804 |
+
"special": true
|
| 805 |
+
},
|
| 806 |
+
"128100": {
|
| 807 |
+
"content": "<|reserved_special_token_92|>",
|
| 808 |
+
"lstrip": false,
|
| 809 |
+
"normalized": false,
|
| 810 |
+
"rstrip": false,
|
| 811 |
+
"single_word": false,
|
| 812 |
+
"special": true
|
| 813 |
+
},
|
| 814 |
+
"128101": {
|
| 815 |
+
"content": "<|reserved_special_token_93|>",
|
| 816 |
+
"lstrip": false,
|
| 817 |
+
"normalized": false,
|
| 818 |
+
"rstrip": false,
|
| 819 |
+
"single_word": false,
|
| 820 |
+
"special": true
|
| 821 |
+
},
|
| 822 |
+
"128102": {
|
| 823 |
+
"content": "<|reserved_special_token_94|>",
|
| 824 |
+
"lstrip": false,
|
| 825 |
+
"normalized": false,
|
| 826 |
+
"rstrip": false,
|
| 827 |
+
"single_word": false,
|
| 828 |
+
"special": true
|
| 829 |
+
},
|
| 830 |
+
"128103": {
|
| 831 |
+
"content": "<|reserved_special_token_95|>",
|
| 832 |
+
"lstrip": false,
|
| 833 |
+
"normalized": false,
|
| 834 |
+
"rstrip": false,
|
| 835 |
+
"single_word": false,
|
| 836 |
+
"special": true
|
| 837 |
+
},
|
| 838 |
+
"128104": {
|
| 839 |
+
"content": "<|reserved_special_token_96|>",
|
| 840 |
+
"lstrip": false,
|
| 841 |
+
"normalized": false,
|
| 842 |
+
"rstrip": false,
|
| 843 |
+
"single_word": false,
|
| 844 |
+
"special": true
|
| 845 |
+
},
|
| 846 |
+
"128105": {
|
| 847 |
+
"content": "<|reserved_special_token_97|>",
|
| 848 |
+
"lstrip": false,
|
| 849 |
+
"normalized": false,
|
| 850 |
+
"rstrip": false,
|
| 851 |
+
"single_word": false,
|
| 852 |
+
"special": true
|
| 853 |
+
},
|
| 854 |
+
"128106": {
|
| 855 |
+
"content": "<|reserved_special_token_98|>",
|
| 856 |
+
"lstrip": false,
|
| 857 |
+
"normalized": false,
|
| 858 |
+
"rstrip": false,
|
| 859 |
+
"single_word": false,
|
| 860 |
+
"special": true
|
| 861 |
+
},
|
| 862 |
+
"128107": {
|
| 863 |
+
"content": "<|reserved_special_token_99|>",
|
| 864 |
+
"lstrip": false,
|
| 865 |
+
"normalized": false,
|
| 866 |
+
"rstrip": false,
|
| 867 |
+
"single_word": false,
|
| 868 |
+
"special": true
|
| 869 |
+
},
|
| 870 |
+
"128108": {
|
| 871 |
+
"content": "<|reserved_special_token_100|>",
|
| 872 |
+
"lstrip": false,
|
| 873 |
+
"normalized": false,
|
| 874 |
+
"rstrip": false,
|
| 875 |
+
"single_word": false,
|
| 876 |
+
"special": true
|
| 877 |
+
},
|
| 878 |
+
"128109": {
|
| 879 |
+
"content": "<|reserved_special_token_101|>",
|
| 880 |
+
"lstrip": false,
|
| 881 |
+
"normalized": false,
|
| 882 |
+
"rstrip": false,
|
| 883 |
+
"single_word": false,
|
| 884 |
+
"special": true
|
| 885 |
+
},
|
| 886 |
+
"128110": {
|
| 887 |
+
"content": "<|reserved_special_token_102|>",
|
| 888 |
+
"lstrip": false,
|
| 889 |
+
"normalized": false,
|
| 890 |
+
"rstrip": false,
|
| 891 |
+
"single_word": false,
|
| 892 |
+
"special": true
|
| 893 |
+
},
|
| 894 |
+
"128111": {
|
| 895 |
+
"content": "<|reserved_special_token_103|>",
|
| 896 |
+
"lstrip": false,
|
| 897 |
+
"normalized": false,
|
| 898 |
+
"rstrip": false,
|
| 899 |
+
"single_word": false,
|
| 900 |
+
"special": true
|
| 901 |
+
},
|
| 902 |
+
"128112": {
|
| 903 |
+
"content": "<|reserved_special_token_104|>",
|
| 904 |
+
"lstrip": false,
|
| 905 |
+
"normalized": false,
|
| 906 |
+
"rstrip": false,
|
| 907 |
+
"single_word": false,
|
| 908 |
+
"special": true
|
| 909 |
+
},
|
| 910 |
+
"128113": {
|
| 911 |
+
"content": "<|reserved_special_token_105|>",
|
| 912 |
+
"lstrip": false,
|
| 913 |
+
"normalized": false,
|
| 914 |
+
"rstrip": false,
|
| 915 |
+
"single_word": false,
|
| 916 |
+
"special": true
|
| 917 |
+
},
|
| 918 |
+
"128114": {
|
| 919 |
+
"content": "<|reserved_special_token_106|>",
|
| 920 |
+
"lstrip": false,
|
| 921 |
+
"normalized": false,
|
| 922 |
+
"rstrip": false,
|
| 923 |
+
"single_word": false,
|
| 924 |
+
"special": true
|
| 925 |
+
},
|
| 926 |
+
"128115": {
|
| 927 |
+
"content": "<|reserved_special_token_107|>",
|
| 928 |
+
"lstrip": false,
|
| 929 |
+
"normalized": false,
|
| 930 |
+
"rstrip": false,
|
| 931 |
+
"single_word": false,
|
| 932 |
+
"special": true
|
| 933 |
+
},
|
| 934 |
+
"128116": {
|
| 935 |
+
"content": "<|reserved_special_token_108|>",
|
| 936 |
+
"lstrip": false,
|
| 937 |
+
"normalized": false,
|
| 938 |
+
"rstrip": false,
|
| 939 |
+
"single_word": false,
|
| 940 |
+
"special": true
|
| 941 |
+
},
|
| 942 |
+
"128117": {
|
| 943 |
+
"content": "<|reserved_special_token_109|>",
|
| 944 |
+
"lstrip": false,
|
| 945 |
+
"normalized": false,
|
| 946 |
+
"rstrip": false,
|
| 947 |
+
"single_word": false,
|
| 948 |
+
"special": true
|
| 949 |
+
},
|
| 950 |
+
"128118": {
|
| 951 |
+
"content": "<|reserved_special_token_110|>",
|
| 952 |
+
"lstrip": false,
|
| 953 |
+
"normalized": false,
|
| 954 |
+
"rstrip": false,
|
| 955 |
+
"single_word": false,
|
| 956 |
+
"special": true
|
| 957 |
+
},
|
| 958 |
+
"128119": {
|
| 959 |
+
"content": "<|reserved_special_token_111|>",
|
| 960 |
+
"lstrip": false,
|
| 961 |
+
"normalized": false,
|
| 962 |
+
"rstrip": false,
|
| 963 |
+
"single_word": false,
|
| 964 |
+
"special": true
|
| 965 |
+
},
|
| 966 |
+
"128120": {
|
| 967 |
+
"content": "<|reserved_special_token_112|>",
|
| 968 |
+
"lstrip": false,
|
| 969 |
+
"normalized": false,
|
| 970 |
+
"rstrip": false,
|
| 971 |
+
"single_word": false,
|
| 972 |
+
"special": true
|
| 973 |
+
},
|
| 974 |
+
"128121": {
|
| 975 |
+
"content": "<|reserved_special_token_113|>",
|
| 976 |
+
"lstrip": false,
|
| 977 |
+
"normalized": false,
|
| 978 |
+
"rstrip": false,
|
| 979 |
+
"single_word": false,
|
| 980 |
+
"special": true
|
| 981 |
+
},
|
| 982 |
+
"128122": {
|
| 983 |
+
"content": "<|reserved_special_token_114|>",
|
| 984 |
+
"lstrip": false,
|
| 985 |
+
"normalized": false,
|
| 986 |
+
"rstrip": false,
|
| 987 |
+
"single_word": false,
|
| 988 |
+
"special": true
|
| 989 |
+
},
|
| 990 |
+
"128123": {
|
| 991 |
+
"content": "<|reserved_special_token_115|>",
|
| 992 |
+
"lstrip": false,
|
| 993 |
+
"normalized": false,
|
| 994 |
+
"rstrip": false,
|
| 995 |
+
"single_word": false,
|
| 996 |
+
"special": true
|
| 997 |
+
},
|
| 998 |
+
"128124": {
|
| 999 |
+
"content": "<|reserved_special_token_116|>",
|
| 1000 |
+
"lstrip": false,
|
| 1001 |
+
"normalized": false,
|
| 1002 |
+
"rstrip": false,
|
| 1003 |
+
"single_word": false,
|
| 1004 |
+
"special": true
|
| 1005 |
+
},
|
| 1006 |
+
"128125": {
|
| 1007 |
+
"content": "<|reserved_special_token_117|>",
|
| 1008 |
+
"lstrip": false,
|
| 1009 |
+
"normalized": false,
|
| 1010 |
+
"rstrip": false,
|
| 1011 |
+
"single_word": false,
|
| 1012 |
+
"special": true
|
| 1013 |
+
},
|
| 1014 |
+
"128126": {
|
| 1015 |
+
"content": "<|reserved_special_token_118|>",
|
| 1016 |
+
"lstrip": false,
|
| 1017 |
+
"normalized": false,
|
| 1018 |
+
"rstrip": false,
|
| 1019 |
+
"single_word": false,
|
| 1020 |
+
"special": true
|
| 1021 |
+
},
|
| 1022 |
+
"128127": {
|
| 1023 |
+
"content": "<|reserved_special_token_119|>",
|
| 1024 |
+
"lstrip": false,
|
| 1025 |
+
"normalized": false,
|
| 1026 |
+
"rstrip": false,
|
| 1027 |
+
"single_word": false,
|
| 1028 |
+
"special": true
|
| 1029 |
+
},
|
| 1030 |
+
"128128": {
|
| 1031 |
+
"content": "<|reserved_special_token_120|>",
|
| 1032 |
+
"lstrip": false,
|
| 1033 |
+
"normalized": false,
|
| 1034 |
+
"rstrip": false,
|
| 1035 |
+
"single_word": false,
|
| 1036 |
+
"special": true
|
| 1037 |
+
},
|
| 1038 |
+
"128129": {
|
| 1039 |
+
"content": "<|reserved_special_token_121|>",
|
| 1040 |
+
"lstrip": false,
|
| 1041 |
+
"normalized": false,
|
| 1042 |
+
"rstrip": false,
|
| 1043 |
+
"single_word": false,
|
| 1044 |
+
"special": true
|
| 1045 |
+
},
|
| 1046 |
+
"128130": {
|
| 1047 |
+
"content": "<|reserved_special_token_122|>",
|
| 1048 |
+
"lstrip": false,
|
| 1049 |
+
"normalized": false,
|
| 1050 |
+
"rstrip": false,
|
| 1051 |
+
"single_word": false,
|
| 1052 |
+
"special": true
|
| 1053 |
+
},
|
| 1054 |
+
"128131": {
|
| 1055 |
+
"content": "<|reserved_special_token_123|>",
|
| 1056 |
+
"lstrip": false,
|
| 1057 |
+
"normalized": false,
|
| 1058 |
+
"rstrip": false,
|
| 1059 |
+
"single_word": false,
|
| 1060 |
+
"special": true
|
| 1061 |
+
},
|
| 1062 |
+
"128132": {
|
| 1063 |
+
"content": "<|reserved_special_token_124|>",
|
| 1064 |
+
"lstrip": false,
|
| 1065 |
+
"normalized": false,
|
| 1066 |
+
"rstrip": false,
|
| 1067 |
+
"single_word": false,
|
| 1068 |
+
"special": true
|
| 1069 |
+
},
|
| 1070 |
+
"128133": {
|
| 1071 |
+
"content": "<|reserved_special_token_125|>",
|
| 1072 |
+
"lstrip": false,
|
| 1073 |
+
"normalized": false,
|
| 1074 |
+
"rstrip": false,
|
| 1075 |
+
"single_word": false,
|
| 1076 |
+
"special": true
|
| 1077 |
+
},
|
| 1078 |
+
"128134": {
|
| 1079 |
+
"content": "<|reserved_special_token_126|>",
|
| 1080 |
+
"lstrip": false,
|
| 1081 |
+
"normalized": false,
|
| 1082 |
+
"rstrip": false,
|
| 1083 |
+
"single_word": false,
|
| 1084 |
+
"special": true
|
| 1085 |
+
},
|
| 1086 |
+
"128135": {
|
| 1087 |
+
"content": "<|reserved_special_token_127|>",
|
| 1088 |
+
"lstrip": false,
|
| 1089 |
+
"normalized": false,
|
| 1090 |
+
"rstrip": false,
|
| 1091 |
+
"single_word": false,
|
| 1092 |
+
"special": true
|
| 1093 |
+
},
|
| 1094 |
+
"128136": {
|
| 1095 |
+
"content": "<|reserved_special_token_128|>",
|
| 1096 |
+
"lstrip": false,
|
| 1097 |
+
"normalized": false,
|
| 1098 |
+
"rstrip": false,
|
| 1099 |
+
"single_word": false,
|
| 1100 |
+
"special": true
|
| 1101 |
+
},
|
| 1102 |
+
"128137": {
|
| 1103 |
+
"content": "<|reserved_special_token_129|>",
|
| 1104 |
+
"lstrip": false,
|
| 1105 |
+
"normalized": false,
|
| 1106 |
+
"rstrip": false,
|
| 1107 |
+
"single_word": false,
|
| 1108 |
+
"special": true
|
| 1109 |
+
},
|
| 1110 |
+
"128138": {
|
| 1111 |
+
"content": "<|reserved_special_token_130|>",
|
| 1112 |
+
"lstrip": false,
|
| 1113 |
+
"normalized": false,
|
| 1114 |
+
"rstrip": false,
|
| 1115 |
+
"single_word": false,
|
| 1116 |
+
"special": true
|
| 1117 |
+
},
|
| 1118 |
+
"128139": {
|
| 1119 |
+
"content": "<|reserved_special_token_131|>",
|
| 1120 |
+
"lstrip": false,
|
| 1121 |
+
"normalized": false,
|
| 1122 |
+
"rstrip": false,
|
| 1123 |
+
"single_word": false,
|
| 1124 |
+
"special": true
|
| 1125 |
+
},
|
| 1126 |
+
"128140": {
|
| 1127 |
+
"content": "<|reserved_special_token_132|>",
|
| 1128 |
+
"lstrip": false,
|
| 1129 |
+
"normalized": false,
|
| 1130 |
+
"rstrip": false,
|
| 1131 |
+
"single_word": false,
|
| 1132 |
+
"special": true
|
| 1133 |
+
},
|
| 1134 |
+
"128141": {
|
| 1135 |
+
"content": "<|reserved_special_token_133|>",
|
| 1136 |
+
"lstrip": false,
|
| 1137 |
+
"normalized": false,
|
| 1138 |
+
"rstrip": false,
|
| 1139 |
+
"single_word": false,
|
| 1140 |
+
"special": true
|
| 1141 |
+
},
|
| 1142 |
+
"128142": {
|
| 1143 |
+
"content": "<|reserved_special_token_134|>",
|
| 1144 |
+
"lstrip": false,
|
| 1145 |
+
"normalized": false,
|
| 1146 |
+
"rstrip": false,
|
| 1147 |
+
"single_word": false,
|
| 1148 |
+
"special": true
|
| 1149 |
+
},
|
| 1150 |
+
"128143": {
|
| 1151 |
+
"content": "<|reserved_special_token_135|>",
|
| 1152 |
+
"lstrip": false,
|
| 1153 |
+
"normalized": false,
|
| 1154 |
+
"rstrip": false,
|
| 1155 |
+
"single_word": false,
|
| 1156 |
+
"special": true
|
| 1157 |
+
},
|
| 1158 |
+
"128144": {
|
| 1159 |
+
"content": "<|reserved_special_token_136|>",
|
| 1160 |
+
"lstrip": false,
|
| 1161 |
+
"normalized": false,
|
| 1162 |
+
"rstrip": false,
|
| 1163 |
+
"single_word": false,
|
| 1164 |
+
"special": true
|
| 1165 |
+
},
|
| 1166 |
+
"128145": {
|
| 1167 |
+
"content": "<|reserved_special_token_137|>",
|
| 1168 |
+
"lstrip": false,
|
| 1169 |
+
"normalized": false,
|
| 1170 |
+
"rstrip": false,
|
| 1171 |
+
"single_word": false,
|
| 1172 |
+
"special": true
|
| 1173 |
+
},
|
| 1174 |
+
"128146": {
|
| 1175 |
+
"content": "<|reserved_special_token_138|>",
|
| 1176 |
+
"lstrip": false,
|
| 1177 |
+
"normalized": false,
|
| 1178 |
+
"rstrip": false,
|
| 1179 |
+
"single_word": false,
|
| 1180 |
+
"special": true
|
| 1181 |
+
},
|
| 1182 |
+
"128147": {
|
| 1183 |
+
"content": "<|reserved_special_token_139|>",
|
| 1184 |
+
"lstrip": false,
|
| 1185 |
+
"normalized": false,
|
| 1186 |
+
"rstrip": false,
|
| 1187 |
+
"single_word": false,
|
| 1188 |
+
"special": true
|
| 1189 |
+
},
|
| 1190 |
+
"128148": {
|
| 1191 |
+
"content": "<|reserved_special_token_140|>",
|
| 1192 |
+
"lstrip": false,
|
| 1193 |
+
"normalized": false,
|
| 1194 |
+
"rstrip": false,
|
| 1195 |
+
"single_word": false,
|
| 1196 |
+
"special": true
|
| 1197 |
+
},
|
| 1198 |
+
"128149": {
|
| 1199 |
+
"content": "<|reserved_special_token_141|>",
|
| 1200 |
+
"lstrip": false,
|
| 1201 |
+
"normalized": false,
|
| 1202 |
+
"rstrip": false,
|
| 1203 |
+
"single_word": false,
|
| 1204 |
+
"special": true
|
| 1205 |
+
},
|
| 1206 |
+
"128150": {
|
| 1207 |
+
"content": "<|reserved_special_token_142|>",
|
| 1208 |
+
"lstrip": false,
|
| 1209 |
+
"normalized": false,
|
| 1210 |
+
"rstrip": false,
|
| 1211 |
+
"single_word": false,
|
| 1212 |
+
"special": true
|
| 1213 |
+
},
|
| 1214 |
+
"128151": {
|
| 1215 |
+
"content": "<|reserved_special_token_143|>",
|
| 1216 |
+
"lstrip": false,
|
| 1217 |
+
"normalized": false,
|
| 1218 |
+
"rstrip": false,
|
| 1219 |
+
"single_word": false,
|
| 1220 |
+
"special": true
|
| 1221 |
+
},
|
| 1222 |
+
"128152": {
|
| 1223 |
+
"content": "<|reserved_special_token_144|>",
|
| 1224 |
+
"lstrip": false,
|
| 1225 |
+
"normalized": false,
|
| 1226 |
+
"rstrip": false,
|
| 1227 |
+
"single_word": false,
|
| 1228 |
+
"special": true
|
| 1229 |
+
},
|
| 1230 |
+
"128153": {
|
| 1231 |
+
"content": "<|reserved_special_token_145|>",
|
| 1232 |
+
"lstrip": false,
|
| 1233 |
+
"normalized": false,
|
| 1234 |
+
"rstrip": false,
|
| 1235 |
+
"single_word": false,
|
| 1236 |
+
"special": true
|
| 1237 |
+
},
|
| 1238 |
+
"128154": {
|
| 1239 |
+
"content": "<|reserved_special_token_146|>",
|
| 1240 |
+
"lstrip": false,
|
| 1241 |
+
"normalized": false,
|
| 1242 |
+
"rstrip": false,
|
| 1243 |
+
"single_word": false,
|
| 1244 |
+
"special": true
|
| 1245 |
+
},
|
| 1246 |
+
"128155": {
|
| 1247 |
+
"content": "<|reserved_special_token_147|>",
|
| 1248 |
+
"lstrip": false,
|
| 1249 |
+
"normalized": false,
|
| 1250 |
+
"rstrip": false,
|
| 1251 |
+
"single_word": false,
|
| 1252 |
+
"special": true
|
| 1253 |
+
},
|
| 1254 |
+
"128156": {
|
| 1255 |
+
"content": "<|reserved_special_token_148|>",
|
| 1256 |
+
"lstrip": false,
|
| 1257 |
+
"normalized": false,
|
| 1258 |
+
"rstrip": false,
|
| 1259 |
+
"single_word": false,
|
| 1260 |
+
"special": true
|
| 1261 |
+
},
|
| 1262 |
+
"128157": {
|
| 1263 |
+
"content": "<|reserved_special_token_149|>",
|
| 1264 |
+
"lstrip": false,
|
| 1265 |
+
"normalized": false,
|
| 1266 |
+
"rstrip": false,
|
| 1267 |
+
"single_word": false,
|
| 1268 |
+
"special": true
|
| 1269 |
+
},
|
| 1270 |
+
"128158": {
|
| 1271 |
+
"content": "<|reserved_special_token_150|>",
|
| 1272 |
+
"lstrip": false,
|
| 1273 |
+
"normalized": false,
|
| 1274 |
+
"rstrip": false,
|
| 1275 |
+
"single_word": false,
|
| 1276 |
+
"special": true
|
| 1277 |
+
},
|
| 1278 |
+
"128159": {
|
| 1279 |
+
"content": "<|reserved_special_token_151|>",
|
| 1280 |
+
"lstrip": false,
|
| 1281 |
+
"normalized": false,
|
| 1282 |
+
"rstrip": false,
|
| 1283 |
+
"single_word": false,
|
| 1284 |
+
"special": true
|
| 1285 |
+
},
|
| 1286 |
+
"128160": {
|
| 1287 |
+
"content": "<|reserved_special_token_152|>",
|
| 1288 |
+
"lstrip": false,
|
| 1289 |
+
"normalized": false,
|
| 1290 |
+
"rstrip": false,
|
| 1291 |
+
"single_word": false,
|
| 1292 |
+
"special": true
|
| 1293 |
+
},
|
| 1294 |
+
"128161": {
|
| 1295 |
+
"content": "<|reserved_special_token_153|>",
|
| 1296 |
+
"lstrip": false,
|
| 1297 |
+
"normalized": false,
|
| 1298 |
+
"rstrip": false,
|
| 1299 |
+
"single_word": false,
|
| 1300 |
+
"special": true
|
| 1301 |
+
},
|
| 1302 |
+
"128162": {
|
| 1303 |
+
"content": "<|reserved_special_token_154|>",
|
| 1304 |
+
"lstrip": false,
|
| 1305 |
+
"normalized": false,
|
| 1306 |
+
"rstrip": false,
|
| 1307 |
+
"single_word": false,
|
| 1308 |
+
"special": true
|
| 1309 |
+
},
|
| 1310 |
+
"128163": {
|
| 1311 |
+
"content": "<|reserved_special_token_155|>",
|
| 1312 |
+
"lstrip": false,
|
| 1313 |
+
"normalized": false,
|
| 1314 |
+
"rstrip": false,
|
| 1315 |
+
"single_word": false,
|
| 1316 |
+
"special": true
|
| 1317 |
+
},
|
| 1318 |
+
"128164": {
|
| 1319 |
+
"content": "<|reserved_special_token_156|>",
|
| 1320 |
+
"lstrip": false,
|
| 1321 |
+
"normalized": false,
|
| 1322 |
+
"rstrip": false,
|
| 1323 |
+
"single_word": false,
|
| 1324 |
+
"special": true
|
| 1325 |
+
},
|
| 1326 |
+
"128165": {
|
| 1327 |
+
"content": "<|reserved_special_token_157|>",
|
| 1328 |
+
"lstrip": false,
|
| 1329 |
+
"normalized": false,
|
| 1330 |
+
"rstrip": false,
|
| 1331 |
+
"single_word": false,
|
| 1332 |
+
"special": true
|
| 1333 |
+
},
|
| 1334 |
+
"128166": {
|
| 1335 |
+
"content": "<|reserved_special_token_158|>",
|
| 1336 |
+
"lstrip": false,
|
| 1337 |
+
"normalized": false,
|
| 1338 |
+
"rstrip": false,
|
| 1339 |
+
"single_word": false,
|
| 1340 |
+
"special": true
|
| 1341 |
+
},
|
| 1342 |
+
"128167": {
|
| 1343 |
+
"content": "<|reserved_special_token_159|>",
|
| 1344 |
+
"lstrip": false,
|
| 1345 |
+
"normalized": false,
|
| 1346 |
+
"rstrip": false,
|
| 1347 |
+
"single_word": false,
|
| 1348 |
+
"special": true
|
| 1349 |
+
},
|
| 1350 |
+
"128168": {
|
| 1351 |
+
"content": "<|reserved_special_token_160|>",
|
| 1352 |
+
"lstrip": false,
|
| 1353 |
+
"normalized": false,
|
| 1354 |
+
"rstrip": false,
|
| 1355 |
+
"single_word": false,
|
| 1356 |
+
"special": true
|
| 1357 |
+
},
|
| 1358 |
+
"128169": {
|
| 1359 |
+
"content": "<|reserved_special_token_161|>",
|
| 1360 |
+
"lstrip": false,
|
| 1361 |
+
"normalized": false,
|
| 1362 |
+
"rstrip": false,
|
| 1363 |
+
"single_word": false,
|
| 1364 |
+
"special": true
|
| 1365 |
+
},
|
| 1366 |
+
"128170": {
|
| 1367 |
+
"content": "<|reserved_special_token_162|>",
|
| 1368 |
+
"lstrip": false,
|
| 1369 |
+
"normalized": false,
|
| 1370 |
+
"rstrip": false,
|
| 1371 |
+
"single_word": false,
|
| 1372 |
+
"special": true
|
| 1373 |
+
},
|
| 1374 |
+
"128171": {
|
| 1375 |
+
"content": "<|reserved_special_token_163|>",
|
| 1376 |
+
"lstrip": false,
|
| 1377 |
+
"normalized": false,
|
| 1378 |
+
"rstrip": false,
|
| 1379 |
+
"single_word": false,
|
| 1380 |
+
"special": true
|
| 1381 |
+
},
|
| 1382 |
+
"128172": {
|
| 1383 |
+
"content": "<|reserved_special_token_164|>",
|
| 1384 |
+
"lstrip": false,
|
| 1385 |
+
"normalized": false,
|
| 1386 |
+
"rstrip": false,
|
| 1387 |
+
"single_word": false,
|
| 1388 |
+
"special": true
|
| 1389 |
+
},
|
| 1390 |
+
"128173": {
|
| 1391 |
+
"content": "<|reserved_special_token_165|>",
|
| 1392 |
+
"lstrip": false,
|
| 1393 |
+
"normalized": false,
|
| 1394 |
+
"rstrip": false,
|
| 1395 |
+
"single_word": false,
|
| 1396 |
+
"special": true
|
| 1397 |
+
},
|
| 1398 |
+
"128174": {
|
| 1399 |
+
"content": "<|reserved_special_token_166|>",
|
| 1400 |
+
"lstrip": false,
|
| 1401 |
+
"normalized": false,
|
| 1402 |
+
"rstrip": false,
|
| 1403 |
+
"single_word": false,
|
| 1404 |
+
"special": true
|
| 1405 |
+
},
|
| 1406 |
+
"128175": {
|
| 1407 |
+
"content": "<|reserved_special_token_167|>",
|
| 1408 |
+
"lstrip": false,
|
| 1409 |
+
"normalized": false,
|
| 1410 |
+
"rstrip": false,
|
| 1411 |
+
"single_word": false,
|
| 1412 |
+
"special": true
|
| 1413 |
+
},
|
| 1414 |
+
"128176": {
|
| 1415 |
+
"content": "<|reserved_special_token_168|>",
|
| 1416 |
+
"lstrip": false,
|
| 1417 |
+
"normalized": false,
|
| 1418 |
+
"rstrip": false,
|
| 1419 |
+
"single_word": false,
|
| 1420 |
+
"special": true
|
| 1421 |
+
},
|
| 1422 |
+
"128177": {
|
| 1423 |
+
"content": "<|reserved_special_token_169|>",
|
| 1424 |
+
"lstrip": false,
|
| 1425 |
+
"normalized": false,
|
| 1426 |
+
"rstrip": false,
|
| 1427 |
+
"single_word": false,
|
| 1428 |
+
"special": true
|
| 1429 |
+
},
|
| 1430 |
+
"128178": {
|
| 1431 |
+
"content": "<|reserved_special_token_170|>",
|
| 1432 |
+
"lstrip": false,
|
| 1433 |
+
"normalized": false,
|
| 1434 |
+
"rstrip": false,
|
| 1435 |
+
"single_word": false,
|
| 1436 |
+
"special": true
|
| 1437 |
+
},
|
| 1438 |
+
"128179": {
|
| 1439 |
+
"content": "<|reserved_special_token_171|>",
|
| 1440 |
+
"lstrip": false,
|
| 1441 |
+
"normalized": false,
|
| 1442 |
+
"rstrip": false,
|
| 1443 |
+
"single_word": false,
|
| 1444 |
+
"special": true
|
| 1445 |
+
},
|
| 1446 |
+
"128180": {
|
| 1447 |
+
"content": "<|reserved_special_token_172|>",
|
| 1448 |
+
"lstrip": false,
|
| 1449 |
+
"normalized": false,
|
| 1450 |
+
"rstrip": false,
|
| 1451 |
+
"single_word": false,
|
| 1452 |
+
"special": true
|
| 1453 |
+
},
|
| 1454 |
+
"128181": {
|
| 1455 |
+
"content": "<|reserved_special_token_173|>",
|
| 1456 |
+
"lstrip": false,
|
| 1457 |
+
"normalized": false,
|
| 1458 |
+
"rstrip": false,
|
| 1459 |
+
"single_word": false,
|
| 1460 |
+
"special": true
|
| 1461 |
+
},
|
| 1462 |
+
"128182": {
|
| 1463 |
+
"content": "<|reserved_special_token_174|>",
|
| 1464 |
+
"lstrip": false,
|
| 1465 |
+
"normalized": false,
|
| 1466 |
+
"rstrip": false,
|
| 1467 |
+
"single_word": false,
|
| 1468 |
+
"special": true
|
| 1469 |
+
},
|
| 1470 |
+
"128183": {
|
| 1471 |
+
"content": "<|reserved_special_token_175|>",
|
| 1472 |
+
"lstrip": false,
|
| 1473 |
+
"normalized": false,
|
| 1474 |
+
"rstrip": false,
|
| 1475 |
+
"single_word": false,
|
| 1476 |
+
"special": true
|
| 1477 |
+
},
|
| 1478 |
+
"128184": {
|
| 1479 |
+
"content": "<|reserved_special_token_176|>",
|
| 1480 |
+
"lstrip": false,
|
| 1481 |
+
"normalized": false,
|
| 1482 |
+
"rstrip": false,
|
| 1483 |
+
"single_word": false,
|
| 1484 |
+
"special": true
|
| 1485 |
+
},
|
| 1486 |
+
"128185": {
|
| 1487 |
+
"content": "<|reserved_special_token_177|>",
|
| 1488 |
+
"lstrip": false,
|
| 1489 |
+
"normalized": false,
|
| 1490 |
+
"rstrip": false,
|
| 1491 |
+
"single_word": false,
|
| 1492 |
+
"special": true
|
| 1493 |
+
},
|
| 1494 |
+
"128186": {
|
| 1495 |
+
"content": "<|reserved_special_token_178|>",
|
| 1496 |
+
"lstrip": false,
|
| 1497 |
+
"normalized": false,
|
| 1498 |
+
"rstrip": false,
|
| 1499 |
+
"single_word": false,
|
| 1500 |
+
"special": true
|
| 1501 |
+
},
|
| 1502 |
+
"128187": {
|
| 1503 |
+
"content": "<|reserved_special_token_179|>",
|
| 1504 |
+
"lstrip": false,
|
| 1505 |
+
"normalized": false,
|
| 1506 |
+
"rstrip": false,
|
| 1507 |
+
"single_word": false,
|
| 1508 |
+
"special": true
|
| 1509 |
+
},
|
| 1510 |
+
"128188": {
|
| 1511 |
+
"content": "<|reserved_special_token_180|>",
|
| 1512 |
+
"lstrip": false,
|
| 1513 |
+
"normalized": false,
|
| 1514 |
+
"rstrip": false,
|
| 1515 |
+
"single_word": false,
|
| 1516 |
+
"special": true
|
| 1517 |
+
},
|
| 1518 |
+
"128189": {
|
| 1519 |
+
"content": "<|reserved_special_token_181|>",
|
| 1520 |
+
"lstrip": false,
|
| 1521 |
+
"normalized": false,
|
| 1522 |
+
"rstrip": false,
|
| 1523 |
+
"single_word": false,
|
| 1524 |
+
"special": true
|
| 1525 |
+
},
|
| 1526 |
+
"128190": {
|
| 1527 |
+
"content": "<|reserved_special_token_182|>",
|
| 1528 |
+
"lstrip": false,
|
| 1529 |
+
"normalized": false,
|
| 1530 |
+
"rstrip": false,
|
| 1531 |
+
"single_word": false,
|
| 1532 |
+
"special": true
|
| 1533 |
+
},
|
| 1534 |
+
"128191": {
|
| 1535 |
+
"content": "<|reserved_special_token_183|>",
|
| 1536 |
+
"lstrip": false,
|
| 1537 |
+
"normalized": false,
|
| 1538 |
+
"rstrip": false,
|
| 1539 |
+
"single_word": false,
|
| 1540 |
+
"special": true
|
| 1541 |
+
},
|
| 1542 |
+
"128192": {
|
| 1543 |
+
"content": "<|reserved_special_token_184|>",
|
| 1544 |
+
"lstrip": false,
|
| 1545 |
+
"normalized": false,
|
| 1546 |
+
"rstrip": false,
|
| 1547 |
+
"single_word": false,
|
| 1548 |
+
"special": true
|
| 1549 |
+
},
|
| 1550 |
+
"128193": {
|
| 1551 |
+
"content": "<|reserved_special_token_185|>",
|
| 1552 |
+
"lstrip": false,
|
| 1553 |
+
"normalized": false,
|
| 1554 |
+
"rstrip": false,
|
| 1555 |
+
"single_word": false,
|
| 1556 |
+
"special": true
|
| 1557 |
+
},
|
| 1558 |
+
"128194": {
|
| 1559 |
+
"content": "<|reserved_special_token_186|>",
|
| 1560 |
+
"lstrip": false,
|
| 1561 |
+
"normalized": false,
|
| 1562 |
+
"rstrip": false,
|
| 1563 |
+
"single_word": false,
|
| 1564 |
+
"special": true
|
| 1565 |
+
},
|
| 1566 |
+
"128195": {
|
| 1567 |
+
"content": "<|reserved_special_token_187|>",
|
| 1568 |
+
"lstrip": false,
|
| 1569 |
+
"normalized": false,
|
| 1570 |
+
"rstrip": false,
|
| 1571 |
+
"single_word": false,
|
| 1572 |
+
"special": true
|
| 1573 |
+
},
|
| 1574 |
+
"128196": {
|
| 1575 |
+
"content": "<|reserved_special_token_188|>",
|
| 1576 |
+
"lstrip": false,
|
| 1577 |
+
"normalized": false,
|
| 1578 |
+
"rstrip": false,
|
| 1579 |
+
"single_word": false,
|
| 1580 |
+
"special": true
|
| 1581 |
+
},
|
| 1582 |
+
"128197": {
|
| 1583 |
+
"content": "<|reserved_special_token_189|>",
|
| 1584 |
+
"lstrip": false,
|
| 1585 |
+
"normalized": false,
|
| 1586 |
+
"rstrip": false,
|
| 1587 |
+
"single_word": false,
|
| 1588 |
+
"special": true
|
| 1589 |
+
},
|
| 1590 |
+
"128198": {
|
| 1591 |
+
"content": "<|reserved_special_token_190|>",
|
| 1592 |
+
"lstrip": false,
|
| 1593 |
+
"normalized": false,
|
| 1594 |
+
"rstrip": false,
|
| 1595 |
+
"single_word": false,
|
| 1596 |
+
"special": true
|
| 1597 |
+
},
|
| 1598 |
+
"128199": {
|
| 1599 |
+
"content": "<|reserved_special_token_191|>",
|
| 1600 |
+
"lstrip": false,
|
| 1601 |
+
"normalized": false,
|
| 1602 |
+
"rstrip": false,
|
| 1603 |
+
"single_word": false,
|
| 1604 |
+
"special": true
|
| 1605 |
+
},
|
| 1606 |
+
"128200": {
|
| 1607 |
+
"content": "<|reserved_special_token_192|>",
|
| 1608 |
+
"lstrip": false,
|
| 1609 |
+
"normalized": false,
|
| 1610 |
+
"rstrip": false,
|
| 1611 |
+
"single_word": false,
|
| 1612 |
+
"special": true
|
| 1613 |
+
},
|
| 1614 |
+
"128201": {
|
| 1615 |
+
"content": "<|reserved_special_token_193|>",
|
| 1616 |
+
"lstrip": false,
|
| 1617 |
+
"normalized": false,
|
| 1618 |
+
"rstrip": false,
|
| 1619 |
+
"single_word": false,
|
| 1620 |
+
"special": true
|
| 1621 |
+
},
|
| 1622 |
+
"128202": {
|
| 1623 |
+
"content": "<|reserved_special_token_194|>",
|
| 1624 |
+
"lstrip": false,
|
| 1625 |
+
"normalized": false,
|
| 1626 |
+
"rstrip": false,
|
| 1627 |
+
"single_word": false,
|
| 1628 |
+
"special": true
|
| 1629 |
+
},
|
| 1630 |
+
"128203": {
|
| 1631 |
+
"content": "<|reserved_special_token_195|>",
|
| 1632 |
+
"lstrip": false,
|
| 1633 |
+
"normalized": false,
|
| 1634 |
+
"rstrip": false,
|
| 1635 |
+
"single_word": false,
|
| 1636 |
+
"special": true
|
| 1637 |
+
},
|
| 1638 |
+
"128204": {
|
| 1639 |
+
"content": "<|reserved_special_token_196|>",
|
| 1640 |
+
"lstrip": false,
|
| 1641 |
+
"normalized": false,
|
| 1642 |
+
"rstrip": false,
|
| 1643 |
+
"single_word": false,
|
| 1644 |
+
"special": true
|
| 1645 |
+
},
|
| 1646 |
+
"128205": {
|
| 1647 |
+
"content": "<|reserved_special_token_197|>",
|
| 1648 |
+
"lstrip": false,
|
| 1649 |
+
"normalized": false,
|
| 1650 |
+
"rstrip": false,
|
| 1651 |
+
"single_word": false,
|
| 1652 |
+
"special": true
|
| 1653 |
+
},
|
| 1654 |
+
"128206": {
|
| 1655 |
+
"content": "<|reserved_special_token_198|>",
|
| 1656 |
+
"lstrip": false,
|
| 1657 |
+
"normalized": false,
|
| 1658 |
+
"rstrip": false,
|
| 1659 |
+
"single_word": false,
|
| 1660 |
+
"special": true
|
| 1661 |
+
},
|
| 1662 |
+
"128207": {
|
| 1663 |
+
"content": "<|reserved_special_token_199|>",
|
| 1664 |
+
"lstrip": false,
|
| 1665 |
+
"normalized": false,
|
| 1666 |
+
"rstrip": false,
|
| 1667 |
+
"single_word": false,
|
| 1668 |
+
"special": true
|
| 1669 |
+
},
|
| 1670 |
+
"128208": {
|
| 1671 |
+
"content": "<|reserved_special_token_200|>",
|
| 1672 |
+
"lstrip": false,
|
| 1673 |
+
"normalized": false,
|
| 1674 |
+
"rstrip": false,
|
| 1675 |
+
"single_word": false,
|
| 1676 |
+
"special": true
|
| 1677 |
+
},
|
| 1678 |
+
"128209": {
|
| 1679 |
+
"content": "<|reserved_special_token_201|>",
|
| 1680 |
+
"lstrip": false,
|
| 1681 |
+
"normalized": false,
|
| 1682 |
+
"rstrip": false,
|
| 1683 |
+
"single_word": false,
|
| 1684 |
+
"special": true
|
| 1685 |
+
},
|
| 1686 |
+
"128210": {
|
| 1687 |
+
"content": "<|reserved_special_token_202|>",
|
| 1688 |
+
"lstrip": false,
|
| 1689 |
+
"normalized": false,
|
| 1690 |
+
"rstrip": false,
|
| 1691 |
+
"single_word": false,
|
| 1692 |
+
"special": true
|
| 1693 |
+
},
|
| 1694 |
+
"128211": {
|
| 1695 |
+
"content": "<|reserved_special_token_203|>",
|
| 1696 |
+
"lstrip": false,
|
| 1697 |
+
"normalized": false,
|
| 1698 |
+
"rstrip": false,
|
| 1699 |
+
"single_word": false,
|
| 1700 |
+
"special": true
|
| 1701 |
+
},
|
| 1702 |
+
"128212": {
|
| 1703 |
+
"content": "<|reserved_special_token_204|>",
|
| 1704 |
+
"lstrip": false,
|
| 1705 |
+
"normalized": false,
|
| 1706 |
+
"rstrip": false,
|
| 1707 |
+
"single_word": false,
|
| 1708 |
+
"special": true
|
| 1709 |
+
},
|
| 1710 |
+
"128213": {
|
| 1711 |
+
"content": "<|reserved_special_token_205|>",
|
| 1712 |
+
"lstrip": false,
|
| 1713 |
+
"normalized": false,
|
| 1714 |
+
"rstrip": false,
|
| 1715 |
+
"single_word": false,
|
| 1716 |
+
"special": true
|
| 1717 |
+
},
|
| 1718 |
+
"128214": {
|
| 1719 |
+
"content": "<|reserved_special_token_206|>",
|
| 1720 |
+
"lstrip": false,
|
| 1721 |
+
"normalized": false,
|
| 1722 |
+
"rstrip": false,
|
| 1723 |
+
"single_word": false,
|
| 1724 |
+
"special": true
|
| 1725 |
+
},
|
| 1726 |
+
"128215": {
|
| 1727 |
+
"content": "<|reserved_special_token_207|>",
|
| 1728 |
+
"lstrip": false,
|
| 1729 |
+
"normalized": false,
|
| 1730 |
+
"rstrip": false,
|
| 1731 |
+
"single_word": false,
|
| 1732 |
+
"special": true
|
| 1733 |
+
},
|
| 1734 |
+
"128216": {
|
| 1735 |
+
"content": "<|reserved_special_token_208|>",
|
| 1736 |
+
"lstrip": false,
|
| 1737 |
+
"normalized": false,
|
| 1738 |
+
"rstrip": false,
|
| 1739 |
+
"single_word": false,
|
| 1740 |
+
"special": true
|
| 1741 |
+
},
|
| 1742 |
+
"128217": {
|
| 1743 |
+
"content": "<|reserved_special_token_209|>",
|
| 1744 |
+
"lstrip": false,
|
| 1745 |
+
"normalized": false,
|
| 1746 |
+
"rstrip": false,
|
| 1747 |
+
"single_word": false,
|
| 1748 |
+
"special": true
|
| 1749 |
+
},
|
| 1750 |
+
"128218": {
|
| 1751 |
+
"content": "<|reserved_special_token_210|>",
|
| 1752 |
+
"lstrip": false,
|
| 1753 |
+
"normalized": false,
|
| 1754 |
+
"rstrip": false,
|
| 1755 |
+
"single_word": false,
|
| 1756 |
+
"special": true
|
| 1757 |
+
},
|
| 1758 |
+
"128219": {
|
| 1759 |
+
"content": "<|reserved_special_token_211|>",
|
| 1760 |
+
"lstrip": false,
|
| 1761 |
+
"normalized": false,
|
| 1762 |
+
"rstrip": false,
|
| 1763 |
+
"single_word": false,
|
| 1764 |
+
"special": true
|
| 1765 |
+
},
|
| 1766 |
+
"128220": {
|
| 1767 |
+
"content": "<|reserved_special_token_212|>",
|
| 1768 |
+
"lstrip": false,
|
| 1769 |
+
"normalized": false,
|
| 1770 |
+
"rstrip": false,
|
| 1771 |
+
"single_word": false,
|
| 1772 |
+
"special": true
|
| 1773 |
+
},
|
| 1774 |
+
"128221": {
|
| 1775 |
+
"content": "<|reserved_special_token_213|>",
|
| 1776 |
+
"lstrip": false,
|
| 1777 |
+
"normalized": false,
|
| 1778 |
+
"rstrip": false,
|
| 1779 |
+
"single_word": false,
|
| 1780 |
+
"special": true
|
| 1781 |
+
},
|
| 1782 |
+
"128222": {
|
| 1783 |
+
"content": "<|reserved_special_token_214|>",
|
| 1784 |
+
"lstrip": false,
|
| 1785 |
+
"normalized": false,
|
| 1786 |
+
"rstrip": false,
|
| 1787 |
+
"single_word": false,
|
| 1788 |
+
"special": true
|
| 1789 |
+
},
|
| 1790 |
+
"128223": {
|
| 1791 |
+
"content": "<|reserved_special_token_215|>",
|
| 1792 |
+
"lstrip": false,
|
| 1793 |
+
"normalized": false,
|
| 1794 |
+
"rstrip": false,
|
| 1795 |
+
"single_word": false,
|
| 1796 |
+
"special": true
|
| 1797 |
+
},
|
| 1798 |
+
"128224": {
|
| 1799 |
+
"content": "<|reserved_special_token_216|>",
|
| 1800 |
+
"lstrip": false,
|
| 1801 |
+
"normalized": false,
|
| 1802 |
+
"rstrip": false,
|
| 1803 |
+
"single_word": false,
|
| 1804 |
+
"special": true
|
| 1805 |
+
},
|
| 1806 |
+
"128225": {
|
| 1807 |
+
"content": "<|reserved_special_token_217|>",
|
| 1808 |
+
"lstrip": false,
|
| 1809 |
+
"normalized": false,
|
| 1810 |
+
"rstrip": false,
|
| 1811 |
+
"single_word": false,
|
| 1812 |
+
"special": true
|
| 1813 |
+
},
|
| 1814 |
+
"128226": {
|
| 1815 |
+
"content": "<|reserved_special_token_218|>",
|
| 1816 |
+
"lstrip": false,
|
| 1817 |
+
"normalized": false,
|
| 1818 |
+
"rstrip": false,
|
| 1819 |
+
"single_word": false,
|
| 1820 |
+
"special": true
|
| 1821 |
+
},
|
| 1822 |
+
"128227": {
|
| 1823 |
+
"content": "<|reserved_special_token_219|>",
|
| 1824 |
+
"lstrip": false,
|
| 1825 |
+
"normalized": false,
|
| 1826 |
+
"rstrip": false,
|
| 1827 |
+
"single_word": false,
|
| 1828 |
+
"special": true
|
| 1829 |
+
},
|
| 1830 |
+
"128228": {
|
| 1831 |
+
"content": "<|reserved_special_token_220|>",
|
| 1832 |
+
"lstrip": false,
|
| 1833 |
+
"normalized": false,
|
| 1834 |
+
"rstrip": false,
|
| 1835 |
+
"single_word": false,
|
| 1836 |
+
"special": true
|
| 1837 |
+
},
|
| 1838 |
+
"128229": {
|
| 1839 |
+
"content": "<|reserved_special_token_221|>",
|
| 1840 |
+
"lstrip": false,
|
| 1841 |
+
"normalized": false,
|
| 1842 |
+
"rstrip": false,
|
| 1843 |
+
"single_word": false,
|
| 1844 |
+
"special": true
|
| 1845 |
+
},
|
| 1846 |
+
"128230": {
|
| 1847 |
+
"content": "<|reserved_special_token_222|>",
|
| 1848 |
+
"lstrip": false,
|
| 1849 |
+
"normalized": false,
|
| 1850 |
+
"rstrip": false,
|
| 1851 |
+
"single_word": false,
|
| 1852 |
+
"special": true
|
| 1853 |
+
},
|
| 1854 |
+
"128231": {
|
| 1855 |
+
"content": "<|reserved_special_token_223|>",
|
| 1856 |
+
"lstrip": false,
|
| 1857 |
+
"normalized": false,
|
| 1858 |
+
"rstrip": false,
|
| 1859 |
+
"single_word": false,
|
| 1860 |
+
"special": true
|
| 1861 |
+
},
|
| 1862 |
+
"128232": {
|
| 1863 |
+
"content": "<|reserved_special_token_224|>",
|
| 1864 |
+
"lstrip": false,
|
| 1865 |
+
"normalized": false,
|
| 1866 |
+
"rstrip": false,
|
| 1867 |
+
"single_word": false,
|
| 1868 |
+
"special": true
|
| 1869 |
+
},
|
| 1870 |
+
"128233": {
|
| 1871 |
+
"content": "<|reserved_special_token_225|>",
|
| 1872 |
+
"lstrip": false,
|
| 1873 |
+
"normalized": false,
|
| 1874 |
+
"rstrip": false,
|
| 1875 |
+
"single_word": false,
|
| 1876 |
+
"special": true
|
| 1877 |
+
},
|
| 1878 |
+
"128234": {
|
| 1879 |
+
"content": "<|reserved_special_token_226|>",
|
| 1880 |
+
"lstrip": false,
|
| 1881 |
+
"normalized": false,
|
| 1882 |
+
"rstrip": false,
|
| 1883 |
+
"single_word": false,
|
| 1884 |
+
"special": true
|
| 1885 |
+
},
|
| 1886 |
+
"128235": {
|
| 1887 |
+
"content": "<|reserved_special_token_227|>",
|
| 1888 |
+
"lstrip": false,
|
| 1889 |
+
"normalized": false,
|
| 1890 |
+
"rstrip": false,
|
| 1891 |
+
"single_word": false,
|
| 1892 |
+
"special": true
|
| 1893 |
+
},
|
| 1894 |
+
"128236": {
|
| 1895 |
+
"content": "<|reserved_special_token_228|>",
|
| 1896 |
+
"lstrip": false,
|
| 1897 |
+
"normalized": false,
|
| 1898 |
+
"rstrip": false,
|
| 1899 |
+
"single_word": false,
|
| 1900 |
+
"special": true
|
| 1901 |
+
},
|
| 1902 |
+
"128237": {
|
| 1903 |
+
"content": "<|reserved_special_token_229|>",
|
| 1904 |
+
"lstrip": false,
|
| 1905 |
+
"normalized": false,
|
| 1906 |
+
"rstrip": false,
|
| 1907 |
+
"single_word": false,
|
| 1908 |
+
"special": true
|
| 1909 |
+
},
|
| 1910 |
+
"128238": {
|
| 1911 |
+
"content": "<|reserved_special_token_230|>",
|
| 1912 |
+
"lstrip": false,
|
| 1913 |
+
"normalized": false,
|
| 1914 |
+
"rstrip": false,
|
| 1915 |
+
"single_word": false,
|
| 1916 |
+
"special": true
|
| 1917 |
+
},
|
| 1918 |
+
"128239": {
|
| 1919 |
+
"content": "<|reserved_special_token_231|>",
|
| 1920 |
+
"lstrip": false,
|
| 1921 |
+
"normalized": false,
|
| 1922 |
+
"rstrip": false,
|
| 1923 |
+
"single_word": false,
|
| 1924 |
+
"special": true
|
| 1925 |
+
},
|
| 1926 |
+
"128240": {
|
| 1927 |
+
"content": "<|reserved_special_token_232|>",
|
| 1928 |
+
"lstrip": false,
|
| 1929 |
+
"normalized": false,
|
| 1930 |
+
"rstrip": false,
|
| 1931 |
+
"single_word": false,
|
| 1932 |
+
"special": true
|
| 1933 |
+
},
|
| 1934 |
+
"128241": {
|
| 1935 |
+
"content": "<|reserved_special_token_233|>",
|
| 1936 |
+
"lstrip": false,
|
| 1937 |
+
"normalized": false,
|
| 1938 |
+
"rstrip": false,
|
| 1939 |
+
"single_word": false,
|
| 1940 |
+
"special": true
|
| 1941 |
+
},
|
| 1942 |
+
"128242": {
|
| 1943 |
+
"content": "<|reserved_special_token_234|>",
|
| 1944 |
+
"lstrip": false,
|
| 1945 |
+
"normalized": false,
|
| 1946 |
+
"rstrip": false,
|
| 1947 |
+
"single_word": false,
|
| 1948 |
+
"special": true
|
| 1949 |
+
},
|
| 1950 |
+
"128243": {
|
| 1951 |
+
"content": "<|reserved_special_token_235|>",
|
| 1952 |
+
"lstrip": false,
|
| 1953 |
+
"normalized": false,
|
| 1954 |
+
"rstrip": false,
|
| 1955 |
+
"single_word": false,
|
| 1956 |
+
"special": true
|
| 1957 |
+
},
|
| 1958 |
+
"128244": {
|
| 1959 |
+
"content": "<|reserved_special_token_236|>",
|
| 1960 |
+
"lstrip": false,
|
| 1961 |
+
"normalized": false,
|
| 1962 |
+
"rstrip": false,
|
| 1963 |
+
"single_word": false,
|
| 1964 |
+
"special": true
|
| 1965 |
+
},
|
| 1966 |
+
"128245": {
|
| 1967 |
+
"content": "<|reserved_special_token_237|>",
|
| 1968 |
+
"lstrip": false,
|
| 1969 |
+
"normalized": false,
|
| 1970 |
+
"rstrip": false,
|
| 1971 |
+
"single_word": false,
|
| 1972 |
+
"special": true
|
| 1973 |
+
},
|
| 1974 |
+
"128246": {
|
| 1975 |
+
"content": "<|reserved_special_token_238|>",
|
| 1976 |
+
"lstrip": false,
|
| 1977 |
+
"normalized": false,
|
| 1978 |
+
"rstrip": false,
|
| 1979 |
+
"single_word": false,
|
| 1980 |
+
"special": true
|
| 1981 |
+
},
|
| 1982 |
+
"128247": {
|
| 1983 |
+
"content": "<|reserved_special_token_239|>",
|
| 1984 |
+
"lstrip": false,
|
| 1985 |
+
"normalized": false,
|
| 1986 |
+
"rstrip": false,
|
| 1987 |
+
"single_word": false,
|
| 1988 |
+
"special": true
|
| 1989 |
+
},
|
| 1990 |
+
"128248": {
|
| 1991 |
+
"content": "<|reserved_special_token_240|>",
|
| 1992 |
+
"lstrip": false,
|
| 1993 |
+
"normalized": false,
|
| 1994 |
+
"rstrip": false,
|
| 1995 |
+
"single_word": false,
|
| 1996 |
+
"special": true
|
| 1997 |
+
},
|
| 1998 |
+
"128249": {
|
| 1999 |
+
"content": "<|reserved_special_token_241|>",
|
| 2000 |
+
"lstrip": false,
|
| 2001 |
+
"normalized": false,
|
| 2002 |
+
"rstrip": false,
|
| 2003 |
+
"single_word": false,
|
| 2004 |
+
"special": true
|
| 2005 |
+
},
|
| 2006 |
+
"128250": {
|
| 2007 |
+
"content": "<|reserved_special_token_242|>",
|
| 2008 |
+
"lstrip": false,
|
| 2009 |
+
"normalized": false,
|
| 2010 |
+
"rstrip": false,
|
| 2011 |
+
"single_word": false,
|
| 2012 |
+
"special": true
|
| 2013 |
+
},
|
| 2014 |
+
"128251": {
|
| 2015 |
+
"content": "<|reserved_special_token_243|>",
|
| 2016 |
+
"lstrip": false,
|
| 2017 |
+
"normalized": false,
|
| 2018 |
+
"rstrip": false,
|
| 2019 |
+
"single_word": false,
|
| 2020 |
+
"special": true
|
| 2021 |
+
},
|
| 2022 |
+
"128252": {
|
| 2023 |
+
"content": "<|reserved_special_token_244|>",
|
| 2024 |
+
"lstrip": false,
|
| 2025 |
+
"normalized": false,
|
| 2026 |
+
"rstrip": false,
|
| 2027 |
+
"single_word": false,
|
| 2028 |
+
"special": true
|
| 2029 |
+
},
|
| 2030 |
+
"128253": {
|
| 2031 |
+
"content": "<|reserved_special_token_245|>",
|
| 2032 |
+
"lstrip": false,
|
| 2033 |
+
"normalized": false,
|
| 2034 |
+
"rstrip": false,
|
| 2035 |
+
"single_word": false,
|
| 2036 |
+
"special": true
|
| 2037 |
+
},
|
| 2038 |
+
"128254": {
|
| 2039 |
+
"content": "<|reserved_special_token_246|>",
|
| 2040 |
+
"lstrip": false,
|
| 2041 |
+
"normalized": false,
|
| 2042 |
+
"rstrip": false,
|
| 2043 |
+
"single_word": false,
|
| 2044 |
+
"special": true
|
| 2045 |
+
},
|
| 2046 |
+
"128255": {
|
| 2047 |
+
"content": "<|reserved_special_token_247|>",
|
| 2048 |
+
"lstrip": false,
|
| 2049 |
+
"normalized": false,
|
| 2050 |
+
"rstrip": false,
|
| 2051 |
+
"single_word": false,
|
| 2052 |
+
"special": true
|
| 2053 |
+
}
|
| 2054 |
+
},
|
| 2055 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
| 2056 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\\n'}}{% endif %}",
|
| 2057 |
+
"clean_up_tokenization_spaces": false,
|
| 2058 |
+
"eos_token": "<|end▁of▁sentence|>",
|
| 2059 |
+
"extra_special_tokens": {},
|
| 2060 |
+
"legacy": true,
|
| 2061 |
+
"model_max_length": 16384,
|
| 2062 |
+
"pad_token": "<|end▁of▁sentence|>",
|
| 2063 |
+
"sp_model_kwargs": {},
|
| 2064 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 2065 |
+
"unk_token": null,
|
| 2066 |
+
"use_default_system_prompt": false
|
| 2067 |
+
}
|
checkpoint-800/trainer_state.json
ADDED
|
@@ -0,0 +1,818 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 800,
|
| 3 |
+
"best_metric": 1.252158284187317,
|
| 4 |
+
"best_model_checkpoint": "outputs/checkpoint-800",
|
| 5 |
+
"epoch": 0.6496142915144133,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 800,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.008120178643930167,
|
| 14 |
+
"grad_norm": 0.9899182319641113,
|
| 15 |
+
"learning_rate": 1.5e-05,
|
| 16 |
+
"loss": 2.2243,
|
| 17 |
+
"mean_token_accuracy": 0.5150829579681158,
|
| 18 |
+
"num_tokens": 105884.0,
|
| 19 |
+
"step": 10
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.016240357287860333,
|
| 23 |
+
"grad_norm": 0.9635991454124451,
|
| 24 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 25 |
+
"loss": 2.0245,
|
| 26 |
+
"mean_token_accuracy": 0.5415308997035027,
|
| 27 |
+
"num_tokens": 216549.0,
|
| 28 |
+
"step": 20
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.024360535931790498,
|
| 32 |
+
"grad_norm": 0.6212347745895386,
|
| 33 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 34 |
+
"loss": 1.664,
|
| 35 |
+
"mean_token_accuracy": 0.5978568278253078,
|
| 36 |
+
"num_tokens": 326591.0,
|
| 37 |
+
"step": 30
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.032480714575720666,
|
| 41 |
+
"grad_norm": 0.39353373646736145,
|
| 42 |
+
"learning_rate": 4.998938009679042e-05,
|
| 43 |
+
"loss": 1.4829,
|
| 44 |
+
"mean_token_accuracy": 0.6291711494326592,
|
| 45 |
+
"num_tokens": 438765.0,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.04060089321965083,
|
| 50 |
+
"grad_norm": 0.3375701904296875,
|
| 51 |
+
"learning_rate": 4.9952680903753627e-05,
|
| 52 |
+
"loss": 1.4594,
|
| 53 |
+
"mean_token_accuracy": 0.6345414012670517,
|
| 54 |
+
"num_tokens": 551707.0,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.048721071863580996,
|
| 59 |
+
"grad_norm": 0.34767618775367737,
|
| 60 |
+
"learning_rate": 4.98898097941902e-05,
|
| 61 |
+
"loss": 1.4302,
|
| 62 |
+
"mean_token_accuracy": 0.6381799459457398,
|
| 63 |
+
"num_tokens": 662676.0,
|
| 64 |
+
"step": 60
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.05684125050751117,
|
| 68 |
+
"grad_norm": 0.35675737261772156,
|
| 69 |
+
"learning_rate": 4.980083271121214e-05,
|
| 70 |
+
"loss": 1.3795,
|
| 71 |
+
"mean_token_accuracy": 0.6466716401278972,
|
| 72 |
+
"num_tokens": 771289.0,
|
| 73 |
+
"step": 70
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.06496142915144133,
|
| 77 |
+
"grad_norm": 0.37088656425476074,
|
| 78 |
+
"learning_rate": 4.968584297949255e-05,
|
| 79 |
+
"loss": 1.4072,
|
| 80 |
+
"mean_token_accuracy": 0.6428142428398133,
|
| 81 |
+
"num_tokens": 882535.0,
|
| 82 |
+
"step": 80
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.0730816077953715,
|
| 86 |
+
"grad_norm": 0.40535271167755127,
|
| 87 |
+
"learning_rate": 4.954496120738094e-05,
|
| 88 |
+
"loss": 1.3712,
|
| 89 |
+
"mean_token_accuracy": 0.6488012038171291,
|
| 90 |
+
"num_tokens": 991659.0,
|
| 91 |
+
"step": 90
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.08120178643930166,
|
| 95 |
+
"grad_norm": 0.39448976516723633,
|
| 96 |
+
"learning_rate": 4.9378335160401766e-05,
|
| 97 |
+
"loss": 1.3543,
|
| 98 |
+
"step": 100
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.08120178643930166,
|
| 102 |
+
"eval_loss": 1.3557080030441284,
|
| 103 |
+
"eval_mean_token_accuracy": 0.6499481635537707,
|
| 104 |
+
"eval_num_tokens": 1102149.0,
|
| 105 |
+
"eval_runtime": 211.2938,
|
| 106 |
+
"eval_samples_per_second": 9.328,
|
| 107 |
+
"eval_steps_per_second": 1.169,
|
| 108 |
+
"step": 100
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.08932196508323183,
|
| 112 |
+
"grad_norm": 0.40397903323173523,
|
| 113 |
+
"learning_rate": 4.918613960626873e-05,
|
| 114 |
+
"loss": 1.3691,
|
| 115 |
+
"mean_token_accuracy": 0.6495238792151212,
|
| 116 |
+
"num_tokens": 1210597.0,
|
| 117 |
+
"step": 110
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09744214372716199,
|
| 121 |
+
"grad_norm": 0.4039655327796936,
|
| 122 |
+
"learning_rate": 4.896857613157765e-05,
|
| 123 |
+
"loss": 1.3264,
|
| 124 |
+
"mean_token_accuracy": 0.6550758637487888,
|
| 125 |
+
"num_tokens": 1322196.0,
|
| 126 |
+
"step": 120
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.10556232237109216,
|
| 130 |
+
"grad_norm": 0.4150333106517792,
|
| 131 |
+
"learning_rate": 4.872587293036991e-05,
|
| 132 |
+
"loss": 1.337,
|
| 133 |
+
"mean_token_accuracy": 0.655381852388382,
|
| 134 |
+
"num_tokens": 1433808.0,
|
| 135 |
+
"step": 130
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.11368250101502234,
|
| 139 |
+
"grad_norm": 0.4298645555973053,
|
| 140 |
+
"learning_rate": 4.845828456478842e-05,
|
| 141 |
+
"loss": 1.3504,
|
| 142 |
+
"mean_token_accuracy": 0.6535526886582375,
|
| 143 |
+
"num_tokens": 1547479.0,
|
| 144 |
+
"step": 140
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.1218026796589525,
|
| 148 |
+
"grad_norm": 0.46692460775375366,
|
| 149 |
+
"learning_rate": 4.8166091698077164e-05,
|
| 150 |
+
"loss": 1.3517,
|
| 151 |
+
"mean_token_accuracy": 0.6504787422716618,
|
| 152 |
+
"num_tokens": 1661034.0,
|
| 153 |
+
"step": 150
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12992285830288267,
|
| 157 |
+
"grad_norm": 0.4362328052520752,
|
| 158 |
+
"learning_rate": 4.784960080020408e-05,
|
| 159 |
+
"loss": 1.3225,
|
| 160 |
+
"mean_token_accuracy": 0.6548900716006756,
|
| 161 |
+
"num_tokens": 1771511.0,
|
| 162 |
+
"step": 160
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.13804303694681283,
|
| 166 |
+
"grad_norm": 0.4326249361038208,
|
| 167 |
+
"learning_rate": 4.750914382641648e-05,
|
| 168 |
+
"loss": 1.3482,
|
| 169 |
+
"mean_token_accuracy": 0.6529437758028507,
|
| 170 |
+
"num_tokens": 1882929.0,
|
| 171 |
+
"step": 170
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.146163215590743,
|
| 175 |
+
"grad_norm": 0.4499496519565582,
|
| 176 |
+
"learning_rate": 4.714507786906581e-05,
|
| 177 |
+
"loss": 1.3546,
|
| 178 |
+
"mean_token_accuracy": 0.651630837470293,
|
| 179 |
+
"num_tokens": 1992465.0,
|
| 180 |
+
"step": 180
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.15428339423467316,
|
| 184 |
+
"grad_norm": 0.4416871666908264,
|
| 185 |
+
"learning_rate": 4.675778478306712e-05,
|
| 186 |
+
"loss": 1.3587,
|
| 187 |
+
"mean_token_accuracy": 0.6499045781791211,
|
| 188 |
+
"num_tokens": 2104073.0,
|
| 189 |
+
"step": 190
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.16240357287860333,
|
| 193 |
+
"grad_norm": 0.4490174353122711,
|
| 194 |
+
"learning_rate": 4.6347670785385884e-05,
|
| 195 |
+
"loss": 1.3257,
|
| 196 |
+
"step": 200
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.16240357287860333,
|
| 200 |
+
"eval_loss": 1.3144221305847168,
|
| 201 |
+
"eval_mean_token_accuracy": 0.6565933012769289,
|
| 202 |
+
"eval_num_tokens": 2215310.0,
|
| 203 |
+
"eval_runtime": 210.8432,
|
| 204 |
+
"eval_samples_per_second": 9.348,
|
| 205 |
+
"eval_steps_per_second": 1.171,
|
| 206 |
+
"step": 200
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.1705237515225335,
|
| 210 |
+
"grad_norm": 0.4184815585613251,
|
| 211 |
+
"learning_rate": 4.5915166028972624e-05,
|
| 212 |
+
"loss": 1.313,
|
| 213 |
+
"mean_token_accuracy": 0.6569435287266969,
|
| 214 |
+
"num_tokens": 2326949.0,
|
| 215 |
+
"step": 210
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.17864393016646365,
|
| 219 |
+
"grad_norm": 0.46081599593162537,
|
| 220 |
+
"learning_rate": 4.546072415159179e-05,
|
| 221 |
+
"loss": 1.3162,
|
| 222 |
+
"mean_token_accuracy": 0.658608315140009,
|
| 223 |
+
"num_tokens": 2440239.0,
|
| 224 |
+
"step": 220
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.18676410881039382,
|
| 228 |
+
"grad_norm": 0.4398249685764313,
|
| 229 |
+
"learning_rate": 4.49848218000184e-05,
|
| 230 |
+
"loss": 1.3042,
|
| 231 |
+
"mean_token_accuracy": 0.6597990304231643,
|
| 232 |
+
"num_tokens": 2549360.0,
|
| 233 |
+
"step": 230
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.19488428745432398,
|
| 237 |
+
"grad_norm": 0.46249088644981384,
|
| 238 |
+
"learning_rate": 4.448795813010142e-05,
|
| 239 |
+
"loss": 1.3134,
|
| 240 |
+
"mean_token_accuracy": 0.6584605030715466,
|
| 241 |
+
"num_tokens": 2660415.0,
|
| 242 |
+
"step": 240
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.20300446609825415,
|
| 246 |
+
"grad_norm": 0.440453439950943,
|
| 247 |
+
"learning_rate": 4.397065428321817e-05,
|
| 248 |
+
"loss": 1.3029,
|
| 249 |
+
"mean_token_accuracy": 0.660743386298418,
|
| 250 |
+
"num_tokens": 2773017.0,
|
| 251 |
+
"step": 250
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.21112464474218431,
|
| 255 |
+
"grad_norm": 0.44051623344421387,
|
| 256 |
+
"learning_rate": 4.343345283966901e-05,
|
| 257 |
+
"loss": 1.305,
|
| 258 |
+
"mean_token_accuracy": 0.6578053869307041,
|
| 259 |
+
"num_tokens": 2883117.0,
|
| 260 |
+
"step": 260
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.2192448233861145,
|
| 264 |
+
"grad_norm": 0.459414005279541,
|
| 265 |
+
"learning_rate": 4.287691724958551e-05,
|
| 266 |
+
"loss": 1.2878,
|
| 267 |
+
"mean_token_accuracy": 0.662683118134737,
|
| 268 |
+
"num_tokens": 2995555.0,
|
| 269 |
+
"step": 270
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.22736500203004467,
|
| 273 |
+
"grad_norm": 0.45349356532096863,
|
| 274 |
+
"learning_rate": 4.230163124194913e-05,
|
| 275 |
+
"loss": 1.315,
|
| 276 |
+
"mean_token_accuracy": 0.6587340161204338,
|
| 277 |
+
"num_tokens": 3105636.0,
|
| 278 |
+
"step": 280
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.23548518067397484,
|
| 282 |
+
"grad_norm": 0.4721125364303589,
|
| 283 |
+
"learning_rate": 4.170819821234001e-05,
|
| 284 |
+
"loss": 1.2847,
|
| 285 |
+
"mean_token_accuracy": 0.6631687037646771,
|
| 286 |
+
"num_tokens": 3214439.0,
|
| 287 |
+
"step": 290
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.243605359317905,
|
| 291 |
+
"grad_norm": 0.4492698013782501,
|
| 292 |
+
"learning_rate": 4.109724059005844e-05,
|
| 293 |
+
"loss": 1.2992,
|
| 294 |
+
"step": 300
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.243605359317905,
|
| 298 |
+
"eval_loss": 1.2922167778015137,
|
| 299 |
+
"eval_mean_token_accuracy": 0.6602695963160712,
|
| 300 |
+
"eval_num_tokens": 3327211.0,
|
| 301 |
+
"eval_runtime": 211.0034,
|
| 302 |
+
"eval_samples_per_second": 9.341,
|
| 303 |
+
"eval_steps_per_second": 1.171,
|
| 304 |
+
"step": 300
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.25172553796183517,
|
| 308 |
+
"grad_norm": 0.4624563753604889,
|
| 309 |
+
"learning_rate": 4.046939918528243e-05,
|
| 310 |
+
"loss": 1.2965,
|
| 311 |
+
"mean_token_accuracy": 0.6618376031517983,
|
| 312 |
+
"num_tokens": 3437825.0,
|
| 313 |
+
"step": 310
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.25984571660576533,
|
| 317 |
+
"grad_norm": 0.46572402119636536,
|
| 318 |
+
"learning_rate": 3.982533251694632e-05,
|
| 319 |
+
"loss": 1.3034,
|
| 320 |
+
"mean_token_accuracy": 0.659632931649685,
|
| 321 |
+
"num_tokens": 3549948.0,
|
| 322 |
+
"step": 320
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.2679658952496955,
|
| 326 |
+
"grad_norm": 0.4801682233810425,
|
| 327 |
+
"learning_rate": 3.916571612204537e-05,
|
| 328 |
+
"loss": 1.2945,
|
| 329 |
+
"mean_token_accuracy": 0.660579564422369,
|
| 330 |
+
"num_tokens": 3659967.0,
|
| 331 |
+
"step": 330
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.27608607389362566,
|
| 335 |
+
"grad_norm": 0.4685429036617279,
|
| 336 |
+
"learning_rate": 3.849124184709073e-05,
|
| 337 |
+
"loss": 1.2818,
|
| 338 |
+
"mean_token_accuracy": 0.662060933560133,
|
| 339 |
+
"num_tokens": 3769655.0,
|
| 340 |
+
"step": 340
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.2842062525375558,
|
| 344 |
+
"grad_norm": 0.489403635263443,
|
| 345 |
+
"learning_rate": 3.7802617122457975e-05,
|
| 346 |
+
"loss": 1.2767,
|
| 347 |
+
"mean_token_accuracy": 0.664181649684906,
|
| 348 |
+
"num_tokens": 3879329.0,
|
| 349 |
+
"step": 350
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.292326431181486,
|
| 353 |
+
"grad_norm": 0.46308156847953796,
|
| 354 |
+
"learning_rate": 3.7100564220390326e-05,
|
| 355 |
+
"loss": 1.2564,
|
| 356 |
+
"mean_token_accuracy": 0.6691928833723069,
|
| 357 |
+
"num_tokens": 3991691.0,
|
| 358 |
+
"step": 360
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.30044660982541616,
|
| 362 |
+
"grad_norm": 0.4625571668148041,
|
| 363 |
+
"learning_rate": 3.6385819497434876e-05,
|
| 364 |
+
"loss": 1.3133,
|
| 365 |
+
"mean_token_accuracy": 0.6571255922317505,
|
| 366 |
+
"num_tokens": 4102451.0,
|
| 367 |
+
"step": 370
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3085667884693463,
|
| 371 |
+
"grad_norm": 0.46258220076560974,
|
| 372 |
+
"learning_rate": 3.565913262210615e-05,
|
| 373 |
+
"loss": 1.3089,
|
| 374 |
+
"mean_token_accuracy": 0.6575767800211907,
|
| 375 |
+
"num_tokens": 4211111.0,
|
| 376 |
+
"step": 380
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.3166869671132765,
|
| 380 |
+
"grad_norm": 0.48985716700553894,
|
| 381 |
+
"learning_rate": 3.4921265788587435e-05,
|
| 382 |
+
"loss": 1.2662,
|
| 383 |
+
"mean_token_accuracy": 0.6672355219721794,
|
| 384 |
+
"num_tokens": 4322281.0,
|
| 385 |
+
"step": 390
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.32480714575720665,
|
| 389 |
+
"grad_norm": 0.4666249454021454,
|
| 390 |
+
"learning_rate": 3.417299291729431e-05,
|
| 391 |
+
"loss": 1.2745,
|
| 392 |
+
"step": 400
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.32480714575720665,
|
| 396 |
+
"eval_loss": 1.278223991394043,
|
| 397 |
+
"eval_mean_token_accuracy": 0.6623295654169461,
|
| 398 |
+
"eval_num_tokens": 4435130.0,
|
| 399 |
+
"eval_runtime": 210.9199,
|
| 400 |
+
"eval_samples_per_second": 9.345,
|
| 401 |
+
"eval_steps_per_second": 1.171,
|
| 402 |
+
"step": 400
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3329273244011368,
|
| 406 |
+
"grad_norm": 0.4835776686668396,
|
| 407 |
+
"learning_rate": 3.341509884313897e-05,
|
| 408 |
+
"loss": 1.3014,
|
| 409 |
+
"mean_token_accuracy": 0.6618138968944549,
|
| 410 |
+
"num_tokens": 4545678.0,
|
| 411 |
+
"step": 410
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.341047503045067,
|
| 415 |
+
"grad_norm": 0.4572070837020874,
|
| 416 |
+
"learning_rate": 3.264837849234685e-05,
|
| 417 |
+
"loss": 1.2974,
|
| 418 |
+
"mean_token_accuracy": 0.6597278229892254,
|
| 419 |
+
"num_tokens": 4657835.0,
|
| 420 |
+
"step": 420
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.34916768168899714,
|
| 424 |
+
"grad_norm": 0.465015709400177,
|
| 425 |
+
"learning_rate": 3.187363604868872e-05,
|
| 426 |
+
"loss": 1.2718,
|
| 427 |
+
"mean_token_accuracy": 0.6638790182769299,
|
| 428 |
+
"num_tokens": 4769188.0,
|
| 429 |
+
"step": 430
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3572878603329273,
|
| 433 |
+
"grad_norm": 0.4718572199344635,
|
| 434 |
+
"learning_rate": 3.109168411000299e-05,
|
| 435 |
+
"loss": 1.2907,
|
| 436 |
+
"mean_token_accuracy": 0.6597667798399925,
|
| 437 |
+
"num_tokens": 4879176.0,
|
| 438 |
+
"step": 440
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.3654080389768575,
|
| 442 |
+
"grad_norm": 0.47551625967025757,
|
| 443 |
+
"learning_rate": 3.03033428358928e-05,
|
| 444 |
+
"loss": 1.2868,
|
| 445 |
+
"mean_token_accuracy": 0.6611412994563579,
|
| 446 |
+
"num_tokens": 4990975.0,
|
| 447 |
+
"step": 450
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.37352821762078764,
|
| 451 |
+
"grad_norm": 0.5067311525344849,
|
| 452 |
+
"learning_rate": 2.9509439087491835e-05,
|
| 453 |
+
"loss": 1.3175,
|
| 454 |
+
"mean_token_accuracy": 0.6562842346727848,
|
| 455 |
+
"num_tokens": 5102530.0,
|
| 456 |
+
"step": 460
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.3816483962647178,
|
| 460 |
+
"grad_norm": 0.4770154654979706,
|
| 461 |
+
"learning_rate": 2.871080556020118e-05,
|
| 462 |
+
"loss": 1.308,
|
| 463 |
+
"mean_token_accuracy": 0.6601759247481823,
|
| 464 |
+
"num_tokens": 5215390.0,
|
| 465 |
+
"step": 470
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.38976857490864797,
|
| 469 |
+
"grad_norm": 0.48466214537620544,
|
| 470 |
+
"learning_rate": 2.7908279910306835e-05,
|
| 471 |
+
"loss": 1.2832,
|
| 472 |
+
"mean_token_accuracy": 0.6627671822905541,
|
| 473 |
+
"num_tokens": 5327706.0,
|
| 474 |
+
"step": 480
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.39788875355257813,
|
| 478 |
+
"grad_norm": 0.4844174385070801,
|
| 479 |
+
"learning_rate": 2.7102703876393944e-05,
|
| 480 |
+
"loss": 1.3071,
|
| 481 |
+
"mean_token_accuracy": 0.6576642289757728,
|
| 482 |
+
"num_tokens": 5436538.0,
|
| 483 |
+
"step": 490
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.4060089321965083,
|
| 487 |
+
"grad_norm": 0.5532021522521973,
|
| 488 |
+
"learning_rate": 2.629492239647926e-05,
|
| 489 |
+
"loss": 1.2879,
|
| 490 |
+
"step": 500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.4060089321965083,
|
| 494 |
+
"eval_loss": 1.267868995666504,
|
| 495 |
+
"eval_mean_token_accuracy": 0.6643349033618263,
|
| 496 |
+
"eval_num_tokens": 5548090.0,
|
| 497 |
+
"eval_runtime": 210.8479,
|
| 498 |
+
"eval_samples_per_second": 9.348,
|
| 499 |
+
"eval_steps_per_second": 1.171,
|
| 500 |
+
"step": 500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.41412911084043846,
|
| 504 |
+
"grad_norm": 0.5015835762023926,
|
| 505 |
+
"learning_rate": 2.5485782721787837e-05,
|
| 506 |
+
"loss": 1.2579,
|
| 507 |
+
"mean_token_accuracy": 0.6646677803248167,
|
| 508 |
+
"num_tokens": 5660582.0,
|
| 509 |
+
"step": 510
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.42224928948436863,
|
| 513 |
+
"grad_norm": 0.5119274854660034,
|
| 514 |
+
"learning_rate": 2.4676133528103497e-05,
|
| 515 |
+
"loss": 1.2906,
|
| 516 |
+
"mean_token_accuracy": 0.660096200555563,
|
| 517 |
+
"num_tokens": 5773353.0,
|
| 518 |
+
"step": 520
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.43036946812829885,
|
| 522 |
+
"grad_norm": 0.475361168384552,
|
| 523 |
+
"learning_rate": 2.3866824025625124e-05,
|
| 524 |
+
"loss": 1.2977,
|
| 525 |
+
"mean_token_accuracy": 0.6588940002024174,
|
| 526 |
+
"num_tokens": 5887792.0,
|
| 527 |
+
"step": 530
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.438489646772229,
|
| 531 |
+
"grad_norm": 0.5254585146903992,
|
| 532 |
+
"learning_rate": 2.305870306826242e-05,
|
| 533 |
+
"loss": 1.2603,
|
| 534 |
+
"mean_token_accuracy": 0.6667217813432217,
|
| 535 |
+
"num_tokens": 5997605.0,
|
| 536 |
+
"step": 540
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.4466098254161592,
|
| 540 |
+
"grad_norm": 0.5108360052108765,
|
| 541 |
+
"learning_rate": 2.225261826330543e-05,
|
| 542 |
+
"loss": 1.291,
|
| 543 |
+
"mean_token_accuracy": 0.6622078493237495,
|
| 544 |
+
"num_tokens": 6108366.0,
|
| 545 |
+
"step": 550
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.45473000406008934,
|
| 549 |
+
"grad_norm": 0.5151691436767578,
|
| 550 |
+
"learning_rate": 2.1449415082401455e-05,
|
| 551 |
+
"loss": 1.2834,
|
| 552 |
+
"mean_token_accuracy": 0.663181109726429,
|
| 553 |
+
"num_tokens": 6218027.0,
|
| 554 |
+
"step": 560
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.4628501827040195,
|
| 558 |
+
"grad_norm": 0.4874868094921112,
|
| 559 |
+
"learning_rate": 2.0649935974772105e-05,
|
| 560 |
+
"loss": 1.297,
|
| 561 |
+
"mean_token_accuracy": 0.6599866427481175,
|
| 562 |
+
"num_tokens": 6330662.0,
|
| 563 |
+
"step": 570
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.4709703613479497,
|
| 567 |
+
"grad_norm": 0.5027274489402771,
|
| 568 |
+
"learning_rate": 1.985501948360041e-05,
|
| 569 |
+
"loss": 1.272,
|
| 570 |
+
"mean_token_accuracy": 0.6621859490871429,
|
| 571 |
+
"num_tokens": 6440999.0,
|
| 572 |
+
"step": 580
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.47909053999187984,
|
| 576 |
+
"grad_norm": 0.4950280785560608,
|
| 577 |
+
"learning_rate": 1.9065499366514757e-05,
|
| 578 |
+
"loss": 1.2779,
|
| 579 |
+
"mean_token_accuracy": 0.6634722009301186,
|
| 580 |
+
"num_tokens": 6553048.0,
|
| 581 |
+
"step": 590
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.48721071863581,
|
| 585 |
+
"grad_norm": 0.512377142906189,
|
| 586 |
+
"learning_rate": 1.828220372109232e-05,
|
| 587 |
+
"loss": 1.2728,
|
| 588 |
+
"step": 600
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.48721071863581,
|
| 592 |
+
"eval_loss": 1.260668396949768,
|
| 593 |
+
"eval_mean_token_accuracy": 0.6655809046768466,
|
| 594 |
+
"eval_num_tokens": 6664275.0,
|
| 595 |
+
"eval_runtime": 210.7964,
|
| 596 |
+
"eval_samples_per_second": 9.35,
|
| 597 |
+
"eval_steps_per_second": 1.172,
|
| 598 |
+
"step": 600
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.49533089727974017,
|
| 602 |
+
"grad_norm": 0.5057377219200134,
|
| 603 |
+
"learning_rate": 1.7505954116299063e-05,
|
| 604 |
+
"loss": 1.2752,
|
| 605 |
+
"mean_token_accuracy": 0.6648487631231547,
|
| 606 |
+
"num_tokens": 6775546.0,
|
| 607 |
+
"step": 610
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.5034510759236703,
|
| 611 |
+
"grad_norm": 0.5137090682983398,
|
| 612 |
+
"learning_rate": 1.6737564730777284e-05,
|
| 613 |
+
"loss": 1.2986,
|
| 614 |
+
"mean_token_accuracy": 0.6603142991662025,
|
| 615 |
+
"num_tokens": 6889845.0,
|
| 616 |
+
"step": 620
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.5115712545676004,
|
| 620 |
+
"grad_norm": 0.5096326470375061,
|
| 621 |
+
"learning_rate": 1.5977841498884723e-05,
|
| 622 |
+
"loss": 1.2546,
|
| 623 |
+
"mean_token_accuracy": 0.6686703085899353,
|
| 624 |
+
"num_tokens": 7000714.0,
|
| 625 |
+
"step": 630
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5196914332115307,
|
| 629 |
+
"grad_norm": 0.5050039291381836,
|
| 630 |
+
"learning_rate": 1.5227581265380685e-05,
|
| 631 |
+
"loss": 1.2688,
|
| 632 |
+
"mean_token_accuracy": 0.6652263507246972,
|
| 633 |
+
"num_tokens": 7109313.0,
|
| 634 |
+
"step": 640
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.5278116118554608,
|
| 638 |
+
"grad_norm": 0.49248260259628296,
|
| 639 |
+
"learning_rate": 1.4487570949645888e-05,
|
| 640 |
+
"loss": 1.2949,
|
| 641 |
+
"mean_token_accuracy": 0.6615142770111561,
|
| 642 |
+
"num_tokens": 7219816.0,
|
| 643 |
+
"step": 650
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.535931790499391,
|
| 647 |
+
"grad_norm": 0.49449214339256287,
|
| 648 |
+
"learning_rate": 1.375858672031276e-05,
|
| 649 |
+
"loss": 1.2692,
|
| 650 |
+
"mean_token_accuracy": 0.6655298680067062,
|
| 651 |
+
"num_tokens": 7331697.0,
|
| 652 |
+
"step": 660
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 0.5440519691433211,
|
| 656 |
+
"grad_norm": 0.5017920732498169,
|
| 657 |
+
"learning_rate": 1.3041393181171688e-05,
|
| 658 |
+
"loss": 1.2766,
|
| 659 |
+
"mean_token_accuracy": 0.6650374494493008,
|
| 660 |
+
"num_tokens": 7440661.0,
|
| 661 |
+
"step": 670
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.5521721477872513,
|
| 665 |
+
"grad_norm": 0.5125038027763367,
|
| 666 |
+
"learning_rate": 1.2336742569207235e-05,
|
| 667 |
+
"loss": 1.285,
|
| 668 |
+
"mean_token_accuracy": 0.6637549869716167,
|
| 669 |
+
"num_tokens": 7550919.0,
|
| 670 |
+
"step": 680
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.5602923264311814,
|
| 674 |
+
"grad_norm": 0.5125107765197754,
|
| 675 |
+
"learning_rate": 1.1645373965605425e-05,
|
| 676 |
+
"loss": 1.2618,
|
| 677 |
+
"mean_token_accuracy": 0.665469516068697,
|
| 678 |
+
"num_tokens": 7661194.0,
|
| 679 |
+
"step": 690
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.5684125050751117,
|
| 683 |
+
"grad_norm": 0.5296525955200195,
|
| 684 |
+
"learning_rate": 1.0968012520559634e-05,
|
| 685 |
+
"loss": 1.258,
|
| 686 |
+
"step": 700
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.5684125050751117,
|
| 690 |
+
"eval_loss": 1.2551279067993164,
|
| 691 |
+
"eval_mean_token_accuracy": 0.6664607558655835,
|
| 692 |
+
"eval_num_tokens": 7772730.0,
|
| 693 |
+
"eval_runtime": 210.9447,
|
| 694 |
+
"eval_samples_per_second": 9.344,
|
| 695 |
+
"eval_steps_per_second": 1.171,
|
| 696 |
+
"step": 700
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.5765326837190419,
|
| 700 |
+
"grad_norm": 0.5269732475280762,
|
| 701 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 702 |
+
"loss": 1.2393,
|
| 703 |
+
"mean_token_accuracy": 0.6693665731698275,
|
| 704 |
+
"num_tokens": 7880412.0,
|
| 705 |
+
"step": 710
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.584652862362972,
|
| 709 |
+
"grad_norm": 0.4768012464046478,
|
| 710 |
+
"learning_rate": 9.658137503861314e-06,
|
| 711 |
+
"loss": 1.2542,
|
| 712 |
+
"mean_token_accuracy": 0.6695502042770386,
|
| 713 |
+
"num_tokens": 7990995.0,
|
| 714 |
+
"step": 720
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.5927730410069022,
|
| 718 |
+
"grad_norm": 0.5196062326431274,
|
| 719 |
+
"learning_rate": 9.026997810219312e-06,
|
| 720 |
+
"loss": 1.2653,
|
| 721 |
+
"mean_token_accuracy": 0.6653387762606144,
|
| 722 |
+
"num_tokens": 8105125.0,
|
| 723 |
+
"step": 730
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.6008932196508323,
|
| 727 |
+
"grad_norm": 0.5181891918182373,
|
| 728 |
+
"learning_rate": 8.412611590146069e-06,
|
| 729 |
+
"loss": 1.2563,
|
| 730 |
+
"mean_token_accuracy": 0.6682513557374478,
|
| 731 |
+
"num_tokens": 8216386.0,
|
| 732 |
+
"step": 740
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.6090133982947625,
|
| 736 |
+
"grad_norm": 0.5035992860794067,
|
| 737 |
+
"learning_rate": 7.815623249945214e-06,
|
| 738 |
+
"loss": 1.274,
|
| 739 |
+
"mean_token_accuracy": 0.6650313429534436,
|
| 740 |
+
"num_tokens": 8328588.0,
|
| 741 |
+
"step": 750
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.6171335769386926,
|
| 745 |
+
"grad_norm": 0.5094414949417114,
|
| 746 |
+
"learning_rate": 7.236658947946886e-06,
|
| 747 |
+
"loss": 1.2657,
|
| 748 |
+
"mean_token_accuracy": 0.6652336426079273,
|
| 749 |
+
"num_tokens": 8440775.0,
|
| 750 |
+
"step": 760
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.6252537555826229,
|
| 754 |
+
"grad_norm": 0.5002747178077698,
|
| 755 |
+
"learning_rate": 6.676325937754102e-06,
|
| 756 |
+
"loss": 1.2878,
|
| 757 |
+
"mean_token_accuracy": 0.6618476249277592,
|
| 758 |
+
"num_tokens": 8550952.0,
|
| 759 |
+
"step": 770
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.633373934226553,
|
| 763 |
+
"grad_norm": 0.5225718021392822,
|
| 764 |
+
"learning_rate": 6.1352119313175945e-06,
|
| 765 |
+
"loss": 1.2509,
|
| 766 |
+
"mean_token_accuracy": 0.6678596146404743,
|
| 767 |
+
"num_tokens": 8660972.0,
|
| 768 |
+
"step": 780
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.6414941128704832,
|
| 772 |
+
"grad_norm": 0.5244067311286926,
|
| 773 |
+
"learning_rate": 5.613884482507123e-06,
|
| 774 |
+
"loss": 1.2952,
|
| 775 |
+
"mean_token_accuracy": 0.6590089030563832,
|
| 776 |
+
"num_tokens": 8774781.0,
|
| 777 |
+
"step": 790
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.6496142915144133,
|
| 781 |
+
"grad_norm": 0.49261534214019775,
|
| 782 |
+
"learning_rate": 5.112890391825845e-06,
|
| 783 |
+
"loss": 1.295,
|
| 784 |
+
"step": 800
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.6496142915144133,
|
| 788 |
+
"eval_loss": 1.252158284187317,
|
| 789 |
+
"eval_mean_token_accuracy": 0.6671061894671637,
|
| 790 |
+
"eval_num_tokens": 8887925.0,
|
| 791 |
+
"eval_runtime": 210.8674,
|
| 792 |
+
"eval_samples_per_second": 9.347,
|
| 793 |
+
"eval_steps_per_second": 1.171,
|
| 794 |
+
"step": 800
|
| 795 |
+
}
|
| 796 |
+
],
|
| 797 |
+
"logging_steps": 10,
|
| 798 |
+
"max_steps": 1000,
|
| 799 |
+
"num_input_tokens_seen": 0,
|
| 800 |
+
"num_train_epochs": 1,
|
| 801 |
+
"save_steps": 100,
|
| 802 |
+
"stateful_callbacks": {
|
| 803 |
+
"TrainerControl": {
|
| 804 |
+
"args": {
|
| 805 |
+
"should_epoch_stop": false,
|
| 806 |
+
"should_evaluate": false,
|
| 807 |
+
"should_log": false,
|
| 808 |
+
"should_save": true,
|
| 809 |
+
"should_training_stop": false
|
| 810 |
+
},
|
| 811 |
+
"attributes": {}
|
| 812 |
+
}
|
| 813 |
+
},
|
| 814 |
+
"total_flos": 4.449884664627364e+17,
|
| 815 |
+
"train_batch_size": 2,
|
| 816 |
+
"trial_name": null,
|
| 817 |
+
"trial_params": null
|
| 818 |
+
}
|
checkpoint-800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f39f026f60bf035a5ea79c75e978e7686347690f8cfd3306b305924fecaee5a
|
| 3 |
+
size 6033
|
checkpoint-900/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
|
| 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 0.15.2
|
checkpoint-900/adapter_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"corda_config": null,
|
| 7 |
+
"eva_config": null,
|
| 8 |
+
"exclude_modules": null,
|
| 9 |
+
"fan_in_fan_out": false,
|
| 10 |
+
"inference_mode": true,
|
| 11 |
+
"init_lora_weights": true,
|
| 12 |
+
"layer_replication": null,
|
| 13 |
+
"layers_pattern": null,
|
| 14 |
+
"layers_to_transform": null,
|
| 15 |
+
"loftq_config": {},
|
| 16 |
+
"lora_alpha": 32,
|
| 17 |
+
"lora_bias": false,
|
| 18 |
+
"lora_dropout": 0.05,
|
| 19 |
+
"megatron_config": null,
|
| 20 |
+
"megatron_core": "megatron.core",
|
| 21 |
+
"modules_to_save": null,
|
| 22 |
+
"peft_type": "LORA",
|
| 23 |
+
"r": 16,
|
| 24 |
+
"rank_pattern": {},
|
| 25 |
+
"revision": null,
|
| 26 |
+
"target_modules": [
|
| 27 |
+
"v_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"o_proj",
|
| 30 |
+
"up_proj",
|
| 31 |
+
"gate_proj",
|
| 32 |
+
"k_proj",
|
| 33 |
+
"q_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"trainable_token_indices": null,
|
| 37 |
+
"use_dora": false,
|
| 38 |
+
"use_rslora": false
|
| 39 |
+
}
|
checkpoint-900/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcc6999b30b5170f03ab58225efa704fb1f9b1c91cf02892475407413dcfdf06
|
| 3 |
+
size 167832240
|
checkpoint-900/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:937e84e7e8d133c7b5b2385d6e7f43cd0ef90389fc5699224a1d2e0df2219d8e
|
| 3 |
+
size 335922851
|
checkpoint-900/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61ff1171886e62f088039d5155274dd5676632e760c883957f061498c6d5f280
|
| 3 |
+
size 14645
|
checkpoint-900/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a0b4230f34cfc1b81dc2c15ef8d265bdd348193f5a746ca2018df11549c7ac0
|
| 3 |
+
size 1383
|
checkpoint-900/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5941455f61a744ddf751730fa50edc4d6b9ce3ba2f42541d0fee1eab2504861a
|
| 3 |
+
size 1465
|
checkpoint-900/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin▁of▁sentence|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end▁of▁sentence|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|end▁of▁sentence|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
checkpoint-900/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
|
| 3 |
+
size 17209530
|
checkpoint-900/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2067 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"128000": {
|
| 7 |
+
"content": "<|begin▁of▁sentence|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"128001": {
|
| 15 |
+
"content": "<|end▁of▁sentence|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"128002": {
|
| 23 |
+
"content": "<|reserved_special_token_0|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"128003": {
|
| 31 |
+
"content": "<|reserved_special_token_1|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"128004": {
|
| 39 |
+
"content": "<|finetune_right_pad_id|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"128005": {
|
| 47 |
+
"content": "<|reserved_special_token_2|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"128006": {
|
| 55 |
+
"content": "<|start_header_id|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"128007": {
|
| 63 |
+
"content": "<|end_header_id|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"128008": {
|
| 71 |
+
"content": "<|eom_id|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"128009": {
|
| 79 |
+
"content": "<|eot_id|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"128010": {
|
| 87 |
+
"content": "<|python_tag|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"128011": {
|
| 95 |
+
"content": "<|User|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"128012": {
|
| 103 |
+
"content": "<|Assistant|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"128013": {
|
| 111 |
+
"content": "<think>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"128014": {
|
| 119 |
+
"content": "</think>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"128015": {
|
| 127 |
+
"content": "<|▁pad▁|>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": true
|
| 133 |
+
},
|
| 134 |
+
"128016": {
|
| 135 |
+
"content": "<|reserved_special_token_8|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": true
|
| 141 |
+
},
|
| 142 |
+
"128017": {
|
| 143 |
+
"content": "<|reserved_special_token_9|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
"128018": {
|
| 151 |
+
"content": "<|reserved_special_token_10|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": true
|
| 157 |
+
},
|
| 158 |
+
"128019": {
|
| 159 |
+
"content": "<|reserved_special_token_11|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": true
|
| 165 |
+
},
|
| 166 |
+
"128020": {
|
| 167 |
+
"content": "<|reserved_special_token_12|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": true
|
| 173 |
+
},
|
| 174 |
+
"128021": {
|
| 175 |
+
"content": "<|reserved_special_token_13|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
},
|
| 182 |
+
"128022": {
|
| 183 |
+
"content": "<|reserved_special_token_14|>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": true
|
| 189 |
+
},
|
| 190 |
+
"128023": {
|
| 191 |
+
"content": "<|reserved_special_token_15|>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": true
|
| 197 |
+
},
|
| 198 |
+
"128024": {
|
| 199 |
+
"content": "<|reserved_special_token_16|>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": true
|
| 205 |
+
},
|
| 206 |
+
"128025": {
|
| 207 |
+
"content": "<|reserved_special_token_17|>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": true
|
| 213 |
+
},
|
| 214 |
+
"128026": {
|
| 215 |
+
"content": "<|reserved_special_token_18|>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
"128027": {
|
| 223 |
+
"content": "<|reserved_special_token_19|>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
},
|
| 230 |
+
"128028": {
|
| 231 |
+
"content": "<|reserved_special_token_20|>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
"128029": {
|
| 239 |
+
"content": "<|reserved_special_token_21|>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"128030": {
|
| 247 |
+
"content": "<|reserved_special_token_22|>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"128031": {
|
| 255 |
+
"content": "<|reserved_special_token_23|>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": true
|
| 261 |
+
},
|
| 262 |
+
"128032": {
|
| 263 |
+
"content": "<|reserved_special_token_24|>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": true
|
| 269 |
+
},
|
| 270 |
+
"128033": {
|
| 271 |
+
"content": "<|reserved_special_token_25|>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": true
|
| 277 |
+
},
|
| 278 |
+
"128034": {
|
| 279 |
+
"content": "<|reserved_special_token_26|>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": true
|
| 285 |
+
},
|
| 286 |
+
"128035": {
|
| 287 |
+
"content": "<|reserved_special_token_27|>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
"128036": {
|
| 295 |
+
"content": "<|reserved_special_token_28|>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
},
|
| 302 |
+
"128037": {
|
| 303 |
+
"content": "<|reserved_special_token_29|>",
|
| 304 |
+
"lstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"rstrip": false,
|
| 307 |
+
"single_word": false,
|
| 308 |
+
"special": true
|
| 309 |
+
},
|
| 310 |
+
"128038": {
|
| 311 |
+
"content": "<|reserved_special_token_30|>",
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"normalized": false,
|
| 314 |
+
"rstrip": false,
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"special": true
|
| 317 |
+
},
|
| 318 |
+
"128039": {
|
| 319 |
+
"content": "<|reserved_special_token_31|>",
|
| 320 |
+
"lstrip": false,
|
| 321 |
+
"normalized": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false,
|
| 324 |
+
"special": true
|
| 325 |
+
},
|
| 326 |
+
"128040": {
|
| 327 |
+
"content": "<|reserved_special_token_32|>",
|
| 328 |
+
"lstrip": false,
|
| 329 |
+
"normalized": false,
|
| 330 |
+
"rstrip": false,
|
| 331 |
+
"single_word": false,
|
| 332 |
+
"special": true
|
| 333 |
+
},
|
| 334 |
+
"128041": {
|
| 335 |
+
"content": "<|reserved_special_token_33|>",
|
| 336 |
+
"lstrip": false,
|
| 337 |
+
"normalized": false,
|
| 338 |
+
"rstrip": false,
|
| 339 |
+
"single_word": false,
|
| 340 |
+
"special": true
|
| 341 |
+
},
|
| 342 |
+
"128042": {
|
| 343 |
+
"content": "<|reserved_special_token_34|>",
|
| 344 |
+
"lstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"rstrip": false,
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"special": true
|
| 349 |
+
},
|
| 350 |
+
"128043": {
|
| 351 |
+
"content": "<|reserved_special_token_35|>",
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"normalized": false,
|
| 354 |
+
"rstrip": false,
|
| 355 |
+
"single_word": false,
|
| 356 |
+
"special": true
|
| 357 |
+
},
|
| 358 |
+
"128044": {
|
| 359 |
+
"content": "<|reserved_special_token_36|>",
|
| 360 |
+
"lstrip": false,
|
| 361 |
+
"normalized": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"single_word": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
"128045": {
|
| 367 |
+
"content": "<|reserved_special_token_37|>",
|
| 368 |
+
"lstrip": false,
|
| 369 |
+
"normalized": false,
|
| 370 |
+
"rstrip": false,
|
| 371 |
+
"single_word": false,
|
| 372 |
+
"special": true
|
| 373 |
+
},
|
| 374 |
+
"128046": {
|
| 375 |
+
"content": "<|reserved_special_token_38|>",
|
| 376 |
+
"lstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"single_word": false,
|
| 380 |
+
"special": true
|
| 381 |
+
},
|
| 382 |
+
"128047": {
|
| 383 |
+
"content": "<|reserved_special_token_39|>",
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"normalized": false,
|
| 386 |
+
"rstrip": false,
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"special": true
|
| 389 |
+
},
|
| 390 |
+
"128048": {
|
| 391 |
+
"content": "<|reserved_special_token_40|>",
|
| 392 |
+
"lstrip": false,
|
| 393 |
+
"normalized": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"single_word": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
"128049": {
|
| 399 |
+
"content": "<|reserved_special_token_41|>",
|
| 400 |
+
"lstrip": false,
|
| 401 |
+
"normalized": false,
|
| 402 |
+
"rstrip": false,
|
| 403 |
+
"single_word": false,
|
| 404 |
+
"special": true
|
| 405 |
+
},
|
| 406 |
+
"128050": {
|
| 407 |
+
"content": "<|reserved_special_token_42|>",
|
| 408 |
+
"lstrip": false,
|
| 409 |
+
"normalized": false,
|
| 410 |
+
"rstrip": false,
|
| 411 |
+
"single_word": false,
|
| 412 |
+
"special": true
|
| 413 |
+
},
|
| 414 |
+
"128051": {
|
| 415 |
+
"content": "<|reserved_special_token_43|>",
|
| 416 |
+
"lstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"rstrip": false,
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"special": true
|
| 421 |
+
},
|
| 422 |
+
"128052": {
|
| 423 |
+
"content": "<|reserved_special_token_44|>",
|
| 424 |
+
"lstrip": false,
|
| 425 |
+
"normalized": false,
|
| 426 |
+
"rstrip": false,
|
| 427 |
+
"single_word": false,
|
| 428 |
+
"special": true
|
| 429 |
+
},
|
| 430 |
+
"128053": {
|
| 431 |
+
"content": "<|reserved_special_token_45|>",
|
| 432 |
+
"lstrip": false,
|
| 433 |
+
"normalized": false,
|
| 434 |
+
"rstrip": false,
|
| 435 |
+
"single_word": false,
|
| 436 |
+
"special": true
|
| 437 |
+
},
|
| 438 |
+
"128054": {
|
| 439 |
+
"content": "<|reserved_special_token_46|>",
|
| 440 |
+
"lstrip": false,
|
| 441 |
+
"normalized": false,
|
| 442 |
+
"rstrip": false,
|
| 443 |
+
"single_word": false,
|
| 444 |
+
"special": true
|
| 445 |
+
},
|
| 446 |
+
"128055": {
|
| 447 |
+
"content": "<|reserved_special_token_47|>",
|
| 448 |
+
"lstrip": false,
|
| 449 |
+
"normalized": false,
|
| 450 |
+
"rstrip": false,
|
| 451 |
+
"single_word": false,
|
| 452 |
+
"special": true
|
| 453 |
+
},
|
| 454 |
+
"128056": {
|
| 455 |
+
"content": "<|reserved_special_token_48|>",
|
| 456 |
+
"lstrip": false,
|
| 457 |
+
"normalized": false,
|
| 458 |
+
"rstrip": false,
|
| 459 |
+
"single_word": false,
|
| 460 |
+
"special": true
|
| 461 |
+
},
|
| 462 |
+
"128057": {
|
| 463 |
+
"content": "<|reserved_special_token_49|>",
|
| 464 |
+
"lstrip": false,
|
| 465 |
+
"normalized": false,
|
| 466 |
+
"rstrip": false,
|
| 467 |
+
"single_word": false,
|
| 468 |
+
"special": true
|
| 469 |
+
},
|
| 470 |
+
"128058": {
|
| 471 |
+
"content": "<|reserved_special_token_50|>",
|
| 472 |
+
"lstrip": false,
|
| 473 |
+
"normalized": false,
|
| 474 |
+
"rstrip": false,
|
| 475 |
+
"single_word": false,
|
| 476 |
+
"special": true
|
| 477 |
+
},
|
| 478 |
+
"128059": {
|
| 479 |
+
"content": "<|reserved_special_token_51|>",
|
| 480 |
+
"lstrip": false,
|
| 481 |
+
"normalized": false,
|
| 482 |
+
"rstrip": false,
|
| 483 |
+
"single_word": false,
|
| 484 |
+
"special": true
|
| 485 |
+
},
|
| 486 |
+
"128060": {
|
| 487 |
+
"content": "<|reserved_special_token_52|>",
|
| 488 |
+
"lstrip": false,
|
| 489 |
+
"normalized": false,
|
| 490 |
+
"rstrip": false,
|
| 491 |
+
"single_word": false,
|
| 492 |
+
"special": true
|
| 493 |
+
},
|
| 494 |
+
"128061": {
|
| 495 |
+
"content": "<|reserved_special_token_53|>",
|
| 496 |
+
"lstrip": false,
|
| 497 |
+
"normalized": false,
|
| 498 |
+
"rstrip": false,
|
| 499 |
+
"single_word": false,
|
| 500 |
+
"special": true
|
| 501 |
+
},
|
| 502 |
+
"128062": {
|
| 503 |
+
"content": "<|reserved_special_token_54|>",
|
| 504 |
+
"lstrip": false,
|
| 505 |
+
"normalized": false,
|
| 506 |
+
"rstrip": false,
|
| 507 |
+
"single_word": false,
|
| 508 |
+
"special": true
|
| 509 |
+
},
|
| 510 |
+
"128063": {
|
| 511 |
+
"content": "<|reserved_special_token_55|>",
|
| 512 |
+
"lstrip": false,
|
| 513 |
+
"normalized": false,
|
| 514 |
+
"rstrip": false,
|
| 515 |
+
"single_word": false,
|
| 516 |
+
"special": true
|
| 517 |
+
},
|
| 518 |
+
"128064": {
|
| 519 |
+
"content": "<|reserved_special_token_56|>",
|
| 520 |
+
"lstrip": false,
|
| 521 |
+
"normalized": false,
|
| 522 |
+
"rstrip": false,
|
| 523 |
+
"single_word": false,
|
| 524 |
+
"special": true
|
| 525 |
+
},
|
| 526 |
+
"128065": {
|
| 527 |
+
"content": "<|reserved_special_token_57|>",
|
| 528 |
+
"lstrip": false,
|
| 529 |
+
"normalized": false,
|
| 530 |
+
"rstrip": false,
|
| 531 |
+
"single_word": false,
|
| 532 |
+
"special": true
|
| 533 |
+
},
|
| 534 |
+
"128066": {
|
| 535 |
+
"content": "<|reserved_special_token_58|>",
|
| 536 |
+
"lstrip": false,
|
| 537 |
+
"normalized": false,
|
| 538 |
+
"rstrip": false,
|
| 539 |
+
"single_word": false,
|
| 540 |
+
"special": true
|
| 541 |
+
},
|
| 542 |
+
"128067": {
|
| 543 |
+
"content": "<|reserved_special_token_59|>",
|
| 544 |
+
"lstrip": false,
|
| 545 |
+
"normalized": false,
|
| 546 |
+
"rstrip": false,
|
| 547 |
+
"single_word": false,
|
| 548 |
+
"special": true
|
| 549 |
+
},
|
| 550 |
+
"128068": {
|
| 551 |
+
"content": "<|reserved_special_token_60|>",
|
| 552 |
+
"lstrip": false,
|
| 553 |
+
"normalized": false,
|
| 554 |
+
"rstrip": false,
|
| 555 |
+
"single_word": false,
|
| 556 |
+
"special": true
|
| 557 |
+
},
|
| 558 |
+
"128069": {
|
| 559 |
+
"content": "<|reserved_special_token_61|>",
|
| 560 |
+
"lstrip": false,
|
| 561 |
+
"normalized": false,
|
| 562 |
+
"rstrip": false,
|
| 563 |
+
"single_word": false,
|
| 564 |
+
"special": true
|
| 565 |
+
},
|
| 566 |
+
"128070": {
|
| 567 |
+
"content": "<|reserved_special_token_62|>",
|
| 568 |
+
"lstrip": false,
|
| 569 |
+
"normalized": false,
|
| 570 |
+
"rstrip": false,
|
| 571 |
+
"single_word": false,
|
| 572 |
+
"special": true
|
| 573 |
+
},
|
| 574 |
+
"128071": {
|
| 575 |
+
"content": "<|reserved_special_token_63|>",
|
| 576 |
+
"lstrip": false,
|
| 577 |
+
"normalized": false,
|
| 578 |
+
"rstrip": false,
|
| 579 |
+
"single_word": false,
|
| 580 |
+
"special": true
|
| 581 |
+
},
|
| 582 |
+
"128072": {
|
| 583 |
+
"content": "<|reserved_special_token_64|>",
|
| 584 |
+
"lstrip": false,
|
| 585 |
+
"normalized": false,
|
| 586 |
+
"rstrip": false,
|
| 587 |
+
"single_word": false,
|
| 588 |
+
"special": true
|
| 589 |
+
},
|
| 590 |
+
"128073": {
|
| 591 |
+
"content": "<|reserved_special_token_65|>",
|
| 592 |
+
"lstrip": false,
|
| 593 |
+
"normalized": false,
|
| 594 |
+
"rstrip": false,
|
| 595 |
+
"single_word": false,
|
| 596 |
+
"special": true
|
| 597 |
+
},
|
| 598 |
+
"128074": {
|
| 599 |
+
"content": "<|reserved_special_token_66|>",
|
| 600 |
+
"lstrip": false,
|
| 601 |
+
"normalized": false,
|
| 602 |
+
"rstrip": false,
|
| 603 |
+
"single_word": false,
|
| 604 |
+
"special": true
|
| 605 |
+
},
|
| 606 |
+
"128075": {
|
| 607 |
+
"content": "<|reserved_special_token_67|>",
|
| 608 |
+
"lstrip": false,
|
| 609 |
+
"normalized": false,
|
| 610 |
+
"rstrip": false,
|
| 611 |
+
"single_word": false,
|
| 612 |
+
"special": true
|
| 613 |
+
},
|
| 614 |
+
"128076": {
|
| 615 |
+
"content": "<|reserved_special_token_68|>",
|
| 616 |
+
"lstrip": false,
|
| 617 |
+
"normalized": false,
|
| 618 |
+
"rstrip": false,
|
| 619 |
+
"single_word": false,
|
| 620 |
+
"special": true
|
| 621 |
+
},
|
| 622 |
+
"128077": {
|
| 623 |
+
"content": "<|reserved_special_token_69|>",
|
| 624 |
+
"lstrip": false,
|
| 625 |
+
"normalized": false,
|
| 626 |
+
"rstrip": false,
|
| 627 |
+
"single_word": false,
|
| 628 |
+
"special": true
|
| 629 |
+
},
|
| 630 |
+
"128078": {
|
| 631 |
+
"content": "<|reserved_special_token_70|>",
|
| 632 |
+
"lstrip": false,
|
| 633 |
+
"normalized": false,
|
| 634 |
+
"rstrip": false,
|
| 635 |
+
"single_word": false,
|
| 636 |
+
"special": true
|
| 637 |
+
},
|
| 638 |
+
"128079": {
|
| 639 |
+
"content": "<|reserved_special_token_71|>",
|
| 640 |
+
"lstrip": false,
|
| 641 |
+
"normalized": false,
|
| 642 |
+
"rstrip": false,
|
| 643 |
+
"single_word": false,
|
| 644 |
+
"special": true
|
| 645 |
+
},
|
| 646 |
+
"128080": {
|
| 647 |
+
"content": "<|reserved_special_token_72|>",
|
| 648 |
+
"lstrip": false,
|
| 649 |
+
"normalized": false,
|
| 650 |
+
"rstrip": false,
|
| 651 |
+
"single_word": false,
|
| 652 |
+
"special": true
|
| 653 |
+
},
|
| 654 |
+
"128081": {
|
| 655 |
+
"content": "<|reserved_special_token_73|>",
|
| 656 |
+
"lstrip": false,
|
| 657 |
+
"normalized": false,
|
| 658 |
+
"rstrip": false,
|
| 659 |
+
"single_word": false,
|
| 660 |
+
"special": true
|
| 661 |
+
},
|
| 662 |
+
"128082": {
|
| 663 |
+
"content": "<|reserved_special_token_74|>",
|
| 664 |
+
"lstrip": false,
|
| 665 |
+
"normalized": false,
|
| 666 |
+
"rstrip": false,
|
| 667 |
+
"single_word": false,
|
| 668 |
+
"special": true
|
| 669 |
+
},
|
| 670 |
+
"128083": {
|
| 671 |
+
"content": "<|reserved_special_token_75|>",
|
| 672 |
+
"lstrip": false,
|
| 673 |
+
"normalized": false,
|
| 674 |
+
"rstrip": false,
|
| 675 |
+
"single_word": false,
|
| 676 |
+
"special": true
|
| 677 |
+
},
|
| 678 |
+
"128084": {
|
| 679 |
+
"content": "<|reserved_special_token_76|>",
|
| 680 |
+
"lstrip": false,
|
| 681 |
+
"normalized": false,
|
| 682 |
+
"rstrip": false,
|
| 683 |
+
"single_word": false,
|
| 684 |
+
"special": true
|
| 685 |
+
},
|
| 686 |
+
"128085": {
|
| 687 |
+
"content": "<|reserved_special_token_77|>",
|
| 688 |
+
"lstrip": false,
|
| 689 |
+
"normalized": false,
|
| 690 |
+
"rstrip": false,
|
| 691 |
+
"single_word": false,
|
| 692 |
+
"special": true
|
| 693 |
+
},
|
| 694 |
+
"128086": {
|
| 695 |
+
"content": "<|reserved_special_token_78|>",
|
| 696 |
+
"lstrip": false,
|
| 697 |
+
"normalized": false,
|
| 698 |
+
"rstrip": false,
|
| 699 |
+
"single_word": false,
|
| 700 |
+
"special": true
|
| 701 |
+
},
|
| 702 |
+
"128087": {
|
| 703 |
+
"content": "<|reserved_special_token_79|>",
|
| 704 |
+
"lstrip": false,
|
| 705 |
+
"normalized": false,
|
| 706 |
+
"rstrip": false,
|
| 707 |
+
"single_word": false,
|
| 708 |
+
"special": true
|
| 709 |
+
},
|
| 710 |
+
"128088": {
|
| 711 |
+
"content": "<|reserved_special_token_80|>",
|
| 712 |
+
"lstrip": false,
|
| 713 |
+
"normalized": false,
|
| 714 |
+
"rstrip": false,
|
| 715 |
+
"single_word": false,
|
| 716 |
+
"special": true
|
| 717 |
+
},
|
| 718 |
+
"128089": {
|
| 719 |
+
"content": "<|reserved_special_token_81|>",
|
| 720 |
+
"lstrip": false,
|
| 721 |
+
"normalized": false,
|
| 722 |
+
"rstrip": false,
|
| 723 |
+
"single_word": false,
|
| 724 |
+
"special": true
|
| 725 |
+
},
|
| 726 |
+
"128090": {
|
| 727 |
+
"content": "<|reserved_special_token_82|>",
|
| 728 |
+
"lstrip": false,
|
| 729 |
+
"normalized": false,
|
| 730 |
+
"rstrip": false,
|
| 731 |
+
"single_word": false,
|
| 732 |
+
"special": true
|
| 733 |
+
},
|
| 734 |
+
"128091": {
|
| 735 |
+
"content": "<|reserved_special_token_83|>",
|
| 736 |
+
"lstrip": false,
|
| 737 |
+
"normalized": false,
|
| 738 |
+
"rstrip": false,
|
| 739 |
+
"single_word": false,
|
| 740 |
+
"special": true
|
| 741 |
+
},
|
| 742 |
+
"128092": {
|
| 743 |
+
"content": "<|reserved_special_token_84|>",
|
| 744 |
+
"lstrip": false,
|
| 745 |
+
"normalized": false,
|
| 746 |
+
"rstrip": false,
|
| 747 |
+
"single_word": false,
|
| 748 |
+
"special": true
|
| 749 |
+
},
|
| 750 |
+
"128093": {
|
| 751 |
+
"content": "<|reserved_special_token_85|>",
|
| 752 |
+
"lstrip": false,
|
| 753 |
+
"normalized": false,
|
| 754 |
+
"rstrip": false,
|
| 755 |
+
"single_word": false,
|
| 756 |
+
"special": true
|
| 757 |
+
},
|
| 758 |
+
"128094": {
|
| 759 |
+
"content": "<|reserved_special_token_86|>",
|
| 760 |
+
"lstrip": false,
|
| 761 |
+
"normalized": false,
|
| 762 |
+
"rstrip": false,
|
| 763 |
+
"single_word": false,
|
| 764 |
+
"special": true
|
| 765 |
+
},
|
| 766 |
+
"128095": {
|
| 767 |
+
"content": "<|reserved_special_token_87|>",
|
| 768 |
+
"lstrip": false,
|
| 769 |
+
"normalized": false,
|
| 770 |
+
"rstrip": false,
|
| 771 |
+
"single_word": false,
|
| 772 |
+
"special": true
|
| 773 |
+
},
|
| 774 |
+
"128096": {
|
| 775 |
+
"content": "<|reserved_special_token_88|>",
|
| 776 |
+
"lstrip": false,
|
| 777 |
+
"normalized": false,
|
| 778 |
+
"rstrip": false,
|
| 779 |
+
"single_word": false,
|
| 780 |
+
"special": true
|
| 781 |
+
},
|
| 782 |
+
"128097": {
|
| 783 |
+
"content": "<|reserved_special_token_89|>",
|
| 784 |
+
"lstrip": false,
|
| 785 |
+
"normalized": false,
|
| 786 |
+
"rstrip": false,
|
| 787 |
+
"single_word": false,
|
| 788 |
+
"special": true
|
| 789 |
+
},
|
| 790 |
+
"128098": {
|
| 791 |
+
"content": "<|reserved_special_token_90|>",
|
| 792 |
+
"lstrip": false,
|
| 793 |
+
"normalized": false,
|
| 794 |
+
"rstrip": false,
|
| 795 |
+
"single_word": false,
|
| 796 |
+
"special": true
|
| 797 |
+
},
|
| 798 |
+
"128099": {
|
| 799 |
+
"content": "<|reserved_special_token_91|>",
|
| 800 |
+
"lstrip": false,
|
| 801 |
+
"normalized": false,
|
| 802 |
+
"rstrip": false,
|
| 803 |
+
"single_word": false,
|
| 804 |
+
"special": true
|
| 805 |
+
},
|
| 806 |
+
"128100": {
|
| 807 |
+
"content": "<|reserved_special_token_92|>",
|
| 808 |
+
"lstrip": false,
|
| 809 |
+
"normalized": false,
|
| 810 |
+
"rstrip": false,
|
| 811 |
+
"single_word": false,
|
| 812 |
+
"special": true
|
| 813 |
+
},
|
| 814 |
+
"128101": {
|
| 815 |
+
"content": "<|reserved_special_token_93|>",
|
| 816 |
+
"lstrip": false,
|
| 817 |
+
"normalized": false,
|
| 818 |
+
"rstrip": false,
|
| 819 |
+
"single_word": false,
|
| 820 |
+
"special": true
|
| 821 |
+
},
|
| 822 |
+
"128102": {
|
| 823 |
+
"content": "<|reserved_special_token_94|>",
|
| 824 |
+
"lstrip": false,
|
| 825 |
+
"normalized": false,
|
| 826 |
+
"rstrip": false,
|
| 827 |
+
"single_word": false,
|
| 828 |
+
"special": true
|
| 829 |
+
},
|
| 830 |
+
"128103": {
|
| 831 |
+
"content": "<|reserved_special_token_95|>",
|
| 832 |
+
"lstrip": false,
|
| 833 |
+
"normalized": false,
|
| 834 |
+
"rstrip": false,
|
| 835 |
+
"single_word": false,
|
| 836 |
+
"special": true
|
| 837 |
+
},
|
| 838 |
+
"128104": {
|
| 839 |
+
"content": "<|reserved_special_token_96|>",
|
| 840 |
+
"lstrip": false,
|
| 841 |
+
"normalized": false,
|
| 842 |
+
"rstrip": false,
|
| 843 |
+
"single_word": false,
|
| 844 |
+
"special": true
|
| 845 |
+
},
|
| 846 |
+
"128105": {
|
| 847 |
+
"content": "<|reserved_special_token_97|>",
|
| 848 |
+
"lstrip": false,
|
| 849 |
+
"normalized": false,
|
| 850 |
+
"rstrip": false,
|
| 851 |
+
"single_word": false,
|
| 852 |
+
"special": true
|
| 853 |
+
},
|
| 854 |
+
"128106": {
|
| 855 |
+
"content": "<|reserved_special_token_98|>",
|
| 856 |
+
"lstrip": false,
|
| 857 |
+
"normalized": false,
|
| 858 |
+
"rstrip": false,
|
| 859 |
+
"single_word": false,
|
| 860 |
+
"special": true
|
| 861 |
+
},
|
| 862 |
+
"128107": {
|
| 863 |
+
"content": "<|reserved_special_token_99|>",
|
| 864 |
+
"lstrip": false,
|
| 865 |
+
"normalized": false,
|
| 866 |
+
"rstrip": false,
|
| 867 |
+
"single_word": false,
|
| 868 |
+
"special": true
|
| 869 |
+
},
|
| 870 |
+
"128108": {
|
| 871 |
+
"content": "<|reserved_special_token_100|>",
|
| 872 |
+
"lstrip": false,
|
| 873 |
+
"normalized": false,
|
| 874 |
+
"rstrip": false,
|
| 875 |
+
"single_word": false,
|
| 876 |
+
"special": true
|
| 877 |
+
},
|
| 878 |
+
"128109": {
|
| 879 |
+
"content": "<|reserved_special_token_101|>",
|
| 880 |
+
"lstrip": false,
|
| 881 |
+
"normalized": false,
|
| 882 |
+
"rstrip": false,
|
| 883 |
+
"single_word": false,
|
| 884 |
+
"special": true
|
| 885 |
+
},
|
| 886 |
+
"128110": {
|
| 887 |
+
"content": "<|reserved_special_token_102|>",
|
| 888 |
+
"lstrip": false,
|
| 889 |
+
"normalized": false,
|
| 890 |
+
"rstrip": false,
|
| 891 |
+
"single_word": false,
|
| 892 |
+
"special": true
|
| 893 |
+
},
|
| 894 |
+
"128111": {
|
| 895 |
+
"content": "<|reserved_special_token_103|>",
|
| 896 |
+
"lstrip": false,
|
| 897 |
+
"normalized": false,
|
| 898 |
+
"rstrip": false,
|
| 899 |
+
"single_word": false,
|
| 900 |
+
"special": true
|
| 901 |
+
},
|
| 902 |
+
"128112": {
|
| 903 |
+
"content": "<|reserved_special_token_104|>",
|
| 904 |
+
"lstrip": false,
|
| 905 |
+
"normalized": false,
|
| 906 |
+
"rstrip": false,
|
| 907 |
+
"single_word": false,
|
| 908 |
+
"special": true
|
| 909 |
+
},
|
| 910 |
+
"128113": {
|
| 911 |
+
"content": "<|reserved_special_token_105|>",
|
| 912 |
+
"lstrip": false,
|
| 913 |
+
"normalized": false,
|
| 914 |
+
"rstrip": false,
|
| 915 |
+
"single_word": false,
|
| 916 |
+
"special": true
|
| 917 |
+
},
|
| 918 |
+
"128114": {
|
| 919 |
+
"content": "<|reserved_special_token_106|>",
|
| 920 |
+
"lstrip": false,
|
| 921 |
+
"normalized": false,
|
| 922 |
+
"rstrip": false,
|
| 923 |
+
"single_word": false,
|
| 924 |
+
"special": true
|
| 925 |
+
},
|
| 926 |
+
"128115": {
|
| 927 |
+
"content": "<|reserved_special_token_107|>",
|
| 928 |
+
"lstrip": false,
|
| 929 |
+
"normalized": false,
|
| 930 |
+
"rstrip": false,
|
| 931 |
+
"single_word": false,
|
| 932 |
+
"special": true
|
| 933 |
+
},
|
| 934 |
+
"128116": {
|
| 935 |
+
"content": "<|reserved_special_token_108|>",
|
| 936 |
+
"lstrip": false,
|
| 937 |
+
"normalized": false,
|
| 938 |
+
"rstrip": false,
|
| 939 |
+
"single_word": false,
|
| 940 |
+
"special": true
|
| 941 |
+
},
|
| 942 |
+
"128117": {
|
| 943 |
+
"content": "<|reserved_special_token_109|>",
|
| 944 |
+
"lstrip": false,
|
| 945 |
+
"normalized": false,
|
| 946 |
+
"rstrip": false,
|
| 947 |
+
"single_word": false,
|
| 948 |
+
"special": true
|
| 949 |
+
},
|
| 950 |
+
"128118": {
|
| 951 |
+
"content": "<|reserved_special_token_110|>",
|
| 952 |
+
"lstrip": false,
|
| 953 |
+
"normalized": false,
|
| 954 |
+
"rstrip": false,
|
| 955 |
+
"single_word": false,
|
| 956 |
+
"special": true
|
| 957 |
+
},
|
| 958 |
+
"128119": {
|
| 959 |
+
"content": "<|reserved_special_token_111|>",
|
| 960 |
+
"lstrip": false,
|
| 961 |
+
"normalized": false,
|
| 962 |
+
"rstrip": false,
|
| 963 |
+
"single_word": false,
|
| 964 |
+
"special": true
|
| 965 |
+
},
|
| 966 |
+
"128120": {
|
| 967 |
+
"content": "<|reserved_special_token_112|>",
|
| 968 |
+
"lstrip": false,
|
| 969 |
+
"normalized": false,
|
| 970 |
+
"rstrip": false,
|
| 971 |
+
"single_word": false,
|
| 972 |
+
"special": true
|
| 973 |
+
},
|
| 974 |
+
"128121": {
|
| 975 |
+
"content": "<|reserved_special_token_113|>",
|
| 976 |
+
"lstrip": false,
|
| 977 |
+
"normalized": false,
|
| 978 |
+
"rstrip": false,
|
| 979 |
+
"single_word": false,
|
| 980 |
+
"special": true
|
| 981 |
+
},
|
| 982 |
+
"128122": {
|
| 983 |
+
"content": "<|reserved_special_token_114|>",
|
| 984 |
+
"lstrip": false,
|
| 985 |
+
"normalized": false,
|
| 986 |
+
"rstrip": false,
|
| 987 |
+
"single_word": false,
|
| 988 |
+
"special": true
|
| 989 |
+
},
|
| 990 |
+
"128123": {
|
| 991 |
+
"content": "<|reserved_special_token_115|>",
|
| 992 |
+
"lstrip": false,
|
| 993 |
+
"normalized": false,
|
| 994 |
+
"rstrip": false,
|
| 995 |
+
"single_word": false,
|
| 996 |
+
"special": true
|
| 997 |
+
},
|
| 998 |
+
"128124": {
|
| 999 |
+
"content": "<|reserved_special_token_116|>",
|
| 1000 |
+
"lstrip": false,
|
| 1001 |
+
"normalized": false,
|
| 1002 |
+
"rstrip": false,
|
| 1003 |
+
"single_word": false,
|
| 1004 |
+
"special": true
|
| 1005 |
+
},
|
| 1006 |
+
"128125": {
|
| 1007 |
+
"content": "<|reserved_special_token_117|>",
|
| 1008 |
+
"lstrip": false,
|
| 1009 |
+
"normalized": false,
|
| 1010 |
+
"rstrip": false,
|
| 1011 |
+
"single_word": false,
|
| 1012 |
+
"special": true
|
| 1013 |
+
},
|
| 1014 |
+
"128126": {
|
| 1015 |
+
"content": "<|reserved_special_token_118|>",
|
| 1016 |
+
"lstrip": false,
|
| 1017 |
+
"normalized": false,
|
| 1018 |
+
"rstrip": false,
|
| 1019 |
+
"single_word": false,
|
| 1020 |
+
"special": true
|
| 1021 |
+
},
|
| 1022 |
+
"128127": {
|
| 1023 |
+
"content": "<|reserved_special_token_119|>",
|
| 1024 |
+
"lstrip": false,
|
| 1025 |
+
"normalized": false,
|
| 1026 |
+
"rstrip": false,
|
| 1027 |
+
"single_word": false,
|
| 1028 |
+
"special": true
|
| 1029 |
+
},
|
| 1030 |
+
"128128": {
|
| 1031 |
+
"content": "<|reserved_special_token_120|>",
|
| 1032 |
+
"lstrip": false,
|
| 1033 |
+
"normalized": false,
|
| 1034 |
+
"rstrip": false,
|
| 1035 |
+
"single_word": false,
|
| 1036 |
+
"special": true
|
| 1037 |
+
},
|
| 1038 |
+
"128129": {
|
| 1039 |
+
"content": "<|reserved_special_token_121|>",
|
| 1040 |
+
"lstrip": false,
|
| 1041 |
+
"normalized": false,
|
| 1042 |
+
"rstrip": false,
|
| 1043 |
+
"single_word": false,
|
| 1044 |
+
"special": true
|
| 1045 |
+
},
|
| 1046 |
+
"128130": {
|
| 1047 |
+
"content": "<|reserved_special_token_122|>",
|
| 1048 |
+
"lstrip": false,
|
| 1049 |
+
"normalized": false,
|
| 1050 |
+
"rstrip": false,
|
| 1051 |
+
"single_word": false,
|
| 1052 |
+
"special": true
|
| 1053 |
+
},
|
| 1054 |
+
"128131": {
|
| 1055 |
+
"content": "<|reserved_special_token_123|>",
|
| 1056 |
+
"lstrip": false,
|
| 1057 |
+
"normalized": false,
|
| 1058 |
+
"rstrip": false,
|
| 1059 |
+
"single_word": false,
|
| 1060 |
+
"special": true
|
| 1061 |
+
},
|
| 1062 |
+
"128132": {
|
| 1063 |
+
"content": "<|reserved_special_token_124|>",
|
| 1064 |
+
"lstrip": false,
|
| 1065 |
+
"normalized": false,
|
| 1066 |
+
"rstrip": false,
|
| 1067 |
+
"single_word": false,
|
| 1068 |
+
"special": true
|
| 1069 |
+
},
|
| 1070 |
+
"128133": {
|
| 1071 |
+
"content": "<|reserved_special_token_125|>",
|
| 1072 |
+
"lstrip": false,
|
| 1073 |
+
"normalized": false,
|
| 1074 |
+
"rstrip": false,
|
| 1075 |
+
"single_word": false,
|
| 1076 |
+
"special": true
|
| 1077 |
+
},
|
| 1078 |
+
"128134": {
|
| 1079 |
+
"content": "<|reserved_special_token_126|>",
|
| 1080 |
+
"lstrip": false,
|
| 1081 |
+
"normalized": false,
|
| 1082 |
+
"rstrip": false,
|
| 1083 |
+
"single_word": false,
|
| 1084 |
+
"special": true
|
| 1085 |
+
},
|
| 1086 |
+
"128135": {
|
| 1087 |
+
"content": "<|reserved_special_token_127|>",
|
| 1088 |
+
"lstrip": false,
|
| 1089 |
+
"normalized": false,
|
| 1090 |
+
"rstrip": false,
|
| 1091 |
+
"single_word": false,
|
| 1092 |
+
"special": true
|
| 1093 |
+
},
|
| 1094 |
+
"128136": {
|
| 1095 |
+
"content": "<|reserved_special_token_128|>",
|
| 1096 |
+
"lstrip": false,
|
| 1097 |
+
"normalized": false,
|
| 1098 |
+
"rstrip": false,
|
| 1099 |
+
"single_word": false,
|
| 1100 |
+
"special": true
|
| 1101 |
+
},
|
| 1102 |
+
"128137": {
|
| 1103 |
+
"content": "<|reserved_special_token_129|>",
|
| 1104 |
+
"lstrip": false,
|
| 1105 |
+
"normalized": false,
|
| 1106 |
+
"rstrip": false,
|
| 1107 |
+
"single_word": false,
|
| 1108 |
+
"special": true
|
| 1109 |
+
},
|
| 1110 |
+
"128138": {
|
| 1111 |
+
"content": "<|reserved_special_token_130|>",
|
| 1112 |
+
"lstrip": false,
|
| 1113 |
+
"normalized": false,
|
| 1114 |
+
"rstrip": false,
|
| 1115 |
+
"single_word": false,
|
| 1116 |
+
"special": true
|
| 1117 |
+
},
|
| 1118 |
+
"128139": {
|
| 1119 |
+
"content": "<|reserved_special_token_131|>",
|
| 1120 |
+
"lstrip": false,
|
| 1121 |
+
"normalized": false,
|
| 1122 |
+
"rstrip": false,
|
| 1123 |
+
"single_word": false,
|
| 1124 |
+
"special": true
|
| 1125 |
+
},
|
| 1126 |
+
"128140": {
|
| 1127 |
+
"content": "<|reserved_special_token_132|>",
|
| 1128 |
+
"lstrip": false,
|
| 1129 |
+
"normalized": false,
|
| 1130 |
+
"rstrip": false,
|
| 1131 |
+
"single_word": false,
|
| 1132 |
+
"special": true
|
| 1133 |
+
},
|
| 1134 |
+
"128141": {
|
| 1135 |
+
"content": "<|reserved_special_token_133|>",
|
| 1136 |
+
"lstrip": false,
|
| 1137 |
+
"normalized": false,
|
| 1138 |
+
"rstrip": false,
|
| 1139 |
+
"single_word": false,
|
| 1140 |
+
"special": true
|
| 1141 |
+
},
|
| 1142 |
+
"128142": {
|
| 1143 |
+
"content": "<|reserved_special_token_134|>",
|
| 1144 |
+
"lstrip": false,
|
| 1145 |
+
"normalized": false,
|
| 1146 |
+
"rstrip": false,
|
| 1147 |
+
"single_word": false,
|
| 1148 |
+
"special": true
|
| 1149 |
+
},
|
| 1150 |
+
"128143": {
|
| 1151 |
+
"content": "<|reserved_special_token_135|>",
|
| 1152 |
+
"lstrip": false,
|
| 1153 |
+
"normalized": false,
|
| 1154 |
+
"rstrip": false,
|
| 1155 |
+
"single_word": false,
|
| 1156 |
+
"special": true
|
| 1157 |
+
},
|
| 1158 |
+
"128144": {
|
| 1159 |
+
"content": "<|reserved_special_token_136|>",
|
| 1160 |
+
"lstrip": false,
|
| 1161 |
+
"normalized": false,
|
| 1162 |
+
"rstrip": false,
|
| 1163 |
+
"single_word": false,
|
| 1164 |
+
"special": true
|
| 1165 |
+
},
|
| 1166 |
+
"128145": {
|
| 1167 |
+
"content": "<|reserved_special_token_137|>",
|
| 1168 |
+
"lstrip": false,
|
| 1169 |
+
"normalized": false,
|
| 1170 |
+
"rstrip": false,
|
| 1171 |
+
"single_word": false,
|
| 1172 |
+
"special": true
|
| 1173 |
+
},
|
| 1174 |
+
"128146": {
|
| 1175 |
+
"content": "<|reserved_special_token_138|>",
|
| 1176 |
+
"lstrip": false,
|
| 1177 |
+
"normalized": false,
|
| 1178 |
+
"rstrip": false,
|
| 1179 |
+
"single_word": false,
|
| 1180 |
+
"special": true
|
| 1181 |
+
},
|
| 1182 |
+
"128147": {
|
| 1183 |
+
"content": "<|reserved_special_token_139|>",
|
| 1184 |
+
"lstrip": false,
|
| 1185 |
+
"normalized": false,
|
| 1186 |
+
"rstrip": false,
|
| 1187 |
+
"single_word": false,
|
| 1188 |
+
"special": true
|
| 1189 |
+
},
|
| 1190 |
+
"128148": {
|
| 1191 |
+
"content": "<|reserved_special_token_140|>",
|
| 1192 |
+
"lstrip": false,
|
| 1193 |
+
"normalized": false,
|
| 1194 |
+
"rstrip": false,
|
| 1195 |
+
"single_word": false,
|
| 1196 |
+
"special": true
|
| 1197 |
+
},
|
| 1198 |
+
"128149": {
|
| 1199 |
+
"content": "<|reserved_special_token_141|>",
|
| 1200 |
+
"lstrip": false,
|
| 1201 |
+
"normalized": false,
|
| 1202 |
+
"rstrip": false,
|
| 1203 |
+
"single_word": false,
|
| 1204 |
+
"special": true
|
| 1205 |
+
},
|
| 1206 |
+
"128150": {
|
| 1207 |
+
"content": "<|reserved_special_token_142|>",
|
| 1208 |
+
"lstrip": false,
|
| 1209 |
+
"normalized": false,
|
| 1210 |
+
"rstrip": false,
|
| 1211 |
+
"single_word": false,
|
| 1212 |
+
"special": true
|
| 1213 |
+
},
|
| 1214 |
+
"128151": {
|
| 1215 |
+
"content": "<|reserved_special_token_143|>",
|
| 1216 |
+
"lstrip": false,
|
| 1217 |
+
"normalized": false,
|
| 1218 |
+
"rstrip": false,
|
| 1219 |
+
"single_word": false,
|
| 1220 |
+
"special": true
|
| 1221 |
+
},
|
| 1222 |
+
"128152": {
|
| 1223 |
+
"content": "<|reserved_special_token_144|>",
|
| 1224 |
+
"lstrip": false,
|
| 1225 |
+
"normalized": false,
|
| 1226 |
+
"rstrip": false,
|
| 1227 |
+
"single_word": false,
|
| 1228 |
+
"special": true
|
| 1229 |
+
},
|
| 1230 |
+
"128153": {
|
| 1231 |
+
"content": "<|reserved_special_token_145|>",
|
| 1232 |
+
"lstrip": false,
|
| 1233 |
+
"normalized": false,
|
| 1234 |
+
"rstrip": false,
|
| 1235 |
+
"single_word": false,
|
| 1236 |
+
"special": true
|
| 1237 |
+
},
|
| 1238 |
+
"128154": {
|
| 1239 |
+
"content": "<|reserved_special_token_146|>",
|
| 1240 |
+
"lstrip": false,
|
| 1241 |
+
"normalized": false,
|
| 1242 |
+
"rstrip": false,
|
| 1243 |
+
"single_word": false,
|
| 1244 |
+
"special": true
|
| 1245 |
+
},
|
| 1246 |
+
"128155": {
|
| 1247 |
+
"content": "<|reserved_special_token_147|>",
|
| 1248 |
+
"lstrip": false,
|
| 1249 |
+
"normalized": false,
|
| 1250 |
+
"rstrip": false,
|
| 1251 |
+
"single_word": false,
|
| 1252 |
+
"special": true
|
| 1253 |
+
},
|
| 1254 |
+
"128156": {
|
| 1255 |
+
"content": "<|reserved_special_token_148|>",
|
| 1256 |
+
"lstrip": false,
|
| 1257 |
+
"normalized": false,
|
| 1258 |
+
"rstrip": false,
|
| 1259 |
+
"single_word": false,
|
| 1260 |
+
"special": true
|
| 1261 |
+
},
|
| 1262 |
+
"128157": {
|
| 1263 |
+
"content": "<|reserved_special_token_149|>",
|
| 1264 |
+
"lstrip": false,
|
| 1265 |
+
"normalized": false,
|
| 1266 |
+
"rstrip": false,
|
| 1267 |
+
"single_word": false,
|
| 1268 |
+
"special": true
|
| 1269 |
+
},
|
| 1270 |
+
"128158": {
|
| 1271 |
+
"content": "<|reserved_special_token_150|>",
|
| 1272 |
+
"lstrip": false,
|
| 1273 |
+
"normalized": false,
|
| 1274 |
+
"rstrip": false,
|
| 1275 |
+
"single_word": false,
|
| 1276 |
+
"special": true
|
| 1277 |
+
},
|
| 1278 |
+
"128159": {
|
| 1279 |
+
"content": "<|reserved_special_token_151|>",
|
| 1280 |
+
"lstrip": false,
|
| 1281 |
+
"normalized": false,
|
| 1282 |
+
"rstrip": false,
|
| 1283 |
+
"single_word": false,
|
| 1284 |
+
"special": true
|
| 1285 |
+
},
|
| 1286 |
+
"128160": {
|
| 1287 |
+
"content": "<|reserved_special_token_152|>",
|
| 1288 |
+
"lstrip": false,
|
| 1289 |
+
"normalized": false,
|
| 1290 |
+
"rstrip": false,
|
| 1291 |
+
"single_word": false,
|
| 1292 |
+
"special": true
|
| 1293 |
+
},
|
| 1294 |
+
"128161": {
|
| 1295 |
+
"content": "<|reserved_special_token_153|>",
|
| 1296 |
+
"lstrip": false,
|
| 1297 |
+
"normalized": false,
|
| 1298 |
+
"rstrip": false,
|
| 1299 |
+
"single_word": false,
|
| 1300 |
+
"special": true
|
| 1301 |
+
},
|
| 1302 |
+
"128162": {
|
| 1303 |
+
"content": "<|reserved_special_token_154|>",
|
| 1304 |
+
"lstrip": false,
|
| 1305 |
+
"normalized": false,
|
| 1306 |
+
"rstrip": false,
|
| 1307 |
+
"single_word": false,
|
| 1308 |
+
"special": true
|
| 1309 |
+
},
|
| 1310 |
+
"128163": {
|
| 1311 |
+
"content": "<|reserved_special_token_155|>",
|
| 1312 |
+
"lstrip": false,
|
| 1313 |
+
"normalized": false,
|
| 1314 |
+
"rstrip": false,
|
| 1315 |
+
"single_word": false,
|
| 1316 |
+
"special": true
|
| 1317 |
+
},
|
| 1318 |
+
"128164": {
|
| 1319 |
+
"content": "<|reserved_special_token_156|>",
|
| 1320 |
+
"lstrip": false,
|
| 1321 |
+
"normalized": false,
|
| 1322 |
+
"rstrip": false,
|
| 1323 |
+
"single_word": false,
|
| 1324 |
+
"special": true
|
| 1325 |
+
},
|
| 1326 |
+
"128165": {
|
| 1327 |
+
"content": "<|reserved_special_token_157|>",
|
| 1328 |
+
"lstrip": false,
|
| 1329 |
+
"normalized": false,
|
| 1330 |
+
"rstrip": false,
|
| 1331 |
+
"single_word": false,
|
| 1332 |
+
"special": true
|
| 1333 |
+
},
|
| 1334 |
+
"128166": {
|
| 1335 |
+
"content": "<|reserved_special_token_158|>",
|
| 1336 |
+
"lstrip": false,
|
| 1337 |
+
"normalized": false,
|
| 1338 |
+
"rstrip": false,
|
| 1339 |
+
"single_word": false,
|
| 1340 |
+
"special": true
|
| 1341 |
+
},
|
| 1342 |
+
"128167": {
|
| 1343 |
+
"content": "<|reserved_special_token_159|>",
|
| 1344 |
+
"lstrip": false,
|
| 1345 |
+
"normalized": false,
|
| 1346 |
+
"rstrip": false,
|
| 1347 |
+
"single_word": false,
|
| 1348 |
+
"special": true
|
| 1349 |
+
},
|
| 1350 |
+
"128168": {
|
| 1351 |
+
"content": "<|reserved_special_token_160|>",
|
| 1352 |
+
"lstrip": false,
|
| 1353 |
+
"normalized": false,
|
| 1354 |
+
"rstrip": false,
|
| 1355 |
+
"single_word": false,
|
| 1356 |
+
"special": true
|
| 1357 |
+
},
|
| 1358 |
+
"128169": {
|
| 1359 |
+
"content": "<|reserved_special_token_161|>",
|
| 1360 |
+
"lstrip": false,
|
| 1361 |
+
"normalized": false,
|
| 1362 |
+
"rstrip": false,
|
| 1363 |
+
"single_word": false,
|
| 1364 |
+
"special": true
|
| 1365 |
+
},
|
| 1366 |
+
"128170": {
|
| 1367 |
+
"content": "<|reserved_special_token_162|>",
|
| 1368 |
+
"lstrip": false,
|
| 1369 |
+
"normalized": false,
|
| 1370 |
+
"rstrip": false,
|
| 1371 |
+
"single_word": false,
|
| 1372 |
+
"special": true
|
| 1373 |
+
},
|
| 1374 |
+
"128171": {
|
| 1375 |
+
"content": "<|reserved_special_token_163|>",
|
| 1376 |
+
"lstrip": false,
|
| 1377 |
+
"normalized": false,
|
| 1378 |
+
"rstrip": false,
|
| 1379 |
+
"single_word": false,
|
| 1380 |
+
"special": true
|
| 1381 |
+
},
|
| 1382 |
+
"128172": {
|
| 1383 |
+
"content": "<|reserved_special_token_164|>",
|
| 1384 |
+
"lstrip": false,
|
| 1385 |
+
"normalized": false,
|
| 1386 |
+
"rstrip": false,
|
| 1387 |
+
"single_word": false,
|
| 1388 |
+
"special": true
|
| 1389 |
+
},
|
| 1390 |
+
"128173": {
|
| 1391 |
+
"content": "<|reserved_special_token_165|>",
|
| 1392 |
+
"lstrip": false,
|
| 1393 |
+
"normalized": false,
|
| 1394 |
+
"rstrip": false,
|
| 1395 |
+
"single_word": false,
|
| 1396 |
+
"special": true
|
| 1397 |
+
},
|
| 1398 |
+
"128174": {
|
| 1399 |
+
"content": "<|reserved_special_token_166|>",
|
| 1400 |
+
"lstrip": false,
|
| 1401 |
+
"normalized": false,
|
| 1402 |
+
"rstrip": false,
|
| 1403 |
+
"single_word": false,
|
| 1404 |
+
"special": true
|
| 1405 |
+
},
|
| 1406 |
+
"128175": {
|
| 1407 |
+
"content": "<|reserved_special_token_167|>",
|
| 1408 |
+
"lstrip": false,
|
| 1409 |
+
"normalized": false,
|
| 1410 |
+
"rstrip": false,
|
| 1411 |
+
"single_word": false,
|
| 1412 |
+
"special": true
|
| 1413 |
+
},
|
| 1414 |
+
"128176": {
|
| 1415 |
+
"content": "<|reserved_special_token_168|>",
|
| 1416 |
+
"lstrip": false,
|
| 1417 |
+
"normalized": false,
|
| 1418 |
+
"rstrip": false,
|
| 1419 |
+
"single_word": false,
|
| 1420 |
+
"special": true
|
| 1421 |
+
},
|
| 1422 |
+
"128177": {
|
| 1423 |
+
"content": "<|reserved_special_token_169|>",
|
| 1424 |
+
"lstrip": false,
|
| 1425 |
+
"normalized": false,
|
| 1426 |
+
"rstrip": false,
|
| 1427 |
+
"single_word": false,
|
| 1428 |
+
"special": true
|
| 1429 |
+
},
|
| 1430 |
+
"128178": {
|
| 1431 |
+
"content": "<|reserved_special_token_170|>",
|
| 1432 |
+
"lstrip": false,
|
| 1433 |
+
"normalized": false,
|
| 1434 |
+
"rstrip": false,
|
| 1435 |
+
"single_word": false,
|
| 1436 |
+
"special": true
|
| 1437 |
+
},
|
| 1438 |
+
"128179": {
|
| 1439 |
+
"content": "<|reserved_special_token_171|>",
|
| 1440 |
+
"lstrip": false,
|
| 1441 |
+
"normalized": false,
|
| 1442 |
+
"rstrip": false,
|
| 1443 |
+
"single_word": false,
|
| 1444 |
+
"special": true
|
| 1445 |
+
},
|
| 1446 |
+
"128180": {
|
| 1447 |
+
"content": "<|reserved_special_token_172|>",
|
| 1448 |
+
"lstrip": false,
|
| 1449 |
+
"normalized": false,
|
| 1450 |
+
"rstrip": false,
|
| 1451 |
+
"single_word": false,
|
| 1452 |
+
"special": true
|
| 1453 |
+
},
|
| 1454 |
+
"128181": {
|
| 1455 |
+
"content": "<|reserved_special_token_173|>",
|
| 1456 |
+
"lstrip": false,
|
| 1457 |
+
"normalized": false,
|
| 1458 |
+
"rstrip": false,
|
| 1459 |
+
"single_word": false,
|
| 1460 |
+
"special": true
|
| 1461 |
+
},
|
| 1462 |
+
"128182": {
|
| 1463 |
+
"content": "<|reserved_special_token_174|>",
|
| 1464 |
+
"lstrip": false,
|
| 1465 |
+
"normalized": false,
|
| 1466 |
+
"rstrip": false,
|
| 1467 |
+
"single_word": false,
|
| 1468 |
+
"special": true
|
| 1469 |
+
},
|
| 1470 |
+
"128183": {
|
| 1471 |
+
"content": "<|reserved_special_token_175|>",
|
| 1472 |
+
"lstrip": false,
|
| 1473 |
+
"normalized": false,
|
| 1474 |
+
"rstrip": false,
|
| 1475 |
+
"single_word": false,
|
| 1476 |
+
"special": true
|
| 1477 |
+
},
|
| 1478 |
+
"128184": {
|
| 1479 |
+
"content": "<|reserved_special_token_176|>",
|
| 1480 |
+
"lstrip": false,
|
| 1481 |
+
"normalized": false,
|
| 1482 |
+
"rstrip": false,
|
| 1483 |
+
"single_word": false,
|
| 1484 |
+
"special": true
|
| 1485 |
+
},
|
| 1486 |
+
"128185": {
|
| 1487 |
+
"content": "<|reserved_special_token_177|>",
|
| 1488 |
+
"lstrip": false,
|
| 1489 |
+
"normalized": false,
|
| 1490 |
+
"rstrip": false,
|
| 1491 |
+
"single_word": false,
|
| 1492 |
+
"special": true
|
| 1493 |
+
},
|
| 1494 |
+
"128186": {
|
| 1495 |
+
"content": "<|reserved_special_token_178|>",
|
| 1496 |
+
"lstrip": false,
|
| 1497 |
+
"normalized": false,
|
| 1498 |
+
"rstrip": false,
|
| 1499 |
+
"single_word": false,
|
| 1500 |
+
"special": true
|
| 1501 |
+
},
|
| 1502 |
+
"128187": {
|
| 1503 |
+
"content": "<|reserved_special_token_179|>",
|
| 1504 |
+
"lstrip": false,
|
| 1505 |
+
"normalized": false,
|
| 1506 |
+
"rstrip": false,
|
| 1507 |
+
"single_word": false,
|
| 1508 |
+
"special": true
|
| 1509 |
+
},
|
| 1510 |
+
"128188": {
|
| 1511 |
+
"content": "<|reserved_special_token_180|>",
|
| 1512 |
+
"lstrip": false,
|
| 1513 |
+
"normalized": false,
|
| 1514 |
+
"rstrip": false,
|
| 1515 |
+
"single_word": false,
|
| 1516 |
+
"special": true
|
| 1517 |
+
},
|
| 1518 |
+
"128189": {
|
| 1519 |
+
"content": "<|reserved_special_token_181|>",
|
| 1520 |
+
"lstrip": false,
|
| 1521 |
+
"normalized": false,
|
| 1522 |
+
"rstrip": false,
|
| 1523 |
+
"single_word": false,
|
| 1524 |
+
"special": true
|
| 1525 |
+
},
|
| 1526 |
+
"128190": {
|
| 1527 |
+
"content": "<|reserved_special_token_182|>",
|
| 1528 |
+
"lstrip": false,
|
| 1529 |
+
"normalized": false,
|
| 1530 |
+
"rstrip": false,
|
| 1531 |
+
"single_word": false,
|
| 1532 |
+
"special": true
|
| 1533 |
+
},
|
| 1534 |
+
"128191": {
|
| 1535 |
+
"content": "<|reserved_special_token_183|>",
|
| 1536 |
+
"lstrip": false,
|
| 1537 |
+
"normalized": false,
|
| 1538 |
+
"rstrip": false,
|
| 1539 |
+
"single_word": false,
|
| 1540 |
+
"special": true
|
| 1541 |
+
},
|
| 1542 |
+
"128192": {
|
| 1543 |
+
"content": "<|reserved_special_token_184|>",
|
| 1544 |
+
"lstrip": false,
|
| 1545 |
+
"normalized": false,
|
| 1546 |
+
"rstrip": false,
|
| 1547 |
+
"single_word": false,
|
| 1548 |
+
"special": true
|
| 1549 |
+
},
|
| 1550 |
+
"128193": {
|
| 1551 |
+
"content": "<|reserved_special_token_185|>",
|
| 1552 |
+
"lstrip": false,
|
| 1553 |
+
"normalized": false,
|
| 1554 |
+
"rstrip": false,
|
| 1555 |
+
"single_word": false,
|
| 1556 |
+
"special": true
|
| 1557 |
+
},
|
| 1558 |
+
"128194": {
|
| 1559 |
+
"content": "<|reserved_special_token_186|>",
|
| 1560 |
+
"lstrip": false,
|
| 1561 |
+
"normalized": false,
|
| 1562 |
+
"rstrip": false,
|
| 1563 |
+
"single_word": false,
|
| 1564 |
+
"special": true
|
| 1565 |
+
},
|
| 1566 |
+
"128195": {
|
| 1567 |
+
"content": "<|reserved_special_token_187|>",
|
| 1568 |
+
"lstrip": false,
|
| 1569 |
+
"normalized": false,
|
| 1570 |
+
"rstrip": false,
|
| 1571 |
+
"single_word": false,
|
| 1572 |
+
"special": true
|
| 1573 |
+
},
|
| 1574 |
+
"128196": {
|
| 1575 |
+
"content": "<|reserved_special_token_188|>",
|
| 1576 |
+
"lstrip": false,
|
| 1577 |
+
"normalized": false,
|
| 1578 |
+
"rstrip": false,
|
| 1579 |
+
"single_word": false,
|
| 1580 |
+
"special": true
|
| 1581 |
+
},
|
| 1582 |
+
"128197": {
|
| 1583 |
+
"content": "<|reserved_special_token_189|>",
|
| 1584 |
+
"lstrip": false,
|
| 1585 |
+
"normalized": false,
|
| 1586 |
+
"rstrip": false,
|
| 1587 |
+
"single_word": false,
|
| 1588 |
+
"special": true
|
| 1589 |
+
},
|
| 1590 |
+
"128198": {
|
| 1591 |
+
"content": "<|reserved_special_token_190|>",
|
| 1592 |
+
"lstrip": false,
|
| 1593 |
+
"normalized": false,
|
| 1594 |
+
"rstrip": false,
|
| 1595 |
+
"single_word": false,
|
| 1596 |
+
"special": true
|
| 1597 |
+
},
|
| 1598 |
+
"128199": {
|
| 1599 |
+
"content": "<|reserved_special_token_191|>",
|
| 1600 |
+
"lstrip": false,
|
| 1601 |
+
"normalized": false,
|
| 1602 |
+
"rstrip": false,
|
| 1603 |
+
"single_word": false,
|
| 1604 |
+
"special": true
|
| 1605 |
+
},
|
| 1606 |
+
"128200": {
|
| 1607 |
+
"content": "<|reserved_special_token_192|>",
|
| 1608 |
+
"lstrip": false,
|
| 1609 |
+
"normalized": false,
|
| 1610 |
+
"rstrip": false,
|
| 1611 |
+
"single_word": false,
|
| 1612 |
+
"special": true
|
| 1613 |
+
},
|
| 1614 |
+
"128201": {
|
| 1615 |
+
"content": "<|reserved_special_token_193|>",
|
| 1616 |
+
"lstrip": false,
|
| 1617 |
+
"normalized": false,
|
| 1618 |
+
"rstrip": false,
|
| 1619 |
+
"single_word": false,
|
| 1620 |
+
"special": true
|
| 1621 |
+
},
|
| 1622 |
+
"128202": {
|
| 1623 |
+
"content": "<|reserved_special_token_194|>",
|
| 1624 |
+
"lstrip": false,
|
| 1625 |
+
"normalized": false,
|
| 1626 |
+
"rstrip": false,
|
| 1627 |
+
"single_word": false,
|
| 1628 |
+
"special": true
|
| 1629 |
+
},
|
| 1630 |
+
"128203": {
|
| 1631 |
+
"content": "<|reserved_special_token_195|>",
|
| 1632 |
+
"lstrip": false,
|
| 1633 |
+
"normalized": false,
|
| 1634 |
+
"rstrip": false,
|
| 1635 |
+
"single_word": false,
|
| 1636 |
+
"special": true
|
| 1637 |
+
},
|
| 1638 |
+
"128204": {
|
| 1639 |
+
"content": "<|reserved_special_token_196|>",
|
| 1640 |
+
"lstrip": false,
|
| 1641 |
+
"normalized": false,
|
| 1642 |
+
"rstrip": false,
|
| 1643 |
+
"single_word": false,
|
| 1644 |
+
"special": true
|
| 1645 |
+
},
|
| 1646 |
+
"128205": {
|
| 1647 |
+
"content": "<|reserved_special_token_197|>",
|
| 1648 |
+
"lstrip": false,
|
| 1649 |
+
"normalized": false,
|
| 1650 |
+
"rstrip": false,
|
| 1651 |
+
"single_word": false,
|
| 1652 |
+
"special": true
|
| 1653 |
+
},
|
| 1654 |
+
"128206": {
|
| 1655 |
+
"content": "<|reserved_special_token_198|>",
|
| 1656 |
+
"lstrip": false,
|
| 1657 |
+
"normalized": false,
|
| 1658 |
+
"rstrip": false,
|
| 1659 |
+
"single_word": false,
|
| 1660 |
+
"special": true
|
| 1661 |
+
},
|
| 1662 |
+
"128207": {
|
| 1663 |
+
"content": "<|reserved_special_token_199|>",
|
| 1664 |
+
"lstrip": false,
|
| 1665 |
+
"normalized": false,
|
| 1666 |
+
"rstrip": false,
|
| 1667 |
+
"single_word": false,
|
| 1668 |
+
"special": true
|
| 1669 |
+
},
|
| 1670 |
+
"128208": {
|
| 1671 |
+
"content": "<|reserved_special_token_200|>",
|
| 1672 |
+
"lstrip": false,
|
| 1673 |
+
"normalized": false,
|
| 1674 |
+
"rstrip": false,
|
| 1675 |
+
"single_word": false,
|
| 1676 |
+
"special": true
|
| 1677 |
+
},
|
| 1678 |
+
"128209": {
|
| 1679 |
+
"content": "<|reserved_special_token_201|>",
|
| 1680 |
+
"lstrip": false,
|
| 1681 |
+
"normalized": false,
|
| 1682 |
+
"rstrip": false,
|
| 1683 |
+
"single_word": false,
|
| 1684 |
+
"special": true
|
| 1685 |
+
},
|
| 1686 |
+
"128210": {
|
| 1687 |
+
"content": "<|reserved_special_token_202|>",
|
| 1688 |
+
"lstrip": false,
|
| 1689 |
+
"normalized": false,
|
| 1690 |
+
"rstrip": false,
|
| 1691 |
+
"single_word": false,
|
| 1692 |
+
"special": true
|
| 1693 |
+
},
|
| 1694 |
+
"128211": {
|
| 1695 |
+
"content": "<|reserved_special_token_203|>",
|
| 1696 |
+
"lstrip": false,
|
| 1697 |
+
"normalized": false,
|
| 1698 |
+
"rstrip": false,
|
| 1699 |
+
"single_word": false,
|
| 1700 |
+
"special": true
|
| 1701 |
+
},
|
| 1702 |
+
"128212": {
|
| 1703 |
+
"content": "<|reserved_special_token_204|>",
|
| 1704 |
+
"lstrip": false,
|
| 1705 |
+
"normalized": false,
|
| 1706 |
+
"rstrip": false,
|
| 1707 |
+
"single_word": false,
|
| 1708 |
+
"special": true
|
| 1709 |
+
},
|
| 1710 |
+
"128213": {
|
| 1711 |
+
"content": "<|reserved_special_token_205|>",
|
| 1712 |
+
"lstrip": false,
|
| 1713 |
+
"normalized": false,
|
| 1714 |
+
"rstrip": false,
|
| 1715 |
+
"single_word": false,
|
| 1716 |
+
"special": true
|
| 1717 |
+
},
|
| 1718 |
+
"128214": {
|
| 1719 |
+
"content": "<|reserved_special_token_206|>",
|
| 1720 |
+
"lstrip": false,
|
| 1721 |
+
"normalized": false,
|
| 1722 |
+
"rstrip": false,
|
| 1723 |
+
"single_word": false,
|
| 1724 |
+
"special": true
|
| 1725 |
+
},
|
| 1726 |
+
"128215": {
|
| 1727 |
+
"content": "<|reserved_special_token_207|>",
|
| 1728 |
+
"lstrip": false,
|
| 1729 |
+
"normalized": false,
|
| 1730 |
+
"rstrip": false,
|
| 1731 |
+
"single_word": false,
|
| 1732 |
+
"special": true
|
| 1733 |
+
},
|
| 1734 |
+
"128216": {
|
| 1735 |
+
"content": "<|reserved_special_token_208|>",
|
| 1736 |
+
"lstrip": false,
|
| 1737 |
+
"normalized": false,
|
| 1738 |
+
"rstrip": false,
|
| 1739 |
+
"single_word": false,
|
| 1740 |
+
"special": true
|
| 1741 |
+
},
|
| 1742 |
+
"128217": {
|
| 1743 |
+
"content": "<|reserved_special_token_209|>",
|
| 1744 |
+
"lstrip": false,
|
| 1745 |
+
"normalized": false,
|
| 1746 |
+
"rstrip": false,
|
| 1747 |
+
"single_word": false,
|
| 1748 |
+
"special": true
|
| 1749 |
+
},
|
| 1750 |
+
"128218": {
|
| 1751 |
+
"content": "<|reserved_special_token_210|>",
|
| 1752 |
+
"lstrip": false,
|
| 1753 |
+
"normalized": false,
|
| 1754 |
+
"rstrip": false,
|
| 1755 |
+
"single_word": false,
|
| 1756 |
+
"special": true
|
| 1757 |
+
},
|
| 1758 |
+
"128219": {
|
| 1759 |
+
"content": "<|reserved_special_token_211|>",
|
| 1760 |
+
"lstrip": false,
|
| 1761 |
+
"normalized": false,
|
| 1762 |
+
"rstrip": false,
|
| 1763 |
+
"single_word": false,
|
| 1764 |
+
"special": true
|
| 1765 |
+
},
|
| 1766 |
+
"128220": {
|
| 1767 |
+
"content": "<|reserved_special_token_212|>",
|
| 1768 |
+
"lstrip": false,
|
| 1769 |
+
"normalized": false,
|
| 1770 |
+
"rstrip": false,
|
| 1771 |
+
"single_word": false,
|
| 1772 |
+
"special": true
|
| 1773 |
+
},
|
| 1774 |
+
"128221": {
|
| 1775 |
+
"content": "<|reserved_special_token_213|>",
|
| 1776 |
+
"lstrip": false,
|
| 1777 |
+
"normalized": false,
|
| 1778 |
+
"rstrip": false,
|
| 1779 |
+
"single_word": false,
|
| 1780 |
+
"special": true
|
| 1781 |
+
},
|
| 1782 |
+
"128222": {
|
| 1783 |
+
"content": "<|reserved_special_token_214|>",
|
| 1784 |
+
"lstrip": false,
|
| 1785 |
+
"normalized": false,
|
| 1786 |
+
"rstrip": false,
|
| 1787 |
+
"single_word": false,
|
| 1788 |
+
"special": true
|
| 1789 |
+
},
|
| 1790 |
+
"128223": {
|
| 1791 |
+
"content": "<|reserved_special_token_215|>",
|
| 1792 |
+
"lstrip": false,
|
| 1793 |
+
"normalized": false,
|
| 1794 |
+
"rstrip": false,
|
| 1795 |
+
"single_word": false,
|
| 1796 |
+
"special": true
|
| 1797 |
+
},
|
| 1798 |
+
"128224": {
|
| 1799 |
+
"content": "<|reserved_special_token_216|>",
|
| 1800 |
+
"lstrip": false,
|
| 1801 |
+
"normalized": false,
|
| 1802 |
+
"rstrip": false,
|
| 1803 |
+
"single_word": false,
|
| 1804 |
+
"special": true
|
| 1805 |
+
},
|
| 1806 |
+
"128225": {
|
| 1807 |
+
"content": "<|reserved_special_token_217|>",
|
| 1808 |
+
"lstrip": false,
|
| 1809 |
+
"normalized": false,
|
| 1810 |
+
"rstrip": false,
|
| 1811 |
+
"single_word": false,
|
| 1812 |
+
"special": true
|
| 1813 |
+
},
|
| 1814 |
+
"128226": {
|
| 1815 |
+
"content": "<|reserved_special_token_218|>",
|
| 1816 |
+
"lstrip": false,
|
| 1817 |
+
"normalized": false,
|
| 1818 |
+
"rstrip": false,
|
| 1819 |
+
"single_word": false,
|
| 1820 |
+
"special": true
|
| 1821 |
+
},
|
| 1822 |
+
"128227": {
|
| 1823 |
+
"content": "<|reserved_special_token_219|>",
|
| 1824 |
+
"lstrip": false,
|
| 1825 |
+
"normalized": false,
|
| 1826 |
+
"rstrip": false,
|
| 1827 |
+
"single_word": false,
|
| 1828 |
+
"special": true
|
| 1829 |
+
},
|
| 1830 |
+
"128228": {
|
| 1831 |
+
"content": "<|reserved_special_token_220|>",
|
| 1832 |
+
"lstrip": false,
|
| 1833 |
+
"normalized": false,
|
| 1834 |
+
"rstrip": false,
|
| 1835 |
+
"single_word": false,
|
| 1836 |
+
"special": true
|
| 1837 |
+
},
|
| 1838 |
+
"128229": {
|
| 1839 |
+
"content": "<|reserved_special_token_221|>",
|
| 1840 |
+
"lstrip": false,
|
| 1841 |
+
"normalized": false,
|
| 1842 |
+
"rstrip": false,
|
| 1843 |
+
"single_word": false,
|
| 1844 |
+
"special": true
|
| 1845 |
+
},
|
| 1846 |
+
"128230": {
|
| 1847 |
+
"content": "<|reserved_special_token_222|>",
|
| 1848 |
+
"lstrip": false,
|
| 1849 |
+
"normalized": false,
|
| 1850 |
+
"rstrip": false,
|
| 1851 |
+
"single_word": false,
|
| 1852 |
+
"special": true
|
| 1853 |
+
},
|
| 1854 |
+
"128231": {
|
| 1855 |
+
"content": "<|reserved_special_token_223|>",
|
| 1856 |
+
"lstrip": false,
|
| 1857 |
+
"normalized": false,
|
| 1858 |
+
"rstrip": false,
|
| 1859 |
+
"single_word": false,
|
| 1860 |
+
"special": true
|
| 1861 |
+
},
|
| 1862 |
+
"128232": {
|
| 1863 |
+
"content": "<|reserved_special_token_224|>",
|
| 1864 |
+
"lstrip": false,
|
| 1865 |
+
"normalized": false,
|
| 1866 |
+
"rstrip": false,
|
| 1867 |
+
"single_word": false,
|
| 1868 |
+
"special": true
|
| 1869 |
+
},
|
| 1870 |
+
"128233": {
|
| 1871 |
+
"content": "<|reserved_special_token_225|>",
|
| 1872 |
+
"lstrip": false,
|
| 1873 |
+
"normalized": false,
|
| 1874 |
+
"rstrip": false,
|
| 1875 |
+
"single_word": false,
|
| 1876 |
+
"special": true
|
| 1877 |
+
},
|
| 1878 |
+
"128234": {
|
| 1879 |
+
"content": "<|reserved_special_token_226|>",
|
| 1880 |
+
"lstrip": false,
|
| 1881 |
+
"normalized": false,
|
| 1882 |
+
"rstrip": false,
|
| 1883 |
+
"single_word": false,
|
| 1884 |
+
"special": true
|
| 1885 |
+
},
|
| 1886 |
+
"128235": {
|
| 1887 |
+
"content": "<|reserved_special_token_227|>",
|
| 1888 |
+
"lstrip": false,
|
| 1889 |
+
"normalized": false,
|
| 1890 |
+
"rstrip": false,
|
| 1891 |
+
"single_word": false,
|
| 1892 |
+
"special": true
|
| 1893 |
+
},
|
| 1894 |
+
"128236": {
|
| 1895 |
+
"content": "<|reserved_special_token_228|>",
|
| 1896 |
+
"lstrip": false,
|
| 1897 |
+
"normalized": false,
|
| 1898 |
+
"rstrip": false,
|
| 1899 |
+
"single_word": false,
|
| 1900 |
+
"special": true
|
| 1901 |
+
},
|
| 1902 |
+
"128237": {
|
| 1903 |
+
"content": "<|reserved_special_token_229|>",
|
| 1904 |
+
"lstrip": false,
|
| 1905 |
+
"normalized": false,
|
| 1906 |
+
"rstrip": false,
|
| 1907 |
+
"single_word": false,
|
| 1908 |
+
"special": true
|
| 1909 |
+
},
|
| 1910 |
+
"128238": {
|
| 1911 |
+
"content": "<|reserved_special_token_230|>",
|
| 1912 |
+
"lstrip": false,
|
| 1913 |
+
"normalized": false,
|
| 1914 |
+
"rstrip": false,
|
| 1915 |
+
"single_word": false,
|
| 1916 |
+
"special": true
|
| 1917 |
+
},
|
| 1918 |
+
"128239": {
|
| 1919 |
+
"content": "<|reserved_special_token_231|>",
|
| 1920 |
+
"lstrip": false,
|
| 1921 |
+
"normalized": false,
|
| 1922 |
+
"rstrip": false,
|
| 1923 |
+
"single_word": false,
|
| 1924 |
+
"special": true
|
| 1925 |
+
},
|
| 1926 |
+
"128240": {
|
| 1927 |
+
"content": "<|reserved_special_token_232|>",
|
| 1928 |
+
"lstrip": false,
|
| 1929 |
+
"normalized": false,
|
| 1930 |
+
"rstrip": false,
|
| 1931 |
+
"single_word": false,
|
| 1932 |
+
"special": true
|
| 1933 |
+
},
|
| 1934 |
+
"128241": {
|
| 1935 |
+
"content": "<|reserved_special_token_233|>",
|
| 1936 |
+
"lstrip": false,
|
| 1937 |
+
"normalized": false,
|
| 1938 |
+
"rstrip": false,
|
| 1939 |
+
"single_word": false,
|
| 1940 |
+
"special": true
|
| 1941 |
+
},
|
| 1942 |
+
"128242": {
|
| 1943 |
+
"content": "<|reserved_special_token_234|>",
|
| 1944 |
+
"lstrip": false,
|
| 1945 |
+
"normalized": false,
|
| 1946 |
+
"rstrip": false,
|
| 1947 |
+
"single_word": false,
|
| 1948 |
+
"special": true
|
| 1949 |
+
},
|
| 1950 |
+
"128243": {
|
| 1951 |
+
"content": "<|reserved_special_token_235|>",
|
| 1952 |
+
"lstrip": false,
|
| 1953 |
+
"normalized": false,
|
| 1954 |
+
"rstrip": false,
|
| 1955 |
+
"single_word": false,
|
| 1956 |
+
"special": true
|
| 1957 |
+
},
|
| 1958 |
+
"128244": {
|
| 1959 |
+
"content": "<|reserved_special_token_236|>",
|
| 1960 |
+
"lstrip": false,
|
| 1961 |
+
"normalized": false,
|
| 1962 |
+
"rstrip": false,
|
| 1963 |
+
"single_word": false,
|
| 1964 |
+
"special": true
|
| 1965 |
+
},
|
| 1966 |
+
"128245": {
|
| 1967 |
+
"content": "<|reserved_special_token_237|>",
|
| 1968 |
+
"lstrip": false,
|
| 1969 |
+
"normalized": false,
|
| 1970 |
+
"rstrip": false,
|
| 1971 |
+
"single_word": false,
|
| 1972 |
+
"special": true
|
| 1973 |
+
},
|
| 1974 |
+
"128246": {
|
| 1975 |
+
"content": "<|reserved_special_token_238|>",
|
| 1976 |
+
"lstrip": false,
|
| 1977 |
+
"normalized": false,
|
| 1978 |
+
"rstrip": false,
|
| 1979 |
+
"single_word": false,
|
| 1980 |
+
"special": true
|
| 1981 |
+
},
|
| 1982 |
+
"128247": {
|
| 1983 |
+
"content": "<|reserved_special_token_239|>",
|
| 1984 |
+
"lstrip": false,
|
| 1985 |
+
"normalized": false,
|
| 1986 |
+
"rstrip": false,
|
| 1987 |
+
"single_word": false,
|
| 1988 |
+
"special": true
|
| 1989 |
+
},
|
| 1990 |
+
"128248": {
|
| 1991 |
+
"content": "<|reserved_special_token_240|>",
|
| 1992 |
+
"lstrip": false,
|
| 1993 |
+
"normalized": false,
|
| 1994 |
+
"rstrip": false,
|
| 1995 |
+
"single_word": false,
|
| 1996 |
+
"special": true
|
| 1997 |
+
},
|
| 1998 |
+
"128249": {
|
| 1999 |
+
"content": "<|reserved_special_token_241|>",
|
| 2000 |
+
"lstrip": false,
|
| 2001 |
+
"normalized": false,
|
| 2002 |
+
"rstrip": false,
|
| 2003 |
+
"single_word": false,
|
| 2004 |
+
"special": true
|
| 2005 |
+
},
|
| 2006 |
+
"128250": {
|
| 2007 |
+
"content": "<|reserved_special_token_242|>",
|
| 2008 |
+
"lstrip": false,
|
| 2009 |
+
"normalized": false,
|
| 2010 |
+
"rstrip": false,
|
| 2011 |
+
"single_word": false,
|
| 2012 |
+
"special": true
|
| 2013 |
+
},
|
| 2014 |
+
"128251": {
|
| 2015 |
+
"content": "<|reserved_special_token_243|>",
|
| 2016 |
+
"lstrip": false,
|
| 2017 |
+
"normalized": false,
|
| 2018 |
+
"rstrip": false,
|
| 2019 |
+
"single_word": false,
|
| 2020 |
+
"special": true
|
| 2021 |
+
},
|
| 2022 |
+
"128252": {
|
| 2023 |
+
"content": "<|reserved_special_token_244|>",
|
| 2024 |
+
"lstrip": false,
|
| 2025 |
+
"normalized": false,
|
| 2026 |
+
"rstrip": false,
|
| 2027 |
+
"single_word": false,
|
| 2028 |
+
"special": true
|
| 2029 |
+
},
|
| 2030 |
+
"128253": {
|
| 2031 |
+
"content": "<|reserved_special_token_245|>",
|
| 2032 |
+
"lstrip": false,
|
| 2033 |
+
"normalized": false,
|
| 2034 |
+
"rstrip": false,
|
| 2035 |
+
"single_word": false,
|
| 2036 |
+
"special": true
|
| 2037 |
+
},
|
| 2038 |
+
"128254": {
|
| 2039 |
+
"content": "<|reserved_special_token_246|>",
|
| 2040 |
+
"lstrip": false,
|
| 2041 |
+
"normalized": false,
|
| 2042 |
+
"rstrip": false,
|
| 2043 |
+
"single_word": false,
|
| 2044 |
+
"special": true
|
| 2045 |
+
},
|
| 2046 |
+
"128255": {
|
| 2047 |
+
"content": "<|reserved_special_token_247|>",
|
| 2048 |
+
"lstrip": false,
|
| 2049 |
+
"normalized": false,
|
| 2050 |
+
"rstrip": false,
|
| 2051 |
+
"single_word": false,
|
| 2052 |
+
"special": true
|
| 2053 |
+
}
|
| 2054 |
+
},
|
| 2055 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
| 2056 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\\n'}}{% endif %}",
|
| 2057 |
+
"clean_up_tokenization_spaces": false,
|
| 2058 |
+
"eos_token": "<|end▁of▁sentence|>",
|
| 2059 |
+
"extra_special_tokens": {},
|
| 2060 |
+
"legacy": true,
|
| 2061 |
+
"model_max_length": 16384,
|
| 2062 |
+
"pad_token": "<|end▁of▁sentence|>",
|
| 2063 |
+
"sp_model_kwargs": {},
|
| 2064 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 2065 |
+
"unk_token": null,
|
| 2066 |
+
"use_default_system_prompt": false
|
| 2067 |
+
}
|
checkpoint-900/trainer_state.json
ADDED
|
@@ -0,0 +1,916 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 900,
|
| 3 |
+
"best_metric": 1.2505640983581543,
|
| 4 |
+
"best_model_checkpoint": "outputs/checkpoint-900",
|
| 5 |
+
"epoch": 0.730816077953715,
|
| 6 |
+
"eval_steps": 100,
|
| 7 |
+
"global_step": 900,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.008120178643930167,
|
| 14 |
+
"grad_norm": 0.9899182319641113,
|
| 15 |
+
"learning_rate": 1.5e-05,
|
| 16 |
+
"loss": 2.2243,
|
| 17 |
+
"mean_token_accuracy": 0.5150829579681158,
|
| 18 |
+
"num_tokens": 105884.0,
|
| 19 |
+
"step": 10
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"epoch": 0.016240357287860333,
|
| 23 |
+
"grad_norm": 0.9635991454124451,
|
| 24 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 25 |
+
"loss": 2.0245,
|
| 26 |
+
"mean_token_accuracy": 0.5415308997035027,
|
| 27 |
+
"num_tokens": 216549.0,
|
| 28 |
+
"step": 20
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.024360535931790498,
|
| 32 |
+
"grad_norm": 0.6212347745895386,
|
| 33 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 34 |
+
"loss": 1.664,
|
| 35 |
+
"mean_token_accuracy": 0.5978568278253078,
|
| 36 |
+
"num_tokens": 326591.0,
|
| 37 |
+
"step": 30
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.032480714575720666,
|
| 41 |
+
"grad_norm": 0.39353373646736145,
|
| 42 |
+
"learning_rate": 4.998938009679042e-05,
|
| 43 |
+
"loss": 1.4829,
|
| 44 |
+
"mean_token_accuracy": 0.6291711494326592,
|
| 45 |
+
"num_tokens": 438765.0,
|
| 46 |
+
"step": 40
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.04060089321965083,
|
| 50 |
+
"grad_norm": 0.3375701904296875,
|
| 51 |
+
"learning_rate": 4.9952680903753627e-05,
|
| 52 |
+
"loss": 1.4594,
|
| 53 |
+
"mean_token_accuracy": 0.6345414012670517,
|
| 54 |
+
"num_tokens": 551707.0,
|
| 55 |
+
"step": 50
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.048721071863580996,
|
| 59 |
+
"grad_norm": 0.34767618775367737,
|
| 60 |
+
"learning_rate": 4.98898097941902e-05,
|
| 61 |
+
"loss": 1.4302,
|
| 62 |
+
"mean_token_accuracy": 0.6381799459457398,
|
| 63 |
+
"num_tokens": 662676.0,
|
| 64 |
+
"step": 60
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.05684125050751117,
|
| 68 |
+
"grad_norm": 0.35675737261772156,
|
| 69 |
+
"learning_rate": 4.980083271121214e-05,
|
| 70 |
+
"loss": 1.3795,
|
| 71 |
+
"mean_token_accuracy": 0.6466716401278972,
|
| 72 |
+
"num_tokens": 771289.0,
|
| 73 |
+
"step": 70
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.06496142915144133,
|
| 77 |
+
"grad_norm": 0.37088656425476074,
|
| 78 |
+
"learning_rate": 4.968584297949255e-05,
|
| 79 |
+
"loss": 1.4072,
|
| 80 |
+
"mean_token_accuracy": 0.6428142428398133,
|
| 81 |
+
"num_tokens": 882535.0,
|
| 82 |
+
"step": 80
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.0730816077953715,
|
| 86 |
+
"grad_norm": 0.40535271167755127,
|
| 87 |
+
"learning_rate": 4.954496120738094e-05,
|
| 88 |
+
"loss": 1.3712,
|
| 89 |
+
"mean_token_accuracy": 0.6488012038171291,
|
| 90 |
+
"num_tokens": 991659.0,
|
| 91 |
+
"step": 90
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.08120178643930166,
|
| 95 |
+
"grad_norm": 0.39448976516723633,
|
| 96 |
+
"learning_rate": 4.9378335160401766e-05,
|
| 97 |
+
"loss": 1.3543,
|
| 98 |
+
"step": 100
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.08120178643930166,
|
| 102 |
+
"eval_loss": 1.3557080030441284,
|
| 103 |
+
"eval_mean_token_accuracy": 0.6499481635537707,
|
| 104 |
+
"eval_num_tokens": 1102149.0,
|
| 105 |
+
"eval_runtime": 211.2938,
|
| 106 |
+
"eval_samples_per_second": 9.328,
|
| 107 |
+
"eval_steps_per_second": 1.169,
|
| 108 |
+
"step": 100
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.08932196508323183,
|
| 112 |
+
"grad_norm": 0.40397903323173523,
|
| 113 |
+
"learning_rate": 4.918613960626873e-05,
|
| 114 |
+
"loss": 1.3691,
|
| 115 |
+
"mean_token_accuracy": 0.6495238792151212,
|
| 116 |
+
"num_tokens": 1210597.0,
|
| 117 |
+
"step": 110
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09744214372716199,
|
| 121 |
+
"grad_norm": 0.4039655327796936,
|
| 122 |
+
"learning_rate": 4.896857613157765e-05,
|
| 123 |
+
"loss": 1.3264,
|
| 124 |
+
"mean_token_accuracy": 0.6550758637487888,
|
| 125 |
+
"num_tokens": 1322196.0,
|
| 126 |
+
"step": 120
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.10556232237109216,
|
| 130 |
+
"grad_norm": 0.4150333106517792,
|
| 131 |
+
"learning_rate": 4.872587293036991e-05,
|
| 132 |
+
"loss": 1.337,
|
| 133 |
+
"mean_token_accuracy": 0.655381852388382,
|
| 134 |
+
"num_tokens": 1433808.0,
|
| 135 |
+
"step": 130
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.11368250101502234,
|
| 139 |
+
"grad_norm": 0.4298645555973053,
|
| 140 |
+
"learning_rate": 4.845828456478842e-05,
|
| 141 |
+
"loss": 1.3504,
|
| 142 |
+
"mean_token_accuracy": 0.6535526886582375,
|
| 143 |
+
"num_tokens": 1547479.0,
|
| 144 |
+
"step": 140
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.1218026796589525,
|
| 148 |
+
"grad_norm": 0.46692460775375366,
|
| 149 |
+
"learning_rate": 4.8166091698077164e-05,
|
| 150 |
+
"loss": 1.3517,
|
| 151 |
+
"mean_token_accuracy": 0.6504787422716618,
|
| 152 |
+
"num_tokens": 1661034.0,
|
| 153 |
+
"step": 150
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12992285830288267,
|
| 157 |
+
"grad_norm": 0.4362328052520752,
|
| 158 |
+
"learning_rate": 4.784960080020408e-05,
|
| 159 |
+
"loss": 1.3225,
|
| 160 |
+
"mean_token_accuracy": 0.6548900716006756,
|
| 161 |
+
"num_tokens": 1771511.0,
|
| 162 |
+
"step": 160
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.13804303694681283,
|
| 166 |
+
"grad_norm": 0.4326249361038208,
|
| 167 |
+
"learning_rate": 4.750914382641648e-05,
|
| 168 |
+
"loss": 1.3482,
|
| 169 |
+
"mean_token_accuracy": 0.6529437758028507,
|
| 170 |
+
"num_tokens": 1882929.0,
|
| 171 |
+
"step": 170
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.146163215590743,
|
| 175 |
+
"grad_norm": 0.4499496519565582,
|
| 176 |
+
"learning_rate": 4.714507786906581e-05,
|
| 177 |
+
"loss": 1.3546,
|
| 178 |
+
"mean_token_accuracy": 0.651630837470293,
|
| 179 |
+
"num_tokens": 1992465.0,
|
| 180 |
+
"step": 180
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.15428339423467316,
|
| 184 |
+
"grad_norm": 0.4416871666908264,
|
| 185 |
+
"learning_rate": 4.675778478306712e-05,
|
| 186 |
+
"loss": 1.3587,
|
| 187 |
+
"mean_token_accuracy": 0.6499045781791211,
|
| 188 |
+
"num_tokens": 2104073.0,
|
| 189 |
+
"step": 190
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.16240357287860333,
|
| 193 |
+
"grad_norm": 0.4490174353122711,
|
| 194 |
+
"learning_rate": 4.6347670785385884e-05,
|
| 195 |
+
"loss": 1.3257,
|
| 196 |
+
"step": 200
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.16240357287860333,
|
| 200 |
+
"eval_loss": 1.3144221305847168,
|
| 201 |
+
"eval_mean_token_accuracy": 0.6565933012769289,
|
| 202 |
+
"eval_num_tokens": 2215310.0,
|
| 203 |
+
"eval_runtime": 210.8432,
|
| 204 |
+
"eval_samples_per_second": 9.348,
|
| 205 |
+
"eval_steps_per_second": 1.171,
|
| 206 |
+
"step": 200
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.1705237515225335,
|
| 210 |
+
"grad_norm": 0.4184815585613251,
|
| 211 |
+
"learning_rate": 4.5915166028972624e-05,
|
| 212 |
+
"loss": 1.313,
|
| 213 |
+
"mean_token_accuracy": 0.6569435287266969,
|
| 214 |
+
"num_tokens": 2326949.0,
|
| 215 |
+
"step": 210
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.17864393016646365,
|
| 219 |
+
"grad_norm": 0.46081599593162537,
|
| 220 |
+
"learning_rate": 4.546072415159179e-05,
|
| 221 |
+
"loss": 1.3162,
|
| 222 |
+
"mean_token_accuracy": 0.658608315140009,
|
| 223 |
+
"num_tokens": 2440239.0,
|
| 224 |
+
"step": 220
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.18676410881039382,
|
| 228 |
+
"grad_norm": 0.4398249685764313,
|
| 229 |
+
"learning_rate": 4.49848218000184e-05,
|
| 230 |
+
"loss": 1.3042,
|
| 231 |
+
"mean_token_accuracy": 0.6597990304231643,
|
| 232 |
+
"num_tokens": 2549360.0,
|
| 233 |
+
"step": 230
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.19488428745432398,
|
| 237 |
+
"grad_norm": 0.46249088644981384,
|
| 238 |
+
"learning_rate": 4.448795813010142e-05,
|
| 239 |
+
"loss": 1.3134,
|
| 240 |
+
"mean_token_accuracy": 0.6584605030715466,
|
| 241 |
+
"num_tokens": 2660415.0,
|
| 242 |
+
"step": 240
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.20300446609825415,
|
| 246 |
+
"grad_norm": 0.440453439950943,
|
| 247 |
+
"learning_rate": 4.397065428321817e-05,
|
| 248 |
+
"loss": 1.3029,
|
| 249 |
+
"mean_token_accuracy": 0.660743386298418,
|
| 250 |
+
"num_tokens": 2773017.0,
|
| 251 |
+
"step": 250
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.21112464474218431,
|
| 255 |
+
"grad_norm": 0.44051623344421387,
|
| 256 |
+
"learning_rate": 4.343345283966901e-05,
|
| 257 |
+
"loss": 1.305,
|
| 258 |
+
"mean_token_accuracy": 0.6578053869307041,
|
| 259 |
+
"num_tokens": 2883117.0,
|
| 260 |
+
"step": 260
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.2192448233861145,
|
| 264 |
+
"grad_norm": 0.459414005279541,
|
| 265 |
+
"learning_rate": 4.287691724958551e-05,
|
| 266 |
+
"loss": 1.2878,
|
| 267 |
+
"mean_token_accuracy": 0.662683118134737,
|
| 268 |
+
"num_tokens": 2995555.0,
|
| 269 |
+
"step": 270
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.22736500203004467,
|
| 273 |
+
"grad_norm": 0.45349356532096863,
|
| 274 |
+
"learning_rate": 4.230163124194913e-05,
|
| 275 |
+
"loss": 1.315,
|
| 276 |
+
"mean_token_accuracy": 0.6587340161204338,
|
| 277 |
+
"num_tokens": 3105636.0,
|
| 278 |
+
"step": 280
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.23548518067397484,
|
| 282 |
+
"grad_norm": 0.4721125364303589,
|
| 283 |
+
"learning_rate": 4.170819821234001e-05,
|
| 284 |
+
"loss": 1.2847,
|
| 285 |
+
"mean_token_accuracy": 0.6631687037646771,
|
| 286 |
+
"num_tokens": 3214439.0,
|
| 287 |
+
"step": 290
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 0.243605359317905,
|
| 291 |
+
"grad_norm": 0.4492698013782501,
|
| 292 |
+
"learning_rate": 4.109724059005844e-05,
|
| 293 |
+
"loss": 1.2992,
|
| 294 |
+
"step": 300
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.243605359317905,
|
| 298 |
+
"eval_loss": 1.2922167778015137,
|
| 299 |
+
"eval_mean_token_accuracy": 0.6602695963160712,
|
| 300 |
+
"eval_num_tokens": 3327211.0,
|
| 301 |
+
"eval_runtime": 211.0034,
|
| 302 |
+
"eval_samples_per_second": 9.341,
|
| 303 |
+
"eval_steps_per_second": 1.171,
|
| 304 |
+
"step": 300
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.25172553796183517,
|
| 308 |
+
"grad_norm": 0.4624563753604889,
|
| 309 |
+
"learning_rate": 4.046939918528243e-05,
|
| 310 |
+
"loss": 1.2965,
|
| 311 |
+
"mean_token_accuracy": 0.6618376031517983,
|
| 312 |
+
"num_tokens": 3437825.0,
|
| 313 |
+
"step": 310
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 0.25984571660576533,
|
| 317 |
+
"grad_norm": 0.46572402119636536,
|
| 318 |
+
"learning_rate": 3.982533251694632e-05,
|
| 319 |
+
"loss": 1.3034,
|
| 320 |
+
"mean_token_accuracy": 0.659632931649685,
|
| 321 |
+
"num_tokens": 3549948.0,
|
| 322 |
+
"step": 320
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.2679658952496955,
|
| 326 |
+
"grad_norm": 0.4801682233810425,
|
| 327 |
+
"learning_rate": 3.916571612204537e-05,
|
| 328 |
+
"loss": 1.2945,
|
| 329 |
+
"mean_token_accuracy": 0.660579564422369,
|
| 330 |
+
"num_tokens": 3659967.0,
|
| 331 |
+
"step": 330
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.27608607389362566,
|
| 335 |
+
"grad_norm": 0.4685429036617279,
|
| 336 |
+
"learning_rate": 3.849124184709073e-05,
|
| 337 |
+
"loss": 1.2818,
|
| 338 |
+
"mean_token_accuracy": 0.662060933560133,
|
| 339 |
+
"num_tokens": 3769655.0,
|
| 340 |
+
"step": 340
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.2842062525375558,
|
| 344 |
+
"grad_norm": 0.489403635263443,
|
| 345 |
+
"learning_rate": 3.7802617122457975e-05,
|
| 346 |
+
"loss": 1.2767,
|
| 347 |
+
"mean_token_accuracy": 0.664181649684906,
|
| 348 |
+
"num_tokens": 3879329.0,
|
| 349 |
+
"step": 350
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 0.292326431181486,
|
| 353 |
+
"grad_norm": 0.46308156847953796,
|
| 354 |
+
"learning_rate": 3.7100564220390326e-05,
|
| 355 |
+
"loss": 1.2564,
|
| 356 |
+
"mean_token_accuracy": 0.6691928833723069,
|
| 357 |
+
"num_tokens": 3991691.0,
|
| 358 |
+
"step": 360
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.30044660982541616,
|
| 362 |
+
"grad_norm": 0.4625571668148041,
|
| 363 |
+
"learning_rate": 3.6385819497434876e-05,
|
| 364 |
+
"loss": 1.3133,
|
| 365 |
+
"mean_token_accuracy": 0.6571255922317505,
|
| 366 |
+
"num_tokens": 4102451.0,
|
| 367 |
+
"step": 370
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3085667884693463,
|
| 371 |
+
"grad_norm": 0.46258220076560974,
|
| 372 |
+
"learning_rate": 3.565913262210615e-05,
|
| 373 |
+
"loss": 1.3089,
|
| 374 |
+
"mean_token_accuracy": 0.6575767800211907,
|
| 375 |
+
"num_tokens": 4211111.0,
|
| 376 |
+
"step": 380
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.3166869671132765,
|
| 380 |
+
"grad_norm": 0.48985716700553894,
|
| 381 |
+
"learning_rate": 3.4921265788587435e-05,
|
| 382 |
+
"loss": 1.2662,
|
| 383 |
+
"mean_token_accuracy": 0.6672355219721794,
|
| 384 |
+
"num_tokens": 4322281.0,
|
| 385 |
+
"step": 390
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 0.32480714575720665,
|
| 389 |
+
"grad_norm": 0.4666249454021454,
|
| 390 |
+
"learning_rate": 3.417299291729431e-05,
|
| 391 |
+
"loss": 1.2745,
|
| 392 |
+
"step": 400
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.32480714575720665,
|
| 396 |
+
"eval_loss": 1.278223991394043,
|
| 397 |
+
"eval_mean_token_accuracy": 0.6623295654169461,
|
| 398 |
+
"eval_num_tokens": 4435130.0,
|
| 399 |
+
"eval_runtime": 210.9199,
|
| 400 |
+
"eval_samples_per_second": 9.345,
|
| 401 |
+
"eval_steps_per_second": 1.171,
|
| 402 |
+
"step": 400
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3329273244011368,
|
| 406 |
+
"grad_norm": 0.4835776686668396,
|
| 407 |
+
"learning_rate": 3.341509884313897e-05,
|
| 408 |
+
"loss": 1.3014,
|
| 409 |
+
"mean_token_accuracy": 0.6618138968944549,
|
| 410 |
+
"num_tokens": 4545678.0,
|
| 411 |
+
"step": 410
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.341047503045067,
|
| 415 |
+
"grad_norm": 0.4572070837020874,
|
| 416 |
+
"learning_rate": 3.264837849234685e-05,
|
| 417 |
+
"loss": 1.2974,
|
| 418 |
+
"mean_token_accuracy": 0.6597278229892254,
|
| 419 |
+
"num_tokens": 4657835.0,
|
| 420 |
+
"step": 420
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.34916768168899714,
|
| 424 |
+
"grad_norm": 0.465015709400177,
|
| 425 |
+
"learning_rate": 3.187363604868872e-05,
|
| 426 |
+
"loss": 1.2718,
|
| 427 |
+
"mean_token_accuracy": 0.6638790182769299,
|
| 428 |
+
"num_tokens": 4769188.0,
|
| 429 |
+
"step": 430
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3572878603329273,
|
| 433 |
+
"grad_norm": 0.4718572199344635,
|
| 434 |
+
"learning_rate": 3.109168411000299e-05,
|
| 435 |
+
"loss": 1.2907,
|
| 436 |
+
"mean_token_accuracy": 0.6597667798399925,
|
| 437 |
+
"num_tokens": 4879176.0,
|
| 438 |
+
"step": 440
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.3654080389768575,
|
| 442 |
+
"grad_norm": 0.47551625967025757,
|
| 443 |
+
"learning_rate": 3.03033428358928e-05,
|
| 444 |
+
"loss": 1.2868,
|
| 445 |
+
"mean_token_accuracy": 0.6611412994563579,
|
| 446 |
+
"num_tokens": 4990975.0,
|
| 447 |
+
"step": 450
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.37352821762078764,
|
| 451 |
+
"grad_norm": 0.5067311525344849,
|
| 452 |
+
"learning_rate": 2.9509439087491835e-05,
|
| 453 |
+
"loss": 1.3175,
|
| 454 |
+
"mean_token_accuracy": 0.6562842346727848,
|
| 455 |
+
"num_tokens": 5102530.0,
|
| 456 |
+
"step": 460
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.3816483962647178,
|
| 460 |
+
"grad_norm": 0.4770154654979706,
|
| 461 |
+
"learning_rate": 2.871080556020118e-05,
|
| 462 |
+
"loss": 1.308,
|
| 463 |
+
"mean_token_accuracy": 0.6601759247481823,
|
| 464 |
+
"num_tokens": 5215390.0,
|
| 465 |
+
"step": 470
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.38976857490864797,
|
| 469 |
+
"grad_norm": 0.48466214537620544,
|
| 470 |
+
"learning_rate": 2.7908279910306835e-05,
|
| 471 |
+
"loss": 1.2832,
|
| 472 |
+
"mean_token_accuracy": 0.6627671822905541,
|
| 473 |
+
"num_tokens": 5327706.0,
|
| 474 |
+
"step": 480
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.39788875355257813,
|
| 478 |
+
"grad_norm": 0.4844174385070801,
|
| 479 |
+
"learning_rate": 2.7102703876393944e-05,
|
| 480 |
+
"loss": 1.3071,
|
| 481 |
+
"mean_token_accuracy": 0.6576642289757728,
|
| 482 |
+
"num_tokens": 5436538.0,
|
| 483 |
+
"step": 490
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.4060089321965083,
|
| 487 |
+
"grad_norm": 0.5532021522521973,
|
| 488 |
+
"learning_rate": 2.629492239647926e-05,
|
| 489 |
+
"loss": 1.2879,
|
| 490 |
+
"step": 500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.4060089321965083,
|
| 494 |
+
"eval_loss": 1.267868995666504,
|
| 495 |
+
"eval_mean_token_accuracy": 0.6643349033618263,
|
| 496 |
+
"eval_num_tokens": 5548090.0,
|
| 497 |
+
"eval_runtime": 210.8479,
|
| 498 |
+
"eval_samples_per_second": 9.348,
|
| 499 |
+
"eval_steps_per_second": 1.171,
|
| 500 |
+
"step": 500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.41412911084043846,
|
| 504 |
+
"grad_norm": 0.5015835762023926,
|
| 505 |
+
"learning_rate": 2.5485782721787837e-05,
|
| 506 |
+
"loss": 1.2579,
|
| 507 |
+
"mean_token_accuracy": 0.6646677803248167,
|
| 508 |
+
"num_tokens": 5660582.0,
|
| 509 |
+
"step": 510
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.42224928948436863,
|
| 513 |
+
"grad_norm": 0.5119274854660034,
|
| 514 |
+
"learning_rate": 2.4676133528103497e-05,
|
| 515 |
+
"loss": 1.2906,
|
| 516 |
+
"mean_token_accuracy": 0.660096200555563,
|
| 517 |
+
"num_tokens": 5773353.0,
|
| 518 |
+
"step": 520
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.43036946812829885,
|
| 522 |
+
"grad_norm": 0.475361168384552,
|
| 523 |
+
"learning_rate": 2.3866824025625124e-05,
|
| 524 |
+
"loss": 1.2977,
|
| 525 |
+
"mean_token_accuracy": 0.6588940002024174,
|
| 526 |
+
"num_tokens": 5887792.0,
|
| 527 |
+
"step": 530
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.438489646772229,
|
| 531 |
+
"grad_norm": 0.5254585146903992,
|
| 532 |
+
"learning_rate": 2.305870306826242e-05,
|
| 533 |
+
"loss": 1.2603,
|
| 534 |
+
"mean_token_accuracy": 0.6667217813432217,
|
| 535 |
+
"num_tokens": 5997605.0,
|
| 536 |
+
"step": 540
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.4466098254161592,
|
| 540 |
+
"grad_norm": 0.5108360052108765,
|
| 541 |
+
"learning_rate": 2.225261826330543e-05,
|
| 542 |
+
"loss": 1.291,
|
| 543 |
+
"mean_token_accuracy": 0.6622078493237495,
|
| 544 |
+
"num_tokens": 6108366.0,
|
| 545 |
+
"step": 550
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.45473000406008934,
|
| 549 |
+
"grad_norm": 0.5151691436767578,
|
| 550 |
+
"learning_rate": 2.1449415082401455e-05,
|
| 551 |
+
"loss": 1.2834,
|
| 552 |
+
"mean_token_accuracy": 0.663181109726429,
|
| 553 |
+
"num_tokens": 6218027.0,
|
| 554 |
+
"step": 560
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.4628501827040195,
|
| 558 |
+
"grad_norm": 0.4874868094921112,
|
| 559 |
+
"learning_rate": 2.0649935974772105e-05,
|
| 560 |
+
"loss": 1.297,
|
| 561 |
+
"mean_token_accuracy": 0.6599866427481175,
|
| 562 |
+
"num_tokens": 6330662.0,
|
| 563 |
+
"step": 570
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.4709703613479497,
|
| 567 |
+
"grad_norm": 0.5027274489402771,
|
| 568 |
+
"learning_rate": 1.985501948360041e-05,
|
| 569 |
+
"loss": 1.272,
|
| 570 |
+
"mean_token_accuracy": 0.6621859490871429,
|
| 571 |
+
"num_tokens": 6440999.0,
|
| 572 |
+
"step": 580
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 0.47909053999187984,
|
| 576 |
+
"grad_norm": 0.4950280785560608,
|
| 577 |
+
"learning_rate": 1.9065499366514757e-05,
|
| 578 |
+
"loss": 1.2779,
|
| 579 |
+
"mean_token_accuracy": 0.6634722009301186,
|
| 580 |
+
"num_tokens": 6553048.0,
|
| 581 |
+
"step": 590
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.48721071863581,
|
| 585 |
+
"grad_norm": 0.512377142906189,
|
| 586 |
+
"learning_rate": 1.828220372109232e-05,
|
| 587 |
+
"loss": 1.2728,
|
| 588 |
+
"step": 600
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 0.48721071863581,
|
| 592 |
+
"eval_loss": 1.260668396949768,
|
| 593 |
+
"eval_mean_token_accuracy": 0.6655809046768466,
|
| 594 |
+
"eval_num_tokens": 6664275.0,
|
| 595 |
+
"eval_runtime": 210.7964,
|
| 596 |
+
"eval_samples_per_second": 9.35,
|
| 597 |
+
"eval_steps_per_second": 1.172,
|
| 598 |
+
"step": 600
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.49533089727974017,
|
| 602 |
+
"grad_norm": 0.5057377219200134,
|
| 603 |
+
"learning_rate": 1.7505954116299063e-05,
|
| 604 |
+
"loss": 1.2752,
|
| 605 |
+
"mean_token_accuracy": 0.6648487631231547,
|
| 606 |
+
"num_tokens": 6775546.0,
|
| 607 |
+
"step": 610
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 0.5034510759236703,
|
| 611 |
+
"grad_norm": 0.5137090682983398,
|
| 612 |
+
"learning_rate": 1.6737564730777284e-05,
|
| 613 |
+
"loss": 1.2986,
|
| 614 |
+
"mean_token_accuracy": 0.6603142991662025,
|
| 615 |
+
"num_tokens": 6889845.0,
|
| 616 |
+
"step": 620
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.5115712545676004,
|
| 620 |
+
"grad_norm": 0.5096326470375061,
|
| 621 |
+
"learning_rate": 1.5977841498884723e-05,
|
| 622 |
+
"loss": 1.2546,
|
| 623 |
+
"mean_token_accuracy": 0.6686703085899353,
|
| 624 |
+
"num_tokens": 7000714.0,
|
| 625 |
+
"step": 630
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5196914332115307,
|
| 629 |
+
"grad_norm": 0.5050039291381836,
|
| 630 |
+
"learning_rate": 1.5227581265380685e-05,
|
| 631 |
+
"loss": 1.2688,
|
| 632 |
+
"mean_token_accuracy": 0.6652263507246972,
|
| 633 |
+
"num_tokens": 7109313.0,
|
| 634 |
+
"step": 640
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.5278116118554608,
|
| 638 |
+
"grad_norm": 0.49248260259628296,
|
| 639 |
+
"learning_rate": 1.4487570949645888e-05,
|
| 640 |
+
"loss": 1.2949,
|
| 641 |
+
"mean_token_accuracy": 0.6615142770111561,
|
| 642 |
+
"num_tokens": 7219816.0,
|
| 643 |
+
"step": 650
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.535931790499391,
|
| 647 |
+
"grad_norm": 0.49449214339256287,
|
| 648 |
+
"learning_rate": 1.375858672031276e-05,
|
| 649 |
+
"loss": 1.2692,
|
| 650 |
+
"mean_token_accuracy": 0.6655298680067062,
|
| 651 |
+
"num_tokens": 7331697.0,
|
| 652 |
+
"step": 660
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 0.5440519691433211,
|
| 656 |
+
"grad_norm": 0.5017920732498169,
|
| 657 |
+
"learning_rate": 1.3041393181171688e-05,
|
| 658 |
+
"loss": 1.2766,
|
| 659 |
+
"mean_token_accuracy": 0.6650374494493008,
|
| 660 |
+
"num_tokens": 7440661.0,
|
| 661 |
+
"step": 670
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.5521721477872513,
|
| 665 |
+
"grad_norm": 0.5125038027763367,
|
| 666 |
+
"learning_rate": 1.2336742569207235e-05,
|
| 667 |
+
"loss": 1.285,
|
| 668 |
+
"mean_token_accuracy": 0.6637549869716167,
|
| 669 |
+
"num_tokens": 7550919.0,
|
| 670 |
+
"step": 680
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.5602923264311814,
|
| 674 |
+
"grad_norm": 0.5125107765197754,
|
| 675 |
+
"learning_rate": 1.1645373965605425e-05,
|
| 676 |
+
"loss": 1.2618,
|
| 677 |
+
"mean_token_accuracy": 0.665469516068697,
|
| 678 |
+
"num_tokens": 7661194.0,
|
| 679 |
+
"step": 690
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"epoch": 0.5684125050751117,
|
| 683 |
+
"grad_norm": 0.5296525955200195,
|
| 684 |
+
"learning_rate": 1.0968012520559634e-05,
|
| 685 |
+
"loss": 1.258,
|
| 686 |
+
"step": 700
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.5684125050751117,
|
| 690 |
+
"eval_loss": 1.2551279067993164,
|
| 691 |
+
"eval_mean_token_accuracy": 0.6664607558655835,
|
| 692 |
+
"eval_num_tokens": 7772730.0,
|
| 693 |
+
"eval_runtime": 210.9447,
|
| 694 |
+
"eval_samples_per_second": 9.344,
|
| 695 |
+
"eval_steps_per_second": 1.171,
|
| 696 |
+
"step": 700
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.5765326837190419,
|
| 700 |
+
"grad_norm": 0.5269732475280762,
|
| 701 |
+
"learning_rate": 1.0305368692688174e-05,
|
| 702 |
+
"loss": 1.2393,
|
| 703 |
+
"mean_token_accuracy": 0.6693665731698275,
|
| 704 |
+
"num_tokens": 7880412.0,
|
| 705 |
+
"step": 710
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.584652862362972,
|
| 709 |
+
"grad_norm": 0.4768012464046478,
|
| 710 |
+
"learning_rate": 9.658137503861314e-06,
|
| 711 |
+
"loss": 1.2542,
|
| 712 |
+
"mean_token_accuracy": 0.6695502042770386,
|
| 713 |
+
"num_tokens": 7990995.0,
|
| 714 |
+
"step": 720
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.5927730410069022,
|
| 718 |
+
"grad_norm": 0.5196062326431274,
|
| 719 |
+
"learning_rate": 9.026997810219312e-06,
|
| 720 |
+
"loss": 1.2653,
|
| 721 |
+
"mean_token_accuracy": 0.6653387762606144,
|
| 722 |
+
"num_tokens": 8105125.0,
|
| 723 |
+
"step": 730
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.6008932196508323,
|
| 727 |
+
"grad_norm": 0.5181891918182373,
|
| 728 |
+
"learning_rate": 8.412611590146069e-06,
|
| 729 |
+
"loss": 1.2563,
|
| 730 |
+
"mean_token_accuracy": 0.6682513557374478,
|
| 731 |
+
"num_tokens": 8216386.0,
|
| 732 |
+
"step": 740
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.6090133982947625,
|
| 736 |
+
"grad_norm": 0.5035992860794067,
|
| 737 |
+
"learning_rate": 7.815623249945214e-06,
|
| 738 |
+
"loss": 1.274,
|
| 739 |
+
"mean_token_accuracy": 0.6650313429534436,
|
| 740 |
+
"num_tokens": 8328588.0,
|
| 741 |
+
"step": 750
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.6171335769386926,
|
| 745 |
+
"grad_norm": 0.5094414949417114,
|
| 746 |
+
"learning_rate": 7.236658947946886e-06,
|
| 747 |
+
"loss": 1.2657,
|
| 748 |
+
"mean_token_accuracy": 0.6652336426079273,
|
| 749 |
+
"num_tokens": 8440775.0,
|
| 750 |
+
"step": 760
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.6252537555826229,
|
| 754 |
+
"grad_norm": 0.5002747178077698,
|
| 755 |
+
"learning_rate": 6.676325937754102e-06,
|
| 756 |
+
"loss": 1.2878,
|
| 757 |
+
"mean_token_accuracy": 0.6618476249277592,
|
| 758 |
+
"num_tokens": 8550952.0,
|
| 759 |
+
"step": 770
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.633373934226553,
|
| 763 |
+
"grad_norm": 0.5225718021392822,
|
| 764 |
+
"learning_rate": 6.1352119313175945e-06,
|
| 765 |
+
"loss": 1.2509,
|
| 766 |
+
"mean_token_accuracy": 0.6678596146404743,
|
| 767 |
+
"num_tokens": 8660972.0,
|
| 768 |
+
"step": 780
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.6414941128704832,
|
| 772 |
+
"grad_norm": 0.5244067311286926,
|
| 773 |
+
"learning_rate": 5.613884482507123e-06,
|
| 774 |
+
"loss": 1.2952,
|
| 775 |
+
"mean_token_accuracy": 0.6590089030563832,
|
| 776 |
+
"num_tokens": 8774781.0,
|
| 777 |
+
"step": 790
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.6496142915144133,
|
| 781 |
+
"grad_norm": 0.49261534214019775,
|
| 782 |
+
"learning_rate": 5.112890391825845e-06,
|
| 783 |
+
"loss": 1.295,
|
| 784 |
+
"step": 800
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 0.6496142915144133,
|
| 788 |
+
"eval_loss": 1.252158284187317,
|
| 789 |
+
"eval_mean_token_accuracy": 0.6671061894671637,
|
| 790 |
+
"eval_num_tokens": 8887925.0,
|
| 791 |
+
"eval_runtime": 210.8674,
|
| 792 |
+
"eval_samples_per_second": 9.347,
|
| 793 |
+
"eval_steps_per_second": 1.171,
|
| 794 |
+
"step": 800
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.6577344701583435,
|
| 798 |
+
"grad_norm": 0.5334400534629822,
|
| 799 |
+
"learning_rate": 4.6327551328920945e-06,
|
| 800 |
+
"loss": 1.2638,
|
| 801 |
+
"mean_token_accuracy": 0.6633151285350323,
|
| 802 |
+
"num_tokens": 8997875.0,
|
| 803 |
+
"step": 810
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.6658546488022736,
|
| 807 |
+
"grad_norm": 0.5012565851211548,
|
| 808 |
+
"learning_rate": 4.173982301290122e-06,
|
| 809 |
+
"loss": 1.2781,
|
| 810 |
+
"mean_token_accuracy": 0.664675948023796,
|
| 811 |
+
"num_tokens": 9109180.0,
|
| 812 |
+
"step": 820
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 0.6739748274462039,
|
| 816 |
+
"grad_norm": 0.48581662774086,
|
| 817 |
+
"learning_rate": 3.737053086367873e-06,
|
| 818 |
+
"loss": 1.2822,
|
| 819 |
+
"mean_token_accuracy": 0.661733690649271,
|
| 820 |
+
"num_tokens": 9219274.0,
|
| 821 |
+
"step": 830
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.682095006090134,
|
| 825 |
+
"grad_norm": 0.5309010148048401,
|
| 826 |
+
"learning_rate": 3.322425766535778e-06,
|
| 827 |
+
"loss": 1.2587,
|
| 828 |
+
"mean_token_accuracy": 0.6681077688932419,
|
| 829 |
+
"num_tokens": 9329034.0,
|
| 830 |
+
"step": 840
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.6902151847340642,
|
| 834 |
+
"grad_norm": 0.5242215394973755,
|
| 835 |
+
"learning_rate": 2.93053522859604e-06,
|
| 836 |
+
"loss": 1.2752,
|
| 837 |
+
"mean_token_accuracy": 0.6624010242521763,
|
| 838 |
+
"num_tokens": 9442125.0,
|
| 839 |
+
"step": 850
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.6983353633779943,
|
| 843 |
+
"grad_norm": 0.5269120931625366,
|
| 844 |
+
"learning_rate": 2.5617925116063924e-06,
|
| 845 |
+
"loss": 1.2709,
|
| 846 |
+
"mean_token_accuracy": 0.6645623348653317,
|
| 847 |
+
"num_tokens": 9552075.0,
|
| 848 |
+
"step": 860
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.7064555420219245,
|
| 852 |
+
"grad_norm": 0.4972967207431793,
|
| 853 |
+
"learning_rate": 2.2165843757568805e-06,
|
| 854 |
+
"loss": 1.2963,
|
| 855 |
+
"mean_token_accuracy": 0.6616993740200996,
|
| 856 |
+
"num_tokens": 9660415.0,
|
| 857 |
+
"step": 870
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.7145757206658546,
|
| 861 |
+
"grad_norm": 0.5121223330497742,
|
| 862 |
+
"learning_rate": 1.8952728967118804e-06,
|
| 863 |
+
"loss": 1.2545,
|
| 864 |
+
"mean_token_accuracy": 0.66772101521492,
|
| 865 |
+
"num_tokens": 9768900.0,
|
| 866 |
+
"step": 880
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.7226958993097848,
|
| 870 |
+
"grad_norm": 0.49714845418930054,
|
| 871 |
+
"learning_rate": 1.5981950858426714e-06,
|
| 872 |
+
"loss": 1.2545,
|
| 873 |
+
"mean_token_accuracy": 0.6676135674118996,
|
| 874 |
+
"num_tokens": 9881161.0,
|
| 875 |
+
"step": 890
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 0.730816077953715,
|
| 879 |
+
"grad_norm": 0.49181970953941345,
|
| 880 |
+
"learning_rate": 1.32566253674907e-06,
|
| 881 |
+
"loss": 1.2582,
|
| 882 |
+
"step": 900
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.730816077953715,
|
| 886 |
+
"eval_loss": 1.2505640983581543,
|
| 887 |
+
"eval_mean_token_accuracy": 0.6674990793954023,
|
| 888 |
+
"eval_num_tokens": 9994374.0,
|
| 889 |
+
"eval_runtime": 210.8211,
|
| 890 |
+
"eval_samples_per_second": 9.349,
|
| 891 |
+
"eval_steps_per_second": 1.172,
|
| 892 |
+
"step": 900
|
| 893 |
+
}
|
| 894 |
+
],
|
| 895 |
+
"logging_steps": 10,
|
| 896 |
+
"max_steps": 1000,
|
| 897 |
+
"num_input_tokens_seen": 0,
|
| 898 |
+
"num_train_epochs": 1,
|
| 899 |
+
"save_steps": 100,
|
| 900 |
+
"stateful_callbacks": {
|
| 901 |
+
"TrainerControl": {
|
| 902 |
+
"args": {
|
| 903 |
+
"should_epoch_stop": false,
|
| 904 |
+
"should_evaluate": false,
|
| 905 |
+
"should_log": false,
|
| 906 |
+
"should_save": true,
|
| 907 |
+
"should_training_stop": false
|
| 908 |
+
},
|
| 909 |
+
"attributes": {}
|
| 910 |
+
}
|
| 911 |
+
},
|
| 912 |
+
"total_flos": 5.004779584391086e+17,
|
| 913 |
+
"train_batch_size": 2,
|
| 914 |
+
"trial_name": null,
|
| 915 |
+
"trial_params": null
|
| 916 |
+
}
|
checkpoint-900/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f39f026f60bf035a5ea79c75e978e7686347690f8cfd3306b305924fecaee5a
|
| 3 |
+
size 6033
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|begin▁of▁sentence|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|end▁of▁sentence|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|end▁of▁sentence|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d91915040cfac999d8c55f4b5bc6e67367c065e3a7a4e4b9438ce1f256addd86
|
| 3 |
+
size 17209530
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2067 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"128000": {
|
| 7 |
+
"content": "<|begin▁of▁sentence|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"128001": {
|
| 15 |
+
"content": "<|end▁of▁sentence|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"128002": {
|
| 23 |
+
"content": "<|reserved_special_token_0|>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"128003": {
|
| 31 |
+
"content": "<|reserved_special_token_1|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
"128004": {
|
| 39 |
+
"content": "<|finetune_right_pad_id|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": true
|
| 45 |
+
},
|
| 46 |
+
"128005": {
|
| 47 |
+
"content": "<|reserved_special_token_2|>",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": false,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": true
|
| 53 |
+
},
|
| 54 |
+
"128006": {
|
| 55 |
+
"content": "<|start_header_id|>",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": true
|
| 61 |
+
},
|
| 62 |
+
"128007": {
|
| 63 |
+
"content": "<|end_header_id|>",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": false,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": true
|
| 69 |
+
},
|
| 70 |
+
"128008": {
|
| 71 |
+
"content": "<|eom_id|>",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
"128009": {
|
| 79 |
+
"content": "<|eot_id|>",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": false,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": true
|
| 85 |
+
},
|
| 86 |
+
"128010": {
|
| 87 |
+
"content": "<|python_tag|>",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": false,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": true
|
| 93 |
+
},
|
| 94 |
+
"128011": {
|
| 95 |
+
"content": "<|User|>",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": false,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"128012": {
|
| 103 |
+
"content": "<|Assistant|>",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": false,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"128013": {
|
| 111 |
+
"content": "<think>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": false,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"128014": {
|
| 119 |
+
"content": "</think>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"128015": {
|
| 127 |
+
"content": "<|▁pad▁|>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": true
|
| 133 |
+
},
|
| 134 |
+
"128016": {
|
| 135 |
+
"content": "<|reserved_special_token_8|>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": false,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": true
|
| 141 |
+
},
|
| 142 |
+
"128017": {
|
| 143 |
+
"content": "<|reserved_special_token_9|>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
"128018": {
|
| 151 |
+
"content": "<|reserved_special_token_10|>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": false,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": true
|
| 157 |
+
},
|
| 158 |
+
"128019": {
|
| 159 |
+
"content": "<|reserved_special_token_11|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": false,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": true
|
| 165 |
+
},
|
| 166 |
+
"128020": {
|
| 167 |
+
"content": "<|reserved_special_token_12|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": false,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": true
|
| 173 |
+
},
|
| 174 |
+
"128021": {
|
| 175 |
+
"content": "<|reserved_special_token_13|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": false,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
},
|
| 182 |
+
"128022": {
|
| 183 |
+
"content": "<|reserved_special_token_14|>",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": false,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": true
|
| 189 |
+
},
|
| 190 |
+
"128023": {
|
| 191 |
+
"content": "<|reserved_special_token_15|>",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": false,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": true
|
| 197 |
+
},
|
| 198 |
+
"128024": {
|
| 199 |
+
"content": "<|reserved_special_token_16|>",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": true
|
| 205 |
+
},
|
| 206 |
+
"128025": {
|
| 207 |
+
"content": "<|reserved_special_token_17|>",
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"normalized": false,
|
| 210 |
+
"rstrip": false,
|
| 211 |
+
"single_word": false,
|
| 212 |
+
"special": true
|
| 213 |
+
},
|
| 214 |
+
"128026": {
|
| 215 |
+
"content": "<|reserved_special_token_18|>",
|
| 216 |
+
"lstrip": false,
|
| 217 |
+
"normalized": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"single_word": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
"128027": {
|
| 223 |
+
"content": "<|reserved_special_token_19|>",
|
| 224 |
+
"lstrip": false,
|
| 225 |
+
"normalized": false,
|
| 226 |
+
"rstrip": false,
|
| 227 |
+
"single_word": false,
|
| 228 |
+
"special": true
|
| 229 |
+
},
|
| 230 |
+
"128028": {
|
| 231 |
+
"content": "<|reserved_special_token_20|>",
|
| 232 |
+
"lstrip": false,
|
| 233 |
+
"normalized": false,
|
| 234 |
+
"rstrip": false,
|
| 235 |
+
"single_word": false,
|
| 236 |
+
"special": true
|
| 237 |
+
},
|
| 238 |
+
"128029": {
|
| 239 |
+
"content": "<|reserved_special_token_21|>",
|
| 240 |
+
"lstrip": false,
|
| 241 |
+
"normalized": false,
|
| 242 |
+
"rstrip": false,
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"special": true
|
| 245 |
+
},
|
| 246 |
+
"128030": {
|
| 247 |
+
"content": "<|reserved_special_token_22|>",
|
| 248 |
+
"lstrip": false,
|
| 249 |
+
"normalized": false,
|
| 250 |
+
"rstrip": false,
|
| 251 |
+
"single_word": false,
|
| 252 |
+
"special": true
|
| 253 |
+
},
|
| 254 |
+
"128031": {
|
| 255 |
+
"content": "<|reserved_special_token_23|>",
|
| 256 |
+
"lstrip": false,
|
| 257 |
+
"normalized": false,
|
| 258 |
+
"rstrip": false,
|
| 259 |
+
"single_word": false,
|
| 260 |
+
"special": true
|
| 261 |
+
},
|
| 262 |
+
"128032": {
|
| 263 |
+
"content": "<|reserved_special_token_24|>",
|
| 264 |
+
"lstrip": false,
|
| 265 |
+
"normalized": false,
|
| 266 |
+
"rstrip": false,
|
| 267 |
+
"single_word": false,
|
| 268 |
+
"special": true
|
| 269 |
+
},
|
| 270 |
+
"128033": {
|
| 271 |
+
"content": "<|reserved_special_token_25|>",
|
| 272 |
+
"lstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"rstrip": false,
|
| 275 |
+
"single_word": false,
|
| 276 |
+
"special": true
|
| 277 |
+
},
|
| 278 |
+
"128034": {
|
| 279 |
+
"content": "<|reserved_special_token_26|>",
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"normalized": false,
|
| 282 |
+
"rstrip": false,
|
| 283 |
+
"single_word": false,
|
| 284 |
+
"special": true
|
| 285 |
+
},
|
| 286 |
+
"128035": {
|
| 287 |
+
"content": "<|reserved_special_token_27|>",
|
| 288 |
+
"lstrip": false,
|
| 289 |
+
"normalized": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"single_word": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
"128036": {
|
| 295 |
+
"content": "<|reserved_special_token_28|>",
|
| 296 |
+
"lstrip": false,
|
| 297 |
+
"normalized": false,
|
| 298 |
+
"rstrip": false,
|
| 299 |
+
"single_word": false,
|
| 300 |
+
"special": true
|
| 301 |
+
},
|
| 302 |
+
"128037": {
|
| 303 |
+
"content": "<|reserved_special_token_29|>",
|
| 304 |
+
"lstrip": false,
|
| 305 |
+
"normalized": false,
|
| 306 |
+
"rstrip": false,
|
| 307 |
+
"single_word": false,
|
| 308 |
+
"special": true
|
| 309 |
+
},
|
| 310 |
+
"128038": {
|
| 311 |
+
"content": "<|reserved_special_token_30|>",
|
| 312 |
+
"lstrip": false,
|
| 313 |
+
"normalized": false,
|
| 314 |
+
"rstrip": false,
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"special": true
|
| 317 |
+
},
|
| 318 |
+
"128039": {
|
| 319 |
+
"content": "<|reserved_special_token_31|>",
|
| 320 |
+
"lstrip": false,
|
| 321 |
+
"normalized": false,
|
| 322 |
+
"rstrip": false,
|
| 323 |
+
"single_word": false,
|
| 324 |
+
"special": true
|
| 325 |
+
},
|
| 326 |
+
"128040": {
|
| 327 |
+
"content": "<|reserved_special_token_32|>",
|
| 328 |
+
"lstrip": false,
|
| 329 |
+
"normalized": false,
|
| 330 |
+
"rstrip": false,
|
| 331 |
+
"single_word": false,
|
| 332 |
+
"special": true
|
| 333 |
+
},
|
| 334 |
+
"128041": {
|
| 335 |
+
"content": "<|reserved_special_token_33|>",
|
| 336 |
+
"lstrip": false,
|
| 337 |
+
"normalized": false,
|
| 338 |
+
"rstrip": false,
|
| 339 |
+
"single_word": false,
|
| 340 |
+
"special": true
|
| 341 |
+
},
|
| 342 |
+
"128042": {
|
| 343 |
+
"content": "<|reserved_special_token_34|>",
|
| 344 |
+
"lstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"rstrip": false,
|
| 347 |
+
"single_word": false,
|
| 348 |
+
"special": true
|
| 349 |
+
},
|
| 350 |
+
"128043": {
|
| 351 |
+
"content": "<|reserved_special_token_35|>",
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"normalized": false,
|
| 354 |
+
"rstrip": false,
|
| 355 |
+
"single_word": false,
|
| 356 |
+
"special": true
|
| 357 |
+
},
|
| 358 |
+
"128044": {
|
| 359 |
+
"content": "<|reserved_special_token_36|>",
|
| 360 |
+
"lstrip": false,
|
| 361 |
+
"normalized": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"single_word": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
"128045": {
|
| 367 |
+
"content": "<|reserved_special_token_37|>",
|
| 368 |
+
"lstrip": false,
|
| 369 |
+
"normalized": false,
|
| 370 |
+
"rstrip": false,
|
| 371 |
+
"single_word": false,
|
| 372 |
+
"special": true
|
| 373 |
+
},
|
| 374 |
+
"128046": {
|
| 375 |
+
"content": "<|reserved_special_token_38|>",
|
| 376 |
+
"lstrip": false,
|
| 377 |
+
"normalized": false,
|
| 378 |
+
"rstrip": false,
|
| 379 |
+
"single_word": false,
|
| 380 |
+
"special": true
|
| 381 |
+
},
|
| 382 |
+
"128047": {
|
| 383 |
+
"content": "<|reserved_special_token_39|>",
|
| 384 |
+
"lstrip": false,
|
| 385 |
+
"normalized": false,
|
| 386 |
+
"rstrip": false,
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"special": true
|
| 389 |
+
},
|
| 390 |
+
"128048": {
|
| 391 |
+
"content": "<|reserved_special_token_40|>",
|
| 392 |
+
"lstrip": false,
|
| 393 |
+
"normalized": false,
|
| 394 |
+
"rstrip": false,
|
| 395 |
+
"single_word": false,
|
| 396 |
+
"special": true
|
| 397 |
+
},
|
| 398 |
+
"128049": {
|
| 399 |
+
"content": "<|reserved_special_token_41|>",
|
| 400 |
+
"lstrip": false,
|
| 401 |
+
"normalized": false,
|
| 402 |
+
"rstrip": false,
|
| 403 |
+
"single_word": false,
|
| 404 |
+
"special": true
|
| 405 |
+
},
|
| 406 |
+
"128050": {
|
| 407 |
+
"content": "<|reserved_special_token_42|>",
|
| 408 |
+
"lstrip": false,
|
| 409 |
+
"normalized": false,
|
| 410 |
+
"rstrip": false,
|
| 411 |
+
"single_word": false,
|
| 412 |
+
"special": true
|
| 413 |
+
},
|
| 414 |
+
"128051": {
|
| 415 |
+
"content": "<|reserved_special_token_43|>",
|
| 416 |
+
"lstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"rstrip": false,
|
| 419 |
+
"single_word": false,
|
| 420 |
+
"special": true
|
| 421 |
+
},
|
| 422 |
+
"128052": {
|
| 423 |
+
"content": "<|reserved_special_token_44|>",
|
| 424 |
+
"lstrip": false,
|
| 425 |
+
"normalized": false,
|
| 426 |
+
"rstrip": false,
|
| 427 |
+
"single_word": false,
|
| 428 |
+
"special": true
|
| 429 |
+
},
|
| 430 |
+
"128053": {
|
| 431 |
+
"content": "<|reserved_special_token_45|>",
|
| 432 |
+
"lstrip": false,
|
| 433 |
+
"normalized": false,
|
| 434 |
+
"rstrip": false,
|
| 435 |
+
"single_word": false,
|
| 436 |
+
"special": true
|
| 437 |
+
},
|
| 438 |
+
"128054": {
|
| 439 |
+
"content": "<|reserved_special_token_46|>",
|
| 440 |
+
"lstrip": false,
|
| 441 |
+
"normalized": false,
|
| 442 |
+
"rstrip": false,
|
| 443 |
+
"single_word": false,
|
| 444 |
+
"special": true
|
| 445 |
+
},
|
| 446 |
+
"128055": {
|
| 447 |
+
"content": "<|reserved_special_token_47|>",
|
| 448 |
+
"lstrip": false,
|
| 449 |
+
"normalized": false,
|
| 450 |
+
"rstrip": false,
|
| 451 |
+
"single_word": false,
|
| 452 |
+
"special": true
|
| 453 |
+
},
|
| 454 |
+
"128056": {
|
| 455 |
+
"content": "<|reserved_special_token_48|>",
|
| 456 |
+
"lstrip": false,
|
| 457 |
+
"normalized": false,
|
| 458 |
+
"rstrip": false,
|
| 459 |
+
"single_word": false,
|
| 460 |
+
"special": true
|
| 461 |
+
},
|
| 462 |
+
"128057": {
|
| 463 |
+
"content": "<|reserved_special_token_49|>",
|
| 464 |
+
"lstrip": false,
|
| 465 |
+
"normalized": false,
|
| 466 |
+
"rstrip": false,
|
| 467 |
+
"single_word": false,
|
| 468 |
+
"special": true
|
| 469 |
+
},
|
| 470 |
+
"128058": {
|
| 471 |
+
"content": "<|reserved_special_token_50|>",
|
| 472 |
+
"lstrip": false,
|
| 473 |
+
"normalized": false,
|
| 474 |
+
"rstrip": false,
|
| 475 |
+
"single_word": false,
|
| 476 |
+
"special": true
|
| 477 |
+
},
|
| 478 |
+
"128059": {
|
| 479 |
+
"content": "<|reserved_special_token_51|>",
|
| 480 |
+
"lstrip": false,
|
| 481 |
+
"normalized": false,
|
| 482 |
+
"rstrip": false,
|
| 483 |
+
"single_word": false,
|
| 484 |
+
"special": true
|
| 485 |
+
},
|
| 486 |
+
"128060": {
|
| 487 |
+
"content": "<|reserved_special_token_52|>",
|
| 488 |
+
"lstrip": false,
|
| 489 |
+
"normalized": false,
|
| 490 |
+
"rstrip": false,
|
| 491 |
+
"single_word": false,
|
| 492 |
+
"special": true
|
| 493 |
+
},
|
| 494 |
+
"128061": {
|
| 495 |
+
"content": "<|reserved_special_token_53|>",
|
| 496 |
+
"lstrip": false,
|
| 497 |
+
"normalized": false,
|
| 498 |
+
"rstrip": false,
|
| 499 |
+
"single_word": false,
|
| 500 |
+
"special": true
|
| 501 |
+
},
|
| 502 |
+
"128062": {
|
| 503 |
+
"content": "<|reserved_special_token_54|>",
|
| 504 |
+
"lstrip": false,
|
| 505 |
+
"normalized": false,
|
| 506 |
+
"rstrip": false,
|
| 507 |
+
"single_word": false,
|
| 508 |
+
"special": true
|
| 509 |
+
},
|
| 510 |
+
"128063": {
|
| 511 |
+
"content": "<|reserved_special_token_55|>",
|
| 512 |
+
"lstrip": false,
|
| 513 |
+
"normalized": false,
|
| 514 |
+
"rstrip": false,
|
| 515 |
+
"single_word": false,
|
| 516 |
+
"special": true
|
| 517 |
+
},
|
| 518 |
+
"128064": {
|
| 519 |
+
"content": "<|reserved_special_token_56|>",
|
| 520 |
+
"lstrip": false,
|
| 521 |
+
"normalized": false,
|
| 522 |
+
"rstrip": false,
|
| 523 |
+
"single_word": false,
|
| 524 |
+
"special": true
|
| 525 |
+
},
|
| 526 |
+
"128065": {
|
| 527 |
+
"content": "<|reserved_special_token_57|>",
|
| 528 |
+
"lstrip": false,
|
| 529 |
+
"normalized": false,
|
| 530 |
+
"rstrip": false,
|
| 531 |
+
"single_word": false,
|
| 532 |
+
"special": true
|
| 533 |
+
},
|
| 534 |
+
"128066": {
|
| 535 |
+
"content": "<|reserved_special_token_58|>",
|
| 536 |
+
"lstrip": false,
|
| 537 |
+
"normalized": false,
|
| 538 |
+
"rstrip": false,
|
| 539 |
+
"single_word": false,
|
| 540 |
+
"special": true
|
| 541 |
+
},
|
| 542 |
+
"128067": {
|
| 543 |
+
"content": "<|reserved_special_token_59|>",
|
| 544 |
+
"lstrip": false,
|
| 545 |
+
"normalized": false,
|
| 546 |
+
"rstrip": false,
|
| 547 |
+
"single_word": false,
|
| 548 |
+
"special": true
|
| 549 |
+
},
|
| 550 |
+
"128068": {
|
| 551 |
+
"content": "<|reserved_special_token_60|>",
|
| 552 |
+
"lstrip": false,
|
| 553 |
+
"normalized": false,
|
| 554 |
+
"rstrip": false,
|
| 555 |
+
"single_word": false,
|
| 556 |
+
"special": true
|
| 557 |
+
},
|
| 558 |
+
"128069": {
|
| 559 |
+
"content": "<|reserved_special_token_61|>",
|
| 560 |
+
"lstrip": false,
|
| 561 |
+
"normalized": false,
|
| 562 |
+
"rstrip": false,
|
| 563 |
+
"single_word": false,
|
| 564 |
+
"special": true
|
| 565 |
+
},
|
| 566 |
+
"128070": {
|
| 567 |
+
"content": "<|reserved_special_token_62|>",
|
| 568 |
+
"lstrip": false,
|
| 569 |
+
"normalized": false,
|
| 570 |
+
"rstrip": false,
|
| 571 |
+
"single_word": false,
|
| 572 |
+
"special": true
|
| 573 |
+
},
|
| 574 |
+
"128071": {
|
| 575 |
+
"content": "<|reserved_special_token_63|>",
|
| 576 |
+
"lstrip": false,
|
| 577 |
+
"normalized": false,
|
| 578 |
+
"rstrip": false,
|
| 579 |
+
"single_word": false,
|
| 580 |
+
"special": true
|
| 581 |
+
},
|
| 582 |
+
"128072": {
|
| 583 |
+
"content": "<|reserved_special_token_64|>",
|
| 584 |
+
"lstrip": false,
|
| 585 |
+
"normalized": false,
|
| 586 |
+
"rstrip": false,
|
| 587 |
+
"single_word": false,
|
| 588 |
+
"special": true
|
| 589 |
+
},
|
| 590 |
+
"128073": {
|
| 591 |
+
"content": "<|reserved_special_token_65|>",
|
| 592 |
+
"lstrip": false,
|
| 593 |
+
"normalized": false,
|
| 594 |
+
"rstrip": false,
|
| 595 |
+
"single_word": false,
|
| 596 |
+
"special": true
|
| 597 |
+
},
|
| 598 |
+
"128074": {
|
| 599 |
+
"content": "<|reserved_special_token_66|>",
|
| 600 |
+
"lstrip": false,
|
| 601 |
+
"normalized": false,
|
| 602 |
+
"rstrip": false,
|
| 603 |
+
"single_word": false,
|
| 604 |
+
"special": true
|
| 605 |
+
},
|
| 606 |
+
"128075": {
|
| 607 |
+
"content": "<|reserved_special_token_67|>",
|
| 608 |
+
"lstrip": false,
|
| 609 |
+
"normalized": false,
|
| 610 |
+
"rstrip": false,
|
| 611 |
+
"single_word": false,
|
| 612 |
+
"special": true
|
| 613 |
+
},
|
| 614 |
+
"128076": {
|
| 615 |
+
"content": "<|reserved_special_token_68|>",
|
| 616 |
+
"lstrip": false,
|
| 617 |
+
"normalized": false,
|
| 618 |
+
"rstrip": false,
|
| 619 |
+
"single_word": false,
|
| 620 |
+
"special": true
|
| 621 |
+
},
|
| 622 |
+
"128077": {
|
| 623 |
+
"content": "<|reserved_special_token_69|>",
|
| 624 |
+
"lstrip": false,
|
| 625 |
+
"normalized": false,
|
| 626 |
+
"rstrip": false,
|
| 627 |
+
"single_word": false,
|
| 628 |
+
"special": true
|
| 629 |
+
},
|
| 630 |
+
"128078": {
|
| 631 |
+
"content": "<|reserved_special_token_70|>",
|
| 632 |
+
"lstrip": false,
|
| 633 |
+
"normalized": false,
|
| 634 |
+
"rstrip": false,
|
| 635 |
+
"single_word": false,
|
| 636 |
+
"special": true
|
| 637 |
+
},
|
| 638 |
+
"128079": {
|
| 639 |
+
"content": "<|reserved_special_token_71|>",
|
| 640 |
+
"lstrip": false,
|
| 641 |
+
"normalized": false,
|
| 642 |
+
"rstrip": false,
|
| 643 |
+
"single_word": false,
|
| 644 |
+
"special": true
|
| 645 |
+
},
|
| 646 |
+
"128080": {
|
| 647 |
+
"content": "<|reserved_special_token_72|>",
|
| 648 |
+
"lstrip": false,
|
| 649 |
+
"normalized": false,
|
| 650 |
+
"rstrip": false,
|
| 651 |
+
"single_word": false,
|
| 652 |
+
"special": true
|
| 653 |
+
},
|
| 654 |
+
"128081": {
|
| 655 |
+
"content": "<|reserved_special_token_73|>",
|
| 656 |
+
"lstrip": false,
|
| 657 |
+
"normalized": false,
|
| 658 |
+
"rstrip": false,
|
| 659 |
+
"single_word": false,
|
| 660 |
+
"special": true
|
| 661 |
+
},
|
| 662 |
+
"128082": {
|
| 663 |
+
"content": "<|reserved_special_token_74|>",
|
| 664 |
+
"lstrip": false,
|
| 665 |
+
"normalized": false,
|
| 666 |
+
"rstrip": false,
|
| 667 |
+
"single_word": false,
|
| 668 |
+
"special": true
|
| 669 |
+
},
|
| 670 |
+
"128083": {
|
| 671 |
+
"content": "<|reserved_special_token_75|>",
|
| 672 |
+
"lstrip": false,
|
| 673 |
+
"normalized": false,
|
| 674 |
+
"rstrip": false,
|
| 675 |
+
"single_word": false,
|
| 676 |
+
"special": true
|
| 677 |
+
},
|
| 678 |
+
"128084": {
|
| 679 |
+
"content": "<|reserved_special_token_76|>",
|
| 680 |
+
"lstrip": false,
|
| 681 |
+
"normalized": false,
|
| 682 |
+
"rstrip": false,
|
| 683 |
+
"single_word": false,
|
| 684 |
+
"special": true
|
| 685 |
+
},
|
| 686 |
+
"128085": {
|
| 687 |
+
"content": "<|reserved_special_token_77|>",
|
| 688 |
+
"lstrip": false,
|
| 689 |
+
"normalized": false,
|
| 690 |
+
"rstrip": false,
|
| 691 |
+
"single_word": false,
|
| 692 |
+
"special": true
|
| 693 |
+
},
|
| 694 |
+
"128086": {
|
| 695 |
+
"content": "<|reserved_special_token_78|>",
|
| 696 |
+
"lstrip": false,
|
| 697 |
+
"normalized": false,
|
| 698 |
+
"rstrip": false,
|
| 699 |
+
"single_word": false,
|
| 700 |
+
"special": true
|
| 701 |
+
},
|
| 702 |
+
"128087": {
|
| 703 |
+
"content": "<|reserved_special_token_79|>",
|
| 704 |
+
"lstrip": false,
|
| 705 |
+
"normalized": false,
|
| 706 |
+
"rstrip": false,
|
| 707 |
+
"single_word": false,
|
| 708 |
+
"special": true
|
| 709 |
+
},
|
| 710 |
+
"128088": {
|
| 711 |
+
"content": "<|reserved_special_token_80|>",
|
| 712 |
+
"lstrip": false,
|
| 713 |
+
"normalized": false,
|
| 714 |
+
"rstrip": false,
|
| 715 |
+
"single_word": false,
|
| 716 |
+
"special": true
|
| 717 |
+
},
|
| 718 |
+
"128089": {
|
| 719 |
+
"content": "<|reserved_special_token_81|>",
|
| 720 |
+
"lstrip": false,
|
| 721 |
+
"normalized": false,
|
| 722 |
+
"rstrip": false,
|
| 723 |
+
"single_word": false,
|
| 724 |
+
"special": true
|
| 725 |
+
},
|
| 726 |
+
"128090": {
|
| 727 |
+
"content": "<|reserved_special_token_82|>",
|
| 728 |
+
"lstrip": false,
|
| 729 |
+
"normalized": false,
|
| 730 |
+
"rstrip": false,
|
| 731 |
+
"single_word": false,
|
| 732 |
+
"special": true
|
| 733 |
+
},
|
| 734 |
+
"128091": {
|
| 735 |
+
"content": "<|reserved_special_token_83|>",
|
| 736 |
+
"lstrip": false,
|
| 737 |
+
"normalized": false,
|
| 738 |
+
"rstrip": false,
|
| 739 |
+
"single_word": false,
|
| 740 |
+
"special": true
|
| 741 |
+
},
|
| 742 |
+
"128092": {
|
| 743 |
+
"content": "<|reserved_special_token_84|>",
|
| 744 |
+
"lstrip": false,
|
| 745 |
+
"normalized": false,
|
| 746 |
+
"rstrip": false,
|
| 747 |
+
"single_word": false,
|
| 748 |
+
"special": true
|
| 749 |
+
},
|
| 750 |
+
"128093": {
|
| 751 |
+
"content": "<|reserved_special_token_85|>",
|
| 752 |
+
"lstrip": false,
|
| 753 |
+
"normalized": false,
|
| 754 |
+
"rstrip": false,
|
| 755 |
+
"single_word": false,
|
| 756 |
+
"special": true
|
| 757 |
+
},
|
| 758 |
+
"128094": {
|
| 759 |
+
"content": "<|reserved_special_token_86|>",
|
| 760 |
+
"lstrip": false,
|
| 761 |
+
"normalized": false,
|
| 762 |
+
"rstrip": false,
|
| 763 |
+
"single_word": false,
|
| 764 |
+
"special": true
|
| 765 |
+
},
|
| 766 |
+
"128095": {
|
| 767 |
+
"content": "<|reserved_special_token_87|>",
|
| 768 |
+
"lstrip": false,
|
| 769 |
+
"normalized": false,
|
| 770 |
+
"rstrip": false,
|
| 771 |
+
"single_word": false,
|
| 772 |
+
"special": true
|
| 773 |
+
},
|
| 774 |
+
"128096": {
|
| 775 |
+
"content": "<|reserved_special_token_88|>",
|
| 776 |
+
"lstrip": false,
|
| 777 |
+
"normalized": false,
|
| 778 |
+
"rstrip": false,
|
| 779 |
+
"single_word": false,
|
| 780 |
+
"special": true
|
| 781 |
+
},
|
| 782 |
+
"128097": {
|
| 783 |
+
"content": "<|reserved_special_token_89|>",
|
| 784 |
+
"lstrip": false,
|
| 785 |
+
"normalized": false,
|
| 786 |
+
"rstrip": false,
|
| 787 |
+
"single_word": false,
|
| 788 |
+
"special": true
|
| 789 |
+
},
|
| 790 |
+
"128098": {
|
| 791 |
+
"content": "<|reserved_special_token_90|>",
|
| 792 |
+
"lstrip": false,
|
| 793 |
+
"normalized": false,
|
| 794 |
+
"rstrip": false,
|
| 795 |
+
"single_word": false,
|
| 796 |
+
"special": true
|
| 797 |
+
},
|
| 798 |
+
"128099": {
|
| 799 |
+
"content": "<|reserved_special_token_91|>",
|
| 800 |
+
"lstrip": false,
|
| 801 |
+
"normalized": false,
|
| 802 |
+
"rstrip": false,
|
| 803 |
+
"single_word": false,
|
| 804 |
+
"special": true
|
| 805 |
+
},
|
| 806 |
+
"128100": {
|
| 807 |
+
"content": "<|reserved_special_token_92|>",
|
| 808 |
+
"lstrip": false,
|
| 809 |
+
"normalized": false,
|
| 810 |
+
"rstrip": false,
|
| 811 |
+
"single_word": false,
|
| 812 |
+
"special": true
|
| 813 |
+
},
|
| 814 |
+
"128101": {
|
| 815 |
+
"content": "<|reserved_special_token_93|>",
|
| 816 |
+
"lstrip": false,
|
| 817 |
+
"normalized": false,
|
| 818 |
+
"rstrip": false,
|
| 819 |
+
"single_word": false,
|
| 820 |
+
"special": true
|
| 821 |
+
},
|
| 822 |
+
"128102": {
|
| 823 |
+
"content": "<|reserved_special_token_94|>",
|
| 824 |
+
"lstrip": false,
|
| 825 |
+
"normalized": false,
|
| 826 |
+
"rstrip": false,
|
| 827 |
+
"single_word": false,
|
| 828 |
+
"special": true
|
| 829 |
+
},
|
| 830 |
+
"128103": {
|
| 831 |
+
"content": "<|reserved_special_token_95|>",
|
| 832 |
+
"lstrip": false,
|
| 833 |
+
"normalized": false,
|
| 834 |
+
"rstrip": false,
|
| 835 |
+
"single_word": false,
|
| 836 |
+
"special": true
|
| 837 |
+
},
|
| 838 |
+
"128104": {
|
| 839 |
+
"content": "<|reserved_special_token_96|>",
|
| 840 |
+
"lstrip": false,
|
| 841 |
+
"normalized": false,
|
| 842 |
+
"rstrip": false,
|
| 843 |
+
"single_word": false,
|
| 844 |
+
"special": true
|
| 845 |
+
},
|
| 846 |
+
"128105": {
|
| 847 |
+
"content": "<|reserved_special_token_97|>",
|
| 848 |
+
"lstrip": false,
|
| 849 |
+
"normalized": false,
|
| 850 |
+
"rstrip": false,
|
| 851 |
+
"single_word": false,
|
| 852 |
+
"special": true
|
| 853 |
+
},
|
| 854 |
+
"128106": {
|
| 855 |
+
"content": "<|reserved_special_token_98|>",
|
| 856 |
+
"lstrip": false,
|
| 857 |
+
"normalized": false,
|
| 858 |
+
"rstrip": false,
|
| 859 |
+
"single_word": false,
|
| 860 |
+
"special": true
|
| 861 |
+
},
|
| 862 |
+
"128107": {
|
| 863 |
+
"content": "<|reserved_special_token_99|>",
|
| 864 |
+
"lstrip": false,
|
| 865 |
+
"normalized": false,
|
| 866 |
+
"rstrip": false,
|
| 867 |
+
"single_word": false,
|
| 868 |
+
"special": true
|
| 869 |
+
},
|
| 870 |
+
"128108": {
|
| 871 |
+
"content": "<|reserved_special_token_100|>",
|
| 872 |
+
"lstrip": false,
|
| 873 |
+
"normalized": false,
|
| 874 |
+
"rstrip": false,
|
| 875 |
+
"single_word": false,
|
| 876 |
+
"special": true
|
| 877 |
+
},
|
| 878 |
+
"128109": {
|
| 879 |
+
"content": "<|reserved_special_token_101|>",
|
| 880 |
+
"lstrip": false,
|
| 881 |
+
"normalized": false,
|
| 882 |
+
"rstrip": false,
|
| 883 |
+
"single_word": false,
|
| 884 |
+
"special": true
|
| 885 |
+
},
|
| 886 |
+
"128110": {
|
| 887 |
+
"content": "<|reserved_special_token_102|>",
|
| 888 |
+
"lstrip": false,
|
| 889 |
+
"normalized": false,
|
| 890 |
+
"rstrip": false,
|
| 891 |
+
"single_word": false,
|
| 892 |
+
"special": true
|
| 893 |
+
},
|
| 894 |
+
"128111": {
|
| 895 |
+
"content": "<|reserved_special_token_103|>",
|
| 896 |
+
"lstrip": false,
|
| 897 |
+
"normalized": false,
|
| 898 |
+
"rstrip": false,
|
| 899 |
+
"single_word": false,
|
| 900 |
+
"special": true
|
| 901 |
+
},
|
| 902 |
+
"128112": {
|
| 903 |
+
"content": "<|reserved_special_token_104|>",
|
| 904 |
+
"lstrip": false,
|
| 905 |
+
"normalized": false,
|
| 906 |
+
"rstrip": false,
|
| 907 |
+
"single_word": false,
|
| 908 |
+
"special": true
|
| 909 |
+
},
|
| 910 |
+
"128113": {
|
| 911 |
+
"content": "<|reserved_special_token_105|>",
|
| 912 |
+
"lstrip": false,
|
| 913 |
+
"normalized": false,
|
| 914 |
+
"rstrip": false,
|
| 915 |
+
"single_word": false,
|
| 916 |
+
"special": true
|
| 917 |
+
},
|
| 918 |
+
"128114": {
|
| 919 |
+
"content": "<|reserved_special_token_106|>",
|
| 920 |
+
"lstrip": false,
|
| 921 |
+
"normalized": false,
|
| 922 |
+
"rstrip": false,
|
| 923 |
+
"single_word": false,
|
| 924 |
+
"special": true
|
| 925 |
+
},
|
| 926 |
+
"128115": {
|
| 927 |
+
"content": "<|reserved_special_token_107|>",
|
| 928 |
+
"lstrip": false,
|
| 929 |
+
"normalized": false,
|
| 930 |
+
"rstrip": false,
|
| 931 |
+
"single_word": false,
|
| 932 |
+
"special": true
|
| 933 |
+
},
|
| 934 |
+
"128116": {
|
| 935 |
+
"content": "<|reserved_special_token_108|>",
|
| 936 |
+
"lstrip": false,
|
| 937 |
+
"normalized": false,
|
| 938 |
+
"rstrip": false,
|
| 939 |
+
"single_word": false,
|
| 940 |
+
"special": true
|
| 941 |
+
},
|
| 942 |
+
"128117": {
|
| 943 |
+
"content": "<|reserved_special_token_109|>",
|
| 944 |
+
"lstrip": false,
|
| 945 |
+
"normalized": false,
|
| 946 |
+
"rstrip": false,
|
| 947 |
+
"single_word": false,
|
| 948 |
+
"special": true
|
| 949 |
+
},
|
| 950 |
+
"128118": {
|
| 951 |
+
"content": "<|reserved_special_token_110|>",
|
| 952 |
+
"lstrip": false,
|
| 953 |
+
"normalized": false,
|
| 954 |
+
"rstrip": false,
|
| 955 |
+
"single_word": false,
|
| 956 |
+
"special": true
|
| 957 |
+
},
|
| 958 |
+
"128119": {
|
| 959 |
+
"content": "<|reserved_special_token_111|>",
|
| 960 |
+
"lstrip": false,
|
| 961 |
+
"normalized": false,
|
| 962 |
+
"rstrip": false,
|
| 963 |
+
"single_word": false,
|
| 964 |
+
"special": true
|
| 965 |
+
},
|
| 966 |
+
"128120": {
|
| 967 |
+
"content": "<|reserved_special_token_112|>",
|
| 968 |
+
"lstrip": false,
|
| 969 |
+
"normalized": false,
|
| 970 |
+
"rstrip": false,
|
| 971 |
+
"single_word": false,
|
| 972 |
+
"special": true
|
| 973 |
+
},
|
| 974 |
+
"128121": {
|
| 975 |
+
"content": "<|reserved_special_token_113|>",
|
| 976 |
+
"lstrip": false,
|
| 977 |
+
"normalized": false,
|
| 978 |
+
"rstrip": false,
|
| 979 |
+
"single_word": false,
|
| 980 |
+
"special": true
|
| 981 |
+
},
|
| 982 |
+
"128122": {
|
| 983 |
+
"content": "<|reserved_special_token_114|>",
|
| 984 |
+
"lstrip": false,
|
| 985 |
+
"normalized": false,
|
| 986 |
+
"rstrip": false,
|
| 987 |
+
"single_word": false,
|
| 988 |
+
"special": true
|
| 989 |
+
},
|
| 990 |
+
"128123": {
|
| 991 |
+
"content": "<|reserved_special_token_115|>",
|
| 992 |
+
"lstrip": false,
|
| 993 |
+
"normalized": false,
|
| 994 |
+
"rstrip": false,
|
| 995 |
+
"single_word": false,
|
| 996 |
+
"special": true
|
| 997 |
+
},
|
| 998 |
+
"128124": {
|
| 999 |
+
"content": "<|reserved_special_token_116|>",
|
| 1000 |
+
"lstrip": false,
|
| 1001 |
+
"normalized": false,
|
| 1002 |
+
"rstrip": false,
|
| 1003 |
+
"single_word": false,
|
| 1004 |
+
"special": true
|
| 1005 |
+
},
|
| 1006 |
+
"128125": {
|
| 1007 |
+
"content": "<|reserved_special_token_117|>",
|
| 1008 |
+
"lstrip": false,
|
| 1009 |
+
"normalized": false,
|
| 1010 |
+
"rstrip": false,
|
| 1011 |
+
"single_word": false,
|
| 1012 |
+
"special": true
|
| 1013 |
+
},
|
| 1014 |
+
"128126": {
|
| 1015 |
+
"content": "<|reserved_special_token_118|>",
|
| 1016 |
+
"lstrip": false,
|
| 1017 |
+
"normalized": false,
|
| 1018 |
+
"rstrip": false,
|
| 1019 |
+
"single_word": false,
|
| 1020 |
+
"special": true
|
| 1021 |
+
},
|
| 1022 |
+
"128127": {
|
| 1023 |
+
"content": "<|reserved_special_token_119|>",
|
| 1024 |
+
"lstrip": false,
|
| 1025 |
+
"normalized": false,
|
| 1026 |
+
"rstrip": false,
|
| 1027 |
+
"single_word": false,
|
| 1028 |
+
"special": true
|
| 1029 |
+
},
|
| 1030 |
+
"128128": {
|
| 1031 |
+
"content": "<|reserved_special_token_120|>",
|
| 1032 |
+
"lstrip": false,
|
| 1033 |
+
"normalized": false,
|
| 1034 |
+
"rstrip": false,
|
| 1035 |
+
"single_word": false,
|
| 1036 |
+
"special": true
|
| 1037 |
+
},
|
| 1038 |
+
"128129": {
|
| 1039 |
+
"content": "<|reserved_special_token_121|>",
|
| 1040 |
+
"lstrip": false,
|
| 1041 |
+
"normalized": false,
|
| 1042 |
+
"rstrip": false,
|
| 1043 |
+
"single_word": false,
|
| 1044 |
+
"special": true
|
| 1045 |
+
},
|
| 1046 |
+
"128130": {
|
| 1047 |
+
"content": "<|reserved_special_token_122|>",
|
| 1048 |
+
"lstrip": false,
|
| 1049 |
+
"normalized": false,
|
| 1050 |
+
"rstrip": false,
|
| 1051 |
+
"single_word": false,
|
| 1052 |
+
"special": true
|
| 1053 |
+
},
|
| 1054 |
+
"128131": {
|
| 1055 |
+
"content": "<|reserved_special_token_123|>",
|
| 1056 |
+
"lstrip": false,
|
| 1057 |
+
"normalized": false,
|
| 1058 |
+
"rstrip": false,
|
| 1059 |
+
"single_word": false,
|
| 1060 |
+
"special": true
|
| 1061 |
+
},
|
| 1062 |
+
"128132": {
|
| 1063 |
+
"content": "<|reserved_special_token_124|>",
|
| 1064 |
+
"lstrip": false,
|
| 1065 |
+
"normalized": false,
|
| 1066 |
+
"rstrip": false,
|
| 1067 |
+
"single_word": false,
|
| 1068 |
+
"special": true
|
| 1069 |
+
},
|
| 1070 |
+
"128133": {
|
| 1071 |
+
"content": "<|reserved_special_token_125|>",
|
| 1072 |
+
"lstrip": false,
|
| 1073 |
+
"normalized": false,
|
| 1074 |
+
"rstrip": false,
|
| 1075 |
+
"single_word": false,
|
| 1076 |
+
"special": true
|
| 1077 |
+
},
|
| 1078 |
+
"128134": {
|
| 1079 |
+
"content": "<|reserved_special_token_126|>",
|
| 1080 |
+
"lstrip": false,
|
| 1081 |
+
"normalized": false,
|
| 1082 |
+
"rstrip": false,
|
| 1083 |
+
"single_word": false,
|
| 1084 |
+
"special": true
|
| 1085 |
+
},
|
| 1086 |
+
"128135": {
|
| 1087 |
+
"content": "<|reserved_special_token_127|>",
|
| 1088 |
+
"lstrip": false,
|
| 1089 |
+
"normalized": false,
|
| 1090 |
+
"rstrip": false,
|
| 1091 |
+
"single_word": false,
|
| 1092 |
+
"special": true
|
| 1093 |
+
},
|
| 1094 |
+
"128136": {
|
| 1095 |
+
"content": "<|reserved_special_token_128|>",
|
| 1096 |
+
"lstrip": false,
|
| 1097 |
+
"normalized": false,
|
| 1098 |
+
"rstrip": false,
|
| 1099 |
+
"single_word": false,
|
| 1100 |
+
"special": true
|
| 1101 |
+
},
|
| 1102 |
+
"128137": {
|
| 1103 |
+
"content": "<|reserved_special_token_129|>",
|
| 1104 |
+
"lstrip": false,
|
| 1105 |
+
"normalized": false,
|
| 1106 |
+
"rstrip": false,
|
| 1107 |
+
"single_word": false,
|
| 1108 |
+
"special": true
|
| 1109 |
+
},
|
| 1110 |
+
"128138": {
|
| 1111 |
+
"content": "<|reserved_special_token_130|>",
|
| 1112 |
+
"lstrip": false,
|
| 1113 |
+
"normalized": false,
|
| 1114 |
+
"rstrip": false,
|
| 1115 |
+
"single_word": false,
|
| 1116 |
+
"special": true
|
| 1117 |
+
},
|
| 1118 |
+
"128139": {
|
| 1119 |
+
"content": "<|reserved_special_token_131|>",
|
| 1120 |
+
"lstrip": false,
|
| 1121 |
+
"normalized": false,
|
| 1122 |
+
"rstrip": false,
|
| 1123 |
+
"single_word": false,
|
| 1124 |
+
"special": true
|
| 1125 |
+
},
|
| 1126 |
+
"128140": {
|
| 1127 |
+
"content": "<|reserved_special_token_132|>",
|
| 1128 |
+
"lstrip": false,
|
| 1129 |
+
"normalized": false,
|
| 1130 |
+
"rstrip": false,
|
| 1131 |
+
"single_word": false,
|
| 1132 |
+
"special": true
|
| 1133 |
+
},
|
| 1134 |
+
"128141": {
|
| 1135 |
+
"content": "<|reserved_special_token_133|>",
|
| 1136 |
+
"lstrip": false,
|
| 1137 |
+
"normalized": false,
|
| 1138 |
+
"rstrip": false,
|
| 1139 |
+
"single_word": false,
|
| 1140 |
+
"special": true
|
| 1141 |
+
},
|
| 1142 |
+
"128142": {
|
| 1143 |
+
"content": "<|reserved_special_token_134|>",
|
| 1144 |
+
"lstrip": false,
|
| 1145 |
+
"normalized": false,
|
| 1146 |
+
"rstrip": false,
|
| 1147 |
+
"single_word": false,
|
| 1148 |
+
"special": true
|
| 1149 |
+
},
|
| 1150 |
+
"128143": {
|
| 1151 |
+
"content": "<|reserved_special_token_135|>",
|
| 1152 |
+
"lstrip": false,
|
| 1153 |
+
"normalized": false,
|
| 1154 |
+
"rstrip": false,
|
| 1155 |
+
"single_word": false,
|
| 1156 |
+
"special": true
|
| 1157 |
+
},
|
| 1158 |
+
"128144": {
|
| 1159 |
+
"content": "<|reserved_special_token_136|>",
|
| 1160 |
+
"lstrip": false,
|
| 1161 |
+
"normalized": false,
|
| 1162 |
+
"rstrip": false,
|
| 1163 |
+
"single_word": false,
|
| 1164 |
+
"special": true
|
| 1165 |
+
},
|
| 1166 |
+
"128145": {
|
| 1167 |
+
"content": "<|reserved_special_token_137|>",
|
| 1168 |
+
"lstrip": false,
|
| 1169 |
+
"normalized": false,
|
| 1170 |
+
"rstrip": false,
|
| 1171 |
+
"single_word": false,
|
| 1172 |
+
"special": true
|
| 1173 |
+
},
|
| 1174 |
+
"128146": {
|
| 1175 |
+
"content": "<|reserved_special_token_138|>",
|
| 1176 |
+
"lstrip": false,
|
| 1177 |
+
"normalized": false,
|
| 1178 |
+
"rstrip": false,
|
| 1179 |
+
"single_word": false,
|
| 1180 |
+
"special": true
|
| 1181 |
+
},
|
| 1182 |
+
"128147": {
|
| 1183 |
+
"content": "<|reserved_special_token_139|>",
|
| 1184 |
+
"lstrip": false,
|
| 1185 |
+
"normalized": false,
|
| 1186 |
+
"rstrip": false,
|
| 1187 |
+
"single_word": false,
|
| 1188 |
+
"special": true
|
| 1189 |
+
},
|
| 1190 |
+
"128148": {
|
| 1191 |
+
"content": "<|reserved_special_token_140|>",
|
| 1192 |
+
"lstrip": false,
|
| 1193 |
+
"normalized": false,
|
| 1194 |
+
"rstrip": false,
|
| 1195 |
+
"single_word": false,
|
| 1196 |
+
"special": true
|
| 1197 |
+
},
|
| 1198 |
+
"128149": {
|
| 1199 |
+
"content": "<|reserved_special_token_141|>",
|
| 1200 |
+
"lstrip": false,
|
| 1201 |
+
"normalized": false,
|
| 1202 |
+
"rstrip": false,
|
| 1203 |
+
"single_word": false,
|
| 1204 |
+
"special": true
|
| 1205 |
+
},
|
| 1206 |
+
"128150": {
|
| 1207 |
+
"content": "<|reserved_special_token_142|>",
|
| 1208 |
+
"lstrip": false,
|
| 1209 |
+
"normalized": false,
|
| 1210 |
+
"rstrip": false,
|
| 1211 |
+
"single_word": false,
|
| 1212 |
+
"special": true
|
| 1213 |
+
},
|
| 1214 |
+
"128151": {
|
| 1215 |
+
"content": "<|reserved_special_token_143|>",
|
| 1216 |
+
"lstrip": false,
|
| 1217 |
+
"normalized": false,
|
| 1218 |
+
"rstrip": false,
|
| 1219 |
+
"single_word": false,
|
| 1220 |
+
"special": true
|
| 1221 |
+
},
|
| 1222 |
+
"128152": {
|
| 1223 |
+
"content": "<|reserved_special_token_144|>",
|
| 1224 |
+
"lstrip": false,
|
| 1225 |
+
"normalized": false,
|
| 1226 |
+
"rstrip": false,
|
| 1227 |
+
"single_word": false,
|
| 1228 |
+
"special": true
|
| 1229 |
+
},
|
| 1230 |
+
"128153": {
|
| 1231 |
+
"content": "<|reserved_special_token_145|>",
|
| 1232 |
+
"lstrip": false,
|
| 1233 |
+
"normalized": false,
|
| 1234 |
+
"rstrip": false,
|
| 1235 |
+
"single_word": false,
|
| 1236 |
+
"special": true
|
| 1237 |
+
},
|
| 1238 |
+
"128154": {
|
| 1239 |
+
"content": "<|reserved_special_token_146|>",
|
| 1240 |
+
"lstrip": false,
|
| 1241 |
+
"normalized": false,
|
| 1242 |
+
"rstrip": false,
|
| 1243 |
+
"single_word": false,
|
| 1244 |
+
"special": true
|
| 1245 |
+
},
|
| 1246 |
+
"128155": {
|
| 1247 |
+
"content": "<|reserved_special_token_147|>",
|
| 1248 |
+
"lstrip": false,
|
| 1249 |
+
"normalized": false,
|
| 1250 |
+
"rstrip": false,
|
| 1251 |
+
"single_word": false,
|
| 1252 |
+
"special": true
|
| 1253 |
+
},
|
| 1254 |
+
"128156": {
|
| 1255 |
+
"content": "<|reserved_special_token_148|>",
|
| 1256 |
+
"lstrip": false,
|
| 1257 |
+
"normalized": false,
|
| 1258 |
+
"rstrip": false,
|
| 1259 |
+
"single_word": false,
|
| 1260 |
+
"special": true
|
| 1261 |
+
},
|
| 1262 |
+
"128157": {
|
| 1263 |
+
"content": "<|reserved_special_token_149|>",
|
| 1264 |
+
"lstrip": false,
|
| 1265 |
+
"normalized": false,
|
| 1266 |
+
"rstrip": false,
|
| 1267 |
+
"single_word": false,
|
| 1268 |
+
"special": true
|
| 1269 |
+
},
|
| 1270 |
+
"128158": {
|
| 1271 |
+
"content": "<|reserved_special_token_150|>",
|
| 1272 |
+
"lstrip": false,
|
| 1273 |
+
"normalized": false,
|
| 1274 |
+
"rstrip": false,
|
| 1275 |
+
"single_word": false,
|
| 1276 |
+
"special": true
|
| 1277 |
+
},
|
| 1278 |
+
"128159": {
|
| 1279 |
+
"content": "<|reserved_special_token_151|>",
|
| 1280 |
+
"lstrip": false,
|
| 1281 |
+
"normalized": false,
|
| 1282 |
+
"rstrip": false,
|
| 1283 |
+
"single_word": false,
|
| 1284 |
+
"special": true
|
| 1285 |
+
},
|
| 1286 |
+
"128160": {
|
| 1287 |
+
"content": "<|reserved_special_token_152|>",
|
| 1288 |
+
"lstrip": false,
|
| 1289 |
+
"normalized": false,
|
| 1290 |
+
"rstrip": false,
|
| 1291 |
+
"single_word": false,
|
| 1292 |
+
"special": true
|
| 1293 |
+
},
|
| 1294 |
+
"128161": {
|
| 1295 |
+
"content": "<|reserved_special_token_153|>",
|
| 1296 |
+
"lstrip": false,
|
| 1297 |
+
"normalized": false,
|
| 1298 |
+
"rstrip": false,
|
| 1299 |
+
"single_word": false,
|
| 1300 |
+
"special": true
|
| 1301 |
+
},
|
| 1302 |
+
"128162": {
|
| 1303 |
+
"content": "<|reserved_special_token_154|>",
|
| 1304 |
+
"lstrip": false,
|
| 1305 |
+
"normalized": false,
|
| 1306 |
+
"rstrip": false,
|
| 1307 |
+
"single_word": false,
|
| 1308 |
+
"special": true
|
| 1309 |
+
},
|
| 1310 |
+
"128163": {
|
| 1311 |
+
"content": "<|reserved_special_token_155|>",
|
| 1312 |
+
"lstrip": false,
|
| 1313 |
+
"normalized": false,
|
| 1314 |
+
"rstrip": false,
|
| 1315 |
+
"single_word": false,
|
| 1316 |
+
"special": true
|
| 1317 |
+
},
|
| 1318 |
+
"128164": {
|
| 1319 |
+
"content": "<|reserved_special_token_156|>",
|
| 1320 |
+
"lstrip": false,
|
| 1321 |
+
"normalized": false,
|
| 1322 |
+
"rstrip": false,
|
| 1323 |
+
"single_word": false,
|
| 1324 |
+
"special": true
|
| 1325 |
+
},
|
| 1326 |
+
"128165": {
|
| 1327 |
+
"content": "<|reserved_special_token_157|>",
|
| 1328 |
+
"lstrip": false,
|
| 1329 |
+
"normalized": false,
|
| 1330 |
+
"rstrip": false,
|
| 1331 |
+
"single_word": false,
|
| 1332 |
+
"special": true
|
| 1333 |
+
},
|
| 1334 |
+
"128166": {
|
| 1335 |
+
"content": "<|reserved_special_token_158|>",
|
| 1336 |
+
"lstrip": false,
|
| 1337 |
+
"normalized": false,
|
| 1338 |
+
"rstrip": false,
|
| 1339 |
+
"single_word": false,
|
| 1340 |
+
"special": true
|
| 1341 |
+
},
|
| 1342 |
+
"128167": {
|
| 1343 |
+
"content": "<|reserved_special_token_159|>",
|
| 1344 |
+
"lstrip": false,
|
| 1345 |
+
"normalized": false,
|
| 1346 |
+
"rstrip": false,
|
| 1347 |
+
"single_word": false,
|
| 1348 |
+
"special": true
|
| 1349 |
+
},
|
| 1350 |
+
"128168": {
|
| 1351 |
+
"content": "<|reserved_special_token_160|>",
|
| 1352 |
+
"lstrip": false,
|
| 1353 |
+
"normalized": false,
|
| 1354 |
+
"rstrip": false,
|
| 1355 |
+
"single_word": false,
|
| 1356 |
+
"special": true
|
| 1357 |
+
},
|
| 1358 |
+
"128169": {
|
| 1359 |
+
"content": "<|reserved_special_token_161|>",
|
| 1360 |
+
"lstrip": false,
|
| 1361 |
+
"normalized": false,
|
| 1362 |
+
"rstrip": false,
|
| 1363 |
+
"single_word": false,
|
| 1364 |
+
"special": true
|
| 1365 |
+
},
|
| 1366 |
+
"128170": {
|
| 1367 |
+
"content": "<|reserved_special_token_162|>",
|
| 1368 |
+
"lstrip": false,
|
| 1369 |
+
"normalized": false,
|
| 1370 |
+
"rstrip": false,
|
| 1371 |
+
"single_word": false,
|
| 1372 |
+
"special": true
|
| 1373 |
+
},
|
| 1374 |
+
"128171": {
|
| 1375 |
+
"content": "<|reserved_special_token_163|>",
|
| 1376 |
+
"lstrip": false,
|
| 1377 |
+
"normalized": false,
|
| 1378 |
+
"rstrip": false,
|
| 1379 |
+
"single_word": false,
|
| 1380 |
+
"special": true
|
| 1381 |
+
},
|
| 1382 |
+
"128172": {
|
| 1383 |
+
"content": "<|reserved_special_token_164|>",
|
| 1384 |
+
"lstrip": false,
|
| 1385 |
+
"normalized": false,
|
| 1386 |
+
"rstrip": false,
|
| 1387 |
+
"single_word": false,
|
| 1388 |
+
"special": true
|
| 1389 |
+
},
|
| 1390 |
+
"128173": {
|
| 1391 |
+
"content": "<|reserved_special_token_165|>",
|
| 1392 |
+
"lstrip": false,
|
| 1393 |
+
"normalized": false,
|
| 1394 |
+
"rstrip": false,
|
| 1395 |
+
"single_word": false,
|
| 1396 |
+
"special": true
|
| 1397 |
+
},
|
| 1398 |
+
"128174": {
|
| 1399 |
+
"content": "<|reserved_special_token_166|>",
|
| 1400 |
+
"lstrip": false,
|
| 1401 |
+
"normalized": false,
|
| 1402 |
+
"rstrip": false,
|
| 1403 |
+
"single_word": false,
|
| 1404 |
+
"special": true
|
| 1405 |
+
},
|
| 1406 |
+
"128175": {
|
| 1407 |
+
"content": "<|reserved_special_token_167|>",
|
| 1408 |
+
"lstrip": false,
|
| 1409 |
+
"normalized": false,
|
| 1410 |
+
"rstrip": false,
|
| 1411 |
+
"single_word": false,
|
| 1412 |
+
"special": true
|
| 1413 |
+
},
|
| 1414 |
+
"128176": {
|
| 1415 |
+
"content": "<|reserved_special_token_168|>",
|
| 1416 |
+
"lstrip": false,
|
| 1417 |
+
"normalized": false,
|
| 1418 |
+
"rstrip": false,
|
| 1419 |
+
"single_word": false,
|
| 1420 |
+
"special": true
|
| 1421 |
+
},
|
| 1422 |
+
"128177": {
|
| 1423 |
+
"content": "<|reserved_special_token_169|>",
|
| 1424 |
+
"lstrip": false,
|
| 1425 |
+
"normalized": false,
|
| 1426 |
+
"rstrip": false,
|
| 1427 |
+
"single_word": false,
|
| 1428 |
+
"special": true
|
| 1429 |
+
},
|
| 1430 |
+
"128178": {
|
| 1431 |
+
"content": "<|reserved_special_token_170|>",
|
| 1432 |
+
"lstrip": false,
|
| 1433 |
+
"normalized": false,
|
| 1434 |
+
"rstrip": false,
|
| 1435 |
+
"single_word": false,
|
| 1436 |
+
"special": true
|
| 1437 |
+
},
|
| 1438 |
+
"128179": {
|
| 1439 |
+
"content": "<|reserved_special_token_171|>",
|
| 1440 |
+
"lstrip": false,
|
| 1441 |
+
"normalized": false,
|
| 1442 |
+
"rstrip": false,
|
| 1443 |
+
"single_word": false,
|
| 1444 |
+
"special": true
|
| 1445 |
+
},
|
| 1446 |
+
"128180": {
|
| 1447 |
+
"content": "<|reserved_special_token_172|>",
|
| 1448 |
+
"lstrip": false,
|
| 1449 |
+
"normalized": false,
|
| 1450 |
+
"rstrip": false,
|
| 1451 |
+
"single_word": false,
|
| 1452 |
+
"special": true
|
| 1453 |
+
},
|
| 1454 |
+
"128181": {
|
| 1455 |
+
"content": "<|reserved_special_token_173|>",
|
| 1456 |
+
"lstrip": false,
|
| 1457 |
+
"normalized": false,
|
| 1458 |
+
"rstrip": false,
|
| 1459 |
+
"single_word": false,
|
| 1460 |
+
"special": true
|
| 1461 |
+
},
|
| 1462 |
+
"128182": {
|
| 1463 |
+
"content": "<|reserved_special_token_174|>",
|
| 1464 |
+
"lstrip": false,
|
| 1465 |
+
"normalized": false,
|
| 1466 |
+
"rstrip": false,
|
| 1467 |
+
"single_word": false,
|
| 1468 |
+
"special": true
|
| 1469 |
+
},
|
| 1470 |
+
"128183": {
|
| 1471 |
+
"content": "<|reserved_special_token_175|>",
|
| 1472 |
+
"lstrip": false,
|
| 1473 |
+
"normalized": false,
|
| 1474 |
+
"rstrip": false,
|
| 1475 |
+
"single_word": false,
|
| 1476 |
+
"special": true
|
| 1477 |
+
},
|
| 1478 |
+
"128184": {
|
| 1479 |
+
"content": "<|reserved_special_token_176|>",
|
| 1480 |
+
"lstrip": false,
|
| 1481 |
+
"normalized": false,
|
| 1482 |
+
"rstrip": false,
|
| 1483 |
+
"single_word": false,
|
| 1484 |
+
"special": true
|
| 1485 |
+
},
|
| 1486 |
+
"128185": {
|
| 1487 |
+
"content": "<|reserved_special_token_177|>",
|
| 1488 |
+
"lstrip": false,
|
| 1489 |
+
"normalized": false,
|
| 1490 |
+
"rstrip": false,
|
| 1491 |
+
"single_word": false,
|
| 1492 |
+
"special": true
|
| 1493 |
+
},
|
| 1494 |
+
"128186": {
|
| 1495 |
+
"content": "<|reserved_special_token_178|>",
|
| 1496 |
+
"lstrip": false,
|
| 1497 |
+
"normalized": false,
|
| 1498 |
+
"rstrip": false,
|
| 1499 |
+
"single_word": false,
|
| 1500 |
+
"special": true
|
| 1501 |
+
},
|
| 1502 |
+
"128187": {
|
| 1503 |
+
"content": "<|reserved_special_token_179|>",
|
| 1504 |
+
"lstrip": false,
|
| 1505 |
+
"normalized": false,
|
| 1506 |
+
"rstrip": false,
|
| 1507 |
+
"single_word": false,
|
| 1508 |
+
"special": true
|
| 1509 |
+
},
|
| 1510 |
+
"128188": {
|
| 1511 |
+
"content": "<|reserved_special_token_180|>",
|
| 1512 |
+
"lstrip": false,
|
| 1513 |
+
"normalized": false,
|
| 1514 |
+
"rstrip": false,
|
| 1515 |
+
"single_word": false,
|
| 1516 |
+
"special": true
|
| 1517 |
+
},
|
| 1518 |
+
"128189": {
|
| 1519 |
+
"content": "<|reserved_special_token_181|>",
|
| 1520 |
+
"lstrip": false,
|
| 1521 |
+
"normalized": false,
|
| 1522 |
+
"rstrip": false,
|
| 1523 |
+
"single_word": false,
|
| 1524 |
+
"special": true
|
| 1525 |
+
},
|
| 1526 |
+
"128190": {
|
| 1527 |
+
"content": "<|reserved_special_token_182|>",
|
| 1528 |
+
"lstrip": false,
|
| 1529 |
+
"normalized": false,
|
| 1530 |
+
"rstrip": false,
|
| 1531 |
+
"single_word": false,
|
| 1532 |
+
"special": true
|
| 1533 |
+
},
|
| 1534 |
+
"128191": {
|
| 1535 |
+
"content": "<|reserved_special_token_183|>",
|
| 1536 |
+
"lstrip": false,
|
| 1537 |
+
"normalized": false,
|
| 1538 |
+
"rstrip": false,
|
| 1539 |
+
"single_word": false,
|
| 1540 |
+
"special": true
|
| 1541 |
+
},
|
| 1542 |
+
"128192": {
|
| 1543 |
+
"content": "<|reserved_special_token_184|>",
|
| 1544 |
+
"lstrip": false,
|
| 1545 |
+
"normalized": false,
|
| 1546 |
+
"rstrip": false,
|
| 1547 |
+
"single_word": false,
|
| 1548 |
+
"special": true
|
| 1549 |
+
},
|
| 1550 |
+
"128193": {
|
| 1551 |
+
"content": "<|reserved_special_token_185|>",
|
| 1552 |
+
"lstrip": false,
|
| 1553 |
+
"normalized": false,
|
| 1554 |
+
"rstrip": false,
|
| 1555 |
+
"single_word": false,
|
| 1556 |
+
"special": true
|
| 1557 |
+
},
|
| 1558 |
+
"128194": {
|
| 1559 |
+
"content": "<|reserved_special_token_186|>",
|
| 1560 |
+
"lstrip": false,
|
| 1561 |
+
"normalized": false,
|
| 1562 |
+
"rstrip": false,
|
| 1563 |
+
"single_word": false,
|
| 1564 |
+
"special": true
|
| 1565 |
+
},
|
| 1566 |
+
"128195": {
|
| 1567 |
+
"content": "<|reserved_special_token_187|>",
|
| 1568 |
+
"lstrip": false,
|
| 1569 |
+
"normalized": false,
|
| 1570 |
+
"rstrip": false,
|
| 1571 |
+
"single_word": false,
|
| 1572 |
+
"special": true
|
| 1573 |
+
},
|
| 1574 |
+
"128196": {
|
| 1575 |
+
"content": "<|reserved_special_token_188|>",
|
| 1576 |
+
"lstrip": false,
|
| 1577 |
+
"normalized": false,
|
| 1578 |
+
"rstrip": false,
|
| 1579 |
+
"single_word": false,
|
| 1580 |
+
"special": true
|
| 1581 |
+
},
|
| 1582 |
+
"128197": {
|
| 1583 |
+
"content": "<|reserved_special_token_189|>",
|
| 1584 |
+
"lstrip": false,
|
| 1585 |
+
"normalized": false,
|
| 1586 |
+
"rstrip": false,
|
| 1587 |
+
"single_word": false,
|
| 1588 |
+
"special": true
|
| 1589 |
+
},
|
| 1590 |
+
"128198": {
|
| 1591 |
+
"content": "<|reserved_special_token_190|>",
|
| 1592 |
+
"lstrip": false,
|
| 1593 |
+
"normalized": false,
|
| 1594 |
+
"rstrip": false,
|
| 1595 |
+
"single_word": false,
|
| 1596 |
+
"special": true
|
| 1597 |
+
},
|
| 1598 |
+
"128199": {
|
| 1599 |
+
"content": "<|reserved_special_token_191|>",
|
| 1600 |
+
"lstrip": false,
|
| 1601 |
+
"normalized": false,
|
| 1602 |
+
"rstrip": false,
|
| 1603 |
+
"single_word": false,
|
| 1604 |
+
"special": true
|
| 1605 |
+
},
|
| 1606 |
+
"128200": {
|
| 1607 |
+
"content": "<|reserved_special_token_192|>",
|
| 1608 |
+
"lstrip": false,
|
| 1609 |
+
"normalized": false,
|
| 1610 |
+
"rstrip": false,
|
| 1611 |
+
"single_word": false,
|
| 1612 |
+
"special": true
|
| 1613 |
+
},
|
| 1614 |
+
"128201": {
|
| 1615 |
+
"content": "<|reserved_special_token_193|>",
|
| 1616 |
+
"lstrip": false,
|
| 1617 |
+
"normalized": false,
|
| 1618 |
+
"rstrip": false,
|
| 1619 |
+
"single_word": false,
|
| 1620 |
+
"special": true
|
| 1621 |
+
},
|
| 1622 |
+
"128202": {
|
| 1623 |
+
"content": "<|reserved_special_token_194|>",
|
| 1624 |
+
"lstrip": false,
|
| 1625 |
+
"normalized": false,
|
| 1626 |
+
"rstrip": false,
|
| 1627 |
+
"single_word": false,
|
| 1628 |
+
"special": true
|
| 1629 |
+
},
|
| 1630 |
+
"128203": {
|
| 1631 |
+
"content": "<|reserved_special_token_195|>",
|
| 1632 |
+
"lstrip": false,
|
| 1633 |
+
"normalized": false,
|
| 1634 |
+
"rstrip": false,
|
| 1635 |
+
"single_word": false,
|
| 1636 |
+
"special": true
|
| 1637 |
+
},
|
| 1638 |
+
"128204": {
|
| 1639 |
+
"content": "<|reserved_special_token_196|>",
|
| 1640 |
+
"lstrip": false,
|
| 1641 |
+
"normalized": false,
|
| 1642 |
+
"rstrip": false,
|
| 1643 |
+
"single_word": false,
|
| 1644 |
+
"special": true
|
| 1645 |
+
},
|
| 1646 |
+
"128205": {
|
| 1647 |
+
"content": "<|reserved_special_token_197|>",
|
| 1648 |
+
"lstrip": false,
|
| 1649 |
+
"normalized": false,
|
| 1650 |
+
"rstrip": false,
|
| 1651 |
+
"single_word": false,
|
| 1652 |
+
"special": true
|
| 1653 |
+
},
|
| 1654 |
+
"128206": {
|
| 1655 |
+
"content": "<|reserved_special_token_198|>",
|
| 1656 |
+
"lstrip": false,
|
| 1657 |
+
"normalized": false,
|
| 1658 |
+
"rstrip": false,
|
| 1659 |
+
"single_word": false,
|
| 1660 |
+
"special": true
|
| 1661 |
+
},
|
| 1662 |
+
"128207": {
|
| 1663 |
+
"content": "<|reserved_special_token_199|>",
|
| 1664 |
+
"lstrip": false,
|
| 1665 |
+
"normalized": false,
|
| 1666 |
+
"rstrip": false,
|
| 1667 |
+
"single_word": false,
|
| 1668 |
+
"special": true
|
| 1669 |
+
},
|
| 1670 |
+
"128208": {
|
| 1671 |
+
"content": "<|reserved_special_token_200|>",
|
| 1672 |
+
"lstrip": false,
|
| 1673 |
+
"normalized": false,
|
| 1674 |
+
"rstrip": false,
|
| 1675 |
+
"single_word": false,
|
| 1676 |
+
"special": true
|
| 1677 |
+
},
|
| 1678 |
+
"128209": {
|
| 1679 |
+
"content": "<|reserved_special_token_201|>",
|
| 1680 |
+
"lstrip": false,
|
| 1681 |
+
"normalized": false,
|
| 1682 |
+
"rstrip": false,
|
| 1683 |
+
"single_word": false,
|
| 1684 |
+
"special": true
|
| 1685 |
+
},
|
| 1686 |
+
"128210": {
|
| 1687 |
+
"content": "<|reserved_special_token_202|>",
|
| 1688 |
+
"lstrip": false,
|
| 1689 |
+
"normalized": false,
|
| 1690 |
+
"rstrip": false,
|
| 1691 |
+
"single_word": false,
|
| 1692 |
+
"special": true
|
| 1693 |
+
},
|
| 1694 |
+
"128211": {
|
| 1695 |
+
"content": "<|reserved_special_token_203|>",
|
| 1696 |
+
"lstrip": false,
|
| 1697 |
+
"normalized": false,
|
| 1698 |
+
"rstrip": false,
|
| 1699 |
+
"single_word": false,
|
| 1700 |
+
"special": true
|
| 1701 |
+
},
|
| 1702 |
+
"128212": {
|
| 1703 |
+
"content": "<|reserved_special_token_204|>",
|
| 1704 |
+
"lstrip": false,
|
| 1705 |
+
"normalized": false,
|
| 1706 |
+
"rstrip": false,
|
| 1707 |
+
"single_word": false,
|
| 1708 |
+
"special": true
|
| 1709 |
+
},
|
| 1710 |
+
"128213": {
|
| 1711 |
+
"content": "<|reserved_special_token_205|>",
|
| 1712 |
+
"lstrip": false,
|
| 1713 |
+
"normalized": false,
|
| 1714 |
+
"rstrip": false,
|
| 1715 |
+
"single_word": false,
|
| 1716 |
+
"special": true
|
| 1717 |
+
},
|
| 1718 |
+
"128214": {
|
| 1719 |
+
"content": "<|reserved_special_token_206|>",
|
| 1720 |
+
"lstrip": false,
|
| 1721 |
+
"normalized": false,
|
| 1722 |
+
"rstrip": false,
|
| 1723 |
+
"single_word": false,
|
| 1724 |
+
"special": true
|
| 1725 |
+
},
|
| 1726 |
+
"128215": {
|
| 1727 |
+
"content": "<|reserved_special_token_207|>",
|
| 1728 |
+
"lstrip": false,
|
| 1729 |
+
"normalized": false,
|
| 1730 |
+
"rstrip": false,
|
| 1731 |
+
"single_word": false,
|
| 1732 |
+
"special": true
|
| 1733 |
+
},
|
| 1734 |
+
"128216": {
|
| 1735 |
+
"content": "<|reserved_special_token_208|>",
|
| 1736 |
+
"lstrip": false,
|
| 1737 |
+
"normalized": false,
|
| 1738 |
+
"rstrip": false,
|
| 1739 |
+
"single_word": false,
|
| 1740 |
+
"special": true
|
| 1741 |
+
},
|
| 1742 |
+
"128217": {
|
| 1743 |
+
"content": "<|reserved_special_token_209|>",
|
| 1744 |
+
"lstrip": false,
|
| 1745 |
+
"normalized": false,
|
| 1746 |
+
"rstrip": false,
|
| 1747 |
+
"single_word": false,
|
| 1748 |
+
"special": true
|
| 1749 |
+
},
|
| 1750 |
+
"128218": {
|
| 1751 |
+
"content": "<|reserved_special_token_210|>",
|
| 1752 |
+
"lstrip": false,
|
| 1753 |
+
"normalized": false,
|
| 1754 |
+
"rstrip": false,
|
| 1755 |
+
"single_word": false,
|
| 1756 |
+
"special": true
|
| 1757 |
+
},
|
| 1758 |
+
"128219": {
|
| 1759 |
+
"content": "<|reserved_special_token_211|>",
|
| 1760 |
+
"lstrip": false,
|
| 1761 |
+
"normalized": false,
|
| 1762 |
+
"rstrip": false,
|
| 1763 |
+
"single_word": false,
|
| 1764 |
+
"special": true
|
| 1765 |
+
},
|
| 1766 |
+
"128220": {
|
| 1767 |
+
"content": "<|reserved_special_token_212|>",
|
| 1768 |
+
"lstrip": false,
|
| 1769 |
+
"normalized": false,
|
| 1770 |
+
"rstrip": false,
|
| 1771 |
+
"single_word": false,
|
| 1772 |
+
"special": true
|
| 1773 |
+
},
|
| 1774 |
+
"128221": {
|
| 1775 |
+
"content": "<|reserved_special_token_213|>",
|
| 1776 |
+
"lstrip": false,
|
| 1777 |
+
"normalized": false,
|
| 1778 |
+
"rstrip": false,
|
| 1779 |
+
"single_word": false,
|
| 1780 |
+
"special": true
|
| 1781 |
+
},
|
| 1782 |
+
"128222": {
|
| 1783 |
+
"content": "<|reserved_special_token_214|>",
|
| 1784 |
+
"lstrip": false,
|
| 1785 |
+
"normalized": false,
|
| 1786 |
+
"rstrip": false,
|
| 1787 |
+
"single_word": false,
|
| 1788 |
+
"special": true
|
| 1789 |
+
},
|
| 1790 |
+
"128223": {
|
| 1791 |
+
"content": "<|reserved_special_token_215|>",
|
| 1792 |
+
"lstrip": false,
|
| 1793 |
+
"normalized": false,
|
| 1794 |
+
"rstrip": false,
|
| 1795 |
+
"single_word": false,
|
| 1796 |
+
"special": true
|
| 1797 |
+
},
|
| 1798 |
+
"128224": {
|
| 1799 |
+
"content": "<|reserved_special_token_216|>",
|
| 1800 |
+
"lstrip": false,
|
| 1801 |
+
"normalized": false,
|
| 1802 |
+
"rstrip": false,
|
| 1803 |
+
"single_word": false,
|
| 1804 |
+
"special": true
|
| 1805 |
+
},
|
| 1806 |
+
"128225": {
|
| 1807 |
+
"content": "<|reserved_special_token_217|>",
|
| 1808 |
+
"lstrip": false,
|
| 1809 |
+
"normalized": false,
|
| 1810 |
+
"rstrip": false,
|
| 1811 |
+
"single_word": false,
|
| 1812 |
+
"special": true
|
| 1813 |
+
},
|
| 1814 |
+
"128226": {
|
| 1815 |
+
"content": "<|reserved_special_token_218|>",
|
| 1816 |
+
"lstrip": false,
|
| 1817 |
+
"normalized": false,
|
| 1818 |
+
"rstrip": false,
|
| 1819 |
+
"single_word": false,
|
| 1820 |
+
"special": true
|
| 1821 |
+
},
|
| 1822 |
+
"128227": {
|
| 1823 |
+
"content": "<|reserved_special_token_219|>",
|
| 1824 |
+
"lstrip": false,
|
| 1825 |
+
"normalized": false,
|
| 1826 |
+
"rstrip": false,
|
| 1827 |
+
"single_word": false,
|
| 1828 |
+
"special": true
|
| 1829 |
+
},
|
| 1830 |
+
"128228": {
|
| 1831 |
+
"content": "<|reserved_special_token_220|>",
|
| 1832 |
+
"lstrip": false,
|
| 1833 |
+
"normalized": false,
|
| 1834 |
+
"rstrip": false,
|
| 1835 |
+
"single_word": false,
|
| 1836 |
+
"special": true
|
| 1837 |
+
},
|
| 1838 |
+
"128229": {
|
| 1839 |
+
"content": "<|reserved_special_token_221|>",
|
| 1840 |
+
"lstrip": false,
|
| 1841 |
+
"normalized": false,
|
| 1842 |
+
"rstrip": false,
|
| 1843 |
+
"single_word": false,
|
| 1844 |
+
"special": true
|
| 1845 |
+
},
|
| 1846 |
+
"128230": {
|
| 1847 |
+
"content": "<|reserved_special_token_222|>",
|
| 1848 |
+
"lstrip": false,
|
| 1849 |
+
"normalized": false,
|
| 1850 |
+
"rstrip": false,
|
| 1851 |
+
"single_word": false,
|
| 1852 |
+
"special": true
|
| 1853 |
+
},
|
| 1854 |
+
"128231": {
|
| 1855 |
+
"content": "<|reserved_special_token_223|>",
|
| 1856 |
+
"lstrip": false,
|
| 1857 |
+
"normalized": false,
|
| 1858 |
+
"rstrip": false,
|
| 1859 |
+
"single_word": false,
|
| 1860 |
+
"special": true
|
| 1861 |
+
},
|
| 1862 |
+
"128232": {
|
| 1863 |
+
"content": "<|reserved_special_token_224|>",
|
| 1864 |
+
"lstrip": false,
|
| 1865 |
+
"normalized": false,
|
| 1866 |
+
"rstrip": false,
|
| 1867 |
+
"single_word": false,
|
| 1868 |
+
"special": true
|
| 1869 |
+
},
|
| 1870 |
+
"128233": {
|
| 1871 |
+
"content": "<|reserved_special_token_225|>",
|
| 1872 |
+
"lstrip": false,
|
| 1873 |
+
"normalized": false,
|
| 1874 |
+
"rstrip": false,
|
| 1875 |
+
"single_word": false,
|
| 1876 |
+
"special": true
|
| 1877 |
+
},
|
| 1878 |
+
"128234": {
|
| 1879 |
+
"content": "<|reserved_special_token_226|>",
|
| 1880 |
+
"lstrip": false,
|
| 1881 |
+
"normalized": false,
|
| 1882 |
+
"rstrip": false,
|
| 1883 |
+
"single_word": false,
|
| 1884 |
+
"special": true
|
| 1885 |
+
},
|
| 1886 |
+
"128235": {
|
| 1887 |
+
"content": "<|reserved_special_token_227|>",
|
| 1888 |
+
"lstrip": false,
|
| 1889 |
+
"normalized": false,
|
| 1890 |
+
"rstrip": false,
|
| 1891 |
+
"single_word": false,
|
| 1892 |
+
"special": true
|
| 1893 |
+
},
|
| 1894 |
+
"128236": {
|
| 1895 |
+
"content": "<|reserved_special_token_228|>",
|
| 1896 |
+
"lstrip": false,
|
| 1897 |
+
"normalized": false,
|
| 1898 |
+
"rstrip": false,
|
| 1899 |
+
"single_word": false,
|
| 1900 |
+
"special": true
|
| 1901 |
+
},
|
| 1902 |
+
"128237": {
|
| 1903 |
+
"content": "<|reserved_special_token_229|>",
|
| 1904 |
+
"lstrip": false,
|
| 1905 |
+
"normalized": false,
|
| 1906 |
+
"rstrip": false,
|
| 1907 |
+
"single_word": false,
|
| 1908 |
+
"special": true
|
| 1909 |
+
},
|
| 1910 |
+
"128238": {
|
| 1911 |
+
"content": "<|reserved_special_token_230|>",
|
| 1912 |
+
"lstrip": false,
|
| 1913 |
+
"normalized": false,
|
| 1914 |
+
"rstrip": false,
|
| 1915 |
+
"single_word": false,
|
| 1916 |
+
"special": true
|
| 1917 |
+
},
|
| 1918 |
+
"128239": {
|
| 1919 |
+
"content": "<|reserved_special_token_231|>",
|
| 1920 |
+
"lstrip": false,
|
| 1921 |
+
"normalized": false,
|
| 1922 |
+
"rstrip": false,
|
| 1923 |
+
"single_word": false,
|
| 1924 |
+
"special": true
|
| 1925 |
+
},
|
| 1926 |
+
"128240": {
|
| 1927 |
+
"content": "<|reserved_special_token_232|>",
|
| 1928 |
+
"lstrip": false,
|
| 1929 |
+
"normalized": false,
|
| 1930 |
+
"rstrip": false,
|
| 1931 |
+
"single_word": false,
|
| 1932 |
+
"special": true
|
| 1933 |
+
},
|
| 1934 |
+
"128241": {
|
| 1935 |
+
"content": "<|reserved_special_token_233|>",
|
| 1936 |
+
"lstrip": false,
|
| 1937 |
+
"normalized": false,
|
| 1938 |
+
"rstrip": false,
|
| 1939 |
+
"single_word": false,
|
| 1940 |
+
"special": true
|
| 1941 |
+
},
|
| 1942 |
+
"128242": {
|
| 1943 |
+
"content": "<|reserved_special_token_234|>",
|
| 1944 |
+
"lstrip": false,
|
| 1945 |
+
"normalized": false,
|
| 1946 |
+
"rstrip": false,
|
| 1947 |
+
"single_word": false,
|
| 1948 |
+
"special": true
|
| 1949 |
+
},
|
| 1950 |
+
"128243": {
|
| 1951 |
+
"content": "<|reserved_special_token_235|>",
|
| 1952 |
+
"lstrip": false,
|
| 1953 |
+
"normalized": false,
|
| 1954 |
+
"rstrip": false,
|
| 1955 |
+
"single_word": false,
|
| 1956 |
+
"special": true
|
| 1957 |
+
},
|
| 1958 |
+
"128244": {
|
| 1959 |
+
"content": "<|reserved_special_token_236|>",
|
| 1960 |
+
"lstrip": false,
|
| 1961 |
+
"normalized": false,
|
| 1962 |
+
"rstrip": false,
|
| 1963 |
+
"single_word": false,
|
| 1964 |
+
"special": true
|
| 1965 |
+
},
|
| 1966 |
+
"128245": {
|
| 1967 |
+
"content": "<|reserved_special_token_237|>",
|
| 1968 |
+
"lstrip": false,
|
| 1969 |
+
"normalized": false,
|
| 1970 |
+
"rstrip": false,
|
| 1971 |
+
"single_word": false,
|
| 1972 |
+
"special": true
|
| 1973 |
+
},
|
| 1974 |
+
"128246": {
|
| 1975 |
+
"content": "<|reserved_special_token_238|>",
|
| 1976 |
+
"lstrip": false,
|
| 1977 |
+
"normalized": false,
|
| 1978 |
+
"rstrip": false,
|
| 1979 |
+
"single_word": false,
|
| 1980 |
+
"special": true
|
| 1981 |
+
},
|
| 1982 |
+
"128247": {
|
| 1983 |
+
"content": "<|reserved_special_token_239|>",
|
| 1984 |
+
"lstrip": false,
|
| 1985 |
+
"normalized": false,
|
| 1986 |
+
"rstrip": false,
|
| 1987 |
+
"single_word": false,
|
| 1988 |
+
"special": true
|
| 1989 |
+
},
|
| 1990 |
+
"128248": {
|
| 1991 |
+
"content": "<|reserved_special_token_240|>",
|
| 1992 |
+
"lstrip": false,
|
| 1993 |
+
"normalized": false,
|
| 1994 |
+
"rstrip": false,
|
| 1995 |
+
"single_word": false,
|
| 1996 |
+
"special": true
|
| 1997 |
+
},
|
| 1998 |
+
"128249": {
|
| 1999 |
+
"content": "<|reserved_special_token_241|>",
|
| 2000 |
+
"lstrip": false,
|
| 2001 |
+
"normalized": false,
|
| 2002 |
+
"rstrip": false,
|
| 2003 |
+
"single_word": false,
|
| 2004 |
+
"special": true
|
| 2005 |
+
},
|
| 2006 |
+
"128250": {
|
| 2007 |
+
"content": "<|reserved_special_token_242|>",
|
| 2008 |
+
"lstrip": false,
|
| 2009 |
+
"normalized": false,
|
| 2010 |
+
"rstrip": false,
|
| 2011 |
+
"single_word": false,
|
| 2012 |
+
"special": true
|
| 2013 |
+
},
|
| 2014 |
+
"128251": {
|
| 2015 |
+
"content": "<|reserved_special_token_243|>",
|
| 2016 |
+
"lstrip": false,
|
| 2017 |
+
"normalized": false,
|
| 2018 |
+
"rstrip": false,
|
| 2019 |
+
"single_word": false,
|
| 2020 |
+
"special": true
|
| 2021 |
+
},
|
| 2022 |
+
"128252": {
|
| 2023 |
+
"content": "<|reserved_special_token_244|>",
|
| 2024 |
+
"lstrip": false,
|
| 2025 |
+
"normalized": false,
|
| 2026 |
+
"rstrip": false,
|
| 2027 |
+
"single_word": false,
|
| 2028 |
+
"special": true
|
| 2029 |
+
},
|
| 2030 |
+
"128253": {
|
| 2031 |
+
"content": "<|reserved_special_token_245|>",
|
| 2032 |
+
"lstrip": false,
|
| 2033 |
+
"normalized": false,
|
| 2034 |
+
"rstrip": false,
|
| 2035 |
+
"single_word": false,
|
| 2036 |
+
"special": true
|
| 2037 |
+
},
|
| 2038 |
+
"128254": {
|
| 2039 |
+
"content": "<|reserved_special_token_246|>",
|
| 2040 |
+
"lstrip": false,
|
| 2041 |
+
"normalized": false,
|
| 2042 |
+
"rstrip": false,
|
| 2043 |
+
"single_word": false,
|
| 2044 |
+
"special": true
|
| 2045 |
+
},
|
| 2046 |
+
"128255": {
|
| 2047 |
+
"content": "<|reserved_special_token_247|>",
|
| 2048 |
+
"lstrip": false,
|
| 2049 |
+
"normalized": false,
|
| 2050 |
+
"rstrip": false,
|
| 2051 |
+
"single_word": false,
|
| 2052 |
+
"special": true
|
| 2053 |
+
}
|
| 2054 |
+
},
|
| 2055 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
| 2056 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<|User|>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<|Assistant|><|tool▁calls▁begin|><|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{%- set ns.is_first = true -%}{%- else %}{{'\\n' + '<|tool▁call▁begin|>' + tool['type'] + '<|tool▁sep|>' + tool['function']['name'] + '\\n' + '```json' + '\\n' + tool['function']['arguments'] + '\\n' + '```' + '<|tool▁call▁end|>'}}{{'<|tool▁calls▁end|><|end▁of▁sentence|>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<|tool▁outputs▁end|>' + message['content'] + '<|end▁of▁sentence|>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<|Assistant|>' + content + '<|end▁of▁sentence|>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<|tool▁outputs▁begin|><|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\\n<|tool▁output▁begin|>' + message['content'] + '<|tool▁output▁end|>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<|tool▁outputs▁end|>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<|Assistant|><think>\\n'}}{% endif %}",
|
| 2057 |
+
"clean_up_tokenization_spaces": false,
|
| 2058 |
+
"eos_token": "<|end▁of▁sentence|>",
|
| 2059 |
+
"extra_special_tokens": {},
|
| 2060 |
+
"legacy": true,
|
| 2061 |
+
"model_max_length": 16384,
|
| 2062 |
+
"pad_token": "<|end▁of▁sentence|>",
|
| 2063 |
+
"sp_model_kwargs": {},
|
| 2064 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 2065 |
+
"unk_token": null,
|
| 2066 |
+
"use_default_system_prompt": false
|
| 2067 |
+
}
|