Upload 10 files
Browse files- README.md +202 -0
- adapter_config.json +34 -0
- added_tokens.json +128 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +157 -0
- tokenizer_config.json +1171 -0
- trainer_state.json +850 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: google/byt5-small
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "google/byt5-small",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 1024,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 512,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q",
|
| 24 |
+
"wo",
|
| 25 |
+
"wi_1",
|
| 26 |
+
"o",
|
| 27 |
+
"wi_0",
|
| 28 |
+
"k",
|
| 29 |
+
"v"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "SEQ_2_SEQ_LM",
|
| 32 |
+
"use_dora": true,
|
| 33 |
+
"use_rslora": true
|
| 34 |
+
}
|
added_tokens.json
ADDED
|
@@ -0,0 +1,128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<extra_id_0>": 259,
|
| 3 |
+
"<extra_id_100>": 359,
|
| 4 |
+
"<extra_id_101>": 360,
|
| 5 |
+
"<extra_id_102>": 361,
|
| 6 |
+
"<extra_id_103>": 362,
|
| 7 |
+
"<extra_id_104>": 363,
|
| 8 |
+
"<extra_id_105>": 364,
|
| 9 |
+
"<extra_id_106>": 365,
|
| 10 |
+
"<extra_id_107>": 366,
|
| 11 |
+
"<extra_id_108>": 367,
|
| 12 |
+
"<extra_id_109>": 368,
|
| 13 |
+
"<extra_id_10>": 269,
|
| 14 |
+
"<extra_id_110>": 369,
|
| 15 |
+
"<extra_id_111>": 370,
|
| 16 |
+
"<extra_id_112>": 371,
|
| 17 |
+
"<extra_id_113>": 372,
|
| 18 |
+
"<extra_id_114>": 373,
|
| 19 |
+
"<extra_id_115>": 374,
|
| 20 |
+
"<extra_id_116>": 375,
|
| 21 |
+
"<extra_id_117>": 376,
|
| 22 |
+
"<extra_id_118>": 377,
|
| 23 |
+
"<extra_id_119>": 378,
|
| 24 |
+
"<extra_id_11>": 270,
|
| 25 |
+
"<extra_id_120>": 379,
|
| 26 |
+
"<extra_id_121>": 380,
|
| 27 |
+
"<extra_id_122>": 381,
|
| 28 |
+
"<extra_id_123>": 382,
|
| 29 |
+
"<extra_id_124>": 383,
|
| 30 |
+
"<extra_id_12>": 271,
|
| 31 |
+
"<extra_id_13>": 272,
|
| 32 |
+
"<extra_id_14>": 273,
|
| 33 |
+
"<extra_id_15>": 274,
|
| 34 |
+
"<extra_id_16>": 275,
|
| 35 |
+
"<extra_id_17>": 276,
|
| 36 |
+
"<extra_id_18>": 277,
|
| 37 |
+
"<extra_id_19>": 278,
|
| 38 |
+
"<extra_id_1>": 260,
|
| 39 |
+
"<extra_id_20>": 279,
|
| 40 |
+
"<extra_id_21>": 280,
|
| 41 |
+
"<extra_id_22>": 281,
|
| 42 |
+
"<extra_id_23>": 282,
|
| 43 |
+
"<extra_id_24>": 283,
|
| 44 |
+
"<extra_id_25>": 284,
|
| 45 |
+
"<extra_id_26>": 285,
|
| 46 |
+
"<extra_id_27>": 286,
|
| 47 |
+
"<extra_id_28>": 287,
|
| 48 |
+
"<extra_id_29>": 288,
|
| 49 |
+
"<extra_id_2>": 261,
|
| 50 |
+
"<extra_id_30>": 289,
|
| 51 |
+
"<extra_id_31>": 290,
|
| 52 |
+
"<extra_id_32>": 291,
|
| 53 |
+
"<extra_id_33>": 292,
|
| 54 |
+
"<extra_id_34>": 293,
|
| 55 |
+
"<extra_id_35>": 294,
|
| 56 |
+
"<extra_id_36>": 295,
|
| 57 |
+
"<extra_id_37>": 296,
|
| 58 |
+
"<extra_id_38>": 297,
|
| 59 |
+
"<extra_id_39>": 298,
|
| 60 |
+
"<extra_id_3>": 262,
|
| 61 |
+
"<extra_id_40>": 299,
|
| 62 |
+
"<extra_id_41>": 300,
|
| 63 |
+
"<extra_id_42>": 301,
|
| 64 |
+
"<extra_id_43>": 302,
|
| 65 |
+
"<extra_id_44>": 303,
|
| 66 |
+
"<extra_id_45>": 304,
|
| 67 |
+
"<extra_id_46>": 305,
|
| 68 |
+
"<extra_id_47>": 306,
|
| 69 |
+
"<extra_id_48>": 307,
|
| 70 |
+
"<extra_id_49>": 308,
|
| 71 |
+
"<extra_id_4>": 263,
|
| 72 |
+
"<extra_id_50>": 309,
|
| 73 |
+
"<extra_id_51>": 310,
|
| 74 |
+
"<extra_id_52>": 311,
|
| 75 |
+
"<extra_id_53>": 312,
|
| 76 |
+
"<extra_id_54>": 313,
|
| 77 |
+
"<extra_id_55>": 314,
|
| 78 |
+
"<extra_id_56>": 315,
|
| 79 |
+
"<extra_id_57>": 316,
|
| 80 |
+
"<extra_id_58>": 317,
|
| 81 |
+
"<extra_id_59>": 318,
|
| 82 |
+
"<extra_id_5>": 264,
|
| 83 |
+
"<extra_id_60>": 319,
|
| 84 |
+
"<extra_id_61>": 320,
|
| 85 |
+
"<extra_id_62>": 321,
|
| 86 |
+
"<extra_id_63>": 322,
|
| 87 |
+
"<extra_id_64>": 323,
|
| 88 |
+
"<extra_id_65>": 324,
|
| 89 |
+
"<extra_id_66>": 325,
|
| 90 |
+
"<extra_id_67>": 326,
|
| 91 |
+
"<extra_id_68>": 327,
|
| 92 |
+
"<extra_id_69>": 328,
|
| 93 |
+
"<extra_id_6>": 265,
|
| 94 |
+
"<extra_id_70>": 329,
|
| 95 |
+
"<extra_id_71>": 330,
|
| 96 |
+
"<extra_id_72>": 331,
|
| 97 |
+
"<extra_id_73>": 332,
|
| 98 |
+
"<extra_id_74>": 333,
|
| 99 |
+
"<extra_id_75>": 334,
|
| 100 |
+
"<extra_id_76>": 335,
|
| 101 |
+
"<extra_id_77>": 336,
|
| 102 |
+
"<extra_id_78>": 337,
|
| 103 |
+
"<extra_id_79>": 338,
|
| 104 |
+
"<extra_id_7>": 266,
|
| 105 |
+
"<extra_id_80>": 339,
|
| 106 |
+
"<extra_id_81>": 340,
|
| 107 |
+
"<extra_id_82>": 341,
|
| 108 |
+
"<extra_id_83>": 342,
|
| 109 |
+
"<extra_id_84>": 343,
|
| 110 |
+
"<extra_id_85>": 344,
|
| 111 |
+
"<extra_id_86>": 345,
|
| 112 |
+
"<extra_id_87>": 346,
|
| 113 |
+
"<extra_id_88>": 347,
|
| 114 |
+
"<extra_id_89>": 348,
|
| 115 |
+
"<extra_id_8>": 267,
|
| 116 |
+
"<extra_id_90>": 349,
|
| 117 |
+
"<extra_id_91>": 350,
|
| 118 |
+
"<extra_id_92>": 351,
|
| 119 |
+
"<extra_id_93>": 352,
|
| 120 |
+
"<extra_id_94>": 353,
|
| 121 |
+
"<extra_id_95>": 354,
|
| 122 |
+
"<extra_id_96>": 355,
|
| 123 |
+
"<extra_id_97>": 356,
|
| 124 |
+
"<extra_id_98>": 357,
|
| 125 |
+
"<extra_id_99>": 358,
|
| 126 |
+
"<extra_id_9>": 268,
|
| 127 |
+
"<|SOP|>": 384
|
| 128 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a54962b57e277d0f1667817f59f3653c9e05bdeb81d95a47d8ea1d14312efb1
|
| 3 |
+
size 403241300
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6d7f01ea766cbdd5cacd8621efedaa9110a9155783e94468b2f9cbb194d0b84
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12041b1c819da5737aec67c135279dcf9c5643522724d2d7289e6e335b7ba4b9
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,157 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>",
|
| 99 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>",
|
| 103 |
+
"<extra_id_100>",
|
| 104 |
+
"<extra_id_101>",
|
| 105 |
+
"<extra_id_102>",
|
| 106 |
+
"<extra_id_103>",
|
| 107 |
+
"<extra_id_104>",
|
| 108 |
+
"<extra_id_105>",
|
| 109 |
+
"<extra_id_106>",
|
| 110 |
+
"<extra_id_107>",
|
| 111 |
+
"<extra_id_108>",
|
| 112 |
+
"<extra_id_109>",
|
| 113 |
+
"<extra_id_110>",
|
| 114 |
+
"<extra_id_111>",
|
| 115 |
+
"<extra_id_112>",
|
| 116 |
+
"<extra_id_113>",
|
| 117 |
+
"<extra_id_114>",
|
| 118 |
+
"<extra_id_115>",
|
| 119 |
+
"<extra_id_116>",
|
| 120 |
+
"<extra_id_117>",
|
| 121 |
+
"<extra_id_118>",
|
| 122 |
+
"<extra_id_119>",
|
| 123 |
+
"<extra_id_120>",
|
| 124 |
+
"<extra_id_121>",
|
| 125 |
+
"<extra_id_122>",
|
| 126 |
+
"<extra_id_123>",
|
| 127 |
+
"<extra_id_124>",
|
| 128 |
+
{
|
| 129 |
+
"content": "<|SOP|>",
|
| 130 |
+
"lstrip": false,
|
| 131 |
+
"normalized": false,
|
| 132 |
+
"rstrip": false,
|
| 133 |
+
"single_word": false
|
| 134 |
+
}
|
| 135 |
+
],
|
| 136 |
+
"eos_token": {
|
| 137 |
+
"content": "</s>",
|
| 138 |
+
"lstrip": false,
|
| 139 |
+
"normalized": true,
|
| 140 |
+
"rstrip": false,
|
| 141 |
+
"single_word": false
|
| 142 |
+
},
|
| 143 |
+
"pad_token": {
|
| 144 |
+
"content": "<pad>",
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"normalized": true,
|
| 147 |
+
"rstrip": false,
|
| 148 |
+
"single_word": false
|
| 149 |
+
},
|
| 150 |
+
"unk_token": {
|
| 151 |
+
"content": "<unk>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false
|
| 156 |
+
}
|
| 157 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,1171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"259": {
|
| 28 |
+
"content": "<extra_id_0>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"260": {
|
| 36 |
+
"content": "<extra_id_1>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"261": {
|
| 44 |
+
"content": "<extra_id_2>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"262": {
|
| 52 |
+
"content": "<extra_id_3>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"263": {
|
| 60 |
+
"content": "<extra_id_4>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"264": {
|
| 68 |
+
"content": "<extra_id_5>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"265": {
|
| 76 |
+
"content": "<extra_id_6>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"266": {
|
| 84 |
+
"content": "<extra_id_7>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"267": {
|
| 92 |
+
"content": "<extra_id_8>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"268": {
|
| 100 |
+
"content": "<extra_id_9>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"269": {
|
| 108 |
+
"content": "<extra_id_10>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"270": {
|
| 116 |
+
"content": "<extra_id_11>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"271": {
|
| 124 |
+
"content": "<extra_id_12>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"272": {
|
| 132 |
+
"content": "<extra_id_13>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"273": {
|
| 140 |
+
"content": "<extra_id_14>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"274": {
|
| 148 |
+
"content": "<extra_id_15>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"275": {
|
| 156 |
+
"content": "<extra_id_16>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"276": {
|
| 164 |
+
"content": "<extra_id_17>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"277": {
|
| 172 |
+
"content": "<extra_id_18>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"278": {
|
| 180 |
+
"content": "<extra_id_19>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"279": {
|
| 188 |
+
"content": "<extra_id_20>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"280": {
|
| 196 |
+
"content": "<extra_id_21>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"281": {
|
| 204 |
+
"content": "<extra_id_22>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"282": {
|
| 212 |
+
"content": "<extra_id_23>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"283": {
|
| 220 |
+
"content": "<extra_id_24>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"284": {
|
| 228 |
+
"content": "<extra_id_25>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"285": {
|
| 236 |
+
"content": "<extra_id_26>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"286": {
|
| 244 |
+
"content": "<extra_id_27>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"287": {
|
| 252 |
+
"content": "<extra_id_28>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"288": {
|
| 260 |
+
"content": "<extra_id_29>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"289": {
|
| 268 |
+
"content": "<extra_id_30>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"290": {
|
| 276 |
+
"content": "<extra_id_31>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"291": {
|
| 284 |
+
"content": "<extra_id_32>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"292": {
|
| 292 |
+
"content": "<extra_id_33>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"293": {
|
| 300 |
+
"content": "<extra_id_34>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"294": {
|
| 308 |
+
"content": "<extra_id_35>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"295": {
|
| 316 |
+
"content": "<extra_id_36>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"296": {
|
| 324 |
+
"content": "<extra_id_37>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"297": {
|
| 332 |
+
"content": "<extra_id_38>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"298": {
|
| 340 |
+
"content": "<extra_id_39>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"299": {
|
| 348 |
+
"content": "<extra_id_40>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"300": {
|
| 356 |
+
"content": "<extra_id_41>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"301": {
|
| 364 |
+
"content": "<extra_id_42>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"302": {
|
| 372 |
+
"content": "<extra_id_43>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"303": {
|
| 380 |
+
"content": "<extra_id_44>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"304": {
|
| 388 |
+
"content": "<extra_id_45>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"305": {
|
| 396 |
+
"content": "<extra_id_46>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"306": {
|
| 404 |
+
"content": "<extra_id_47>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"307": {
|
| 412 |
+
"content": "<extra_id_48>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"308": {
|
| 420 |
+
"content": "<extra_id_49>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"309": {
|
| 428 |
+
"content": "<extra_id_50>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"310": {
|
| 436 |
+
"content": "<extra_id_51>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"311": {
|
| 444 |
+
"content": "<extra_id_52>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"312": {
|
| 452 |
+
"content": "<extra_id_53>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"313": {
|
| 460 |
+
"content": "<extra_id_54>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"314": {
|
| 468 |
+
"content": "<extra_id_55>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"315": {
|
| 476 |
+
"content": "<extra_id_56>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"316": {
|
| 484 |
+
"content": "<extra_id_57>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"317": {
|
| 492 |
+
"content": "<extra_id_58>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"318": {
|
| 500 |
+
"content": "<extra_id_59>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"319": {
|
| 508 |
+
"content": "<extra_id_60>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"320": {
|
| 516 |
+
"content": "<extra_id_61>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"321": {
|
| 524 |
+
"content": "<extra_id_62>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"322": {
|
| 532 |
+
"content": "<extra_id_63>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"323": {
|
| 540 |
+
"content": "<extra_id_64>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"324": {
|
| 548 |
+
"content": "<extra_id_65>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"325": {
|
| 556 |
+
"content": "<extra_id_66>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"326": {
|
| 564 |
+
"content": "<extra_id_67>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"327": {
|
| 572 |
+
"content": "<extra_id_68>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"328": {
|
| 580 |
+
"content": "<extra_id_69>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"329": {
|
| 588 |
+
"content": "<extra_id_70>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"330": {
|
| 596 |
+
"content": "<extra_id_71>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"331": {
|
| 604 |
+
"content": "<extra_id_72>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"332": {
|
| 612 |
+
"content": "<extra_id_73>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"333": {
|
| 620 |
+
"content": "<extra_id_74>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"334": {
|
| 628 |
+
"content": "<extra_id_75>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"335": {
|
| 636 |
+
"content": "<extra_id_76>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"336": {
|
| 644 |
+
"content": "<extra_id_77>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"337": {
|
| 652 |
+
"content": "<extra_id_78>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"338": {
|
| 660 |
+
"content": "<extra_id_79>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"339": {
|
| 668 |
+
"content": "<extra_id_80>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"340": {
|
| 676 |
+
"content": "<extra_id_81>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"341": {
|
| 684 |
+
"content": "<extra_id_82>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"342": {
|
| 692 |
+
"content": "<extra_id_83>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"343": {
|
| 700 |
+
"content": "<extra_id_84>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"344": {
|
| 708 |
+
"content": "<extra_id_85>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"345": {
|
| 716 |
+
"content": "<extra_id_86>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"346": {
|
| 724 |
+
"content": "<extra_id_87>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"347": {
|
| 732 |
+
"content": "<extra_id_88>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"348": {
|
| 740 |
+
"content": "<extra_id_89>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"349": {
|
| 748 |
+
"content": "<extra_id_90>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"350": {
|
| 756 |
+
"content": "<extra_id_91>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"351": {
|
| 764 |
+
"content": "<extra_id_92>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"352": {
|
| 772 |
+
"content": "<extra_id_93>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"353": {
|
| 780 |
+
"content": "<extra_id_94>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"354": {
|
| 788 |
+
"content": "<extra_id_95>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"355": {
|
| 796 |
+
"content": "<extra_id_96>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"356": {
|
| 804 |
+
"content": "<extra_id_97>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"357": {
|
| 812 |
+
"content": "<extra_id_98>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"358": {
|
| 820 |
+
"content": "<extra_id_99>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"359": {
|
| 828 |
+
"content": "<extra_id_100>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"360": {
|
| 836 |
+
"content": "<extra_id_101>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"361": {
|
| 844 |
+
"content": "<extra_id_102>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"362": {
|
| 852 |
+
"content": "<extra_id_103>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"363": {
|
| 860 |
+
"content": "<extra_id_104>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"364": {
|
| 868 |
+
"content": "<extra_id_105>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"365": {
|
| 876 |
+
"content": "<extra_id_106>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"366": {
|
| 884 |
+
"content": "<extra_id_107>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"367": {
|
| 892 |
+
"content": "<extra_id_108>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"368": {
|
| 900 |
+
"content": "<extra_id_109>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"369": {
|
| 908 |
+
"content": "<extra_id_110>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"370": {
|
| 916 |
+
"content": "<extra_id_111>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"371": {
|
| 924 |
+
"content": "<extra_id_112>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"372": {
|
| 932 |
+
"content": "<extra_id_113>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"373": {
|
| 940 |
+
"content": "<extra_id_114>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"374": {
|
| 948 |
+
"content": "<extra_id_115>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"375": {
|
| 956 |
+
"content": "<extra_id_116>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"376": {
|
| 964 |
+
"content": "<extra_id_117>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"377": {
|
| 972 |
+
"content": "<extra_id_118>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"378": {
|
| 980 |
+
"content": "<extra_id_119>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"379": {
|
| 988 |
+
"content": "<extra_id_120>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"380": {
|
| 996 |
+
"content": "<extra_id_121>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"381": {
|
| 1004 |
+
"content": "<extra_id_122>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"382": {
|
| 1012 |
+
"content": "<extra_id_123>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"383": {
|
| 1020 |
+
"content": "<extra_id_124>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"384": {
|
| 1028 |
+
"content": "<|SOP|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
}
|
| 1035 |
+
},
|
| 1036 |
+
"additional_special_tokens": [
|
| 1037 |
+
"<extra_id_0>",
|
| 1038 |
+
"<extra_id_1>",
|
| 1039 |
+
"<extra_id_2>",
|
| 1040 |
+
"<extra_id_3>",
|
| 1041 |
+
"<extra_id_4>",
|
| 1042 |
+
"<extra_id_5>",
|
| 1043 |
+
"<extra_id_6>",
|
| 1044 |
+
"<extra_id_7>",
|
| 1045 |
+
"<extra_id_8>",
|
| 1046 |
+
"<extra_id_9>",
|
| 1047 |
+
"<extra_id_10>",
|
| 1048 |
+
"<extra_id_11>",
|
| 1049 |
+
"<extra_id_12>",
|
| 1050 |
+
"<extra_id_13>",
|
| 1051 |
+
"<extra_id_14>",
|
| 1052 |
+
"<extra_id_15>",
|
| 1053 |
+
"<extra_id_16>",
|
| 1054 |
+
"<extra_id_17>",
|
| 1055 |
+
"<extra_id_18>",
|
| 1056 |
+
"<extra_id_19>",
|
| 1057 |
+
"<extra_id_20>",
|
| 1058 |
+
"<extra_id_21>",
|
| 1059 |
+
"<extra_id_22>",
|
| 1060 |
+
"<extra_id_23>",
|
| 1061 |
+
"<extra_id_24>",
|
| 1062 |
+
"<extra_id_25>",
|
| 1063 |
+
"<extra_id_26>",
|
| 1064 |
+
"<extra_id_27>",
|
| 1065 |
+
"<extra_id_28>",
|
| 1066 |
+
"<extra_id_29>",
|
| 1067 |
+
"<extra_id_30>",
|
| 1068 |
+
"<extra_id_31>",
|
| 1069 |
+
"<extra_id_32>",
|
| 1070 |
+
"<extra_id_33>",
|
| 1071 |
+
"<extra_id_34>",
|
| 1072 |
+
"<extra_id_35>",
|
| 1073 |
+
"<extra_id_36>",
|
| 1074 |
+
"<extra_id_37>",
|
| 1075 |
+
"<extra_id_38>",
|
| 1076 |
+
"<extra_id_39>",
|
| 1077 |
+
"<extra_id_40>",
|
| 1078 |
+
"<extra_id_41>",
|
| 1079 |
+
"<extra_id_42>",
|
| 1080 |
+
"<extra_id_43>",
|
| 1081 |
+
"<extra_id_44>",
|
| 1082 |
+
"<extra_id_45>",
|
| 1083 |
+
"<extra_id_46>",
|
| 1084 |
+
"<extra_id_47>",
|
| 1085 |
+
"<extra_id_48>",
|
| 1086 |
+
"<extra_id_49>",
|
| 1087 |
+
"<extra_id_50>",
|
| 1088 |
+
"<extra_id_51>",
|
| 1089 |
+
"<extra_id_52>",
|
| 1090 |
+
"<extra_id_53>",
|
| 1091 |
+
"<extra_id_54>",
|
| 1092 |
+
"<extra_id_55>",
|
| 1093 |
+
"<extra_id_56>",
|
| 1094 |
+
"<extra_id_57>",
|
| 1095 |
+
"<extra_id_58>",
|
| 1096 |
+
"<extra_id_59>",
|
| 1097 |
+
"<extra_id_60>",
|
| 1098 |
+
"<extra_id_61>",
|
| 1099 |
+
"<extra_id_62>",
|
| 1100 |
+
"<extra_id_63>",
|
| 1101 |
+
"<extra_id_64>",
|
| 1102 |
+
"<extra_id_65>",
|
| 1103 |
+
"<extra_id_66>",
|
| 1104 |
+
"<extra_id_67>",
|
| 1105 |
+
"<extra_id_68>",
|
| 1106 |
+
"<extra_id_69>",
|
| 1107 |
+
"<extra_id_70>",
|
| 1108 |
+
"<extra_id_71>",
|
| 1109 |
+
"<extra_id_72>",
|
| 1110 |
+
"<extra_id_73>",
|
| 1111 |
+
"<extra_id_74>",
|
| 1112 |
+
"<extra_id_75>",
|
| 1113 |
+
"<extra_id_76>",
|
| 1114 |
+
"<extra_id_77>",
|
| 1115 |
+
"<extra_id_78>",
|
| 1116 |
+
"<extra_id_79>",
|
| 1117 |
+
"<extra_id_80>",
|
| 1118 |
+
"<extra_id_81>",
|
| 1119 |
+
"<extra_id_82>",
|
| 1120 |
+
"<extra_id_83>",
|
| 1121 |
+
"<extra_id_84>",
|
| 1122 |
+
"<extra_id_85>",
|
| 1123 |
+
"<extra_id_86>",
|
| 1124 |
+
"<extra_id_87>",
|
| 1125 |
+
"<extra_id_88>",
|
| 1126 |
+
"<extra_id_89>",
|
| 1127 |
+
"<extra_id_90>",
|
| 1128 |
+
"<extra_id_91>",
|
| 1129 |
+
"<extra_id_92>",
|
| 1130 |
+
"<extra_id_93>",
|
| 1131 |
+
"<extra_id_94>",
|
| 1132 |
+
"<extra_id_95>",
|
| 1133 |
+
"<extra_id_96>",
|
| 1134 |
+
"<extra_id_97>",
|
| 1135 |
+
"<extra_id_98>",
|
| 1136 |
+
"<extra_id_99>",
|
| 1137 |
+
"<extra_id_100>",
|
| 1138 |
+
"<extra_id_101>",
|
| 1139 |
+
"<extra_id_102>",
|
| 1140 |
+
"<extra_id_103>",
|
| 1141 |
+
"<extra_id_104>",
|
| 1142 |
+
"<extra_id_105>",
|
| 1143 |
+
"<extra_id_106>",
|
| 1144 |
+
"<extra_id_107>",
|
| 1145 |
+
"<extra_id_108>",
|
| 1146 |
+
"<extra_id_109>",
|
| 1147 |
+
"<extra_id_110>",
|
| 1148 |
+
"<extra_id_111>",
|
| 1149 |
+
"<extra_id_112>",
|
| 1150 |
+
"<extra_id_113>",
|
| 1151 |
+
"<extra_id_114>",
|
| 1152 |
+
"<extra_id_115>",
|
| 1153 |
+
"<extra_id_116>",
|
| 1154 |
+
"<extra_id_117>",
|
| 1155 |
+
"<extra_id_118>",
|
| 1156 |
+
"<extra_id_119>",
|
| 1157 |
+
"<extra_id_120>",
|
| 1158 |
+
"<extra_id_121>",
|
| 1159 |
+
"<extra_id_122>",
|
| 1160 |
+
"<extra_id_123>",
|
| 1161 |
+
"<extra_id_124>",
|
| 1162 |
+
"<|SOP|>"
|
| 1163 |
+
],
|
| 1164 |
+
"clean_up_tokenization_spaces": false,
|
| 1165 |
+
"eos_token": "</s>",
|
| 1166 |
+
"extra_ids": 0,
|
| 1167 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 1168 |
+
"pad_token": "<pad>",
|
| 1169 |
+
"tokenizer_class": "ByT5Tokenizer",
|
| 1170 |
+
"unk_token": "<unk>"
|
| 1171 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,850 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.6808745861053467,
|
| 3 |
+
"best_model_checkpoint": "model_training/byt5_small/checkpoints-random-09-07-09-31/checkpoint-475",
|
| 4 |
+
"epoch": 7.715736040609137,
|
| 5 |
+
"eval_steps": 25,
|
| 6 |
+
"global_step": 475,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.08121827411167512,
|
| 13 |
+
"grad_norm": 1909.4637451171875,
|
| 14 |
+
"learning_rate": 5.102040816326531e-05,
|
| 15 |
+
"loss": 57.0818,
|
| 16 |
+
"step": 5
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.16243654822335024,
|
| 20 |
+
"grad_norm": 99.90604400634766,
|
| 21 |
+
"learning_rate": 0.00010204081632653062,
|
| 22 |
+
"loss": 16.1261,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2436548223350254,
|
| 27 |
+
"grad_norm": 3.8745250701904297,
|
| 28 |
+
"learning_rate": 0.00015306122448979594,
|
| 29 |
+
"loss": 4.167,
|
| 30 |
+
"step": 15
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3248730964467005,
|
| 34 |
+
"grad_norm": 2.7964189052581787,
|
| 35 |
+
"learning_rate": 0.00020408163265306123,
|
| 36 |
+
"loss": 3.5792,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.40609137055837563,
|
| 41 |
+
"grad_norm": 2.3573312759399414,
|
| 42 |
+
"learning_rate": 0.00025510204081632655,
|
| 43 |
+
"loss": 2.6289,
|
| 44 |
+
"step": 25
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.40609137055837563,
|
| 48 |
+
"eval_loss": 1.9594327211380005,
|
| 49 |
+
"eval_runtime": 89.1162,
|
| 50 |
+
"eval_samples_per_second": 11.221,
|
| 51 |
+
"eval_steps_per_second": 1.403,
|
| 52 |
+
"step": 25
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.4873096446700508,
|
| 56 |
+
"grad_norm": 4.407505512237549,
|
| 57 |
+
"learning_rate": 0.0003061224489795919,
|
| 58 |
+
"loss": 2.181,
|
| 59 |
+
"step": 30
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.5685279187817259,
|
| 63 |
+
"grad_norm": 2.605747699737549,
|
| 64 |
+
"learning_rate": 0.00035714285714285714,
|
| 65 |
+
"loss": 2.1089,
|
| 66 |
+
"step": 35
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.649746192893401,
|
| 70 |
+
"grad_norm": 6.306596755981445,
|
| 71 |
+
"learning_rate": 0.00040816326530612246,
|
| 72 |
+
"loss": 2.0922,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.7309644670050761,
|
| 77 |
+
"grad_norm": 19.09569549560547,
|
| 78 |
+
"learning_rate": 0.0004591836734693878,
|
| 79 |
+
"loss": 2.0705,
|
| 80 |
+
"step": 45
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.8121827411167513,
|
| 84 |
+
"grad_norm": 1.264049768447876,
|
| 85 |
+
"learning_rate": 0.0004999935985425297,
|
| 86 |
+
"loss": 2.0794,
|
| 87 |
+
"step": 50
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.8121827411167513,
|
| 91 |
+
"eval_loss": 1.8679453134536743,
|
| 92 |
+
"eval_runtime": 89.0729,
|
| 93 |
+
"eval_samples_per_second": 11.227,
|
| 94 |
+
"eval_steps_per_second": 1.403,
|
| 95 |
+
"step": 50
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.8934010152284264,
|
| 99 |
+
"grad_norm": 1.4896085262298584,
|
| 100 |
+
"learning_rate": 0.0004997695819512612,
|
| 101 |
+
"loss": 2.0143,
|
| 102 |
+
"step": 55
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.9746192893401016,
|
| 106 |
+
"grad_norm": 4.419875144958496,
|
| 107 |
+
"learning_rate": 0.0004992258202402822,
|
| 108 |
+
"loss": 2.0938,
|
| 109 |
+
"step": 60
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.0558375634517767,
|
| 113 |
+
"grad_norm": 5.774366855621338,
|
| 114 |
+
"learning_rate": 0.0004983630095117843,
|
| 115 |
+
"loss": 2.0798,
|
| 116 |
+
"step": 65
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.1370558375634519,
|
| 120 |
+
"grad_norm": 1.4512771368026733,
|
| 121 |
+
"learning_rate": 0.0004971822543018662,
|
| 122 |
+
"loss": 2.0285,
|
| 123 |
+
"step": 70
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.218274111675127,
|
| 127 |
+
"grad_norm": 3.769318103790283,
|
| 128 |
+
"learning_rate": 0.0004956850661665511,
|
| 129 |
+
"loss": 2.1148,
|
| 130 |
+
"step": 75
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.218274111675127,
|
| 134 |
+
"eval_loss": 2.073261260986328,
|
| 135 |
+
"eval_runtime": 89.1696,
|
| 136 |
+
"eval_samples_per_second": 11.215,
|
| 137 |
+
"eval_steps_per_second": 1.402,
|
| 138 |
+
"step": 75
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.299492385786802,
|
| 142 |
+
"grad_norm": 5.518929481506348,
|
| 143 |
+
"learning_rate": 0.0004938733617467517,
|
| 144 |
+
"loss": 2.2383,
|
| 145 |
+
"step": 80
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 1.380710659898477,
|
| 149 |
+
"grad_norm": 3.9714841842651367,
|
| 150 |
+
"learning_rate": 0.0004917494603146632,
|
| 151 |
+
"loss": 2.168,
|
| 152 |
+
"step": 85
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.4619289340101522,
|
| 156 |
+
"grad_norm": 6.865543365478516,
|
| 157 |
+
"learning_rate": 0.0004893160808047222,
|
| 158 |
+
"loss": 2.1865,
|
| 159 |
+
"step": 90
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.5431472081218274,
|
| 163 |
+
"grad_norm": 1.2264541387557983,
|
| 164 |
+
"learning_rate": 0.00048657633833293557,
|
| 165 |
+
"loss": 2.1268,
|
| 166 |
+
"step": 95
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.6243654822335025,
|
| 170 |
+
"grad_norm": 1.3554304838180542,
|
| 171 |
+
"learning_rate": 0.0004835337402090316,
|
| 172 |
+
"loss": 1.9755,
|
| 173 |
+
"step": 100
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.6243654822335025,
|
| 177 |
+
"eval_loss": 1.8600231409072876,
|
| 178 |
+
"eval_runtime": 89.191,
|
| 179 |
+
"eval_samples_per_second": 11.212,
|
| 180 |
+
"eval_steps_per_second": 1.401,
|
| 181 |
+
"step": 100
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 1.7055837563451777,
|
| 185 |
+
"grad_norm": 0.7942481637001038,
|
| 186 |
+
"learning_rate": 0.0004801921814465414,
|
| 187 |
+
"loss": 1.9525,
|
| 188 |
+
"step": 105
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.7868020304568528,
|
| 192 |
+
"grad_norm": 0.5718096494674683,
|
| 193 |
+
"learning_rate": 0.00047655593977655674,
|
| 194 |
+
"loss": 1.9006,
|
| 195 |
+
"step": 110
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.868020304568528,
|
| 199 |
+
"grad_norm": 1.3327739238739014,
|
| 200 |
+
"learning_rate": 0.0004726296701715489,
|
| 201 |
+
"loss": 1.8652,
|
| 202 |
+
"step": 115
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.9492385786802031,
|
| 206 |
+
"grad_norm": 1.577561616897583,
|
| 207 |
+
"learning_rate": 0.00046841839888625623,
|
| 208 |
+
"loss": 1.8377,
|
| 209 |
+
"step": 120
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 2.030456852791878,
|
| 213 |
+
"grad_norm": 0.5204086899757385,
|
| 214 |
+
"learning_rate": 0.0004639275170232734,
|
| 215 |
+
"loss": 1.8577,
|
| 216 |
+
"step": 125
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 2.030456852791878,
|
| 220 |
+
"eval_loss": 1.7442234754562378,
|
| 221 |
+
"eval_runtime": 89.0663,
|
| 222 |
+
"eval_samples_per_second": 11.228,
|
| 223 |
+
"eval_steps_per_second": 1.403,
|
| 224 |
+
"step": 125
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.1116751269035534,
|
| 228 |
+
"grad_norm": 2.453739643096924,
|
| 229 |
+
"learning_rate": 0.0004591627736315743,
|
| 230 |
+
"loss": 1.8342,
|
| 231 |
+
"step": 130
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.1928934010152283,
|
| 235 |
+
"grad_norm": 0.7246991395950317,
|
| 236 |
+
"learning_rate": 0.0004541302683468084,
|
| 237 |
+
"loss": 1.7917,
|
| 238 |
+
"step": 135
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 2.2741116751269037,
|
| 242 |
+
"grad_norm": 0.6339123845100403,
|
| 243 |
+
"learning_rate": 0.0004488364435827881,
|
| 244 |
+
"loss": 1.82,
|
| 245 |
+
"step": 140
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 2.3553299492385786,
|
| 249 |
+
"grad_norm": 0.36034825444221497,
|
| 250 |
+
"learning_rate": 0.00044328807628416644,
|
| 251 |
+
"loss": 1.8474,
|
| 252 |
+
"step": 145
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.436548223350254,
|
| 256 |
+
"grad_norm": 0.30923303961753845,
|
| 257 |
+
"learning_rate": 0.0004374922692508611,
|
| 258 |
+
"loss": 1.8128,
|
| 259 |
+
"step": 150
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 2.436548223350254,
|
| 263 |
+
"eval_loss": 1.7244406938552856,
|
| 264 |
+
"eval_runtime": 89.0785,
|
| 265 |
+
"eval_samples_per_second": 11.226,
|
| 266 |
+
"eval_steps_per_second": 1.403,
|
| 267 |
+
"step": 150
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.517766497461929,
|
| 271 |
+
"grad_norm": 0.3758034110069275,
|
| 272 |
+
"learning_rate": 0.0004314564420453311,
|
| 273 |
+
"loss": 1.8011,
|
| 274 |
+
"step": 155
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.598984771573604,
|
| 278 |
+
"grad_norm": 0.9316683411598206,
|
| 279 |
+
"learning_rate": 0.0004251883214943475,
|
| 280 |
+
"loss": 1.7757,
|
| 281 |
+
"step": 160
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.6802030456852792,
|
| 285 |
+
"grad_norm": 0.5500881671905518,
|
| 286 |
+
"learning_rate": 0.0004186959317974155,
|
| 287 |
+
"loss": 1.7824,
|
| 288 |
+
"step": 165
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.761421319796954,
|
| 292 |
+
"grad_norm": 0.3643234372138977,
|
| 293 |
+
"learning_rate": 0.00041198758425451266,
|
| 294 |
+
"loss": 1.7431,
|
| 295 |
+
"step": 170
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.8426395939086295,
|
| 299 |
+
"grad_norm": 0.5587167739868164,
|
| 300 |
+
"learning_rate": 0.00040507186662629185,
|
| 301 |
+
"loss": 1.7935,
|
| 302 |
+
"step": 175
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.8426395939086295,
|
| 306 |
+
"eval_loss": 1.7120025157928467,
|
| 307 |
+
"eval_runtime": 89.075,
|
| 308 |
+
"eval_samples_per_second": 11.226,
|
| 309 |
+
"eval_steps_per_second": 1.403,
|
| 310 |
+
"step": 175
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 2.9238578680203045,
|
| 314 |
+
"grad_norm": 0.44406819343566895,
|
| 315 |
+
"learning_rate": 0.0003979576321403705,
|
| 316 |
+
"loss": 1.7312,
|
| 317 |
+
"step": 180
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.00507614213198,
|
| 321 |
+
"grad_norm": 0.7630233764648438,
|
| 322 |
+
"learning_rate": 0.0003906539881577793,
|
| 323 |
+
"loss": 1.8026,
|
| 324 |
+
"step": 185
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 3.0862944162436547,
|
| 328 |
+
"grad_norm": 0.41732481122016907,
|
| 329 |
+
"learning_rate": 0.0003831702845140801,
|
| 330 |
+
"loss": 1.7905,
|
| 331 |
+
"step": 190
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 3.16751269035533,
|
| 335 |
+
"grad_norm": 0.522934079170227,
|
| 336 |
+
"learning_rate": 0.00037551610155007613,
|
| 337 |
+
"loss": 1.7802,
|
| 338 |
+
"step": 195
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.248730964467005,
|
| 342 |
+
"grad_norm": 0.5810943841934204,
|
| 343 |
+
"learning_rate": 0.00036770123784744027,
|
| 344 |
+
"loss": 1.7463,
|
| 345 |
+
"step": 200
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.248730964467005,
|
| 349 |
+
"eval_loss": 1.7069350481033325,
|
| 350 |
+
"eval_runtime": 89.0777,
|
| 351 |
+
"eval_samples_per_second": 11.226,
|
| 352 |
+
"eval_steps_per_second": 1.403,
|
| 353 |
+
"step": 200
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 3.3299492385786804,
|
| 357 |
+
"grad_norm": 0.1446053683757782,
|
| 358 |
+
"learning_rate": 0.00035973569768495855,
|
| 359 |
+
"loss": 1.7338,
|
| 360 |
+
"step": 205
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.4111675126903553,
|
| 364 |
+
"grad_norm": 0.5621339678764343,
|
| 365 |
+
"learning_rate": 0.0003516296782314491,
|
| 366 |
+
"loss": 1.7331,
|
| 367 |
+
"step": 210
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 3.4923857868020303,
|
| 371 |
+
"grad_norm": 0.25368839502334595,
|
| 372 |
+
"learning_rate": 0.00034339355649175095,
|
| 373 |
+
"loss": 1.8015,
|
| 374 |
+
"step": 215
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.5736040609137056,
|
| 378 |
+
"grad_norm": 0.12756070494651794,
|
| 379 |
+
"learning_rate": 0.00033503787602249364,
|
| 380 |
+
"loss": 1.7295,
|
| 381 |
+
"step": 220
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.6548223350253806,
|
| 385 |
+
"grad_norm": 0.265066921710968,
|
| 386 |
+
"learning_rate": 0.00032657333343465356,
|
| 387 |
+
"loss": 1.7455,
|
| 388 |
+
"step": 225
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 3.6548223350253806,
|
| 392 |
+
"eval_loss": 1.726246953010559,
|
| 393 |
+
"eval_runtime": 89.0736,
|
| 394 |
+
"eval_samples_per_second": 11.227,
|
| 395 |
+
"eval_steps_per_second": 1.403,
|
| 396 |
+
"step": 225
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.736040609137056,
|
| 400 |
+
"grad_norm": 1.8155518770217896,
|
| 401 |
+
"learning_rate": 0.0003180107647001769,
|
| 402 |
+
"loss": 1.7157,
|
| 403 |
+
"step": 230
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 3.817258883248731,
|
| 407 |
+
"grad_norm": 0.34362295269966125,
|
| 408 |
+
"learning_rate": 0.0003093611312801979,
|
| 409 |
+
"loss": 1.7732,
|
| 410 |
+
"step": 235
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.8984771573604062,
|
| 414 |
+
"grad_norm": 0.4821447432041168,
|
| 415 |
+
"learning_rate": 0.00030063550609261025,
|
| 416 |
+
"loss": 1.7483,
|
| 417 |
+
"step": 240
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 3.979695431472081,
|
| 421 |
+
"grad_norm": 0.359451562166214,
|
| 422 |
+
"learning_rate": 0.000291845059336957,
|
| 423 |
+
"loss": 1.7725,
|
| 424 |
+
"step": 245
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 4.060913705583756,
|
| 428 |
+
"grad_norm": 27.946842193603516,
|
| 429 |
+
"learning_rate": 0.0002830010441947834,
|
| 430 |
+
"loss": 2.2729,
|
| 431 |
+
"step": 250
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 4.060913705583756,
|
| 435 |
+
"eval_loss": 9.357398986816406,
|
| 436 |
+
"eval_runtime": 89.1669,
|
| 437 |
+
"eval_samples_per_second": 11.215,
|
| 438 |
+
"eval_steps_per_second": 1.402,
|
| 439 |
+
"step": 250
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 4.1421319796954315,
|
| 443 |
+
"grad_norm": 0.8487386107444763,
|
| 444 |
+
"learning_rate": 0.00027411478242376017,
|
| 445 |
+
"loss": 3.5769,
|
| 446 |
+
"step": 255
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.223350253807107,
|
| 450 |
+
"grad_norm": 2.305914878845215,
|
| 451 |
+
"learning_rate": 0.00026519764986401774,
|
| 452 |
+
"loss": 1.824,
|
| 453 |
+
"step": 260
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 4.304568527918782,
|
| 457 |
+
"grad_norm": 0.5802918076515198,
|
| 458 |
+
"learning_rate": 0.000256261061875247,
|
| 459 |
+
"loss": 1.7698,
|
| 460 |
+
"step": 265
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 4.385786802030457,
|
| 464 |
+
"grad_norm": 0.5246661901473999,
|
| 465 |
+
"learning_rate": 0.0002473164587232079,
|
| 466 |
+
"loss": 1.8066,
|
| 467 |
+
"step": 270
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 4.467005076142132,
|
| 471 |
+
"grad_norm": 0.15261879563331604,
|
| 472 |
+
"learning_rate": 0.0002383752909343547,
|
| 473 |
+
"loss": 1.7924,
|
| 474 |
+
"step": 275
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 4.467005076142132,
|
| 478 |
+
"eval_loss": 1.708724021911621,
|
| 479 |
+
"eval_runtime": 89.1842,
|
| 480 |
+
"eval_samples_per_second": 11.213,
|
| 481 |
+
"eval_steps_per_second": 1.402,
|
| 482 |
+
"step": 275
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 4.548223350253807,
|
| 486 |
+
"grad_norm": 0.34460264444351196,
|
| 487 |
+
"learning_rate": 0.0002294490046373259,
|
| 488 |
+
"loss": 1.7864,
|
| 489 |
+
"step": 280
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 4.629441624365482,
|
| 493 |
+
"grad_norm": 0.2242611199617386,
|
| 494 |
+
"learning_rate": 0.00022054902691006405,
|
| 495 |
+
"loss": 1.788,
|
| 496 |
+
"step": 285
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 4.710659898477157,
|
| 500 |
+
"grad_norm": 0.19834347069263458,
|
| 501 |
+
"learning_rate": 0.00021168675115132315,
|
| 502 |
+
"loss": 1.7513,
|
| 503 |
+
"step": 290
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 4.791878172588833,
|
| 507 |
+
"grad_norm": 0.2671795189380646,
|
| 508 |
+
"learning_rate": 0.00020287352249529153,
|
| 509 |
+
"loss": 1.786,
|
| 510 |
+
"step": 295
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 4.873096446700508,
|
| 514 |
+
"grad_norm": 0.10885637998580933,
|
| 515 |
+
"learning_rate": 0.00019412062328800044,
|
| 516 |
+
"loss": 1.7419,
|
| 517 |
+
"step": 300
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 4.873096446700508,
|
| 521 |
+
"eval_loss": 1.6944421529769897,
|
| 522 |
+
"eval_runtime": 89.2057,
|
| 523 |
+
"eval_samples_per_second": 11.21,
|
| 524 |
+
"eval_steps_per_second": 1.401,
|
| 525 |
+
"step": 300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 4.9543147208121825,
|
| 529 |
+
"grad_norm": 0.14026451110839844,
|
| 530 |
+
"learning_rate": 0.000185439258644112,
|
| 531 |
+
"loss": 1.7621,
|
| 532 |
+
"step": 305
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 5.035532994923858,
|
| 536 |
+
"grad_norm": 0.24394521117210388,
|
| 537 |
+
"learning_rate": 0.00017684054210257517,
|
| 538 |
+
"loss": 1.7105,
|
| 539 |
+
"step": 310
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 5.116751269035533,
|
| 543 |
+
"grad_norm": 0.17971426248550415,
|
| 544 |
+
"learning_rate": 0.00016833548139951395,
|
| 545 |
+
"loss": 1.7346,
|
| 546 |
+
"step": 315
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 5.197969543147208,
|
| 550 |
+
"grad_norm": 0.17999742925167084,
|
| 551 |
+
"learning_rate": 0.0001599349643765599,
|
| 552 |
+
"loss": 1.7767,
|
| 553 |
+
"step": 320
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 5.279187817258883,
|
| 557 |
+
"grad_norm": 0.10608798265457153,
|
| 558 |
+
"learning_rate": 0.0001516497450426686,
|
| 559 |
+
"loss": 1.8044,
|
| 560 |
+
"step": 325
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 5.279187817258883,
|
| 564 |
+
"eval_loss": 1.6952660083770752,
|
| 565 |
+
"eval_runtime": 89.0986,
|
| 566 |
+
"eval_samples_per_second": 11.224,
|
| 567 |
+
"eval_steps_per_second": 1.403,
|
| 568 |
+
"step": 325
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 5.3604060913705585,
|
| 572 |
+
"grad_norm": 0.09113989025354385,
|
| 573 |
+
"learning_rate": 0.00014349042980726362,
|
| 574 |
+
"loss": 1.7125,
|
| 575 |
+
"step": 330
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.441624365482234,
|
| 579 |
+
"grad_norm": 0.11321850121021271,
|
| 580 |
+
"learning_rate": 0.0001354674639023318,
|
| 581 |
+
"loss": 1.7597,
|
| 582 |
+
"step": 335
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 5.522842639593908,
|
| 586 |
+
"grad_norm": 0.1310632973909378,
|
| 587 |
+
"learning_rate": 0.00012759111801085066,
|
| 588 |
+
"loss": 1.7256,
|
| 589 |
+
"step": 340
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 5.604060913705584,
|
| 593 |
+
"grad_norm": 0.10128358006477356,
|
| 594 |
+
"learning_rate": 0.00011987147511866788,
|
| 595 |
+
"loss": 1.7871,
|
| 596 |
+
"step": 345
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 5.685279187817259,
|
| 600 |
+
"grad_norm": 0.3035777807235718,
|
| 601 |
+
"learning_rate": 0.00011231841760666186,
|
| 602 |
+
"loss": 1.7318,
|
| 603 |
+
"step": 350
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 5.685279187817259,
|
| 607 |
+
"eval_loss": 1.688687801361084,
|
| 608 |
+
"eval_runtime": 89.0633,
|
| 609 |
+
"eval_samples_per_second": 11.228,
|
| 610 |
+
"eval_steps_per_second": 1.403,
|
| 611 |
+
"step": 350
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 5.7664974619289335,
|
| 615 |
+
"grad_norm": 0.12795297801494598,
|
| 616 |
+
"learning_rate": 0.0001049416145997094,
|
| 617 |
+
"loss": 1.7698,
|
| 618 |
+
"step": 355
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 5.847715736040609,
|
| 622 |
+
"grad_norm": 0.15086208283901215,
|
| 623 |
+
"learning_rate": 9.775050958865584e-05,
|
| 624 |
+
"loss": 1.7826,
|
| 625 |
+
"step": 360
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 5.928934010152284,
|
| 629 |
+
"grad_norm": 0.14251065254211426,
|
| 630 |
+
"learning_rate": 9.075430834113152e-05,
|
| 631 |
+
"loss": 1.6859,
|
| 632 |
+
"step": 365
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 6.01015228426396,
|
| 636 |
+
"grad_norm": 0.0902705043554306,
|
| 637 |
+
"learning_rate": 8.396196711669335e-05,
|
| 638 |
+
"loss": 1.7259,
|
| 639 |
+
"step": 370
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 6.091370558375634,
|
| 643 |
+
"grad_norm": 0.23637209832668304,
|
| 644 |
+
"learning_rate": 7.738218120137671e-05,
|
| 645 |
+
"loss": 1.7052,
|
| 646 |
+
"step": 375
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 6.091370558375634,
|
| 650 |
+
"eval_loss": 1.6875873804092407,
|
| 651 |
+
"eval_runtime": 89.1637,
|
| 652 |
+
"eval_samples_per_second": 11.215,
|
| 653 |
+
"eval_steps_per_second": 1.402,
|
| 654 |
+
"step": 375
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 6.1725888324873095,
|
| 658 |
+
"grad_norm": 0.07396359741687775,
|
| 659 |
+
"learning_rate": 7.102337377633394e-05,
|
| 660 |
+
"loss": 1.7372,
|
| 661 |
+
"step": 380
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 6.253807106598985,
|
| 665 |
+
"grad_norm": 0.21548880636692047,
|
| 666 |
+
"learning_rate": 6.489368513481228e-05,
|
| 667 |
+
"loss": 1.7448,
|
| 668 |
+
"step": 385
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 6.33502538071066,
|
| 672 |
+
"grad_norm": 0.19514048099517822,
|
| 673 |
+
"learning_rate": 5.9000962261273136e-05,
|
| 674 |
+
"loss": 1.7359,
|
| 675 |
+
"step": 390
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 6.416243654822335,
|
| 679 |
+
"grad_norm": 0.16353292763233185,
|
| 680 |
+
"learning_rate": 5.3352748785993164e-05,
|
| 681 |
+
"loss": 1.7747,
|
| 682 |
+
"step": 395
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 6.49746192893401,
|
| 686 |
+
"grad_norm": 0.19792306423187256,
|
| 687 |
+
"learning_rate": 4.795627532800806e-05,
|
| 688 |
+
"loss": 1.7363,
|
| 689 |
+
"step": 400
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 6.49746192893401,
|
| 693 |
+
"eval_loss": 1.6819108724594116,
|
| 694 |
+
"eval_runtime": 89.1529,
|
| 695 |
+
"eval_samples_per_second": 11.217,
|
| 696 |
+
"eval_steps_per_second": 1.402,
|
| 697 |
+
"step": 400
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 6.5786802030456855,
|
| 701 |
+
"grad_norm": 0.08929474651813507,
|
| 702 |
+
"learning_rate": 4.281845023876074e-05,
|
| 703 |
+
"loss": 1.6744,
|
| 704 |
+
"step": 405
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 6.659898477157361,
|
| 708 |
+
"grad_norm": 0.09701024740934372,
|
| 709 |
+
"learning_rate": 3.794585075830329e-05,
|
| 710 |
+
"loss": 1.7144,
|
| 711 |
+
"step": 410
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 6.741116751269035,
|
| 715 |
+
"grad_norm": 0.06863227486610413,
|
| 716 |
+
"learning_rate": 3.334471459537497e-05,
|
| 717 |
+
"loss": 1.7863,
|
| 718 |
+
"step": 415
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 6.822335025380711,
|
| 722 |
+
"grad_norm": 0.07492458820343018,
|
| 723 |
+
"learning_rate": 2.902093194213526e-05,
|
| 724 |
+
"loss": 1.7385,
|
| 725 |
+
"step": 420
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 6.903553299492386,
|
| 729 |
+
"grad_norm": 0.09851057827472687,
|
| 730 |
+
"learning_rate": 2.4980037933772488e-05,
|
| 731 |
+
"loss": 1.7655,
|
| 732 |
+
"step": 425
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 6.903553299492386,
|
| 736 |
+
"eval_loss": 1.6825205087661743,
|
| 737 |
+
"eval_runtime": 89.1368,
|
| 738 |
+
"eval_samples_per_second": 11.219,
|
| 739 |
+
"eval_steps_per_second": 1.402,
|
| 740 |
+
"step": 425
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 6.9847715736040605,
|
| 744 |
+
"grad_norm": 0.07320298254489899,
|
| 745 |
+
"learning_rate": 2.122720556264357e-05,
|
| 746 |
+
"loss": 1.7219,
|
| 747 |
+
"step": 430
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 7.065989847715736,
|
| 751 |
+
"grad_norm": 0.07251249998807907,
|
| 752 |
+
"learning_rate": 1.776723905601438e-05,
|
| 753 |
+
"loss": 1.7049,
|
| 754 |
+
"step": 435
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 7.147208121827411,
|
| 758 |
+
"grad_norm": 0.07650978118181229,
|
| 759 |
+
"learning_rate": 1.4604567725877926e-05,
|
| 760 |
+
"loss": 1.7445,
|
| 761 |
+
"step": 440
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 7.228426395939087,
|
| 765 |
+
"grad_norm": 0.0650210827589035,
|
| 766 |
+
"learning_rate": 1.1743240298725116e-05,
|
| 767 |
+
"loss": 1.7892,
|
| 768 |
+
"step": 445
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 7.309644670050761,
|
| 772 |
+
"grad_norm": 0.06279773265123367,
|
| 773 |
+
"learning_rate": 9.18691973252539e-06,
|
| 774 |
+
"loss": 1.747,
|
| 775 |
+
"step": 450
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 7.309644670050761,
|
| 779 |
+
"eval_loss": 1.6831755638122559,
|
| 780 |
+
"eval_runtime": 89.0915,
|
| 781 |
+
"eval_samples_per_second": 11.224,
|
| 782 |
+
"eval_steps_per_second": 1.403,
|
| 783 |
+
"step": 450
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 7.3908629441624365,
|
| 787 |
+
"grad_norm": 0.0952860563993454,
|
| 788 |
+
"learning_rate": 6.938878527553066e-06,
|
| 789 |
+
"loss": 1.7054,
|
| 790 |
+
"step": 455
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 7.472081218274112,
|
| 794 |
+
"grad_norm": 0.07091079652309418,
|
| 795 |
+
"learning_rate": 5.001994537062265e-06,
|
| 796 |
+
"loss": 1.7471,
|
| 797 |
+
"step": 460
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 7.553299492385786,
|
| 801 |
+
"grad_norm": 0.07213548570871353,
|
| 802 |
+
"learning_rate": 3.3787472831732225e-06,
|
| 803 |
+
"loss": 1.7511,
|
| 804 |
+
"step": 465
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 7.634517766497462,
|
| 808 |
+
"grad_norm": 0.06398265808820724,
|
| 809 |
+
"learning_rate": 2.071214782686265e-06,
|
| 810 |
+
"loss": 1.6653,
|
| 811 |
+
"step": 470
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 7.715736040609137,
|
| 815 |
+
"grad_norm": 0.06733715534210205,
|
| 816 |
+
"learning_rate": 1.0810708868871643e-06,
|
| 817 |
+
"loss": 1.7363,
|
| 818 |
+
"step": 475
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 7.715736040609137,
|
| 822 |
+
"eval_loss": 1.6808745861053467,
|
| 823 |
+
"eval_runtime": 89.164,
|
| 824 |
+
"eval_samples_per_second": 11.215,
|
| 825 |
+
"eval_steps_per_second": 1.402,
|
| 826 |
+
"step": 475
|
| 827 |
+
}
|
| 828 |
+
],
|
| 829 |
+
"logging_steps": 5,
|
| 830 |
+
"max_steps": 488,
|
| 831 |
+
"num_input_tokens_seen": 0,
|
| 832 |
+
"num_train_epochs": 8,
|
| 833 |
+
"save_steps": 25,
|
| 834 |
+
"stateful_callbacks": {
|
| 835 |
+
"TrainerControl": {
|
| 836 |
+
"args": {
|
| 837 |
+
"should_epoch_stop": false,
|
| 838 |
+
"should_evaluate": false,
|
| 839 |
+
"should_log": false,
|
| 840 |
+
"should_save": true,
|
| 841 |
+
"should_training_stop": false
|
| 842 |
+
},
|
| 843 |
+
"attributes": {}
|
| 844 |
+
}
|
| 845 |
+
},
|
| 846 |
+
"total_flos": 4.663017499145011e+17,
|
| 847 |
+
"train_batch_size": 8,
|
| 848 |
+
"trial_name": null,
|
| 849 |
+
"trial_params": null
|
| 850 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d97902bfc13c1b9ab8a3422b9a3725fc0b6cfbf917f062593b85e961fd03f09
|
| 3 |
+
size 5432
|