Model save
Browse files- README.md +172 -0
- final/config.json +32 -0
- final/merges.txt +0 -0
- final/model.safetensors +3 -0
- final/special_tokens_map.json +45 -0
- final/tokenizer.json +0 -0
- final/tokenizer_config.json +186 -0
- final/training_args.bin +3 -0
- final/vocab.json +0 -0
- model.safetensors +1 -1
README.md
ADDED
|
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: bigcode/starencoder
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- precision
|
| 7 |
+
- recall
|
| 8 |
+
- accuracy
|
| 9 |
+
model-index:
|
| 10 |
+
- name: classifier-llama3-markdown-500k
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# classifier-llama3-markdown-500k
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [bigcode/starencoder](https://huggingface.co/bigcode/starencoder) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.3043
|
| 22 |
+
- Precision: 0.6007
|
| 23 |
+
- Recall: 0.5268
|
| 24 |
+
- F1 Macro: 0.5255
|
| 25 |
+
- Accuracy: 0.6694
|
| 26 |
+
- F1 Binary Minimum3: 0.8552
|
| 27 |
+
- F1 Binary Minimum2: 0.9316
|
| 28 |
+
|
| 29 |
+
## Model description
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Intended uses & limitations
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training and evaluation data
|
| 38 |
+
|
| 39 |
+
More information needed
|
| 40 |
+
|
| 41 |
+
## Training procedure
|
| 42 |
+
|
| 43 |
+
### Training hyperparameters
|
| 44 |
+
|
| 45 |
+
The following hyperparameters were used during training:
|
| 46 |
+
- learning_rate: 0.0001
|
| 47 |
+
- train_batch_size: 16
|
| 48 |
+
- eval_batch_size: 256
|
| 49 |
+
- seed: 0
|
| 50 |
+
- distributed_type: multi-GPU
|
| 51 |
+
- num_devices: 8
|
| 52 |
+
- total_train_batch_size: 128
|
| 53 |
+
- total_eval_batch_size: 2048
|
| 54 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 55 |
+
- lr_scheduler_type: linear
|
| 56 |
+
- lr_scheduler_warmup_steps: 200
|
| 57 |
+
- num_epochs: 30
|
| 58 |
+
|
| 59 |
+
### Training results
|
| 60 |
+
|
| 61 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy | F1 Binary Minimum3 | F1 Binary Minimum2 |
|
| 62 |
+
|:-------------:|:-------:|:------:|:---------------:|:---------:|:------:|:--------:|:--------:|:------------------:|:------------------:|
|
| 63 |
+
| No log | 0 | 0 | 9.3055 | 0.0541 | 0.2 | 0.0852 | 0.2707 | 0 | 0 |
|
| 64 |
+
| 0.3498 | 0.2946 | 1000 | 0.3644 | 0.5104 | 0.4920 | 0.4872 | 0.6121 | 0.8302 | 0.9179 |
|
| 65 |
+
| 0.3395 | 0.5891 | 2000 | 0.3504 | 0.5128 | 0.4955 | 0.4867 | 0.6306 | 0.8445 | 0.9174 |
|
| 66 |
+
| 0.3426 | 0.8837 | 3000 | 0.3387 | 0.5200 | 0.5029 | 0.5005 | 0.6349 | 0.8435 | 0.9229 |
|
| 67 |
+
| 0.3533 | 1.1782 | 4000 | 0.3362 | 0.5195 | 0.5056 | 0.5032 | 0.6367 | 0.8441 | 0.9225 |
|
| 68 |
+
| 0.3308 | 1.4728 | 5000 | 0.3306 | 0.5229 | 0.5065 | 0.5040 | 0.6456 | 0.8483 | 0.9242 |
|
| 69 |
+
| 0.3453 | 1.7673 | 6000 | 0.3297 | 0.5248 | 0.5034 | 0.5020 | 0.6443 | 0.8495 | 0.9239 |
|
| 70 |
+
| 0.3339 | 2.0619 | 7000 | 0.3258 | 0.5225 | 0.5106 | 0.5078 | 0.6494 | 0.8492 | 0.9247 |
|
| 71 |
+
| 0.3442 | 2.3564 | 8000 | 0.3339 | 0.5441 | 0.5139 | 0.5114 | 0.6418 | 0.8423 | 0.9256 |
|
| 72 |
+
| 0.323 | 2.6510 | 9000 | 0.3235 | 0.5249 | 0.5114 | 0.5090 | 0.6528 | 0.8503 | 0.9260 |
|
| 73 |
+
| 0.3077 | 2.9455 | 10000 | 0.3230 | 0.5268 | 0.5096 | 0.5088 | 0.6495 | 0.8501 | 0.9260 |
|
| 74 |
+
| 0.3215 | 3.2401 | 11000 | 0.3435 | 0.5266 | 0.5127 | 0.5092 | 0.6343 | 0.8378 | 0.9239 |
|
| 75 |
+
| 0.3183 | 3.5346 | 12000 | 0.3287 | 0.5397 | 0.5205 | 0.5174 | 0.6495 | 0.8453 | 0.9268 |
|
| 76 |
+
| 0.3205 | 3.8292 | 13000 | 0.3223 | 0.5430 | 0.5178 | 0.5155 | 0.6514 | 0.8481 | 0.9270 |
|
| 77 |
+
| 0.3325 | 4.1237 | 14000 | 0.3200 | 0.5601 | 0.5166 | 0.5154 | 0.6533 | 0.8490 | 0.9273 |
|
| 78 |
+
| 0.3057 | 4.4183 | 15000 | 0.3183 | 0.5282 | 0.5156 | 0.5141 | 0.6560 | 0.8507 | 0.9278 |
|
| 79 |
+
| 0.2949 | 4.7128 | 16000 | 0.3176 | 0.5551 | 0.5184 | 0.5166 | 0.6577 | 0.8511 | 0.9276 |
|
| 80 |
+
| 0.3045 | 5.0074 | 17000 | 0.3230 | 0.5263 | 0.5123 | 0.5086 | 0.6574 | 0.8517 | 0.9262 |
|
| 81 |
+
| 0.3115 | 5.3019 | 18000 | 0.3200 | 0.5487 | 0.5209 | 0.5165 | 0.6569 | 0.8506 | 0.9262 |
|
| 82 |
+
| 0.3065 | 5.5965 | 19000 | 0.3170 | 0.5813 | 0.5166 | 0.5157 | 0.6589 | 0.8522 | 0.9288 |
|
| 83 |
+
| 0.3133 | 5.8910 | 20000 | 0.3201 | 0.5424 | 0.5243 | 0.5215 | 0.6580 | 0.8498 | 0.9285 |
|
| 84 |
+
| 0.3099 | 6.1856 | 21000 | 0.3198 | 0.5389 | 0.5208 | 0.5184 | 0.6540 | 0.8487 | 0.9277 |
|
| 85 |
+
| 0.3055 | 6.4801 | 22000 | 0.3190 | 0.5391 | 0.5247 | 0.5205 | 0.6585 | 0.8497 | 0.9286 |
|
| 86 |
+
| 0.3176 | 6.7747 | 23000 | 0.3163 | 0.5574 | 0.5196 | 0.5185 | 0.6571 | 0.8511 | 0.9281 |
|
| 87 |
+
| 0.3135 | 7.0692 | 24000 | 0.3149 | 0.5579 | 0.5192 | 0.5181 | 0.6590 | 0.8519 | 0.9287 |
|
| 88 |
+
| 0.3061 | 7.3638 | 25000 | 0.3140 | 0.5540 | 0.5197 | 0.5185 | 0.6601 | 0.8520 | 0.9287 |
|
| 89 |
+
| 0.3214 | 7.6583 | 26000 | 0.3149 | 0.5534 | 0.5228 | 0.5205 | 0.6597 | 0.8513 | 0.9287 |
|
| 90 |
+
| 0.3024 | 7.9529 | 27000 | 0.3255 | 0.5368 | 0.5158 | 0.5149 | 0.6475 | 0.8486 | 0.9248 |
|
| 91 |
+
| 0.2981 | 8.2474 | 28000 | 0.3234 | 0.5361 | 0.5195 | 0.5176 | 0.6510 | 0.8476 | 0.9271 |
|
| 92 |
+
| 0.3057 | 8.5420 | 29000 | 0.3144 | 0.5445 | 0.5232 | 0.5212 | 0.6597 | 0.8508 | 0.9289 |
|
| 93 |
+
| 0.3041 | 8.8365 | 30000 | 0.3149 | 0.5629 | 0.5201 | 0.5189 | 0.6572 | 0.8517 | 0.9283 |
|
| 94 |
+
| 0.3082 | 9.1311 | 31000 | 0.3146 | 0.5477 | 0.5240 | 0.5221 | 0.6606 | 0.8518 | 0.9292 |
|
| 95 |
+
| 0.3125 | 9.4256 | 32000 | 0.3120 | 0.5709 | 0.5190 | 0.5178 | 0.6625 | 0.8531 | 0.9296 |
|
| 96 |
+
| 0.3072 | 9.7202 | 33000 | 0.3132 | 0.5721 | 0.5184 | 0.5186 | 0.6596 | 0.8530 | 0.9289 |
|
| 97 |
+
| 0.3141 | 10.0147 | 34000 | 0.3121 | 0.5493 | 0.5242 | 0.5224 | 0.6628 | 0.8523 | 0.9294 |
|
| 98 |
+
| 0.3022 | 10.3093 | 35000 | 0.3114 | 0.5696 | 0.5225 | 0.5206 | 0.6646 | 0.8530 | 0.9291 |
|
| 99 |
+
| 0.3042 | 10.6038 | 36000 | 0.3132 | 0.5511 | 0.5264 | 0.5234 | 0.6629 | 0.8521 | 0.9293 |
|
| 100 |
+
| 0.3063 | 10.8984 | 37000 | 0.3116 | 0.5688 | 0.5216 | 0.5189 | 0.6632 | 0.8531 | 0.9283 |
|
| 101 |
+
| 0.307 | 11.1929 | 38000 | 0.3109 | 0.5645 | 0.5220 | 0.5210 | 0.6635 | 0.8530 | 0.9294 |
|
| 102 |
+
| 0.314 | 11.4875 | 39000 | 0.3140 | 0.5618 | 0.5225 | 0.5189 | 0.6641 | 0.8530 | 0.9281 |
|
| 103 |
+
| 0.3111 | 11.7820 | 40000 | 0.3143 | 0.5288 | 0.5181 | 0.5144 | 0.6627 | 0.8528 | 0.9278 |
|
| 104 |
+
| 0.3279 | 12.0766 | 41000 | 0.3144 | 0.5602 | 0.5266 | 0.5242 | 0.6604 | 0.8506 | 0.9295 |
|
| 105 |
+
| 0.3121 | 12.3711 | 42000 | 0.3097 | 0.5611 | 0.5221 | 0.5210 | 0.6655 | 0.8536 | 0.9303 |
|
| 106 |
+
| 0.3055 | 12.6657 | 43000 | 0.3100 | 0.5571 | 0.5233 | 0.5220 | 0.6633 | 0.8535 | 0.9299 |
|
| 107 |
+
| 0.3162 | 12.9602 | 44000 | 0.3090 | 0.5650 | 0.5243 | 0.5230 | 0.6658 | 0.8537 | 0.9301 |
|
| 108 |
+
| 0.3056 | 13.2548 | 45000 | 0.3108 | 0.5991 | 0.5182 | 0.5180 | 0.6639 | 0.8537 | 0.9298 |
|
| 109 |
+
| 0.2897 | 13.5493 | 46000 | 0.3090 | 0.5596 | 0.5256 | 0.5234 | 0.6658 | 0.8541 | 0.9301 |
|
| 110 |
+
| 0.2988 | 13.8439 | 47000 | 0.3094 | 0.5728 | 0.5218 | 0.5207 | 0.6646 | 0.8541 | 0.9304 |
|
| 111 |
+
| 0.2959 | 14.1384 | 48000 | 0.3096 | 0.5538 | 0.5259 | 0.5243 | 0.6648 | 0.8529 | 0.9304 |
|
| 112 |
+
| 0.2986 | 14.4330 | 49000 | 0.3097 | 0.6318 | 0.5200 | 0.5185 | 0.6653 | 0.8534 | 0.9305 |
|
| 113 |
+
| 0.3047 | 14.7275 | 50000 | 0.3086 | 0.5668 | 0.5244 | 0.5230 | 0.6663 | 0.8539 | 0.9309 |
|
| 114 |
+
| 0.2932 | 15.0221 | 51000 | 0.3090 | 0.5612 | 0.5251 | 0.5237 | 0.6647 | 0.8537 | 0.9303 |
|
| 115 |
+
| 0.3075 | 15.3166 | 52000 | 0.3080 | 0.5818 | 0.5245 | 0.5226 | 0.6676 | 0.8545 | 0.9302 |
|
| 116 |
+
| 0.302 | 15.6112 | 53000 | 0.3108 | 0.5529 | 0.5272 | 0.5244 | 0.6629 | 0.8521 | 0.9300 |
|
| 117 |
+
| 0.3179 | 15.9057 | 54000 | 0.3081 | 0.5837 | 0.5225 | 0.5220 | 0.6645 | 0.8539 | 0.9302 |
|
| 118 |
+
| 0.3177 | 16.2003 | 55000 | 0.3100 | 0.5665 | 0.5238 | 0.5231 | 0.6624 | 0.8532 | 0.9299 |
|
| 119 |
+
| 0.3074 | 16.4948 | 56000 | 0.3079 | 0.5715 | 0.5240 | 0.5221 | 0.6672 | 0.8542 | 0.9303 |
|
| 120 |
+
| 0.2997 | 16.7894 | 57000 | 0.3074 | 0.5825 | 0.5235 | 0.5221 | 0.6670 | 0.8540 | 0.9307 |
|
| 121 |
+
| 0.3074 | 17.0839 | 58000 | 0.3074 | 0.5995 | 0.5216 | 0.5211 | 0.6658 | 0.8540 | 0.9308 |
|
| 122 |
+
| 0.3012 | 17.3785 | 59000 | 0.3070 | 0.5656 | 0.5259 | 0.5246 | 0.6671 | 0.8542 | 0.9303 |
|
| 123 |
+
| 0.3006 | 17.6730 | 60000 | 0.3072 | 0.5569 | 0.5275 | 0.5254 | 0.6675 | 0.8544 | 0.9306 |
|
| 124 |
+
| 0.3101 | 17.9676 | 61000 | 0.3069 | 0.5836 | 0.5254 | 0.5242 | 0.6668 | 0.8545 | 0.9308 |
|
| 125 |
+
| 0.2887 | 18.2622 | 62000 | 0.3094 | 0.5714 | 0.5256 | 0.5248 | 0.6627 | 0.8533 | 0.9295 |
|
| 126 |
+
| 0.3043 | 18.5567 | 63000 | 0.3068 | 0.5662 | 0.5279 | 0.5259 | 0.6690 | 0.8542 | 0.9310 |
|
| 127 |
+
| 0.2998 | 18.8513 | 64000 | 0.3087 | 0.5764 | 0.5264 | 0.5254 | 0.6641 | 0.8533 | 0.9304 |
|
| 128 |
+
| 0.3014 | 19.1458 | 65000 | 0.3061 | 0.5621 | 0.5281 | 0.5262 | 0.6686 | 0.8542 | 0.9312 |
|
| 129 |
+
| 0.3109 | 19.4404 | 66000 | 0.3098 | 0.5328 | 0.5182 | 0.5161 | 0.6663 | 0.8547 | 0.9304 |
|
| 130 |
+
| 0.3084 | 19.7349 | 67000 | 0.3107 | 0.5749 | 0.5265 | 0.5249 | 0.6615 | 0.8513 | 0.9298 |
|
| 131 |
+
| 0.2999 | 20.0295 | 68000 | 0.3061 | 0.5997 | 0.5248 | 0.5233 | 0.6681 | 0.8543 | 0.9310 |
|
| 132 |
+
| 0.3053 | 20.3240 | 69000 | 0.3073 | 0.5664 | 0.5256 | 0.5246 | 0.6652 | 0.8544 | 0.9304 |
|
| 133 |
+
| 0.3033 | 20.6186 | 70000 | 0.3102 | 0.5811 | 0.5270 | 0.5254 | 0.6623 | 0.8518 | 0.9297 |
|
| 134 |
+
| 0.3124 | 20.9131 | 71000 | 0.3057 | 0.6007 | 0.5250 | 0.5238 | 0.6685 | 0.8550 | 0.9313 |
|
| 135 |
+
| 0.3113 | 21.2077 | 72000 | 0.3080 | 0.5908 | 0.5257 | 0.5254 | 0.6643 | 0.8541 | 0.9300 |
|
| 136 |
+
| 0.2879 | 21.5022 | 73000 | 0.3067 | 0.5679 | 0.5240 | 0.5238 | 0.6664 | 0.8548 | 0.9307 |
|
| 137 |
+
| 0.2977 | 21.7968 | 74000 | 0.3064 | 0.5671 | 0.5285 | 0.5265 | 0.6677 | 0.8549 | 0.9311 |
|
| 138 |
+
| 0.2967 | 22.0913 | 75000 | 0.3054 | 0.5725 | 0.5269 | 0.5250 | 0.6697 | 0.8548 | 0.9309 |
|
| 139 |
+
| 0.2993 | 22.3859 | 76000 | 0.3060 | 0.6008 | 0.5234 | 0.5225 | 0.6686 | 0.8552 | 0.9314 |
|
| 140 |
+
| 0.2874 | 22.6804 | 77000 | 0.3054 | 0.6007 | 0.5237 | 0.5231 | 0.6679 | 0.8548 | 0.9313 |
|
| 141 |
+
| 0.3046 | 22.9750 | 78000 | 0.3053 | 0.6011 | 0.5269 | 0.5253 | 0.6689 | 0.8550 | 0.9314 |
|
| 142 |
+
| 0.2963 | 23.2695 | 79000 | 0.3056 | 0.7346 | 0.5232 | 0.5225 | 0.6682 | 0.8554 | 0.9314 |
|
| 143 |
+
| 0.3113 | 23.5641 | 80000 | 0.3052 | 0.5737 | 0.5275 | 0.5256 | 0.6698 | 0.8553 | 0.9314 |
|
| 144 |
+
| 0.3072 | 23.8586 | 81000 | 0.3054 | 0.5848 | 0.5246 | 0.5242 | 0.6679 | 0.8549 | 0.9312 |
|
| 145 |
+
| 0.3004 | 24.1532 | 82000 | 0.3055 | 0.5742 | 0.5254 | 0.5247 | 0.6671 | 0.8549 | 0.9310 |
|
| 146 |
+
| 0.2939 | 24.4477 | 83000 | 0.3055 | 0.5656 | 0.5289 | 0.5264 | 0.6700 | 0.8545 | 0.9312 |
|
| 147 |
+
| 0.3127 | 24.7423 | 84000 | 0.3050 | 0.5666 | 0.5288 | 0.5265 | 0.6693 | 0.8551 | 0.9313 |
|
| 148 |
+
| 0.3148 | 25.0368 | 85000 | 0.3046 | 0.5842 | 0.5265 | 0.5255 | 0.6698 | 0.8548 | 0.9316 |
|
| 149 |
+
| 0.3029 | 25.3314 | 86000 | 0.3048 | 0.6004 | 0.5269 | 0.5253 | 0.6693 | 0.8549 | 0.9315 |
|
| 150 |
+
| 0.3098 | 25.6259 | 87000 | 0.3070 | 0.5745 | 0.5253 | 0.5250 | 0.6657 | 0.8550 | 0.9302 |
|
| 151 |
+
| 0.2965 | 25.9205 | 88000 | 0.3046 | 0.5666 | 0.5278 | 0.5260 | 0.6699 | 0.8550 | 0.9314 |
|
| 152 |
+
| 0.2929 | 26.2150 | 89000 | 0.3047 | 0.5661 | 0.5278 | 0.5258 | 0.6703 | 0.8546 | 0.9314 |
|
| 153 |
+
| 0.2995 | 26.5096 | 90000 | 0.3048 | 0.6003 | 0.5255 | 0.5242 | 0.6695 | 0.8549 | 0.9313 |
|
| 154 |
+
| 0.2888 | 26.8041 | 91000 | 0.3057 | 0.5670 | 0.5278 | 0.5264 | 0.6674 | 0.8551 | 0.9307 |
|
| 155 |
+
| 0.2903 | 27.0987 | 92000 | 0.3045 | 0.6009 | 0.5264 | 0.5251 | 0.6690 | 0.8552 | 0.9315 |
|
| 156 |
+
| 0.2928 | 27.3932 | 93000 | 0.3049 | 0.5738 | 0.5269 | 0.5259 | 0.6681 | 0.8548 | 0.9310 |
|
| 157 |
+
| 0.2933 | 27.6878 | 94000 | 0.3044 | 0.5836 | 0.5267 | 0.5254 | 0.6688 | 0.8548 | 0.9314 |
|
| 158 |
+
| 0.305 | 27.9823 | 95000 | 0.3044 | 0.6011 | 0.5263 | 0.5252 | 0.6693 | 0.8552 | 0.9315 |
|
| 159 |
+
| 0.2952 | 28.2769 | 96000 | 0.3050 | 0.5671 | 0.5264 | 0.5255 | 0.6674 | 0.8548 | 0.9308 |
|
| 160 |
+
| 0.3055 | 28.5714 | 97000 | 0.3045 | 0.5737 | 0.5273 | 0.5259 | 0.6689 | 0.8548 | 0.9313 |
|
| 161 |
+
| 0.2978 | 28.8660 | 98000 | 0.3045 | 0.6007 | 0.5266 | 0.5254 | 0.6685 | 0.8548 | 0.9314 |
|
| 162 |
+
| 0.3093 | 29.1605 | 99000 | 0.3049 | 0.5741 | 0.5271 | 0.5259 | 0.6679 | 0.8550 | 0.9310 |
|
| 163 |
+
| 0.2949 | 29.4551 | 100000 | 0.3045 | 0.5839 | 0.5271 | 0.5258 | 0.6685 | 0.8550 | 0.9313 |
|
| 164 |
+
| 0.3012 | 29.7496 | 101000 | 0.3043 | 0.6007 | 0.5268 | 0.5255 | 0.6694 | 0.8552 | 0.9316 |
|
| 165 |
+
|
| 166 |
+
|
| 167 |
+
### Framework versions
|
| 168 |
+
|
| 169 |
+
- Transformers 4.43.4
|
| 170 |
+
- Pytorch 2.4.0+cu121
|
| 171 |
+
- Datasets 2.21.0
|
| 172 |
+
- Tokenizers 0.19.1
|
final/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bigcode/starencoder",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": 0.0,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0"
|
| 13 |
+
},
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"label2id": {
|
| 17 |
+
"LABEL_0": 0
|
| 18 |
+
},
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"max_position_embeddings": 1024,
|
| 21 |
+
"model_type": "bert",
|
| 22 |
+
"num_attention_heads": 12,
|
| 23 |
+
"num_hidden_layers": 12,
|
| 24 |
+
"pad_token_id": 49152,
|
| 25 |
+
"position_embedding_type": "absolute",
|
| 26 |
+
"problem_type": "regression",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.43.4",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 49156
|
| 32 |
+
}
|
final/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
final/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7382dd2fe917c4887d68a488f830fbd632a8be6a47edb17e6a443121f50dbee6
|
| 3 |
+
size 496772092
|
final/special_tokens_map.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|endoftext|>",
|
| 4 |
+
"<fim_prefix>",
|
| 5 |
+
"<fim_middle>",
|
| 6 |
+
"<fim_suffix>",
|
| 7 |
+
"<fim_pad>",
|
| 8 |
+
"<filename>",
|
| 9 |
+
"<gh_stars>",
|
| 10 |
+
"<issue_start>",
|
| 11 |
+
"<issue_comment>",
|
| 12 |
+
"<issue_closed>",
|
| 13 |
+
"<jupyter_start>",
|
| 14 |
+
"<jupyter_text>",
|
| 15 |
+
"<jupyter_code>",
|
| 16 |
+
"<jupyter_output>",
|
| 17 |
+
"<empty_output>",
|
| 18 |
+
"<commit_before>",
|
| 19 |
+
"<commit_msg>",
|
| 20 |
+
"<commit_after>",
|
| 21 |
+
"<reponame>"
|
| 22 |
+
],
|
| 23 |
+
"bos_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"eos_token": {
|
| 31 |
+
"content": "<|endoftext|>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"pad_token": "<|endoftext|>",
|
| 38 |
+
"unk_token": {
|
| 39 |
+
"content": "<|endoftext|>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": false,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
}
|
| 45 |
+
}
|
final/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
final/tokenizer_config.json
ADDED
|
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<fim_prefix>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<fim_middle>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<fim_suffix>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<fim_pad>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"5": {
|
| 45 |
+
"content": "<filename>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"6": {
|
| 53 |
+
"content": "<gh_stars>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"7": {
|
| 61 |
+
"content": "<issue_start>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"8": {
|
| 69 |
+
"content": "<issue_comment>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"9": {
|
| 77 |
+
"content": "<issue_closed>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"10": {
|
| 85 |
+
"content": "<jupyter_start>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"11": {
|
| 93 |
+
"content": "<jupyter_text>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"12": {
|
| 101 |
+
"content": "<jupyter_code>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"13": {
|
| 109 |
+
"content": "<jupyter_output>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"14": {
|
| 117 |
+
"content": "<empty_output>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"15": {
|
| 125 |
+
"content": "<commit_before>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"16": {
|
| 133 |
+
"content": "<commit_msg>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"17": {
|
| 141 |
+
"content": "<commit_after>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"18": {
|
| 149 |
+
"content": "<reponame>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
}
|
| 156 |
+
},
|
| 157 |
+
"additional_special_tokens": [
|
| 158 |
+
"<|endoftext|>",
|
| 159 |
+
"<fim_prefix>",
|
| 160 |
+
"<fim_middle>",
|
| 161 |
+
"<fim_suffix>",
|
| 162 |
+
"<fim_pad>",
|
| 163 |
+
"<filename>",
|
| 164 |
+
"<gh_stars>",
|
| 165 |
+
"<issue_start>",
|
| 166 |
+
"<issue_comment>",
|
| 167 |
+
"<issue_closed>",
|
| 168 |
+
"<jupyter_start>",
|
| 169 |
+
"<jupyter_text>",
|
| 170 |
+
"<jupyter_code>",
|
| 171 |
+
"<jupyter_output>",
|
| 172 |
+
"<empty_output>",
|
| 173 |
+
"<commit_before>",
|
| 174 |
+
"<commit_msg>",
|
| 175 |
+
"<commit_after>",
|
| 176 |
+
"<reponame>"
|
| 177 |
+
],
|
| 178 |
+
"bos_token": "<|endoftext|>",
|
| 179 |
+
"clean_up_tokenization_spaces": true,
|
| 180 |
+
"eos_token": "<|endoftext|>",
|
| 181 |
+
"model_max_length": 1024,
|
| 182 |
+
"pad_token": "<|endoftext|>",
|
| 183 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 184 |
+
"unk_token": "<|endoftext|>",
|
| 185 |
+
"vocab_size": 49152
|
| 186 |
+
}
|
final/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b953c46933ae3b6f24a3d95e90a5272506621d785372cea90b2a928b3c8fed1
|
| 3 |
+
size 5368
|
final/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 496772092
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7382dd2fe917c4887d68a488f830fbd632a8be6a47edb17e6a443121f50dbee6
|
| 3 |
size 496772092
|