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-typescript-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-typescript-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: 0.3169
|
| 22 |
+
- Precision: 0.7165
|
| 23 |
+
- Recall: 0.3667
|
| 24 |
+
- F1 Macro: 0.4017
|
| 25 |
+
- Accuracy: 0.6556
|
| 26 |
+
- F1 Binary Minimum3: 0.5559
|
| 27 |
+
- F1 Binary Minimum2: 0.9293
|
| 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 | 4.5438 | 0.0358 | 0.2 | 0.0607 | 0.1788 | 0 | 0 |
|
| 64 |
+
| 0.3468 | 0.2960 | 1000 | 0.3515 | 0.4698 | 0.3119 | 0.3243 | 0.6325 | 0.4623 | 0.9243 |
|
| 65 |
+
| 0.3432 | 0.5921 | 2000 | 0.3465 | 0.5149 | 0.3365 | 0.3559 | 0.6356 | 0.5743 | 0.9252 |
|
| 66 |
+
| 0.345 | 0.8881 | 3000 | 0.3374 | 0.5098 | 0.3361 | 0.3564 | 0.6431 | 0.5591 | 0.9264 |
|
| 67 |
+
| 0.3487 | 1.1841 | 4000 | 0.3350 | 0.5081 | 0.3339 | 0.3557 | 0.6438 | 0.5224 | 0.9265 |
|
| 68 |
+
| 0.3461 | 1.4802 | 5000 | 0.3331 | 0.5103 | 0.3427 | 0.3673 | 0.6455 | 0.5533 | 0.9269 |
|
| 69 |
+
| 0.3193 | 1.7762 | 6000 | 0.3339 | 0.5122 | 0.3453 | 0.3687 | 0.6449 | 0.5696 | 0.9273 |
|
| 70 |
+
| 0.3301 | 2.0722 | 7000 | 0.3312 | 0.5107 | 0.3492 | 0.3756 | 0.6472 | 0.5585 | 0.9270 |
|
| 71 |
+
| 0.3246 | 2.3683 | 8000 | 0.3411 | 0.5137 | 0.3533 | 0.3783 | 0.6396 | 0.5934 | 0.9260 |
|
| 72 |
+
| 0.3301 | 2.6643 | 9000 | 0.3362 | 0.5139 | 0.3530 | 0.3791 | 0.6438 | 0.5876 | 0.9264 |
|
| 73 |
+
| 0.3342 | 2.9603 | 10000 | 0.3306 | 0.5019 | 0.3407 | 0.3642 | 0.6462 | 0.5157 | 0.9268 |
|
| 74 |
+
| 0.3321 | 3.2564 | 11000 | 0.3287 | 0.5076 | 0.3521 | 0.3796 | 0.6481 | 0.5594 | 0.9275 |
|
| 75 |
+
| 0.3434 | 3.5524 | 12000 | 0.3368 | 0.4982 | 0.3309 | 0.3501 | 0.6418 | 0.4749 | 0.9249 |
|
| 76 |
+
| 0.3305 | 3.8484 | 13000 | 0.3297 | 0.5043 | 0.3391 | 0.3635 | 0.6467 | 0.5192 | 0.9266 |
|
| 77 |
+
| 0.3187 | 4.1445 | 14000 | 0.3274 | 0.5044 | 0.3480 | 0.3751 | 0.6483 | 0.5470 | 0.9266 |
|
| 78 |
+
| 0.3252 | 4.4405 | 15000 | 0.3323 | 0.5137 | 0.3585 | 0.3864 | 0.6449 | 0.5870 | 0.9273 |
|
| 79 |
+
| 0.3316 | 4.7365 | 16000 | 0.3275 | 0.5032 | 0.3458 | 0.3716 | 0.6485 | 0.5302 | 0.9270 |
|
| 80 |
+
| 0.3362 | 5.0326 | 17000 | 0.3305 | 0.4999 | 0.3403 | 0.3641 | 0.6452 | 0.5011 | 0.9265 |
|
| 81 |
+
| 0.3256 | 5.3286 | 18000 | 0.3257 | 0.5044 | 0.3489 | 0.3755 | 0.6496 | 0.5446 | 0.9277 |
|
| 82 |
+
| 0.3392 | 5.6246 | 19000 | 0.3291 | 0.4991 | 0.3463 | 0.3717 | 0.6474 | 0.5152 | 0.9266 |
|
| 83 |
+
| 0.3264 | 5.9207 | 20000 | 0.3259 | 0.5120 | 0.3466 | 0.3738 | 0.6493 | 0.5481 | 0.9278 |
|
| 84 |
+
| 0.3303 | 6.2167 | 21000 | 0.3251 | 0.5138 | 0.3512 | 0.3802 | 0.6496 | 0.5513 | 0.9280 |
|
| 85 |
+
| 0.3296 | 6.5127 | 22000 | 0.3286 | 0.4984 | 0.3449 | 0.3698 | 0.6471 | 0.5119 | 0.9263 |
|
| 86 |
+
| 0.3291 | 6.8088 | 23000 | 0.3324 | 0.5159 | 0.3661 | 0.3953 | 0.6461 | 0.5937 | 0.9279 |
|
| 87 |
+
| 0.3222 | 7.1048 | 24000 | 0.3245 | 0.5127 | 0.3517 | 0.3806 | 0.6506 | 0.5544 | 0.9276 |
|
| 88 |
+
| 0.3292 | 7.4008 | 25000 | 0.3251 | 0.5130 | 0.3568 | 0.3867 | 0.6505 | 0.5573 | 0.9281 |
|
| 89 |
+
| 0.32 | 7.6969 | 26000 | 0.3245 | 0.5117 | 0.3585 | 0.3888 | 0.6505 | 0.5614 | 0.9285 |
|
| 90 |
+
| 0.3318 | 7.9929 | 27000 | 0.3243 | 0.5097 | 0.3504 | 0.3789 | 0.6507 | 0.5360 | 0.9276 |
|
| 91 |
+
| 0.3305 | 8.2889 | 28000 | 0.3237 | 0.5109 | 0.3536 | 0.3832 | 0.6502 | 0.5494 | 0.9280 |
|
| 92 |
+
| 0.3423 | 8.5850 | 29000 | 0.3314 | 0.4979 | 0.3425 | 0.3662 | 0.6464 | 0.4955 | 0.9263 |
|
| 93 |
+
| 0.3212 | 8.8810 | 30000 | 0.3236 | 0.5155 | 0.3552 | 0.3846 | 0.6509 | 0.5628 | 0.9285 |
|
| 94 |
+
| 0.3211 | 9.1770 | 31000 | 0.3231 | 0.5130 | 0.3581 | 0.3888 | 0.6510 | 0.5587 | 0.9283 |
|
| 95 |
+
| 0.3362 | 9.4731 | 32000 | 0.3238 | 0.5080 | 0.3541 | 0.3836 | 0.6506 | 0.5315 | 0.9280 |
|
| 96 |
+
| 0.3305 | 9.7691 | 33000 | 0.3261 | 0.5054 | 0.3471 | 0.3737 | 0.6498 | 0.5115 | 0.9277 |
|
| 97 |
+
| 0.3185 | 10.0651 | 34000 | 0.3232 | 0.5152 | 0.3571 | 0.3872 | 0.6520 | 0.5640 | 0.9284 |
|
| 98 |
+
| 0.3347 | 10.3612 | 35000 | 0.3255 | 0.5044 | 0.3511 | 0.3787 | 0.6505 | 0.5154 | 0.9277 |
|
| 99 |
+
| 0.3293 | 10.6572 | 36000 | 0.3262 | 0.7152 | 0.3651 | 0.3969 | 0.6487 | 0.5816 | 0.9283 |
|
| 100 |
+
| 0.3291 | 10.9532 | 37000 | 0.3256 | 0.5181 | 0.3615 | 0.3918 | 0.6497 | 0.5804 | 0.9281 |
|
| 101 |
+
| 0.3221 | 11.2493 | 38000 | 0.3239 | 0.7123 | 0.3637 | 0.3959 | 0.6491 | 0.5714 | 0.9282 |
|
| 102 |
+
| 0.3216 | 11.5453 | 39000 | 0.3299 | 0.5013 | 0.3475 | 0.3733 | 0.6481 | 0.4941 | 0.9269 |
|
| 103 |
+
| 0.3248 | 11.8413 | 40000 | 0.3219 | 0.5122 | 0.3551 | 0.3854 | 0.6519 | 0.5367 | 0.9283 |
|
| 104 |
+
| 0.3285 | 12.1374 | 41000 | 0.3232 | 0.5056 | 0.3540 | 0.3829 | 0.6516 | 0.5265 | 0.9278 |
|
| 105 |
+
| 0.3243 | 12.4334 | 42000 | 0.3260 | 0.7169 | 0.3688 | 0.4009 | 0.6493 | 0.5867 | 0.9283 |
|
| 106 |
+
| 0.3186 | 12.7294 | 43000 | 0.3220 | 0.7092 | 0.3603 | 0.3923 | 0.6513 | 0.5507 | 0.9282 |
|
| 107 |
+
| 0.3316 | 13.0255 | 44000 | 0.3220 | 0.5121 | 0.3544 | 0.3844 | 0.6525 | 0.5347 | 0.9286 |
|
| 108 |
+
| 0.3157 | 13.3215 | 45000 | 0.3217 | 0.5100 | 0.3602 | 0.3910 | 0.6528 | 0.5548 | 0.9285 |
|
| 109 |
+
| 0.3211 | 13.6175 | 46000 | 0.3226 | 0.7178 | 0.3622 | 0.3940 | 0.6524 | 0.5755 | 0.9285 |
|
| 110 |
+
| 0.3249 | 13.9136 | 47000 | 0.3235 | 0.7053 | 0.3576 | 0.3887 | 0.6516 | 0.5287 | 0.9281 |
|
| 111 |
+
| 0.3226 | 14.2096 | 48000 | 0.3211 | 0.7134 | 0.3587 | 0.3907 | 0.6522 | 0.5586 | 0.9279 |
|
| 112 |
+
| 0.326 | 14.5056 | 49000 | 0.3208 | 0.7141 | 0.3632 | 0.3958 | 0.6535 | 0.5641 | 0.9284 |
|
| 113 |
+
| 0.3211 | 14.8017 | 50000 | 0.3293 | 0.5021 | 0.3460 | 0.3722 | 0.6483 | 0.4897 | 0.9271 |
|
| 114 |
+
| 0.3232 | 15.0977 | 51000 | 0.3207 | 0.7174 | 0.3632 | 0.3968 | 0.6536 | 0.5650 | 0.9290 |
|
| 115 |
+
| 0.3232 | 15.3937 | 52000 | 0.3200 | 0.5125 | 0.3592 | 0.3901 | 0.6548 | 0.5483 | 0.9291 |
|
| 116 |
+
| 0.3248 | 15.6898 | 53000 | 0.3224 | 0.5108 | 0.3540 | 0.3835 | 0.6526 | 0.5195 | 0.9287 |
|
| 117 |
+
| 0.3132 | 15.9858 | 54000 | 0.3216 | 0.5151 | 0.3634 | 0.3944 | 0.6528 | 0.5765 | 0.9287 |
|
| 118 |
+
| 0.3235 | 16.2818 | 55000 | 0.3216 | 0.7181 | 0.3698 | 0.4042 | 0.6526 | 0.5777 | 0.9289 |
|
| 119 |
+
| 0.3253 | 16.5779 | 56000 | 0.3230 | 0.5082 | 0.3527 | 0.3815 | 0.6523 | 0.5142 | 0.9283 |
|
| 120 |
+
| 0.3185 | 16.8739 | 57000 | 0.3200 | 0.5145 | 0.3576 | 0.3884 | 0.6540 | 0.5569 | 0.9285 |
|
| 121 |
+
| 0.3268 | 17.1699 | 58000 | 0.3201 | 0.7159 | 0.3691 | 0.4037 | 0.6538 | 0.5689 | 0.9291 |
|
| 122 |
+
| 0.3191 | 17.4660 | 59000 | 0.3207 | 0.7187 | 0.3696 | 0.4042 | 0.6543 | 0.5763 | 0.9288 |
|
| 123 |
+
| 0.318 | 17.7620 | 60000 | 0.3194 | 0.7146 | 0.3598 | 0.3922 | 0.6544 | 0.5493 | 0.9288 |
|
| 124 |
+
| 0.3049 | 18.0580 | 61000 | 0.3196 | 0.7099 | 0.3601 | 0.3931 | 0.6536 | 0.5355 | 0.9287 |
|
| 125 |
+
| 0.3298 | 18.3541 | 62000 | 0.3212 | 0.5084 | 0.3563 | 0.3864 | 0.6531 | 0.5300 | 0.9285 |
|
| 126 |
+
| 0.3257 | 18.6501 | 63000 | 0.3216 | 0.7201 | 0.3682 | 0.4025 | 0.6528 | 0.5782 | 0.9285 |
|
| 127 |
+
| 0.3277 | 18.9461 | 64000 | 0.3188 | 0.7140 | 0.3595 | 0.3920 | 0.6540 | 0.5413 | 0.9291 |
|
| 128 |
+
| 0.3187 | 19.2422 | 65000 | 0.3189 | 0.7147 | 0.3654 | 0.3999 | 0.6540 | 0.5593 | 0.9287 |
|
| 129 |
+
| 0.319 | 19.5382 | 66000 | 0.3204 | 0.5114 | 0.3550 | 0.3853 | 0.6534 | 0.5199 | 0.9291 |
|
| 130 |
+
| 0.3125 | 19.8342 | 67000 | 0.3198 | 0.5149 | 0.3602 | 0.3914 | 0.6553 | 0.5636 | 0.9286 |
|
| 131 |
+
| 0.3114 | 20.1303 | 68000 | 0.3185 | 0.5150 | 0.3590 | 0.3903 | 0.6550 | 0.5508 | 0.9289 |
|
| 132 |
+
| 0.3163 | 20.4263 | 69000 | 0.3187 | 0.7171 | 0.3688 | 0.4036 | 0.6550 | 0.5685 | 0.9290 |
|
| 133 |
+
| 0.3146 | 20.7223 | 70000 | 0.3184 | 0.7171 | 0.3673 | 0.4021 | 0.6556 | 0.5613 | 0.9293 |
|
| 134 |
+
| 0.3223 | 21.0184 | 71000 | 0.3203 | 0.5083 | 0.3570 | 0.3869 | 0.6538 | 0.5281 | 0.9287 |
|
| 135 |
+
| 0.3209 | 21.3144 | 72000 | 0.3187 | 0.7155 | 0.3700 | 0.4050 | 0.6551 | 0.5671 | 0.9290 |
|
| 136 |
+
| 0.3111 | 21.6104 | 73000 | 0.3182 | 0.7131 | 0.3656 | 0.3998 | 0.6552 | 0.5537 | 0.9292 |
|
| 137 |
+
| 0.3173 | 21.9065 | 74000 | 0.3187 | 0.7184 | 0.3690 | 0.4050 | 0.6547 | 0.5688 | 0.9290 |
|
| 138 |
+
| 0.3304 | 22.2025 | 75000 | 0.3181 | 0.7117 | 0.3628 | 0.3966 | 0.6550 | 0.5463 | 0.9293 |
|
| 139 |
+
| 0.3235 | 22.4985 | 76000 | 0.3212 | 0.7214 | 0.3728 | 0.4089 | 0.6542 | 0.5811 | 0.9286 |
|
| 140 |
+
| 0.3196 | 22.7946 | 77000 | 0.3179 | 0.7138 | 0.3620 | 0.3959 | 0.6550 | 0.5459 | 0.9290 |
|
| 141 |
+
| 0.3089 | 23.0906 | 78000 | 0.3193 | 0.7196 | 0.3730 | 0.4082 | 0.6553 | 0.5781 | 0.9292 |
|
| 142 |
+
| 0.3129 | 23.3866 | 79000 | 0.3227 | 0.6800 | 0.3785 | 0.4156 | 0.6514 | 0.5868 | 0.9288 |
|
| 143 |
+
| 0.3149 | 23.6827 | 80000 | 0.3178 | 0.7180 | 0.3658 | 0.4005 | 0.6561 | 0.5608 | 0.9290 |
|
| 144 |
+
| 0.3164 | 23.9787 | 81000 | 0.3179 | 0.7176 | 0.3698 | 0.4060 | 0.6557 | 0.5660 | 0.9289 |
|
| 145 |
+
| 0.3157 | 24.2747 | 82000 | 0.3195 | 0.7200 | 0.3726 | 0.4089 | 0.6551 | 0.5771 | 0.9290 |
|
| 146 |
+
| 0.3144 | 24.5708 | 83000 | 0.3183 | 0.7130 | 0.3612 | 0.3951 | 0.6547 | 0.5369 | 0.9293 |
|
| 147 |
+
| 0.3131 | 24.8668 | 84000 | 0.3179 | 0.7146 | 0.3610 | 0.3949 | 0.6553 | 0.5384 | 0.9295 |
|
| 148 |
+
| 0.3087 | 25.1628 | 85000 | 0.3172 | 0.7169 | 0.3638 | 0.3982 | 0.6559 | 0.5540 | 0.9294 |
|
| 149 |
+
| 0.3227 | 25.4589 | 86000 | 0.3177 | 0.7176 | 0.3733 | 0.4098 | 0.6558 | 0.5698 | 0.9292 |
|
| 150 |
+
| 0.3202 | 25.7549 | 87000 | 0.3176 | 0.7184 | 0.3659 | 0.4008 | 0.6555 | 0.5586 | 0.9291 |
|
| 151 |
+
| 0.3279 | 26.0509 | 88000 | 0.3176 | 0.7178 | 0.3706 | 0.4071 | 0.6557 | 0.5627 | 0.9293 |
|
| 152 |
+
| 0.3212 | 26.3470 | 89000 | 0.3175 | 0.7179 | 0.3668 | 0.4016 | 0.6554 | 0.5638 | 0.9290 |
|
| 153 |
+
| 0.3186 | 26.6430 | 90000 | 0.3172 | 0.7150 | 0.3652 | 0.3999 | 0.6559 | 0.5497 | 0.9294 |
|
| 154 |
+
| 0.3186 | 26.9390 | 91000 | 0.3171 | 0.7163 | 0.3648 | 0.3996 | 0.6556 | 0.5496 | 0.9293 |
|
| 155 |
+
| 0.3133 | 27.2351 | 92000 | 0.3185 | 0.7100 | 0.3618 | 0.3953 | 0.6549 | 0.5324 | 0.9293 |
|
| 156 |
+
| 0.3148 | 27.5311 | 93000 | 0.3176 | 0.7187 | 0.3711 | 0.4075 | 0.6561 | 0.5679 | 0.9292 |
|
| 157 |
+
| 0.3201 | 27.8271 | 94000 | 0.3170 | 0.7173 | 0.3681 | 0.4033 | 0.6558 | 0.5587 | 0.9293 |
|
| 158 |
+
| 0.321 | 28.1231 | 95000 | 0.3173 | 0.7141 | 0.3654 | 0.4000 | 0.6556 | 0.5476 | 0.9292 |
|
| 159 |
+
| 0.3169 | 28.4192 | 96000 | 0.3171 | 0.7177 | 0.3682 | 0.4034 | 0.6559 | 0.5597 | 0.9294 |
|
| 160 |
+
| 0.3231 | 28.7152 | 97000 | 0.3169 | 0.7154 | 0.3651 | 0.3998 | 0.6556 | 0.5523 | 0.9293 |
|
| 161 |
+
| 0.3181 | 29.0112 | 98000 | 0.3169 | 0.7164 | 0.3672 | 0.4022 | 0.6556 | 0.5572 | 0.9293 |
|
| 162 |
+
| 0.3261 | 29.3073 | 99000 | 0.3173 | 0.7181 | 0.3700 | 0.4063 | 0.6560 | 0.5659 | 0.9291 |
|
| 163 |
+
| 0.3181 | 29.6033 | 100000 | 0.3170 | 0.7177 | 0.3695 | 0.4058 | 0.6558 | 0.5615 | 0.9292 |
|
| 164 |
+
| 0.3149 | 29.8993 | 101000 | 0.3169 | 0.7165 | 0.3667 | 0.4017 | 0.6556 | 0.5559 | 0.9293 |
|
| 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 sha256:2b244c3a408c4ad80fb17a35e824749db44a7b46cee8f13b86b9595ebcca367a
|
| 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:cf2c5b19df03d02089bcd1fbee856d50435906786e4404b7519c8126fa1485a6
|
| 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 sha256:2b244c3a408c4ad80fb17a35e824749db44a7b46cee8f13b86b9595ebcca367a
|
| 3 |
size 496772092
|