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-php-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-php-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: 0.3237
|
| 22 |
+
- Precision: 0.4988
|
| 23 |
+
- Recall: 0.3690
|
| 24 |
+
- F1 Macro: 0.3961
|
| 25 |
+
- Accuracy: 0.6229
|
| 26 |
+
- F1 Binary Minimum3: 0.6382
|
| 27 |
+
- F1 Binary Minimum2: 0.9386
|
| 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 | 6.4099 | 0.0294 | 0.2 | 0.0513 | 0.1471 | 0 | 0 |
|
| 64 |
+
| 0.3844 | 0.2955 | 1000 | 0.3684 | 0.4654 | 0.3097 | 0.3196 | 0.5828 | 0.6038 | 0.9300 |
|
| 65 |
+
| 0.3739 | 0.5910 | 2000 | 0.3584 | 0.4903 | 0.3176 | 0.3308 | 0.5921 | 0.5791 | 0.9321 |
|
| 66 |
+
| 0.3648 | 0.8865 | 3000 | 0.3598 | 0.4776 | 0.3252 | 0.3393 | 0.5900 | 0.6469 | 0.9307 |
|
| 67 |
+
| 0.3471 | 1.1820 | 4000 | 0.3505 | 0.4862 | 0.3290 | 0.3457 | 0.5980 | 0.6182 | 0.9328 |
|
| 68 |
+
| 0.3481 | 1.4775 | 5000 | 0.3498 | 0.4805 | 0.3314 | 0.3506 | 0.5972 | 0.6235 | 0.9323 |
|
| 69 |
+
| 0.3558 | 1.7730 | 6000 | 0.3480 | 0.4905 | 0.3258 | 0.3423 | 0.5969 | 0.6219 | 0.9324 |
|
| 70 |
+
| 0.3523 | 2.0686 | 7000 | 0.3485 | 0.4931 | 0.3315 | 0.3492 | 0.5995 | 0.5795 | 0.9337 |
|
| 71 |
+
| 0.3714 | 2.3641 | 8000 | 0.3461 | 0.4874 | 0.3316 | 0.3507 | 0.5995 | 0.6196 | 0.9326 |
|
| 72 |
+
| 0.3584 | 2.6596 | 9000 | 0.3455 | 0.4910 | 0.3335 | 0.3522 | 0.6006 | 0.6346 | 0.9331 |
|
| 73 |
+
| 0.3595 | 2.9551 | 10000 | 0.3491 | 0.4885 | 0.3282 | 0.3445 | 0.5966 | 0.6446 | 0.9316 |
|
| 74 |
+
| 0.3464 | 3.2506 | 11000 | 0.3423 | 0.4917 | 0.3398 | 0.3598 | 0.6052 | 0.6108 | 0.9349 |
|
| 75 |
+
| 0.3572 | 3.5461 | 12000 | 0.3426 | 0.4822 | 0.3419 | 0.3620 | 0.6054 | 0.6354 | 0.9341 |
|
| 76 |
+
| 0.3598 | 3.8416 | 13000 | 0.3468 | 0.4823 | 0.3367 | 0.3559 | 0.5975 | 0.6475 | 0.9327 |
|
| 77 |
+
| 0.3553 | 4.1371 | 14000 | 0.3483 | 0.4941 | 0.3394 | 0.3579 | 0.6033 | 0.5638 | 0.9350 |
|
| 78 |
+
| 0.3626 | 4.4326 | 15000 | 0.3405 | 0.4971 | 0.3345 | 0.3538 | 0.6040 | 0.6172 | 0.9343 |
|
| 79 |
+
| 0.3499 | 4.7281 | 16000 | 0.3401 | 0.4912 | 0.3408 | 0.3613 | 0.6052 | 0.6330 | 0.9345 |
|
| 80 |
+
| 0.3468 | 5.0236 | 17000 | 0.3391 | 0.4881 | 0.3415 | 0.3621 | 0.6064 | 0.6278 | 0.9346 |
|
| 81 |
+
| 0.333 | 5.3191 | 18000 | 0.3408 | 0.4977 | 0.3400 | 0.3584 | 0.6066 | 0.5884 | 0.9360 |
|
| 82 |
+
| 0.3512 | 5.6147 | 19000 | 0.3388 | 0.5002 | 0.3443 | 0.3645 | 0.6091 | 0.6127 | 0.9355 |
|
| 83 |
+
| 0.3583 | 5.9102 | 20000 | 0.3396 | 0.4946 | 0.3375 | 0.3580 | 0.6039 | 0.6352 | 0.9339 |
|
| 84 |
+
| 0.3391 | 6.2057 | 21000 | 0.3465 | 0.4947 | 0.3380 | 0.3550 | 0.6037 | 0.5646 | 0.9347 |
|
| 85 |
+
| 0.3396 | 6.5012 | 22000 | 0.3371 | 0.4962 | 0.3453 | 0.3658 | 0.6089 | 0.6147 | 0.9361 |
|
| 86 |
+
| 0.3476 | 6.7967 | 23000 | 0.3381 | 0.4890 | 0.3458 | 0.3672 | 0.6071 | 0.6411 | 0.9349 |
|
| 87 |
+
| 0.3517 | 7.0922 | 24000 | 0.3377 | 0.4958 | 0.3454 | 0.3654 | 0.6100 | 0.5965 | 0.9359 |
|
| 88 |
+
| 0.3501 | 7.3877 | 25000 | 0.3462 | 0.4840 | 0.3390 | 0.3580 | 0.5963 | 0.6580 | 0.9322 |
|
| 89 |
+
| 0.3421 | 7.6832 | 26000 | 0.3407 | 0.4875 | 0.3394 | 0.3600 | 0.6035 | 0.6388 | 0.9332 |
|
| 90 |
+
| 0.3392 | 7.9787 | 27000 | 0.3360 | 0.4951 | 0.3446 | 0.3666 | 0.6090 | 0.6150 | 0.9354 |
|
| 91 |
+
| 0.3444 | 8.2742 | 28000 | 0.3369 | 0.4895 | 0.3485 | 0.3707 | 0.6082 | 0.6457 | 0.9350 |
|
| 92 |
+
| 0.3566 | 8.5697 | 29000 | 0.3385 | 0.4846 | 0.3485 | 0.3708 | 0.6069 | 0.6518 | 0.9345 |
|
| 93 |
+
| 0.3395 | 8.8652 | 30000 | 0.3347 | 0.4931 | 0.3503 | 0.3719 | 0.6129 | 0.6252 | 0.9363 |
|
| 94 |
+
| 0.3451 | 9.1608 | 31000 | 0.3332 | 0.5022 | 0.3522 | 0.3744 | 0.6148 | 0.6200 | 0.9367 |
|
| 95 |
+
| 0.3383 | 9.4563 | 32000 | 0.3419 | 0.4969 | 0.3481 | 0.3641 | 0.6080 | 0.5704 | 0.9364 |
|
| 96 |
+
| 0.3361 | 9.7518 | 33000 | 0.3334 | 0.4912 | 0.3511 | 0.3740 | 0.6113 | 0.6353 | 0.9358 |
|
| 97 |
+
| 0.3427 | 10.0473 | 34000 | 0.3342 | 0.4988 | 0.3495 | 0.3721 | 0.6111 | 0.6444 | 0.9354 |
|
| 98 |
+
| 0.339 | 10.3428 | 35000 | 0.3337 | 0.4940 | 0.3602 | 0.3823 | 0.6155 | 0.6148 | 0.9374 |
|
| 99 |
+
| 0.3373 | 10.6383 | 36000 | 0.3322 | 0.4979 | 0.3512 | 0.3743 | 0.6134 | 0.6179 | 0.9365 |
|
| 100 |
+
| 0.3368 | 10.9338 | 37000 | 0.3328 | 0.4951 | 0.3527 | 0.3757 | 0.6131 | 0.6438 | 0.9359 |
|
| 101 |
+
| 0.3324 | 11.2293 | 38000 | 0.3336 | 0.4908 | 0.3537 | 0.3772 | 0.6107 | 0.6461 | 0.9360 |
|
| 102 |
+
| 0.3334 | 11.5248 | 39000 | 0.3322 | 0.4955 | 0.3585 | 0.3819 | 0.6163 | 0.6476 | 0.9369 |
|
| 103 |
+
| 0.3334 | 11.8203 | 40000 | 0.3309 | 0.4975 | 0.3570 | 0.3806 | 0.6162 | 0.6358 | 0.9370 |
|
| 104 |
+
| 0.3386 | 12.1158 | 41000 | 0.3305 | 0.4969 | 0.3592 | 0.3823 | 0.6183 | 0.6327 | 0.9373 |
|
| 105 |
+
| 0.3349 | 12.4113 | 42000 | 0.3320 | 0.4908 | 0.3575 | 0.3813 | 0.6148 | 0.6500 | 0.9363 |
|
| 106 |
+
| 0.3287 | 12.7069 | 43000 | 0.3313 | 0.4941 | 0.3588 | 0.3841 | 0.6144 | 0.6390 | 0.9367 |
|
| 107 |
+
| 0.3401 | 13.0024 | 44000 | 0.3311 | 0.4955 | 0.3572 | 0.3793 | 0.6161 | 0.6080 | 0.9377 |
|
| 108 |
+
| 0.3385 | 13.2979 | 45000 | 0.3308 | 0.4912 | 0.3586 | 0.3828 | 0.6162 | 0.6478 | 0.9367 |
|
| 109 |
+
| 0.3338 | 13.5934 | 46000 | 0.3300 | 0.4925 | 0.3612 | 0.3862 | 0.6167 | 0.6440 | 0.9370 |
|
| 110 |
+
| 0.3403 | 13.8889 | 47000 | 0.3421 | 0.4886 | 0.3540 | 0.3764 | 0.6011 | 0.6671 | 0.9342 |
|
| 111 |
+
| 0.3382 | 14.1844 | 48000 | 0.3335 | 0.4998 | 0.3556 | 0.3762 | 0.6143 | 0.5815 | 0.9377 |
|
| 112 |
+
| 0.3397 | 14.4799 | 49000 | 0.3289 | 0.4986 | 0.3539 | 0.3771 | 0.6167 | 0.6117 | 0.9373 |
|
| 113 |
+
| 0.327 | 14.7754 | 50000 | 0.3312 | 0.4942 | 0.3599 | 0.3815 | 0.6170 | 0.5997 | 0.9377 |
|
| 114 |
+
| 0.3388 | 15.0709 | 51000 | 0.3295 | 0.4965 | 0.3546 | 0.3795 | 0.6156 | 0.6222 | 0.9366 |
|
| 115 |
+
| 0.3375 | 15.3664 | 52000 | 0.3285 | 0.4960 | 0.3598 | 0.3833 | 0.6196 | 0.6211 | 0.9380 |
|
| 116 |
+
| 0.3316 | 15.6619 | 53000 | 0.3288 | 0.4977 | 0.3585 | 0.3833 | 0.6172 | 0.6431 | 0.9370 |
|
| 117 |
+
| 0.3306 | 15.9574 | 54000 | 0.3307 | 0.4947 | 0.3582 | 0.3838 | 0.6139 | 0.6407 | 0.9365 |
|
| 118 |
+
| 0.3449 | 16.2530 | 55000 | 0.3313 | 0.4947 | 0.3580 | 0.3828 | 0.6138 | 0.6562 | 0.9359 |
|
| 119 |
+
| 0.339 | 16.5485 | 56000 | 0.3306 | 0.4933 | 0.3623 | 0.3877 | 0.6150 | 0.6571 | 0.9364 |
|
| 120 |
+
| 0.3389 | 16.8440 | 57000 | 0.3286 | 0.4956 | 0.3654 | 0.3909 | 0.6177 | 0.6494 | 0.9376 |
|
| 121 |
+
| 0.3306 | 17.1395 | 58000 | 0.3269 | 0.4947 | 0.3676 | 0.3936 | 0.6201 | 0.6368 | 0.9379 |
|
| 122 |
+
| 0.3257 | 17.4350 | 59000 | 0.3313 | 0.4968 | 0.3590 | 0.3845 | 0.6133 | 0.6561 | 0.9357 |
|
| 123 |
+
| 0.3325 | 17.7305 | 60000 | 0.3284 | 0.4976 | 0.3595 | 0.3850 | 0.6166 | 0.6461 | 0.9368 |
|
| 124 |
+
| 0.3413 | 18.0260 | 61000 | 0.3271 | 0.4969 | 0.3628 | 0.3884 | 0.6190 | 0.6466 | 0.9374 |
|
| 125 |
+
| 0.3257 | 18.3215 | 62000 | 0.3276 | 0.4921 | 0.3676 | 0.3942 | 0.6187 | 0.6459 | 0.9376 |
|
| 126 |
+
| 0.3367 | 18.6170 | 63000 | 0.3266 | 0.4969 | 0.3644 | 0.3888 | 0.6214 | 0.6190 | 0.9385 |
|
| 127 |
+
| 0.3428 | 18.9125 | 64000 | 0.3261 | 0.4974 | 0.3618 | 0.3862 | 0.6203 | 0.6256 | 0.9381 |
|
| 128 |
+
| 0.3405 | 19.2080 | 65000 | 0.3260 | 0.4962 | 0.3651 | 0.3909 | 0.6210 | 0.6394 | 0.9377 |
|
| 129 |
+
| 0.3284 | 19.5035 | 66000 | 0.3263 | 0.4954 | 0.3627 | 0.3887 | 0.6192 | 0.6364 | 0.9374 |
|
| 130 |
+
| 0.3247 | 19.7991 | 67000 | 0.3263 | 0.4968 | 0.3624 | 0.3882 | 0.6195 | 0.6305 | 0.9376 |
|
| 131 |
+
| 0.3205 | 20.0946 | 68000 | 0.3261 | 0.4968 | 0.3660 | 0.3907 | 0.6212 | 0.6159 | 0.9386 |
|
| 132 |
+
| 0.3349 | 20.3901 | 69000 | 0.3265 | 0.4978 | 0.3666 | 0.3934 | 0.6198 | 0.6477 | 0.9376 |
|
| 133 |
+
| 0.3246 | 20.6856 | 70000 | 0.3262 | 0.4999 | 0.3626 | 0.3890 | 0.6195 | 0.6404 | 0.9376 |
|
| 134 |
+
| 0.3355 | 20.9811 | 71000 | 0.3274 | 0.4944 | 0.3636 | 0.3874 | 0.6187 | 0.6006 | 0.9383 |
|
| 135 |
+
| 0.3421 | 21.2766 | 72000 | 0.3253 | 0.4980 | 0.3636 | 0.3892 | 0.6211 | 0.6272 | 0.9382 |
|
| 136 |
+
| 0.3345 | 21.5721 | 73000 | 0.3258 | 0.5012 | 0.3625 | 0.3892 | 0.6199 | 0.6383 | 0.9373 |
|
| 137 |
+
| 0.3227 | 21.8676 | 74000 | 0.3248 | 0.4977 | 0.3672 | 0.3931 | 0.6228 | 0.6303 | 0.9385 |
|
| 138 |
+
| 0.3284 | 22.1631 | 75000 | 0.3248 | 0.4986 | 0.3658 | 0.3914 | 0.6224 | 0.6244 | 0.9387 |
|
| 139 |
+
| 0.3394 | 22.4586 | 76000 | 0.3255 | 0.4985 | 0.3661 | 0.3932 | 0.6196 | 0.6409 | 0.9379 |
|
| 140 |
+
| 0.314 | 22.7541 | 77000 | 0.3255 | 0.4969 | 0.3683 | 0.3950 | 0.6209 | 0.6438 | 0.9380 |
|
| 141 |
+
| 0.3268 | 23.0496 | 78000 | 0.3268 | 0.4987 | 0.3650 | 0.3919 | 0.6186 | 0.6503 | 0.9371 |
|
| 142 |
+
| 0.3285 | 23.3452 | 79000 | 0.3252 | 0.4995 | 0.3653 | 0.3913 | 0.6221 | 0.6216 | 0.9384 |
|
| 143 |
+
| 0.3304 | 23.6407 | 80000 | 0.3245 | 0.4984 | 0.3659 | 0.3918 | 0.6224 | 0.6325 | 0.9386 |
|
| 144 |
+
| 0.3298 | 23.9362 | 81000 | 0.3243 | 0.4975 | 0.3691 | 0.3955 | 0.6228 | 0.6370 | 0.9385 |
|
| 145 |
+
| 0.3206 | 24.2317 | 82000 | 0.3249 | 0.4964 | 0.3670 | 0.3939 | 0.6203 | 0.6417 | 0.9379 |
|
| 146 |
+
| 0.3326 | 24.5272 | 83000 | 0.3265 | 0.4959 | 0.3668 | 0.3933 | 0.6191 | 0.6535 | 0.9376 |
|
| 147 |
+
| 0.3265 | 24.8227 | 84000 | 0.3244 | 0.4988 | 0.3690 | 0.3958 | 0.6227 | 0.6387 | 0.9386 |
|
| 148 |
+
| 0.3406 | 25.1182 | 85000 | 0.3242 | 0.4998 | 0.3669 | 0.3939 | 0.6220 | 0.6308 | 0.9384 |
|
| 149 |
+
| 0.3276 | 25.4137 | 86000 | 0.3241 | 0.5000 | 0.3686 | 0.3955 | 0.6227 | 0.6342 | 0.9387 |
|
| 150 |
+
| 0.3277 | 25.7092 | 87000 | 0.3240 | 0.4983 | 0.3707 | 0.3976 | 0.6235 | 0.6373 | 0.9387 |
|
| 151 |
+
| 0.315 | 26.0047 | 88000 | 0.3244 | 0.4969 | 0.3697 | 0.3966 | 0.6225 | 0.6424 | 0.9383 |
|
| 152 |
+
| 0.3306 | 26.3002 | 89000 | 0.3254 | 0.5631 | 0.3684 | 0.3968 | 0.6198 | 0.6480 | 0.9379 |
|
| 153 |
+
| 0.3341 | 26.5957 | 90000 | 0.3237 | 0.4991 | 0.3697 | 0.3968 | 0.6239 | 0.6317 | 0.9389 |
|
| 154 |
+
| 0.3344 | 26.8913 | 91000 | 0.3241 | 0.4996 | 0.3649 | 0.3920 | 0.6217 | 0.6324 | 0.9380 |
|
| 155 |
+
| 0.3286 | 27.1868 | 92000 | 0.3242 | 0.4972 | 0.3680 | 0.3951 | 0.6214 | 0.6400 | 0.9382 |
|
| 156 |
+
| 0.3217 | 27.4823 | 93000 | 0.3238 | 0.4988 | 0.3688 | 0.3959 | 0.6223 | 0.6332 | 0.9386 |
|
| 157 |
+
| 0.3241 | 27.7778 | 94000 | 0.3242 | 0.4972 | 0.3673 | 0.3944 | 0.6215 | 0.6394 | 0.9381 |
|
| 158 |
+
| 0.3287 | 28.0733 | 95000 | 0.3236 | 0.5010 | 0.3693 | 0.3964 | 0.6235 | 0.6297 | 0.9390 |
|
| 159 |
+
| 0.3381 | 28.3688 | 96000 | 0.3239 | 0.4992 | 0.3682 | 0.3954 | 0.6222 | 0.6397 | 0.9383 |
|
| 160 |
+
| 0.3287 | 28.6643 | 97000 | 0.3235 | 0.4989 | 0.3695 | 0.3964 | 0.6234 | 0.6348 | 0.9388 |
|
| 161 |
+
| 0.3185 | 28.9598 | 98000 | 0.3239 | 0.4988 | 0.3689 | 0.3961 | 0.6225 | 0.6398 | 0.9384 |
|
| 162 |
+
| 0.3289 | 29.2553 | 99000 | 0.3238 | 0.4986 | 0.3691 | 0.3963 | 0.6225 | 0.6399 | 0.9385 |
|
| 163 |
+
| 0.3301 | 29.5508 | 100000 | 0.3235 | 0.4997 | 0.3682 | 0.3951 | 0.6231 | 0.6292 | 0.9388 |
|
| 164 |
+
| 0.3261 | 29.8463 | 101000 | 0.3237 | 0.4988 | 0.3690 | 0.3961 | 0.6229 | 0.6382 | 0.9386 |
|
| 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 sha256:49584826350ac7a5594c10ec5e451e5084b00afabebeba68b908b6586bc7e971
|
| 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 sha256:88ac6e93be17eb3e0e5f326c051072452ed86a598c1226ee334b3db7fbf228b6
|
| 3 |
+
size 5304
|
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 sha256:49584826350ac7a5594c10ec5e451e5084b00afabebeba68b908b6586bc7e971
|
| 3 |
size 496772092
|