Model save
Browse files- README.md +171 -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 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-c-sharp-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-c-sharp-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: 0.3976
|
| 22 |
+
- Precision: 0.4844
|
| 23 |
+
- Recall: 0.3567
|
| 24 |
+
- F1 Macro: 0.3780
|
| 25 |
+
- Accuracy: 0.5809
|
| 26 |
+
- F1 Binary Minimum3: 0.6447
|
| 27 |
+
- F1 Binary Minimum2: 0.9079
|
| 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 | 5.5906 | 0.0374 | 0.2 | 0.0630 | 0.1870 | 0 | 0 |
|
| 64 |
+
| 0.4303 | 0.2991 | 1000 | 0.4344 | 0.4626 | 0.3128 | 0.3229 | 0.5565 | 0.5903 | 0.9038 |
|
| 65 |
+
| 0.4238 | 0.5983 | 2000 | 0.4268 | 0.4721 | 0.3366 | 0.3523 | 0.5667 | 0.6412 | 0.9052 |
|
| 66 |
+
| 0.4281 | 0.8974 | 3000 | 0.4229 | 0.4743 | 0.3374 | 0.3523 | 0.5685 | 0.6456 | 0.9051 |
|
| 67 |
+
| 0.4149 | 1.1965 | 4000 | 0.4171 | 0.4751 | 0.3347 | 0.3506 | 0.5700 | 0.6347 | 0.9056 |
|
| 68 |
+
| 0.4229 | 1.4957 | 5000 | 0.4192 | 0.4738 | 0.3493 | 0.3657 | 0.5699 | 0.6557 | 0.9058 |
|
| 69 |
+
| 0.4321 | 1.7948 | 6000 | 0.4126 | 0.4755 | 0.3452 | 0.3648 | 0.5736 | 0.6351 | 0.9063 |
|
| 70 |
+
| 0.408 | 2.0939 | 7000 | 0.4157 | 0.4677 | 0.3417 | 0.3617 | 0.5693 | 0.6088 | 0.9045 |
|
| 71 |
+
| 0.4117 | 2.3931 | 8000 | 0.4125 | 0.4783 | 0.3465 | 0.3635 | 0.5726 | 0.6492 | 0.9060 |
|
| 72 |
+
| 0.4172 | 2.6922 | 9000 | 0.4219 | 0.4819 | 0.3495 | 0.3611 | 0.5671 | 0.6665 | 0.9051 |
|
| 73 |
+
| 0.4061 | 2.9913 | 10000 | 0.4140 | 0.4737 | 0.3336 | 0.3515 | 0.5689 | 0.6022 | 0.9053 |
|
| 74 |
+
| 0.4192 | 3.2905 | 11000 | 0.4098 | 0.4805 | 0.3458 | 0.3634 | 0.5728 | 0.6487 | 0.9061 |
|
| 75 |
+
| 0.4218 | 3.5896 | 12000 | 0.4082 | 0.4836 | 0.3324 | 0.3484 | 0.5723 | 0.6237 | 0.9068 |
|
| 76 |
+
| 0.4007 | 3.8887 | 13000 | 0.4122 | 0.4829 | 0.3514 | 0.3671 | 0.5730 | 0.6594 | 0.9062 |
|
| 77 |
+
| 0.4122 | 4.1879 | 14000 | 0.4061 | 0.4789 | 0.3466 | 0.3666 | 0.5754 | 0.6369 | 0.9068 |
|
| 78 |
+
| 0.406 | 4.4870 | 15000 | 0.4070 | 0.4810 | 0.3521 | 0.3717 | 0.5753 | 0.6480 | 0.9068 |
|
| 79 |
+
| 0.4184 | 4.7861 | 16000 | 0.4060 | 0.4809 | 0.3460 | 0.3656 | 0.5752 | 0.6390 | 0.9069 |
|
| 80 |
+
| 0.4124 | 5.0853 | 17000 | 0.4057 | 0.4782 | 0.3491 | 0.3698 | 0.5763 | 0.6358 | 0.9065 |
|
| 81 |
+
| 0.4038 | 5.3844 | 18000 | 0.4130 | 0.4841 | 0.3473 | 0.3608 | 0.5697 | 0.6569 | 0.9054 |
|
| 82 |
+
| 0.4182 | 5.6835 | 19000 | 0.4048 | 0.4799 | 0.3431 | 0.3622 | 0.5748 | 0.6352 | 0.9066 |
|
| 83 |
+
| 0.4067 | 5.9827 | 20000 | 0.4047 | 0.4801 | 0.3520 | 0.3736 | 0.5766 | 0.6364 | 0.9073 |
|
| 84 |
+
| 0.4106 | 6.2818 | 21000 | 0.4096 | 0.4741 | 0.3349 | 0.3521 | 0.5708 | 0.6032 | 0.9056 |
|
| 85 |
+
| 0.4046 | 6.5809 | 22000 | 0.4043 | 0.4834 | 0.3408 | 0.3597 | 0.5753 | 0.6285 | 0.9069 |
|
| 86 |
+
| 0.3939 | 6.8800 | 23000 | 0.4075 | 0.4798 | 0.3597 | 0.3779 | 0.5763 | 0.6575 | 0.9072 |
|
| 87 |
+
| 0.4154 | 7.1792 | 24000 | 0.4057 | 0.4756 | 0.3465 | 0.3672 | 0.5754 | 0.6242 | 0.9063 |
|
| 88 |
+
| 0.4033 | 7.4783 | 25000 | 0.4054 | 0.4785 | 0.3449 | 0.3657 | 0.5749 | 0.6156 | 0.9067 |
|
| 89 |
+
| 0.4152 | 7.7774 | 26000 | 0.4033 | 0.4770 | 0.3500 | 0.3713 | 0.5765 | 0.6341 | 0.9067 |
|
| 90 |
+
| 0.4093 | 8.0766 | 27000 | 0.4046 | 0.4826 | 0.3528 | 0.3727 | 0.5769 | 0.6516 | 0.9075 |
|
| 91 |
+
| 0.404 | 8.3757 | 28000 | 0.4038 | 0.4835 | 0.3491 | 0.3683 | 0.5757 | 0.6448 | 0.9074 |
|
| 92 |
+
| 0.4173 | 8.6748 | 29000 | 0.4149 | 0.4835 | 0.3529 | 0.3642 | 0.5700 | 0.6695 | 0.9052 |
|
| 93 |
+
| 0.4199 | 8.9740 | 30000 | 0.4045 | 0.4829 | 0.3547 | 0.3735 | 0.5776 | 0.6551 | 0.9072 |
|
| 94 |
+
| 0.4053 | 9.2731 | 31000 | 0.4091 | 0.4681 | 0.3463 | 0.3670 | 0.5712 | 0.6069 | 0.9040 |
|
| 95 |
+
| 0.4072 | 9.5722 | 32000 | 0.4027 | 0.4801 | 0.3464 | 0.3671 | 0.5765 | 0.6280 | 0.9072 |
|
| 96 |
+
| 0.3984 | 9.8714 | 33000 | 0.4029 | 0.4786 | 0.3568 | 0.3772 | 0.5779 | 0.6508 | 0.9075 |
|
| 97 |
+
| 0.4075 | 10.1705 | 34000 | 0.4084 | 0.4716 | 0.3434 | 0.3639 | 0.5710 | 0.6008 | 0.9052 |
|
| 98 |
+
| 0.4016 | 10.4696 | 35000 | 0.4021 | 0.4817 | 0.3527 | 0.3732 | 0.5781 | 0.6445 | 0.9078 |
|
| 99 |
+
| 0.4077 | 10.7688 | 36000 | 0.4066 | 0.4759 | 0.3627 | 0.3824 | 0.5759 | 0.6582 | 0.9076 |
|
| 100 |
+
| 0.4039 | 11.0679 | 37000 | 0.4069 | 0.4707 | 0.3473 | 0.3683 | 0.5731 | 0.6108 | 0.9052 |
|
| 101 |
+
| 0.4107 | 11.3670 | 38000 | 0.4021 | 0.4807 | 0.3522 | 0.3741 | 0.5784 | 0.6346 | 0.9075 |
|
| 102 |
+
| 0.4208 | 11.6662 | 39000 | 0.4046 | 0.4872 | 0.3498 | 0.3674 | 0.5763 | 0.6531 | 0.9072 |
|
| 103 |
+
| 0.4028 | 11.9653 | 40000 | 0.4019 | 0.4788 | 0.3501 | 0.3716 | 0.5772 | 0.6292 | 0.9070 |
|
| 104 |
+
| 0.4084 | 12.2644 | 41000 | 0.4067 | 0.4809 | 0.3613 | 0.3789 | 0.5761 | 0.6635 | 0.9075 |
|
| 105 |
+
| 0.397 | 12.5636 | 42000 | 0.4023 | 0.4864 | 0.3506 | 0.3697 | 0.5775 | 0.6500 | 0.9077 |
|
| 106 |
+
| 0.4122 | 12.8627 | 43000 | 0.4012 | 0.4791 | 0.3516 | 0.3732 | 0.5781 | 0.6370 | 0.9066 |
|
| 107 |
+
| 0.3996 | 13.1618 | 44000 | 0.4046 | 0.4829 | 0.3565 | 0.3747 | 0.5766 | 0.6589 | 0.9075 |
|
| 108 |
+
| 0.4065 | 13.4610 | 45000 | 0.4015 | 0.4853 | 0.3487 | 0.3681 | 0.5782 | 0.6420 | 0.9073 |
|
| 109 |
+
| 0.4099 | 13.7601 | 46000 | 0.4044 | 0.4824 | 0.3576 | 0.3758 | 0.5773 | 0.6605 | 0.9074 |
|
| 110 |
+
| 0.3996 | 14.0592 | 47000 | 0.4007 | 0.4839 | 0.3476 | 0.3687 | 0.5782 | 0.6298 | 0.9074 |
|
| 111 |
+
| 0.4141 | 14.3584 | 48000 | 0.4022 | 0.4816 | 0.3584 | 0.3777 | 0.5781 | 0.6554 | 0.9074 |
|
| 112 |
+
| 0.4148 | 14.6575 | 49000 | 0.4021 | 0.4841 | 0.3401 | 0.3593 | 0.5760 | 0.6213 | 0.9071 |
|
| 113 |
+
| 0.399 | 14.9566 | 50000 | 0.4004 | 0.4815 | 0.3569 | 0.3784 | 0.5793 | 0.6447 | 0.9078 |
|
| 114 |
+
| 0.4095 | 15.2558 | 51000 | 0.4052 | 0.4750 | 0.3464 | 0.3675 | 0.5739 | 0.6091 | 0.9056 |
|
| 115 |
+
| 0.407 | 15.5549 | 52000 | 0.4006 | 0.4829 | 0.3557 | 0.3767 | 0.5792 | 0.6466 | 0.9078 |
|
| 116 |
+
| 0.3992 | 15.8540 | 53000 | 0.4014 | 0.4836 | 0.3535 | 0.3726 | 0.5781 | 0.6494 | 0.9070 |
|
| 117 |
+
| 0.4021 | 16.1532 | 54000 | 0.4037 | 0.4820 | 0.3580 | 0.3759 | 0.5770 | 0.6597 | 0.9073 |
|
| 118 |
+
| 0.4098 | 16.4523 | 55000 | 0.4034 | 0.4853 | 0.3519 | 0.3693 | 0.5757 | 0.6536 | 0.9066 |
|
| 119 |
+
| 0.4091 | 16.7514 | 56000 | 0.4000 | 0.4830 | 0.3523 | 0.3726 | 0.5782 | 0.6419 | 0.9075 |
|
| 120 |
+
| 0.3989 | 17.0506 | 57000 | 0.3997 | 0.4800 | 0.3546 | 0.3763 | 0.5786 | 0.6380 | 0.9076 |
|
| 121 |
+
| 0.3974 | 17.3497 | 58000 | 0.4038 | 0.4847 | 0.3574 | 0.3745 | 0.5770 | 0.6588 | 0.9070 |
|
| 122 |
+
| 0.4046 | 17.6488 | 59000 | 0.3997 | 0.4837 | 0.3484 | 0.3692 | 0.5785 | 0.6328 | 0.9074 |
|
| 123 |
+
| 0.4033 | 17.9480 | 60000 | 0.4028 | 0.4849 | 0.3571 | 0.3752 | 0.5780 | 0.6599 | 0.9076 |
|
| 124 |
+
| 0.3988 | 18.2471 | 61000 | 0.4002 | 0.4767 | 0.3544 | 0.3768 | 0.5784 | 0.6307 | 0.9069 |
|
| 125 |
+
| 0.4064 | 18.5462 | 62000 | 0.3995 | 0.4853 | 0.3551 | 0.3761 | 0.5799 | 0.6450 | 0.9079 |
|
| 126 |
+
| 0.4107 | 18.8453 | 63000 | 0.4002 | 0.4855 | 0.3546 | 0.3744 | 0.5791 | 0.6522 | 0.9078 |
|
| 127 |
+
| 0.4047 | 19.1445 | 64000 | 0.3992 | 0.4864 | 0.3526 | 0.3729 | 0.5798 | 0.6456 | 0.9079 |
|
| 128 |
+
| 0.405 | 19.4436 | 65000 | 0.3991 | 0.4860 | 0.3483 | 0.3679 | 0.5786 | 0.6416 | 0.9075 |
|
| 129 |
+
| 0.4002 | 19.7427 | 66000 | 0.4000 | 0.4853 | 0.3516 | 0.3709 | 0.5781 | 0.6473 | 0.9072 |
|
| 130 |
+
| 0.393 | 20.0419 | 67000 | 0.4005 | 0.4854 | 0.3569 | 0.3763 | 0.5799 | 0.6552 | 0.9078 |
|
| 131 |
+
| 0.3946 | 20.3410 | 68000 | 0.4027 | 0.4822 | 0.3587 | 0.3765 | 0.5770 | 0.6609 | 0.9074 |
|
| 132 |
+
| 0.4107 | 20.6401 | 69000 | 0.4041 | 0.4848 | 0.3575 | 0.3740 | 0.5759 | 0.6605 | 0.9072 |
|
| 133 |
+
| 0.4044 | 20.9393 | 70000 | 0.3985 | 0.4832 | 0.3554 | 0.3771 | 0.5801 | 0.6423 | 0.9078 |
|
| 134 |
+
| 0.3865 | 21.2384 | 71000 | 0.3987 | 0.4828 | 0.3595 | 0.3812 | 0.5807 | 0.6462 | 0.9083 |
|
| 135 |
+
| 0.3958 | 21.5375 | 72000 | 0.3985 | 0.4831 | 0.3559 | 0.3779 | 0.5799 | 0.6385 | 0.9078 |
|
| 136 |
+
| 0.4097 | 21.8367 | 73000 | 0.3992 | 0.4886 | 0.3533 | 0.3734 | 0.5796 | 0.6464 | 0.9074 |
|
| 137 |
+
| 0.4098 | 22.1358 | 74000 | 0.3986 | 0.4839 | 0.3558 | 0.3774 | 0.5803 | 0.6428 | 0.9079 |
|
| 138 |
+
| 0.4058 | 22.4349 | 75000 | 0.3988 | 0.4805 | 0.3553 | 0.3776 | 0.5794 | 0.6366 | 0.9075 |
|
| 139 |
+
| 0.389 | 22.7341 | 76000 | 0.3993 | 0.4852 | 0.3574 | 0.3775 | 0.5797 | 0.6530 | 0.9079 |
|
| 140 |
+
| 0.3903 | 23.0332 | 77000 | 0.4034 | 0.6830 | 0.3632 | 0.3816 | 0.5771 | 0.6624 | 0.9076 |
|
| 141 |
+
| 0.4029 | 23.3323 | 78000 | 0.3996 | 0.4812 | 0.3492 | 0.3707 | 0.5777 | 0.6267 | 0.9070 |
|
| 142 |
+
| 0.3989 | 23.6315 | 79000 | 0.3987 | 0.4817 | 0.3599 | 0.3809 | 0.5815 | 0.6518 | 0.9081 |
|
| 143 |
+
| 0.4032 | 23.9306 | 80000 | 0.3983 | 0.4849 | 0.3550 | 0.3760 | 0.5807 | 0.6451 | 0.9081 |
|
| 144 |
+
| 0.3981 | 24.2297 | 81000 | 0.3980 | 0.4820 | 0.3570 | 0.3783 | 0.5805 | 0.6444 | 0.9077 |
|
| 145 |
+
| 0.3913 | 24.5289 | 82000 | 0.3981 | 0.4825 | 0.3533 | 0.3750 | 0.5799 | 0.6365 | 0.9078 |
|
| 146 |
+
| 0.3964 | 24.8280 | 83000 | 0.3985 | 0.4883 | 0.3532 | 0.3733 | 0.5802 | 0.6448 | 0.9078 |
|
| 147 |
+
| 0.3942 | 25.1271 | 84000 | 0.3978 | 0.4843 | 0.3526 | 0.3740 | 0.5800 | 0.6394 | 0.9079 |
|
| 148 |
+
| 0.4057 | 25.4263 | 85000 | 0.3984 | 0.4870 | 0.3580 | 0.3787 | 0.5812 | 0.6500 | 0.9082 |
|
| 149 |
+
| 0.4076 | 25.7254 | 86000 | 0.4014 | 0.4862 | 0.3555 | 0.3726 | 0.5777 | 0.6590 | 0.9072 |
|
| 150 |
+
| 0.4003 | 26.0245 | 87000 | 0.3979 | 0.4804 | 0.3602 | 0.3820 | 0.5809 | 0.6442 | 0.9079 |
|
| 151 |
+
| 0.3979 | 26.3237 | 88000 | 0.3981 | 0.4845 | 0.3570 | 0.3778 | 0.5803 | 0.6472 | 0.9077 |
|
| 152 |
+
| 0.4201 | 26.6228 | 89000 | 0.3998 | 0.4827 | 0.3603 | 0.3799 | 0.5793 | 0.6561 | 0.9079 |
|
| 153 |
+
| 0.4014 | 26.9219 | 90000 | 0.3977 | 0.4844 | 0.3569 | 0.3782 | 0.5810 | 0.6457 | 0.9081 |
|
| 154 |
+
| 0.4031 | 27.2211 | 91000 | 0.3977 | 0.4838 | 0.3584 | 0.3802 | 0.5816 | 0.6442 | 0.9081 |
|
| 155 |
+
| 0.3843 | 27.5202 | 92000 | 0.3985 | 0.4876 | 0.3551 | 0.3751 | 0.5803 | 0.6500 | 0.9079 |
|
| 156 |
+
| 0.405 | 27.8193 | 93000 | 0.3978 | 0.4846 | 0.3566 | 0.3776 | 0.5809 | 0.6456 | 0.9079 |
|
| 157 |
+
| 0.394 | 28.1185 | 94000 | 0.3978 | 0.4828 | 0.3596 | 0.3811 | 0.5812 | 0.6483 | 0.9080 |
|
| 158 |
+
| 0.4047 | 28.4176 | 95000 | 0.3976 | 0.4856 | 0.3553 | 0.3768 | 0.5808 | 0.6426 | 0.9080 |
|
| 159 |
+
| 0.3874 | 28.7167 | 96000 | 0.3976 | 0.4844 | 0.3572 | 0.3788 | 0.5813 | 0.6447 | 0.9082 |
|
| 160 |
+
| 0.3974 | 29.0159 | 97000 | 0.3976 | 0.4852 | 0.3570 | 0.3786 | 0.5810 | 0.6441 | 0.9081 |
|
| 161 |
+
| 0.4096 | 29.3150 | 98000 | 0.3978 | 0.4855 | 0.3581 | 0.3791 | 0.5809 | 0.6473 | 0.9080 |
|
| 162 |
+
| 0.397 | 29.6141 | 99000 | 0.3976 | 0.4850 | 0.3586 | 0.3801 | 0.5815 | 0.6462 | 0.9081 |
|
| 163 |
+
| 0.4048 | 29.9133 | 100000 | 0.3976 | 0.4844 | 0.3567 | 0.3780 | 0.5809 | 0.6447 | 0.9079 |
|
| 164 |
+
|
| 165 |
+
|
| 166 |
+
### Framework versions
|
| 167 |
+
|
| 168 |
+
- Transformers 4.43.4
|
| 169 |
+
- Pytorch 2.4.0+cu121
|
| 170 |
+
- Datasets 2.21.0
|
| 171 |
+
- 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:ec399b901d8987abfb5696948275aac5507d8c430a9b4d153a348264a0a11883
|
| 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 sha256:58884e58777a7d9dcd661486cb3d1a2c3303122b035099091a33d59731e772a6
|
| 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:ec399b901d8987abfb5696948275aac5507d8c430a9b4d153a348264a0a11883
|
| 3 |
size 496772092
|