Model save
Browse files- README.md +173 -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 +1,173 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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-shell-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-shell-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: 0.3628
|
22 |
+
- Precision: 0.6557
|
23 |
+
- Recall: 0.5002
|
24 |
+
- F1 Macro: 0.5093
|
25 |
+
- Accuracy: 0.6202
|
26 |
+
- F1 Binary Minimum3: 0.8655
|
27 |
+
- F1 Binary Minimum2: 0.9307
|
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 | 6.9862 | 0.0476 | 0.2 | 0.0769 | 0.2382 | 0 | 0 |
|
64 |
+
| 0.4093 | 0.2928 | 1000 | 0.4109 | 0.5009 | 0.4593 | 0.4662 | 0.5836 | 0.8543 | 0.9213 |
|
65 |
+
| 0.4015 | 0.5857 | 2000 | 0.4013 | 0.5537 | 0.4682 | 0.4762 | 0.5887 | 0.8605 | 0.9208 |
|
66 |
+
| 0.4088 | 0.8785 | 3000 | 0.3942 | 0.5063 | 0.4684 | 0.4749 | 0.5941 | 0.8566 | 0.9245 |
|
67 |
+
| 0.399 | 1.1713 | 4000 | 0.3928 | 0.5838 | 0.4809 | 0.4902 | 0.5979 | 0.8622 | 0.9245 |
|
68 |
+
| 0.3884 | 1.4641 | 5000 | 0.3934 | 0.5752 | 0.4867 | 0.4955 | 0.6011 | 0.8632 | 0.9253 |
|
69 |
+
| 0.3962 | 1.7570 | 6000 | 0.3869 | 0.6081 | 0.4831 | 0.4927 | 0.6019 | 0.8621 | 0.9259 |
|
70 |
+
| 0.393 | 2.0498 | 7000 | 0.3999 | 0.5715 | 0.4686 | 0.4776 | 0.5826 | 0.8639 | 0.9175 |
|
71 |
+
| 0.4009 | 2.3426 | 8000 | 0.3823 | 0.6038 | 0.4872 | 0.4965 | 0.6056 | 0.8603 | 0.9271 |
|
72 |
+
| 0.3898 | 2.6354 | 9000 | 0.3895 | 0.5640 | 0.4893 | 0.4986 | 0.6018 | 0.8646 | 0.9252 |
|
73 |
+
| 0.3784 | 2.9283 | 10000 | 0.3813 | 0.6028 | 0.4817 | 0.4898 | 0.6052 | 0.8587 | 0.9278 |
|
74 |
+
| 0.4001 | 3.2211 | 11000 | 0.3806 | 0.6109 | 0.4842 | 0.4934 | 0.6051 | 0.8624 | 0.9263 |
|
75 |
+
| 0.3802 | 3.5139 | 12000 | 0.3828 | 0.6116 | 0.4782 | 0.4876 | 0.5992 | 0.8623 | 0.9244 |
|
76 |
+
| 0.3939 | 3.8067 | 13000 | 0.3832 | 0.6118 | 0.4774 | 0.4871 | 0.5980 | 0.8623 | 0.9234 |
|
77 |
+
| 0.3809 | 4.0996 | 14000 | 0.3800 | 0.6068 | 0.4884 | 0.4958 | 0.6098 | 0.8573 | 0.9287 |
|
78 |
+
| 0.3857 | 4.3924 | 15000 | 0.3786 | 0.6104 | 0.4880 | 0.4979 | 0.6063 | 0.8631 | 0.9275 |
|
79 |
+
| 0.401 | 4.6852 | 16000 | 0.3770 | 0.6241 | 0.4858 | 0.4949 | 0.6076 | 0.8613 | 0.9284 |
|
80 |
+
| 0.3737 | 4.9780 | 17000 | 0.3814 | 0.5728 | 0.4897 | 0.4991 | 0.6050 | 0.8647 | 0.9262 |
|
81 |
+
| 0.3792 | 5.2709 | 18000 | 0.3828 | 0.5930 | 0.4836 | 0.4936 | 0.6008 | 0.8651 | 0.9245 |
|
82 |
+
| 0.3882 | 5.5637 | 19000 | 0.3811 | 0.5800 | 0.4877 | 0.4973 | 0.6036 | 0.8645 | 0.9259 |
|
83 |
+
| 0.3683 | 5.8565 | 20000 | 0.3777 | 0.5816 | 0.4915 | 0.5012 | 0.6080 | 0.8643 | 0.9276 |
|
84 |
+
| 0.3816 | 6.1493 | 21000 | 0.3757 | 0.6353 | 0.4862 | 0.4945 | 0.6098 | 0.8600 | 0.9291 |
|
85 |
+
| 0.3857 | 6.4422 | 22000 | 0.3751 | 0.5801 | 0.4950 | 0.5039 | 0.6120 | 0.8627 | 0.9291 |
|
86 |
+
| 0.3948 | 6.7350 | 23000 | 0.3742 | 0.6232 | 0.4909 | 0.5004 | 0.6104 | 0.8617 | 0.9285 |
|
87 |
+
| 0.3817 | 7.0278 | 24000 | 0.3754 | 0.5829 | 0.4954 | 0.5041 | 0.6119 | 0.8626 | 0.9291 |
|
88 |
+
| 0.375 | 7.3206 | 25000 | 0.3735 | 0.6155 | 0.4916 | 0.4993 | 0.6129 | 0.8611 | 0.9291 |
|
89 |
+
| 0.3773 | 7.6135 | 26000 | 0.3730 | 0.6185 | 0.4923 | 0.5014 | 0.6119 | 0.8610 | 0.9291 |
|
90 |
+
| 0.3774 | 7.9063 | 27000 | 0.3735 | 0.6334 | 0.4879 | 0.4970 | 0.6100 | 0.8625 | 0.9288 |
|
91 |
+
| 0.3788 | 8.1991 | 28000 | 0.3736 | 0.6012 | 0.4934 | 0.5028 | 0.6114 | 0.8634 | 0.9288 |
|
92 |
+
| 0.3601 | 8.4919 | 29000 | 0.3771 | 0.5904 | 0.4921 | 0.5022 | 0.6081 | 0.8641 | 0.9276 |
|
93 |
+
| 0.3779 | 8.7848 | 30000 | 0.3724 | 0.6157 | 0.4934 | 0.5019 | 0.6133 | 0.8626 | 0.9293 |
|
94 |
+
| 0.3732 | 9.0776 | 31000 | 0.3820 | 0.5773 | 0.4939 | 0.5038 | 0.6067 | 0.8656 | 0.9272 |
|
95 |
+
| 0.3729 | 9.3704 | 32000 | 0.3725 | 0.6023 | 0.4934 | 0.5030 | 0.6117 | 0.8637 | 0.9289 |
|
96 |
+
| 0.378 | 9.6633 | 33000 | 0.3742 | 0.6092 | 0.4903 | 0.5002 | 0.6089 | 0.8638 | 0.9279 |
|
97 |
+
| 0.3794 | 9.9561 | 34000 | 0.3713 | 0.6021 | 0.4971 | 0.5063 | 0.6146 | 0.8628 | 0.9297 |
|
98 |
+
| 0.3703 | 10.2489 | 35000 | 0.3718 | 0.6222 | 0.4923 | 0.5016 | 0.6121 | 0.8642 | 0.9288 |
|
99 |
+
| 0.3614 | 10.5417 | 36000 | 0.3711 | 0.6300 | 0.4930 | 0.5023 | 0.6125 | 0.8633 | 0.9289 |
|
100 |
+
| 0.3822 | 10.8346 | 37000 | 0.3729 | 0.6324 | 0.4881 | 0.4951 | 0.6127 | 0.8591 | 0.9299 |
|
101 |
+
| 0.3775 | 11.1274 | 38000 | 0.3914 | 0.5661 | 0.4887 | 0.4986 | 0.5967 | 0.8657 | 0.9234 |
|
102 |
+
| 0.3709 | 11.4202 | 39000 | 0.3741 | 0.6303 | 0.4897 | 0.4958 | 0.6138 | 0.8569 | 0.9301 |
|
103 |
+
| 0.3749 | 11.7130 | 40000 | 0.3770 | 0.5928 | 0.4919 | 0.5021 | 0.6071 | 0.8650 | 0.9269 |
|
104 |
+
| 0.3683 | 12.0059 | 41000 | 0.3707 | 0.6075 | 0.4951 | 0.5037 | 0.6141 | 0.8645 | 0.9295 |
|
105 |
+
| 0.3772 | 12.2987 | 42000 | 0.3756 | 0.5952 | 0.4942 | 0.5042 | 0.6096 | 0.8655 | 0.9279 |
|
106 |
+
| 0.3829 | 12.5915 | 43000 | 0.3705 | 0.5929 | 0.4980 | 0.5070 | 0.6147 | 0.8643 | 0.9293 |
|
107 |
+
| 0.3736 | 12.8843 | 44000 | 0.3688 | 0.6151 | 0.4971 | 0.5059 | 0.6161 | 0.8636 | 0.9300 |
|
108 |
+
| 0.3795 | 13.1772 | 45000 | 0.3704 | 0.6011 | 0.4975 | 0.5071 | 0.6141 | 0.864 | 0.9295 |
|
109 |
+
| 0.3756 | 13.4700 | 46000 | 0.3704 | 0.6181 | 0.4967 | 0.5041 | 0.6168 | 0.8621 | 0.9296 |
|
110 |
+
| 0.3711 | 13.7628 | 47000 | 0.3684 | 0.6255 | 0.4955 | 0.5038 | 0.6160 | 0.8626 | 0.9301 |
|
111 |
+
| 0.3764 | 14.0556 | 48000 | 0.3696 | 0.6068 | 0.4973 | 0.5069 | 0.6150 | 0.8643 | 0.9295 |
|
112 |
+
| 0.3666 | 14.3485 | 49000 | 0.3688 | 0.6085 | 0.4982 | 0.5071 | 0.6158 | 0.8642 | 0.9298 |
|
113 |
+
| 0.3617 | 14.6413 | 50000 | 0.3738 | 0.6002 | 0.4948 | 0.5048 | 0.6104 | 0.8657 | 0.9282 |
|
114 |
+
| 0.381 | 14.9341 | 51000 | 0.3681 | 0.6233 | 0.4978 | 0.5074 | 0.6158 | 0.8642 | 0.9299 |
|
115 |
+
| 0.3678 | 15.2269 | 52000 | 0.3674 | 0.6279 | 0.4985 | 0.5076 | 0.6172 | 0.8645 | 0.9300 |
|
116 |
+
| 0.3818 | 15.5198 | 53000 | 0.3684 | 0.6307 | 0.4966 | 0.5043 | 0.6175 | 0.8626 | 0.9297 |
|
117 |
+
| 0.3831 | 15.8126 | 54000 | 0.3674 | 0.6156 | 0.4979 | 0.5067 | 0.6166 | 0.8639 | 0.9301 |
|
118 |
+
| 0.3737 | 16.1054 | 55000 | 0.3694 | 0.5929 | 0.4994 | 0.5086 | 0.6156 | 0.8651 | 0.9300 |
|
119 |
+
| 0.3603 | 16.3982 | 56000 | 0.3675 | 0.6336 | 0.4958 | 0.5053 | 0.6161 | 0.8643 | 0.9296 |
|
120 |
+
| 0.3696 | 16.6911 | 57000 | 0.3676 | 0.6210 | 0.4972 | 0.5068 | 0.6155 | 0.8648 | 0.9296 |
|
121 |
+
| 0.3726 | 16.9839 | 58000 | 0.3671 | 0.6501 | 0.4952 | 0.5035 | 0.6169 | 0.8627 | 0.9302 |
|
122 |
+
| 0.3817 | 17.2767 | 59000 | 0.3696 | 0.6388 | 0.4924 | 0.5023 | 0.6119 | 0.8648 | 0.9282 |
|
123 |
+
| 0.3651 | 17.5695 | 60000 | 0.3660 | 0.6414 | 0.4972 | 0.5061 | 0.6183 | 0.8639 | 0.9303 |
|
124 |
+
| 0.3649 | 17.8624 | 61000 | 0.3667 | 0.6346 | 0.4984 | 0.5061 | 0.6187 | 0.8628 | 0.9297 |
|
125 |
+
| 0.3767 | 18.1552 | 62000 | 0.3658 | 0.6303 | 0.5000 | 0.5095 | 0.6186 | 0.8641 | 0.9304 |
|
126 |
+
| 0.3619 | 18.4480 | 63000 | 0.3675 | 0.6397 | 0.4933 | 0.5000 | 0.6170 | 0.8608 | 0.9302 |
|
127 |
+
| 0.3735 | 18.7408 | 64000 | 0.3708 | 0.6168 | 0.4959 | 0.5060 | 0.6122 | 0.8663 | 0.9283 |
|
128 |
+
| 0.3673 | 19.0337 | 65000 | 0.3679 | 0.6050 | 0.5000 | 0.5093 | 0.6165 | 0.8654 | 0.9298 |
|
129 |
+
| 0.3671 | 19.3265 | 66000 | 0.3671 | 0.6489 | 0.4945 | 0.5040 | 0.6148 | 0.8649 | 0.9294 |
|
130 |
+
| 0.372 | 19.6193 | 67000 | 0.3654 | 0.6490 | 0.4975 | 0.5064 | 0.6183 | 0.8650 | 0.9302 |
|
131 |
+
| 0.3711 | 19.9122 | 68000 | 0.3649 | 0.6327 | 0.4997 | 0.5085 | 0.6188 | 0.8639 | 0.9304 |
|
132 |
+
| 0.36 | 20.2050 | 69000 | 0.3648 | 0.6307 | 0.4995 | 0.5077 | 0.6190 | 0.8648 | 0.9303 |
|
133 |
+
| 0.3718 | 20.4978 | 70000 | 0.3651 | 0.6370 | 0.4985 | 0.5079 | 0.6183 | 0.8650 | 0.9304 |
|
134 |
+
| 0.3762 | 20.7906 | 71000 | 0.3656 | 0.6448 | 0.4976 | 0.5067 | 0.6172 | 0.8653 | 0.9299 |
|
135 |
+
| 0.3602 | 21.0835 | 72000 | 0.3645 | 0.6468 | 0.4976 | 0.5059 | 0.6187 | 0.8640 | 0.9303 |
|
136 |
+
| 0.3624 | 21.3763 | 73000 | 0.3679 | 0.6015 | 0.5009 | 0.5105 | 0.6165 | 0.8662 | 0.9296 |
|
137 |
+
| 0.3774 | 21.6691 | 74000 | 0.3649 | 0.6171 | 0.5005 | 0.5094 | 0.6187 | 0.8649 | 0.9304 |
|
138 |
+
| 0.3724 | 21.9619 | 75000 | 0.3646 | 0.6370 | 0.5010 | 0.5102 | 0.6194 | 0.8654 | 0.9304 |
|
139 |
+
| 0.3762 | 22.2548 | 76000 | 0.3642 | 0.6594 | 0.4977 | 0.5068 | 0.6182 | 0.8645 | 0.9300 |
|
140 |
+
| 0.3795 | 22.5476 | 77000 | 0.3674 | 0.6267 | 0.4968 | 0.5067 | 0.6151 | 0.8659 | 0.9291 |
|
141 |
+
| 0.3774 | 22.8404 | 78000 | 0.3660 | 0.6146 | 0.4995 | 0.5090 | 0.6171 | 0.8658 | 0.9297 |
|
142 |
+
| 0.351 | 23.1332 | 79000 | 0.3648 | 0.6453 | 0.4993 | 0.5087 | 0.6180 | 0.8653 | 0.9302 |
|
143 |
+
| 0.3645 | 23.4261 | 80000 | 0.3643 | 0.6314 | 0.4953 | 0.5023 | 0.6193 | 0.8629 | 0.9304 |
|
144 |
+
| 0.3664 | 23.7189 | 81000 | 0.3644 | 0.6284 | 0.5017 | 0.5101 | 0.6202 | 0.8654 | 0.9303 |
|
145 |
+
| 0.3641 | 24.0117 | 82000 | 0.3655 | 0.6297 | 0.4991 | 0.5090 | 0.6174 | 0.8655 | 0.9299 |
|
146 |
+
| 0.3588 | 24.3045 | 83000 | 0.3646 | 0.6656 | 0.4986 | 0.5084 | 0.6179 | 0.8656 | 0.9300 |
|
147 |
+
| 0.3721 | 24.5974 | 84000 | 0.3633 | 0.6598 | 0.4988 | 0.5078 | 0.6197 | 0.8643 | 0.9307 |
|
148 |
+
| 0.3644 | 24.8902 | 85000 | 0.3636 | 0.6465 | 0.4980 | 0.5053 | 0.6202 | 0.8636 | 0.9304 |
|
149 |
+
| 0.3555 | 25.1830 | 86000 | 0.3631 | 0.6518 | 0.4985 | 0.5064 | 0.6203 | 0.8638 | 0.9306 |
|
150 |
+
| 0.3607 | 25.4758 | 87000 | 0.3641 | 0.6353 | 0.4997 | 0.5091 | 0.6186 | 0.8654 | 0.9303 |
|
151 |
+
| 0.3643 | 25.7687 | 88000 | 0.3629 | 0.6528 | 0.4991 | 0.5072 | 0.6210 | 0.8645 | 0.9308 |
|
152 |
+
| 0.3715 | 26.0615 | 89000 | 0.3644 | 0.6259 | 0.5000 | 0.5092 | 0.6184 | 0.8660 | 0.9303 |
|
153 |
+
| 0.3662 | 26.3543 | 90000 | 0.3642 | 0.6294 | 0.5007 | 0.5102 | 0.6190 | 0.8656 | 0.9303 |
|
154 |
+
| 0.36 | 26.6471 | 91000 | 0.3640 | 0.6215 | 0.5011 | 0.5104 | 0.6194 | 0.8657 | 0.9305 |
|
155 |
+
| 0.3676 | 26.9400 | 92000 | 0.3632 | 0.6607 | 0.4987 | 0.5079 | 0.6192 | 0.8656 | 0.9306 |
|
156 |
+
| 0.3614 | 27.2328 | 93000 | 0.3644 | 0.6186 | 0.5002 | 0.5094 | 0.6187 | 0.8659 | 0.9304 |
|
157 |
+
| 0.3622 | 27.5256 | 94000 | 0.3627 | 0.6478 | 0.4987 | 0.5062 | 0.6210 | 0.8642 | 0.9307 |
|
158 |
+
| 0.3431 | 27.8184 | 95000 | 0.3633 | 0.6520 | 0.5003 | 0.5097 | 0.6195 | 0.8654 | 0.9305 |
|
159 |
+
| 0.3625 | 28.1113 | 96000 | 0.3628 | 0.6578 | 0.5007 | 0.5099 | 0.6199 | 0.8656 | 0.9305 |
|
160 |
+
| 0.3795 | 28.4041 | 97000 | 0.3625 | 0.6436 | 0.4978 | 0.5054 | 0.6200 | 0.8646 | 0.9308 |
|
161 |
+
| 0.3626 | 28.6969 | 98000 | 0.3638 | 0.6261 | 0.5008 | 0.5099 | 0.6193 | 0.8657 | 0.9304 |
|
162 |
+
| 0.3701 | 28.9898 | 99000 | 0.3625 | 0.6597 | 0.4995 | 0.5083 | 0.6203 | 0.8647 | 0.9308 |
|
163 |
+
| 0.3643 | 29.2826 | 100000 | 0.3630 | 0.6583 | 0.5005 | 0.5098 | 0.6199 | 0.8654 | 0.9306 |
|
164 |
+
| 0.3594 | 29.5754 | 101000 | 0.3626 | 0.6603 | 0.4997 | 0.5086 | 0.6205 | 0.8651 | 0.9308 |
|
165 |
+
| 0.3569 | 29.8682 | 102000 | 0.3628 | 0.6557 | 0.5002 | 0.5093 | 0.6202 | 0.8655 | 0.9307 |
|
166 |
+
|
167 |
+
|
168 |
+
### Framework versions
|
169 |
+
|
170 |
+
- Transformers 4.43.4
|
171 |
+
- Pytorch 2.4.0+cu121
|
172 |
+
- Datasets 2.21.0
|
173 |
+
- 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:f6011adc984a7139c76dc13c347c36408fc4a18469dea37ab033bff2b667c9b4
|
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 sha256:08dda137201ebeb848d47fbb8cd6bf5a87b99a2685899659a303d1482720c0ee
|
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:f6011adc984a7139c76dc13c347c36408fc4a18469dea37ab033bff2b667c9b4
|
3 |
size 496772092
|