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-java-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-java-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: 0.3339
|
22 |
+
- Precision: 0.7086
|
23 |
+
- Recall: 0.4035
|
24 |
+
- F1 Macro: 0.4297
|
25 |
+
- Accuracy: 0.6370
|
26 |
+
- F1 Binary Minimum3: 0.7202
|
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 | 6.4612 | 0.0266 | 0.2 | 0.0470 | 0.1330 | 0 | 0 |
|
64 |
+
| 0.3818 | 0.2936 | 1000 | 0.3828 | 0.4885 | 0.3550 | 0.3697 | 0.6056 | 0.7105 | 0.9351 |
|
65 |
+
| 0.3773 | 0.5872 | 2000 | 0.3656 | 0.4854 | 0.3527 | 0.3704 | 0.6141 | 0.7005 | 0.9347 |
|
66 |
+
| 0.3586 | 0.8808 | 3000 | 0.3592 | 0.4868 | 0.3677 | 0.3898 | 0.6197 | 0.7037 | 0.9356 |
|
67 |
+
| 0.3726 | 1.1744 | 4000 | 0.3573 | 0.4863 | 0.3705 | 0.3927 | 0.6188 | 0.7089 | 0.9349 |
|
68 |
+
| 0.3624 | 1.4680 | 5000 | 0.3531 | 0.4963 | 0.3833 | 0.4059 | 0.6237 | 0.7191 | 0.9373 |
|
69 |
+
| 0.3586 | 1.7616 | 6000 | 0.3512 | 0.4953 | 0.3817 | 0.4051 | 0.6251 | 0.7153 | 0.9367 |
|
70 |
+
| 0.3584 | 2.0552 | 7000 | 0.3543 | 0.4865 | 0.3709 | 0.3941 | 0.6219 | 0.7010 | 0.9353 |
|
71 |
+
| 0.3628 | 2.3488 | 8000 | 0.3493 | 0.4976 | 0.3836 | 0.4070 | 0.6265 | 0.7179 | 0.9368 |
|
72 |
+
| 0.36 | 2.6424 | 9000 | 0.3543 | 0.4846 | 0.3710 | 0.3944 | 0.6212 | 0.6952 | 0.9349 |
|
73 |
+
| 0.3502 | 2.9360 | 10000 | 0.3520 | 0.4925 | 0.4040 | 0.4219 | 0.6258 | 0.7274 | 0.9369 |
|
74 |
+
| 0.3583 | 3.2296 | 11000 | 0.3478 | 0.4891 | 0.3895 | 0.4143 | 0.6257 | 0.7105 | 0.9360 |
|
75 |
+
| 0.3594 | 3.5232 | 12000 | 0.3483 | 0.4909 | 0.3958 | 0.4191 | 0.6268 | 0.7185 | 0.9368 |
|
76 |
+
| 0.3523 | 3.8168 | 13000 | 0.3510 | 0.4874 | 0.3773 | 0.4018 | 0.6237 | 0.7005 | 0.9352 |
|
77 |
+
| 0.3419 | 4.1104 | 14000 | 0.3528 | 0.4823 | 0.3869 | 0.4114 | 0.6234 | 0.7001 | 0.9341 |
|
78 |
+
| 0.3457 | 4.4040 | 15000 | 0.3485 | 0.4988 | 0.3956 | 0.4162 | 0.6274 | 0.7250 | 0.9369 |
|
79 |
+
| 0.3575 | 4.6976 | 16000 | 0.3500 | 0.5014 | 0.4013 | 0.4210 | 0.6268 | 0.7281 | 0.9377 |
|
80 |
+
| 0.3476 | 4.9912 | 17000 | 0.3499 | 0.5020 | 0.4029 | 0.4217 | 0.6275 | 0.7299 | 0.9379 |
|
81 |
+
| 0.3562 | 5.2848 | 18000 | 0.3454 | 0.4958 | 0.3933 | 0.4169 | 0.6288 | 0.7190 | 0.9371 |
|
82 |
+
| 0.3461 | 5.5784 | 19000 | 0.3451 | 0.4910 | 0.3904 | 0.4153 | 0.6281 | 0.7108 | 0.9359 |
|
83 |
+
| 0.3444 | 5.8720 | 20000 | 0.3436 | 0.4971 | 0.3864 | 0.4110 | 0.6287 | 0.7152 | 0.9364 |
|
84 |
+
| 0.3403 | 6.1656 | 21000 | 0.3450 | 0.4986 | 0.3982 | 0.4203 | 0.6298 | 0.7259 | 0.9373 |
|
85 |
+
| 0.3502 | 6.4592 | 22000 | 0.3452 | 0.4931 | 0.3828 | 0.4079 | 0.6276 | 0.7077 | 0.9361 |
|
86 |
+
| 0.3476 | 6.7528 | 23000 | 0.3542 | 0.7095 | 0.4026 | 0.4183 | 0.6243 | 0.7321 | 0.9376 |
|
87 |
+
| 0.3403 | 7.0464 | 24000 | 0.3431 | 0.4992 | 0.3905 | 0.4153 | 0.6308 | 0.7156 | 0.9369 |
|
88 |
+
| 0.3543 | 7.3400 | 25000 | 0.3443 | 0.5061 | 0.3950 | 0.4164 | 0.6303 | 0.7252 | 0.9379 |
|
89 |
+
| 0.3478 | 7.6336 | 26000 | 0.3430 | 0.4985 | 0.3962 | 0.4189 | 0.6305 | 0.7227 | 0.9372 |
|
90 |
+
| 0.3523 | 7.9272 | 27000 | 0.3425 | 0.4958 | 0.3941 | 0.4191 | 0.6309 | 0.7138 | 0.9367 |
|
91 |
+
| 0.3495 | 8.2208 | 28000 | 0.3429 | 0.4963 | 0.3880 | 0.4134 | 0.6300 | 0.7118 | 0.9368 |
|
92 |
+
| 0.3492 | 8.5144 | 29000 | 0.3492 | 0.7052 | 0.4057 | 0.4231 | 0.6278 | 0.7315 | 0.9376 |
|
93 |
+
| 0.3426 | 8.8080 | 30000 | 0.3498 | 0.7065 | 0.4029 | 0.4211 | 0.6267 | 0.7306 | 0.9379 |
|
94 |
+
| 0.3471 | 9.1016 | 31000 | 0.3440 | 0.5101 | 0.3913 | 0.4132 | 0.6302 | 0.7269 | 0.9378 |
|
95 |
+
| 0.3468 | 9.3952 | 32000 | 0.3429 | 0.5062 | 0.3969 | 0.4179 | 0.6315 | 0.7265 | 0.9376 |
|
96 |
+
| 0.3484 | 9.6888 | 33000 | 0.3410 | 0.4969 | 0.3975 | 0.4210 | 0.6312 | 0.7195 | 0.9370 |
|
97 |
+
| 0.3482 | 9.9824 | 34000 | 0.3406 | 0.5032 | 0.3898 | 0.4147 | 0.6314 | 0.7161 | 0.9375 |
|
98 |
+
| 0.3408 | 10.2760 | 35000 | 0.3409 | 0.4990 | 0.3990 | 0.4227 | 0.6320 | 0.7206 | 0.9376 |
|
99 |
+
| 0.3476 | 10.5696 | 36000 | 0.3404 | 0.5055 | 0.3874 | 0.4119 | 0.6314 | 0.7173 | 0.9379 |
|
100 |
+
| 0.3391 | 10.8632 | 37000 | 0.3429 | 0.7050 | 0.4040 | 0.4246 | 0.6315 | 0.7276 | 0.9381 |
|
101 |
+
| 0.3403 | 11.1568 | 38000 | 0.3409 | 0.7022 | 0.4016 | 0.4244 | 0.6331 | 0.7245 | 0.9377 |
|
102 |
+
| 0.3354 | 11.4504 | 39000 | 0.3425 | 0.7096 | 0.3982 | 0.4192 | 0.6317 | 0.7276 | 0.9378 |
|
103 |
+
| 0.3462 | 11.7440 | 40000 | 0.3412 | 0.4983 | 0.3915 | 0.4175 | 0.6324 | 0.7088 | 0.9371 |
|
104 |
+
| 0.3374 | 12.0376 | 41000 | 0.3437 | 0.4857 | 0.4019 | 0.4264 | 0.6297 | 0.7074 | 0.9350 |
|
105 |
+
| 0.3537 | 12.3312 | 42000 | 0.3430 | 0.7070 | 0.4052 | 0.4246 | 0.6323 | 0.7298 | 0.9378 |
|
106 |
+
| 0.3466 | 12.6248 | 43000 | 0.3388 | 0.7051 | 0.3952 | 0.4197 | 0.6336 | 0.7211 | 0.9378 |
|
107 |
+
| 0.342 | 12.9184 | 44000 | 0.3471 | 0.4908 | 0.3793 | 0.4047 | 0.6261 | 0.6961 | 0.9353 |
|
108 |
+
| 0.3437 | 13.2120 | 45000 | 0.3396 | 0.7069 | 0.3922 | 0.4161 | 0.6331 | 0.7193 | 0.9374 |
|
109 |
+
| 0.335 | 13.5056 | 46000 | 0.3395 | 0.7111 | 0.3953 | 0.4186 | 0.6338 | 0.7246 | 0.9382 |
|
110 |
+
| 0.3466 | 13.7992 | 47000 | 0.3384 | 0.7042 | 0.3986 | 0.4224 | 0.6333 | 0.7219 | 0.9378 |
|
111 |
+
| 0.353 | 14.0928 | 48000 | 0.3407 | 0.6951 | 0.3941 | 0.4209 | 0.6316 | 0.7058 | 0.9368 |
|
112 |
+
| 0.3444 | 14.3864 | 49000 | 0.3395 | 0.7014 | 0.3893 | 0.4159 | 0.6330 | 0.7119 | 0.9374 |
|
113 |
+
| 0.3328 | 14.6800 | 50000 | 0.3424 | 0.7149 | 0.4036 | 0.4235 | 0.6333 | 0.7313 | 0.9382 |
|
114 |
+
| 0.3374 | 14.9736 | 51000 | 0.3378 | 0.7023 | 0.3953 | 0.4205 | 0.6337 | 0.7168 | 0.9375 |
|
115 |
+
| 0.335 | 15.2672 | 52000 | 0.3385 | 0.7048 | 0.4025 | 0.4252 | 0.6342 | 0.7265 | 0.9379 |
|
116 |
+
| 0.3441 | 15.5608 | 53000 | 0.3384 | 0.7116 | 0.3918 | 0.4154 | 0.6336 | 0.7223 | 0.9380 |
|
117 |
+
| 0.3395 | 15.8544 | 54000 | 0.3409 | 0.6944 | 0.3944 | 0.4213 | 0.6318 | 0.7034 | 0.9367 |
|
118 |
+
| 0.3558 | 16.1480 | 55000 | 0.3373 | 0.7042 | 0.3983 | 0.4235 | 0.6354 | 0.7175 | 0.9378 |
|
119 |
+
| 0.328 | 16.4416 | 56000 | 0.3389 | 0.7083 | 0.4069 | 0.4292 | 0.6350 | 0.7280 | 0.9386 |
|
120 |
+
| 0.3416 | 16.7352 | 57000 | 0.3373 | 0.7048 | 0.4045 | 0.4284 | 0.6353 | 0.7227 | 0.9383 |
|
121 |
+
| 0.3275 | 17.0288 | 58000 | 0.3375 | 0.7096 | 0.4008 | 0.4250 | 0.6354 | 0.7241 | 0.9384 |
|
122 |
+
| 0.3528 | 17.3224 | 59000 | 0.3366 | 0.7077 | 0.3967 | 0.4213 | 0.6354 | 0.7196 | 0.9382 |
|
123 |
+
| 0.3504 | 17.6160 | 60000 | 0.3365 | 0.7039 | 0.3970 | 0.4220 | 0.6341 | 0.7166 | 0.9379 |
|
124 |
+
| 0.3292 | 17.9096 | 61000 | 0.3367 | 0.7064 | 0.4033 | 0.4280 | 0.6359 | 0.7229 | 0.9385 |
|
125 |
+
| 0.3382 | 18.2032 | 62000 | 0.3476 | 0.7160 | 0.4088 | 0.4247 | 0.6299 | 0.7363 | 0.9378 |
|
126 |
+
| 0.3349 | 18.4968 | 63000 | 0.3376 | 0.7017 | 0.3927 | 0.4195 | 0.6337 | 0.7074 | 0.9379 |
|
127 |
+
| 0.3401 | 18.7904 | 64000 | 0.3361 | 0.7030 | 0.3994 | 0.4251 | 0.6352 | 0.7154 | 0.9379 |
|
128 |
+
| 0.3365 | 19.0840 | 65000 | 0.3362 | 0.7016 | 0.4026 | 0.4276 | 0.6354 | 0.7168 | 0.9378 |
|
129 |
+
| 0.3385 | 19.3776 | 66000 | 0.3361 | 0.7031 | 0.3992 | 0.4256 | 0.6347 | 0.7134 | 0.9381 |
|
130 |
+
| 0.3395 | 19.6712 | 67000 | 0.3379 | 0.7092 | 0.4054 | 0.4282 | 0.6354 | 0.7263 | 0.9380 |
|
131 |
+
| 0.3383 | 19.9648 | 68000 | 0.3417 | 0.7138 | 0.4116 | 0.4313 | 0.6343 | 0.7337 | 0.9384 |
|
132 |
+
| 0.3356 | 20.2584 | 69000 | 0.3359 | 0.7086 | 0.3992 | 0.4235 | 0.6356 | 0.7221 | 0.9380 |
|
133 |
+
| 0.3363 | 20.5520 | 70000 | 0.3365 | 0.7088 | 0.4062 | 0.4305 | 0.6367 | 0.7260 | 0.9384 |
|
134 |
+
| 0.3333 | 20.8456 | 71000 | 0.3365 | 0.7018 | 0.3933 | 0.4201 | 0.6340 | 0.7091 | 0.9380 |
|
135 |
+
| 0.3298 | 21.1392 | 72000 | 0.3351 | 0.7074 | 0.3976 | 0.4239 | 0.6358 | 0.7160 | 0.9385 |
|
136 |
+
| 0.3372 | 21.4328 | 73000 | 0.3349 | 0.7061 | 0.4002 | 0.4261 | 0.6364 | 0.7191 | 0.9383 |
|
137 |
+
| 0.3424 | 21.7264 | 74000 | 0.3352 | 0.7052 | 0.3990 | 0.4256 | 0.6356 | 0.7153 | 0.9384 |
|
138 |
+
| 0.3393 | 22.0200 | 75000 | 0.3371 | 0.7007 | 0.3948 | 0.4223 | 0.6340 | 0.7072 | 0.9378 |
|
139 |
+
| 0.3305 | 22.3136 | 76000 | 0.3377 | 0.6977 | 0.3956 | 0.4222 | 0.6336 | 0.7065 | 0.9375 |
|
140 |
+
| 0.3343 | 22.6072 | 77000 | 0.3374 | 0.7115 | 0.4086 | 0.4310 | 0.6360 | 0.7283 | 0.9385 |
|
141 |
+
| 0.3378 | 22.9008 | 78000 | 0.3349 | 0.7064 | 0.4023 | 0.4286 | 0.6363 | 0.7180 | 0.9383 |
|
142 |
+
| 0.3443 | 23.1944 | 79000 | 0.3349 | 0.7061 | 0.4039 | 0.4309 | 0.6367 | 0.7170 | 0.9382 |
|
143 |
+
| 0.3464 | 23.4880 | 80000 | 0.3390 | 0.7120 | 0.4123 | 0.4332 | 0.6353 | 0.7313 | 0.9385 |
|
144 |
+
| 0.3355 | 23.7816 | 81000 | 0.3350 | 0.7107 | 0.4041 | 0.4287 | 0.6369 | 0.7237 | 0.9383 |
|
145 |
+
| 0.3312 | 24.0752 | 82000 | 0.3347 | 0.7080 | 0.3984 | 0.4258 | 0.6366 | 0.7152 | 0.9387 |
|
146 |
+
| 0.3526 | 24.3688 | 83000 | 0.3349 | 0.7087 | 0.4059 | 0.4309 | 0.6368 | 0.7237 | 0.9386 |
|
147 |
+
| 0.3438 | 24.6624 | 84000 | 0.3344 | 0.7090 | 0.3990 | 0.4248 | 0.6362 | 0.7201 | 0.9382 |
|
148 |
+
| 0.3365 | 24.9560 | 85000 | 0.3344 | 0.7092 | 0.4026 | 0.4293 | 0.6369 | 0.7194 | 0.9386 |
|
149 |
+
| 0.3529 | 25.2496 | 86000 | 0.3354 | 0.7081 | 0.4090 | 0.4337 | 0.6372 | 0.7263 | 0.9385 |
|
150 |
+
| 0.3398 | 25.5432 | 87000 | 0.3343 | 0.7114 | 0.4018 | 0.4280 | 0.6371 | 0.7215 | 0.9386 |
|
151 |
+
| 0.3349 | 25.8368 | 88000 | 0.3342 | 0.7074 | 0.4036 | 0.4305 | 0.6368 | 0.7173 | 0.9385 |
|
152 |
+
| 0.343 | 26.1304 | 89000 | 0.3348 | 0.7051 | 0.4011 | 0.4289 | 0.6365 | 0.7131 | 0.9382 |
|
153 |
+
| 0.3408 | 26.4240 | 90000 | 0.3345 | 0.7064 | 0.4002 | 0.4274 | 0.6368 | 0.7144 | 0.9384 |
|
154 |
+
| 0.3264 | 26.7176 | 91000 | 0.3344 | 0.7111 | 0.4038 | 0.4297 | 0.6374 | 0.7223 | 0.9387 |
|
155 |
+
| 0.3308 | 27.0112 | 92000 | 0.3341 | 0.7077 | 0.4025 | 0.4297 | 0.6369 | 0.7171 | 0.9387 |
|
156 |
+
| 0.3354 | 27.3048 | 93000 | 0.3364 | 0.7153 | 0.4059 | 0.4292 | 0.6368 | 0.7296 | 0.9384 |
|
157 |
+
| 0.3448 | 27.5984 | 94000 | 0.3340 | 0.7083 | 0.4024 | 0.4293 | 0.6367 | 0.7184 | 0.9386 |
|
158 |
+
| 0.3404 | 27.8920 | 95000 | 0.3340 | 0.7086 | 0.4014 | 0.4287 | 0.6372 | 0.7165 | 0.9386 |
|
159 |
+
| 0.3382 | 28.1856 | 96000 | 0.3339 | 0.7079 | 0.4023 | 0.4288 | 0.6367 | 0.7190 | 0.9384 |
|
160 |
+
| 0.3318 | 28.4792 | 97000 | 0.3339 | 0.7069 | 0.4049 | 0.4314 | 0.6369 | 0.7187 | 0.9385 |
|
161 |
+
| 0.331 | 28.7728 | 98000 | 0.3345 | 0.7106 | 0.4060 | 0.4310 | 0.6377 | 0.7249 | 0.9387 |
|
162 |
+
| 0.3372 | 29.0664 | 99000 | 0.3342 | 0.7104 | 0.4040 | 0.4293 | 0.6372 | 0.7228 | 0.9385 |
|
163 |
+
| 0.3401 | 29.3600 | 100000 | 0.3339 | 0.7084 | 0.4033 | 0.4295 | 0.6367 | 0.7196 | 0.9386 |
|
164 |
+
| 0.331 | 29.6536 | 101000 | 0.3341 | 0.7102 | 0.4045 | 0.4299 | 0.6372 | 0.7226 | 0.9386 |
|
165 |
+
| 0.3378 | 29.9472 | 102000 | 0.3339 | 0.7086 | 0.4035 | 0.4297 | 0.6370 | 0.7202 | 0.9386 |
|
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 sha256:59c5f16ac6912c42ff8d761c5865813855435fc95a0b6133b694104cb53ebebc
|
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 sha256:43a20d0543893c9be8a3ba5d78d838a92e8a552e6b62c17019dfe6448a774612
|
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 sha256:59c5f16ac6912c42ff8d761c5865813855435fc95a0b6133b694104cb53ebebc
|
3 |
size 496772092
|