Upload 10 files
Browse files- README.md +194 -3
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +28 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,194 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: gpt2
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
metrics:
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: models
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# models
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 3.4132
|
| 21 |
+
- Accuracy: 0.1055
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 5e-05
|
| 41 |
+
- train_batch_size: 64
|
| 42 |
+
- eval_batch_size: 256
|
| 43 |
+
- seed: 42
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- num_epochs: 3.0
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:------:|:-----:|:---------------:|:--------:|
|
| 52 |
+
| 5.4919 | 0.0221 | 100 | 4.9232 | 0.0666 |
|
| 53 |
+
| 4.381 | 0.0442 | 200 | 4.5587 | 0.0778 |
|
| 54 |
+
| 4.1011 | 0.0663 | 300 | 4.3706 | 0.0836 |
|
| 55 |
+
| 3.9359 | 0.0884 | 400 | 4.2434 | 0.0910 |
|
| 56 |
+
| 3.8161 | 0.1105 | 500 | 4.1663 | 0.0884 |
|
| 57 |
+
| 3.713 | 0.1326 | 600 | 4.0792 | 0.0939 |
|
| 58 |
+
| 3.6528 | 0.1547 | 700 | 4.0379 | 0.0925 |
|
| 59 |
+
| 3.5841 | 0.1768 | 800 | 3.9787 | 0.0936 |
|
| 60 |
+
| 3.5107 | 0.1989 | 900 | 3.9410 | 0.0946 |
|
| 61 |
+
| 3.4819 | 0.2210 | 1000 | 3.9099 | 0.0937 |
|
| 62 |
+
| 3.4388 | 0.2431 | 1100 | 3.8965 | 0.0940 |
|
| 63 |
+
| 3.4286 | 0.2653 | 1200 | 3.8627 | 0.0947 |
|
| 64 |
+
| 3.39 | 0.2874 | 1300 | 3.8378 | 0.0951 |
|
| 65 |
+
| 3.3659 | 0.3095 | 1400 | 3.8112 | 0.0960 |
|
| 66 |
+
| 3.3106 | 0.3316 | 1500 | 3.7943 | 0.0961 |
|
| 67 |
+
| 3.289 | 0.3537 | 1600 | 3.7917 | 0.0963 |
|
| 68 |
+
| 3.2774 | 0.3758 | 1700 | 3.7344 | 0.0981 |
|
| 69 |
+
| 3.2522 | 0.3979 | 1800 | 3.7512 | 0.0966 |
|
| 70 |
+
| 3.2242 | 0.4200 | 1900 | 3.7253 | 0.0980 |
|
| 71 |
+
| 3.23 | 0.4421 | 2000 | 3.7178 | 0.0977 |
|
| 72 |
+
| 3.193 | 0.4642 | 2100 | 3.6704 | 0.1013 |
|
| 73 |
+
| 3.1785 | 0.4863 | 2200 | 3.6979 | 0.0978 |
|
| 74 |
+
| 3.1548 | 0.5084 | 2300 | 3.6605 | 0.0998 |
|
| 75 |
+
| 3.1462 | 0.5305 | 2400 | 3.6843 | 0.0993 |
|
| 76 |
+
| 3.1432 | 0.5526 | 2500 | 3.6521 | 0.0995 |
|
| 77 |
+
| 3.1122 | 0.5747 | 2600 | 3.6481 | 0.0992 |
|
| 78 |
+
| 3.099 | 0.5968 | 2700 | 3.6302 | 0.1003 |
|
| 79 |
+
| 3.0936 | 0.6189 | 2800 | 3.6259 | 0.1008 |
|
| 80 |
+
| 3.1073 | 0.6410 | 2900 | 3.6341 | 0.0999 |
|
| 81 |
+
| 3.0484 | 0.6631 | 3000 | 3.6255 | 0.0998 |
|
| 82 |
+
| 3.0754 | 0.6852 | 3100 | 3.6538 | 0.1006 |
|
| 83 |
+
| 3.0563 | 0.7073 | 3200 | 3.5784 | 0.1017 |
|
| 84 |
+
| 3.0552 | 0.7294 | 3300 | 3.6309 | 0.1007 |
|
| 85 |
+
| 3.042 | 0.7515 | 3400 | 3.6018 | 0.1011 |
|
| 86 |
+
| 3.0203 | 0.7737 | 3500 | 3.5722 | 0.1010 |
|
| 87 |
+
| 3.0342 | 0.7958 | 3600 | 3.6028 | 0.1007 |
|
| 88 |
+
| 3.0306 | 0.8179 | 3700 | 3.5744 | 0.1017 |
|
| 89 |
+
| 3.0146 | 0.8400 | 3800 | 3.5778 | 0.1020 |
|
| 90 |
+
| 2.9996 | 0.8621 | 3900 | 3.5687 | 0.1015 |
|
| 91 |
+
| 3.0084 | 0.8842 | 4000 | 3.5571 | 0.1021 |
|
| 92 |
+
| 3.0052 | 0.9063 | 4100 | 3.5482 | 0.1023 |
|
| 93 |
+
| 2.9913 | 0.9284 | 4200 | 3.5543 | 0.1021 |
|
| 94 |
+
| 2.9684 | 0.9505 | 4300 | 3.5561 | 0.1022 |
|
| 95 |
+
| 2.9816 | 0.9726 | 4400 | 3.5141 | 0.1026 |
|
| 96 |
+
| 2.9628 | 0.9947 | 4500 | 3.5097 | 0.1031 |
|
| 97 |
+
| 2.9465 | 1.0168 | 4600 | 3.5310 | 0.1024 |
|
| 98 |
+
| 2.9349 | 1.0389 | 4700 | 3.5224 | 0.1033 |
|
| 99 |
+
| 2.9144 | 1.0610 | 4800 | 3.5388 | 0.1031 |
|
| 100 |
+
| 2.9476 | 1.0831 | 4900 | 3.5327 | 0.1033 |
|
| 101 |
+
| 2.9228 | 1.1052 | 5000 | 3.5370 | 0.1032 |
|
| 102 |
+
| 2.9122 | 1.1273 | 5100 | 3.5189 | 0.1033 |
|
| 103 |
+
| 2.9151 | 1.1494 | 5200 | 3.5119 | 0.1037 |
|
| 104 |
+
| 2.907 | 1.1715 | 5300 | 3.5090 | 0.1032 |
|
| 105 |
+
| 2.9189 | 1.1936 | 5400 | 3.5097 | 0.1037 |
|
| 106 |
+
| 2.9065 | 1.2157 | 5500 | 3.5006 | 0.1038 |
|
| 107 |
+
| 2.9075 | 1.2378 | 5600 | 3.4733 | 0.1042 |
|
| 108 |
+
| 2.8725 | 1.2599 | 5700 | 3.4937 | 0.1040 |
|
| 109 |
+
| 2.884 | 1.2821 | 5800 | 3.4992 | 0.1036 |
|
| 110 |
+
| 2.918 | 1.3042 | 5900 | 3.4763 | 0.1040 |
|
| 111 |
+
| 2.8647 | 1.3263 | 6000 | 3.5051 | 0.1041 |
|
| 112 |
+
| 2.8706 | 1.3484 | 6100 | 3.4771 | 0.1040 |
|
| 113 |
+
| 2.881 | 1.3705 | 6200 | 3.5170 | 0.1039 |
|
| 114 |
+
| 2.8788 | 1.3926 | 6300 | 3.5088 | 0.1040 |
|
| 115 |
+
| 2.8865 | 1.4147 | 6400 | 3.4944 | 0.1040 |
|
| 116 |
+
| 2.8605 | 1.4368 | 6500 | 3.5082 | 0.1042 |
|
| 117 |
+
| 2.8764 | 1.4589 | 6600 | 3.4666 | 0.1041 |
|
| 118 |
+
| 2.8828 | 1.4810 | 6700 | 3.5027 | 0.1041 |
|
| 119 |
+
| 2.8522 | 1.5031 | 6800 | 3.4695 | 0.1044 |
|
| 120 |
+
| 2.8674 | 1.5252 | 6900 | 3.4941 | 0.1041 |
|
| 121 |
+
| 2.8239 | 1.5473 | 7000 | 3.4779 | 0.1043 |
|
| 122 |
+
| 2.8633 | 1.5694 | 7100 | 3.5005 | 0.1046 |
|
| 123 |
+
| 2.8383 | 1.5915 | 7200 | 3.5013 | 0.1046 |
|
| 124 |
+
| 2.8555 | 1.6136 | 7300 | 3.4846 | 0.1046 |
|
| 125 |
+
| 2.8497 | 1.6357 | 7400 | 3.4165 | 0.1071 |
|
| 126 |
+
| 2.857 | 1.6578 | 7500 | 3.4531 | 0.1054 |
|
| 127 |
+
| 2.8239 | 1.6799 | 7600 | 3.4938 | 0.1048 |
|
| 128 |
+
| 2.8145 | 1.7020 | 7700 | 3.4814 | 0.1050 |
|
| 129 |
+
| 2.8429 | 1.7241 | 7800 | 3.4734 | 0.1043 |
|
| 130 |
+
| 2.8146 | 1.7462 | 7900 | 3.4483 | 0.1048 |
|
| 131 |
+
| 2.8285 | 1.7683 | 8000 | 3.4382 | 0.1051 |
|
| 132 |
+
| 2.8254 | 1.7905 | 8100 | 3.4824 | 0.1049 |
|
| 133 |
+
| 2.8318 | 1.8126 | 8200 | 3.4698 | 0.1053 |
|
| 134 |
+
| 2.8299 | 1.8347 | 8300 | 3.4737 | 0.1045 |
|
| 135 |
+
| 2.8332 | 1.8568 | 8400 | 3.4688 | 0.1051 |
|
| 136 |
+
| 2.8274 | 1.8789 | 8500 | 3.4308 | 0.1054 |
|
| 137 |
+
| 2.8171 | 1.9010 | 8600 | 3.4647 | 0.1053 |
|
| 138 |
+
| 2.8355 | 1.9231 | 8700 | 3.4586 | 0.1047 |
|
| 139 |
+
| 2.8031 | 1.9452 | 8800 | 3.4529 | 0.1049 |
|
| 140 |
+
| 2.8234 | 1.9673 | 8900 | 3.4379 | 0.1053 |
|
| 141 |
+
| 2.8097 | 1.9894 | 9000 | 3.4536 | 0.1055 |
|
| 142 |
+
| 2.7828 | 2.0115 | 9100 | 3.4409 | 0.1055 |
|
| 143 |
+
| 2.8027 | 2.0336 | 9200 | 3.4506 | 0.1055 |
|
| 144 |
+
| 2.7836 | 2.0557 | 9300 | 3.4617 | 0.1053 |
|
| 145 |
+
| 2.7874 | 2.0778 | 9400 | 3.4509 | 0.1050 |
|
| 146 |
+
| 2.7894 | 2.0999 | 9500 | 3.4132 | 0.1055 |
|
| 147 |
+
| 2.7863 | 2.1220 | 9600 | 3.4198 | 0.1055 |
|
| 148 |
+
| 2.7663 | 2.1441 | 9700 | 3.4524 | 0.1054 |
|
| 149 |
+
| 2.7846 | 2.1662 | 9800 | 3.4518 | 0.1056 |
|
| 150 |
+
| 2.7985 | 2.1883 | 9900 | 3.4453 | 0.1054 |
|
| 151 |
+
| 2.7947 | 2.2104 | 10000 | 3.4307 | 0.1056 |
|
| 152 |
+
| 2.7946 | 2.2325 | 10100 | 3.4598 | 0.1055 |
|
| 153 |
+
| 2.783 | 2.2546 | 10200 | 3.4523 | 0.1055 |
|
| 154 |
+
| 2.7763 | 2.2767 | 10300 | 3.4441 | 0.1056 |
|
| 155 |
+
| 2.7786 | 2.2989 | 10400 | 3.4659 | 0.1052 |
|
| 156 |
+
| 2.7672 | 2.3210 | 10500 | 3.4527 | 0.1053 |
|
| 157 |
+
| 2.767 | 2.3431 | 10600 | 3.4608 | 0.1053 |
|
| 158 |
+
| 2.7972 | 2.3652 | 10700 | 3.4277 | 0.1060 |
|
| 159 |
+
| 2.7958 | 2.3873 | 10800 | 3.4488 | 0.1053 |
|
| 160 |
+
| 2.774 | 2.4094 | 10900 | 3.4499 | 0.1056 |
|
| 161 |
+
| 2.7802 | 2.4315 | 11000 | 3.4281 | 0.1056 |
|
| 162 |
+
| 2.7576 | 2.4536 | 11100 | 3.4363 | 0.1058 |
|
| 163 |
+
| 2.76 | 2.4757 | 11200 | 3.4393 | 0.1059 |
|
| 164 |
+
| 2.7792 | 2.4978 | 11300 | 3.4389 | 0.1056 |
|
| 165 |
+
| 2.7804 | 2.5199 | 11400 | 3.4378 | 0.1060 |
|
| 166 |
+
| 2.7804 | 2.5420 | 11500 | 3.4236 | 0.1062 |
|
| 167 |
+
| 2.7835 | 2.5641 | 11600 | 3.4372 | 0.1060 |
|
| 168 |
+
| 2.7444 | 2.5862 | 11700 | 3.4518 | 0.1058 |
|
| 169 |
+
| 2.7636 | 2.6083 | 11800 | 3.4181 | 0.1060 |
|
| 170 |
+
| 2.7675 | 2.6304 | 11900 | 3.4290 | 0.1057 |
|
| 171 |
+
| 2.7487 | 2.6525 | 12000 | 3.4279 | 0.1058 |
|
| 172 |
+
| 2.7529 | 2.6746 | 12100 | 3.4300 | 0.1058 |
|
| 173 |
+
| 2.7819 | 2.6967 | 12200 | 3.4153 | 0.1062 |
|
| 174 |
+
| 2.7595 | 2.7188 | 12300 | 3.4477 | 0.1058 |
|
| 175 |
+
| 2.7585 | 2.7409 | 12400 | 3.4171 | 0.1059 |
|
| 176 |
+
| 2.7367 | 2.7630 | 12500 | 3.4297 | 0.1059 |
|
| 177 |
+
| 2.7701 | 2.7851 | 12600 | 3.4184 | 0.1058 |
|
| 178 |
+
| 2.7811 | 2.8073 | 12700 | 3.4334 | 0.1059 |
|
| 179 |
+
| 2.768 | 2.8294 | 12800 | 3.4295 | 0.1062 |
|
| 180 |
+
| 2.7715 | 2.8515 | 12900 | 3.4443 | 0.1058 |
|
| 181 |
+
| 2.7479 | 2.8736 | 13000 | 3.4344 | 0.1057 |
|
| 182 |
+
| 2.7479 | 2.8957 | 13100 | 3.4395 | 0.1059 |
|
| 183 |
+
| 2.7688 | 2.9178 | 13200 | 3.4270 | 0.1058 |
|
| 184 |
+
| 2.7708 | 2.9399 | 13300 | 3.4311 | 0.1059 |
|
| 185 |
+
| 2.7443 | 2.9620 | 13400 | 3.4314 | 0.1059 |
|
| 186 |
+
| 2.7428 | 2.9841 | 13500 | 3.4300 | 0.1059 |
|
| 187 |
+
|
| 188 |
+
|
| 189 |
+
### Framework versions
|
| 190 |
+
|
| 191 |
+
- Transformers 4.41.2
|
| 192 |
+
- Pytorch 2.3.1+cu121
|
| 193 |
+
- Datasets 2.20.0
|
| 194 |
+
- Tokenizers 0.19.1
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.41.2",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50257
|
| 39 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "4.41.2"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25064e9835a94378d87691fecce17995e4b96025247edfe2ac5475268d5c55c2
|
| 3 |
+
size 497774208
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "[PAD]",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
}
|
| 20 |
+
},
|
| 21 |
+
"bos_token": "<|endoftext|>",
|
| 22 |
+
"clean_up_tokenization_spaces": true,
|
| 23 |
+
"eos_token": "<|endoftext|>",
|
| 24 |
+
"model_max_length": 128,
|
| 25 |
+
"pad_token": "[PAD]",
|
| 26 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 27 |
+
"unk_token": "<|endoftext|>"
|
| 28 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0eed350dac80b446dba0f898c91902f38c0204879b37062ec310b8533af905ad
|
| 3 |
+
size 5176
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|