End of training
Browse files- README.md +486 -0
- config.json +41 -0
- generation_config.json +6 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,486 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: gpt2-medium
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: gpt2-medium-custom-functions-dataset-python
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# gpt2-medium-custom-functions-dataset-python
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.4735
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 2e-05
|
| 38 |
+
- train_batch_size: 8
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- num_epochs: 10
|
| 44 |
+
|
| 45 |
+
### Training results
|
| 46 |
+
|
| 47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 49 |
+
| 2.6637 | 0.02 | 1 | 2.1553 |
|
| 50 |
+
| 2.4565 | 0.05 | 2 | 2.0239 |
|
| 51 |
+
| 2.1968 | 0.07 | 3 | 1.9137 |
|
| 52 |
+
| 2.2327 | 0.09 | 4 | 1.8194 |
|
| 53 |
+
| 2.0672 | 0.12 | 5 | 1.7425 |
|
| 54 |
+
| 1.9292 | 0.14 | 6 | 1.6721 |
|
| 55 |
+
| 1.8293 | 0.16 | 7 | 1.6049 |
|
| 56 |
+
| 1.71 | 0.19 | 8 | 1.5385 |
|
| 57 |
+
| 1.8569 | 0.21 | 9 | 1.4786 |
|
| 58 |
+
| 1.7208 | 0.23 | 10 | 1.4236 |
|
| 59 |
+
| 1.6461 | 0.26 | 11 | 1.3770 |
|
| 60 |
+
| 1.6146 | 0.28 | 12 | 1.3361 |
|
| 61 |
+
| 1.5799 | 0.3 | 13 | 1.3006 |
|
| 62 |
+
| 1.515 | 0.33 | 14 | 1.2690 |
|
| 63 |
+
| 1.4448 | 0.35 | 15 | 1.2488 |
|
| 64 |
+
| 1.2871 | 0.37 | 16 | 1.2254 |
|
| 65 |
+
| 1.6566 | 0.4 | 17 | 1.1972 |
|
| 66 |
+
| 1.4823 | 0.42 | 18 | 1.1638 |
|
| 67 |
+
| 1.4655 | 0.44 | 19 | 1.1379 |
|
| 68 |
+
| 1.3227 | 0.47 | 20 | 1.1172 |
|
| 69 |
+
| 1.4135 | 0.49 | 21 | 1.0973 |
|
| 70 |
+
| 1.4835 | 0.51 | 22 | 1.0784 |
|
| 71 |
+
| 1.401 | 0.53 | 23 | 1.0607 |
|
| 72 |
+
| 1.3294 | 0.56 | 24 | 1.0455 |
|
| 73 |
+
| 1.4781 | 0.58 | 25 | 1.0302 |
|
| 74 |
+
| 1.1167 | 0.6 | 26 | 1.0153 |
|
| 75 |
+
| 1.3876 | 0.63 | 27 | 1.0017 |
|
| 76 |
+
| 1.1708 | 0.65 | 28 | 0.9911 |
|
| 77 |
+
| 1.2199 | 0.67 | 29 | 0.9833 |
|
| 78 |
+
| 1.2328 | 0.7 | 30 | 0.9709 |
|
| 79 |
+
| 1.5262 | 0.72 | 31 | 0.9599 |
|
| 80 |
+
| 1.1906 | 0.74 | 32 | 0.9501 |
|
| 81 |
+
| 1.191 | 0.77 | 33 | 0.9404 |
|
| 82 |
+
| 1.0422 | 0.79 | 34 | 0.9291 |
|
| 83 |
+
| 1.277 | 0.81 | 35 | 0.9183 |
|
| 84 |
+
| 1.1522 | 0.84 | 36 | 0.9092 |
|
| 85 |
+
| 1.1841 | 0.86 | 37 | 0.9006 |
|
| 86 |
+
| 1.2538 | 0.88 | 38 | 0.8931 |
|
| 87 |
+
| 1.1318 | 0.91 | 39 | 0.8862 |
|
| 88 |
+
| 1.012 | 0.93 | 40 | 0.8807 |
|
| 89 |
+
| 1.0553 | 0.95 | 41 | 0.8753 |
|
| 90 |
+
| 1.0566 | 0.98 | 42 | 0.8691 |
|
| 91 |
+
| 1.1235 | 1.0 | 43 | 0.8638 |
|
| 92 |
+
| 1.1207 | 1.02 | 44 | 0.8591 |
|
| 93 |
+
| 1.0835 | 1.05 | 45 | 0.8544 |
|
| 94 |
+
| 1.3731 | 1.07 | 46 | 0.8505 |
|
| 95 |
+
| 0.9843 | 1.09 | 47 | 0.8450 |
|
| 96 |
+
| 0.9201 | 1.12 | 48 | 0.8385 |
|
| 97 |
+
| 1.0392 | 1.14 | 49 | 0.8340 |
|
| 98 |
+
| 1.1158 | 1.16 | 50 | 0.8297 |
|
| 99 |
+
| 0.8518 | 1.19 | 51 | 0.8247 |
|
| 100 |
+
| 0.8871 | 1.21 | 52 | 0.8185 |
|
| 101 |
+
| 1.0378 | 1.23 | 53 | 0.8124 |
|
| 102 |
+
| 1.1116 | 1.26 | 54 | 0.8083 |
|
| 103 |
+
| 1.0364 | 1.28 | 55 | 0.8043 |
|
| 104 |
+
| 0.8949 | 1.3 | 56 | 0.7988 |
|
| 105 |
+
| 1.068 | 1.33 | 57 | 0.7925 |
|
| 106 |
+
| 0.9319 | 1.35 | 58 | 0.7859 |
|
| 107 |
+
| 0.7654 | 1.37 | 59 | 0.7818 |
|
| 108 |
+
| 0.8887 | 1.4 | 60 | 0.7787 |
|
| 109 |
+
| 1.0294 | 1.42 | 61 | 0.7748 |
|
| 110 |
+
| 1.1351 | 1.44 | 62 | 0.7711 |
|
| 111 |
+
| 0.998 | 1.47 | 63 | 0.7689 |
|
| 112 |
+
| 1.1106 | 1.49 | 64 | 0.7679 |
|
| 113 |
+
| 0.9606 | 1.51 | 65 | 0.7660 |
|
| 114 |
+
| 0.9273 | 1.53 | 66 | 0.7628 |
|
| 115 |
+
| 0.9725 | 1.56 | 67 | 0.7595 |
|
| 116 |
+
| 1.0205 | 1.58 | 68 | 0.7569 |
|
| 117 |
+
| 1.0131 | 1.6 | 69 | 0.7549 |
|
| 118 |
+
| 0.9203 | 1.63 | 70 | 0.7530 |
|
| 119 |
+
| 0.898 | 1.65 | 71 | 0.7508 |
|
| 120 |
+
| 0.817 | 1.67 | 72 | 0.7478 |
|
| 121 |
+
| 0.9439 | 1.7 | 73 | 0.7447 |
|
| 122 |
+
| 1.079 | 1.72 | 74 | 0.7427 |
|
| 123 |
+
| 0.9806 | 1.74 | 75 | 0.7398 |
|
| 124 |
+
| 1.261 | 1.77 | 76 | 0.7369 |
|
| 125 |
+
| 1.0824 | 1.79 | 77 | 0.7340 |
|
| 126 |
+
| 0.9523 | 1.81 | 78 | 0.7317 |
|
| 127 |
+
| 0.9734 | 1.84 | 79 | 0.7300 |
|
| 128 |
+
| 1.0786 | 1.86 | 80 | 0.7302 |
|
| 129 |
+
| 0.8675 | 1.88 | 81 | 0.7298 |
|
| 130 |
+
| 0.851 | 1.91 | 82 | 0.7279 |
|
| 131 |
+
| 1.066 | 1.93 | 83 | 0.7254 |
|
| 132 |
+
| 1.137 | 1.95 | 84 | 0.7239 |
|
| 133 |
+
| 1.1387 | 1.98 | 85 | 0.7224 |
|
| 134 |
+
| 0.739 | 2.0 | 86 | 0.7207 |
|
| 135 |
+
| 0.8809 | 2.02 | 87 | 0.7192 |
|
| 136 |
+
| 1.0253 | 2.05 | 88 | 0.7178 |
|
| 137 |
+
| 0.8942 | 2.07 | 89 | 0.7160 |
|
| 138 |
+
| 0.8436 | 2.09 | 90 | 0.7134 |
|
| 139 |
+
| 0.8356 | 2.12 | 91 | 0.7115 |
|
| 140 |
+
| 0.9951 | 2.14 | 92 | 0.7110 |
|
| 141 |
+
| 0.7637 | 2.16 | 93 | 0.7098 |
|
| 142 |
+
| 0.722 | 2.19 | 94 | 0.7087 |
|
| 143 |
+
| 1.023 | 2.21 | 95 | 0.7072 |
|
| 144 |
+
| 0.7015 | 2.23 | 96 | 0.7044 |
|
| 145 |
+
| 0.8949 | 2.26 | 97 | 0.7017 |
|
| 146 |
+
| 0.9573 | 2.28 | 98 | 0.6996 |
|
| 147 |
+
| 0.8989 | 2.3 | 99 | 0.6987 |
|
| 148 |
+
| 0.9738 | 2.33 | 100 | 0.6983 |
|
| 149 |
+
| 0.8317 | 2.35 | 101 | 0.6970 |
|
| 150 |
+
| 0.9778 | 2.37 | 102 | 0.6951 |
|
| 151 |
+
| 0.7919 | 2.4 | 103 | 0.6924 |
|
| 152 |
+
| 0.653 | 2.42 | 104 | 0.6898 |
|
| 153 |
+
| 0.9133 | 2.44 | 105 | 0.6873 |
|
| 154 |
+
| 0.8521 | 2.47 | 106 | 0.6841 |
|
| 155 |
+
| 0.8673 | 2.49 | 107 | 0.6808 |
|
| 156 |
+
| 0.8792 | 2.51 | 108 | 0.6777 |
|
| 157 |
+
| 0.8635 | 2.53 | 109 | 0.6747 |
|
| 158 |
+
| 1.0299 | 2.56 | 110 | 0.6719 |
|
| 159 |
+
| 0.7554 | 2.58 | 111 | 0.6694 |
|
| 160 |
+
| 0.9195 | 2.6 | 112 | 0.6671 |
|
| 161 |
+
| 0.8374 | 2.63 | 113 | 0.6649 |
|
| 162 |
+
| 0.8847 | 2.65 | 114 | 0.6628 |
|
| 163 |
+
| 0.938 | 2.67 | 115 | 0.6615 |
|
| 164 |
+
| 0.8967 | 2.7 | 116 | 0.6603 |
|
| 165 |
+
| 0.8264 | 2.72 | 117 | 0.6594 |
|
| 166 |
+
| 0.9195 | 2.74 | 118 | 0.6591 |
|
| 167 |
+
| 0.8584 | 2.77 | 119 | 0.6588 |
|
| 168 |
+
| 0.8058 | 2.79 | 120 | 0.6578 |
|
| 169 |
+
| 1.0978 | 2.81 | 121 | 0.6560 |
|
| 170 |
+
| 0.7889 | 2.84 | 122 | 0.6544 |
|
| 171 |
+
| 0.7865 | 2.86 | 123 | 0.6527 |
|
| 172 |
+
| 0.8553 | 2.88 | 124 | 0.6507 |
|
| 173 |
+
| 0.9134 | 2.91 | 125 | 0.6486 |
|
| 174 |
+
| 0.7911 | 2.93 | 126 | 0.6463 |
|
| 175 |
+
| 0.9675 | 2.95 | 127 | 0.6439 |
|
| 176 |
+
| 0.761 | 2.98 | 128 | 0.6417 |
|
| 177 |
+
| 0.6347 | 3.0 | 129 | 0.6394 |
|
| 178 |
+
| 0.7608 | 3.02 | 130 | 0.6368 |
|
| 179 |
+
| 0.7563 | 3.05 | 131 | 0.6352 |
|
| 180 |
+
| 0.8059 | 3.07 | 132 | 0.6333 |
|
| 181 |
+
| 0.8825 | 3.09 | 133 | 0.6320 |
|
| 182 |
+
| 0.7952 | 3.12 | 134 | 0.6307 |
|
| 183 |
+
| 0.9209 | 3.14 | 135 | 0.6299 |
|
| 184 |
+
| 0.8556 | 3.16 | 136 | 0.6295 |
|
| 185 |
+
| 0.8613 | 3.19 | 137 | 0.6289 |
|
| 186 |
+
| 0.7908 | 3.21 | 138 | 0.6288 |
|
| 187 |
+
| 0.7728 | 3.23 | 139 | 0.6285 |
|
| 188 |
+
| 0.707 | 3.26 | 140 | 0.6280 |
|
| 189 |
+
| 0.8353 | 3.28 | 141 | 0.6270 |
|
| 190 |
+
| 0.9482 | 3.3 | 142 | 0.6265 |
|
| 191 |
+
| 0.726 | 3.33 | 143 | 0.6260 |
|
| 192 |
+
| 0.7594 | 3.35 | 144 | 0.6250 |
|
| 193 |
+
| 0.9403 | 3.37 | 145 | 0.6237 |
|
| 194 |
+
| 0.8986 | 3.4 | 146 | 0.6218 |
|
| 195 |
+
| 0.7309 | 3.42 | 147 | 0.6204 |
|
| 196 |
+
| 0.8011 | 3.44 | 148 | 0.6197 |
|
| 197 |
+
| 0.7373 | 3.47 | 149 | 0.6193 |
|
| 198 |
+
| 0.6195 | 3.49 | 150 | 0.6174 |
|
| 199 |
+
| 0.8668 | 3.51 | 151 | 0.6154 |
|
| 200 |
+
| 0.8096 | 3.53 | 152 | 0.6136 |
|
| 201 |
+
| 0.9364 | 3.56 | 153 | 0.6116 |
|
| 202 |
+
| 0.7081 | 3.58 | 154 | 0.6105 |
|
| 203 |
+
| 0.7799 | 3.6 | 155 | 0.6091 |
|
| 204 |
+
| 0.7862 | 3.63 | 156 | 0.6090 |
|
| 205 |
+
| 0.7221 | 3.65 | 157 | 0.6097 |
|
| 206 |
+
| 0.7605 | 3.67 | 158 | 0.6090 |
|
| 207 |
+
| 0.7481 | 3.7 | 159 | 0.6071 |
|
| 208 |
+
| 0.776 | 3.72 | 160 | 0.6045 |
|
| 209 |
+
| 0.9396 | 3.74 | 161 | 0.6022 |
|
| 210 |
+
| 0.7166 | 3.77 | 162 | 0.6001 |
|
| 211 |
+
| 0.709 | 3.79 | 163 | 0.5985 |
|
| 212 |
+
| 0.8412 | 3.81 | 164 | 0.5970 |
|
| 213 |
+
| 0.7692 | 3.84 | 165 | 0.5956 |
|
| 214 |
+
| 0.7621 | 3.86 | 166 | 0.5942 |
|
| 215 |
+
| 0.7832 | 3.88 | 167 | 0.5930 |
|
| 216 |
+
| 0.7455 | 3.91 | 168 | 0.5919 |
|
| 217 |
+
| 0.7888 | 3.93 | 169 | 0.5913 |
|
| 218 |
+
| 0.7197 | 3.95 | 170 | 0.5908 |
|
| 219 |
+
| 0.7936 | 3.98 | 171 | 0.5900 |
|
| 220 |
+
| 0.5976 | 4.0 | 172 | 0.5890 |
|
| 221 |
+
| 0.6375 | 4.02 | 173 | 0.5874 |
|
| 222 |
+
| 0.7342 | 4.05 | 174 | 0.5859 |
|
| 223 |
+
| 0.644 | 4.07 | 175 | 0.5845 |
|
| 224 |
+
| 0.7232 | 4.09 | 176 | 0.5831 |
|
| 225 |
+
| 0.7743 | 4.12 | 177 | 0.5819 |
|
| 226 |
+
| 0.8015 | 4.14 | 178 | 0.5808 |
|
| 227 |
+
| 0.7475 | 4.16 | 179 | 0.5801 |
|
| 228 |
+
| 0.7005 | 4.19 | 180 | 0.5797 |
|
| 229 |
+
| 0.7032 | 4.21 | 181 | 0.5795 |
|
| 230 |
+
| 0.8204 | 4.23 | 182 | 0.5789 |
|
| 231 |
+
| 0.7674 | 4.26 | 183 | 0.5787 |
|
| 232 |
+
| 0.7219 | 4.28 | 184 | 0.5781 |
|
| 233 |
+
| 0.624 | 4.3 | 185 | 0.5771 |
|
| 234 |
+
| 0.7429 | 4.33 | 186 | 0.5755 |
|
| 235 |
+
| 0.6445 | 4.35 | 187 | 0.5730 |
|
| 236 |
+
| 0.7782 | 4.37 | 188 | 0.5712 |
|
| 237 |
+
| 0.7882 | 4.4 | 189 | 0.5698 |
|
| 238 |
+
| 0.7005 | 4.42 | 190 | 0.5687 |
|
| 239 |
+
| 0.7509 | 4.44 | 191 | 0.5678 |
|
| 240 |
+
| 0.6764 | 4.47 | 192 | 0.5671 |
|
| 241 |
+
| 0.6529 | 4.49 | 193 | 0.5667 |
|
| 242 |
+
| 0.6101 | 4.51 | 194 | 0.5668 |
|
| 243 |
+
| 0.8211 | 4.53 | 195 | 0.5674 |
|
| 244 |
+
| 0.7529 | 4.56 | 196 | 0.5667 |
|
| 245 |
+
| 0.8615 | 4.58 | 197 | 0.5651 |
|
| 246 |
+
| 0.8099 | 4.6 | 198 | 0.5641 |
|
| 247 |
+
| 0.7145 | 4.63 | 199 | 0.5635 |
|
| 248 |
+
| 0.7437 | 4.65 | 200 | 0.5632 |
|
| 249 |
+
| 0.873 | 4.67 | 201 | 0.5631 |
|
| 250 |
+
| 0.7937 | 4.7 | 202 | 0.5620 |
|
| 251 |
+
| 0.7493 | 4.72 | 203 | 0.5608 |
|
| 252 |
+
| 0.7614 | 4.74 | 204 | 0.5596 |
|
| 253 |
+
| 0.6642 | 4.77 | 205 | 0.5585 |
|
| 254 |
+
| 0.5854 | 4.79 | 206 | 0.5576 |
|
| 255 |
+
| 0.6442 | 4.81 | 207 | 0.5572 |
|
| 256 |
+
| 0.859 | 4.84 | 208 | 0.5562 |
|
| 257 |
+
| 0.6627 | 4.86 | 209 | 0.5553 |
|
| 258 |
+
| 0.8024 | 4.88 | 210 | 0.5540 |
|
| 259 |
+
| 0.7443 | 4.91 | 211 | 0.5526 |
|
| 260 |
+
| 0.6725 | 4.93 | 212 | 0.5520 |
|
| 261 |
+
| 0.749 | 4.95 | 213 | 0.5521 |
|
| 262 |
+
| 0.7687 | 4.98 | 214 | 0.5521 |
|
| 263 |
+
| 0.5998 | 5.0 | 215 | 0.5522 |
|
| 264 |
+
| 0.7578 | 5.02 | 216 | 0.5526 |
|
| 265 |
+
| 0.7074 | 5.05 | 217 | 0.5536 |
|
| 266 |
+
| 0.5647 | 5.07 | 218 | 0.5543 |
|
| 267 |
+
| 0.7475 | 5.09 | 219 | 0.5539 |
|
| 268 |
+
| 0.5776 | 5.12 | 220 | 0.5523 |
|
| 269 |
+
| 0.7232 | 5.14 | 221 | 0.5507 |
|
| 270 |
+
| 0.6487 | 5.16 | 222 | 0.5491 |
|
| 271 |
+
| 0.6446 | 5.19 | 223 | 0.5477 |
|
| 272 |
+
| 0.8951 | 5.21 | 224 | 0.5467 |
|
| 273 |
+
| 0.7706 | 5.23 | 225 | 0.5460 |
|
| 274 |
+
| 0.6351 | 5.26 | 226 | 0.5453 |
|
| 275 |
+
| 0.7336 | 5.28 | 227 | 0.5445 |
|
| 276 |
+
| 0.6329 | 5.3 | 228 | 0.5436 |
|
| 277 |
+
| 0.5795 | 5.33 | 229 | 0.5430 |
|
| 278 |
+
| 0.7553 | 5.35 | 230 | 0.5428 |
|
| 279 |
+
| 0.6959 | 5.37 | 231 | 0.5430 |
|
| 280 |
+
| 0.5945 | 5.4 | 232 | 0.5427 |
|
| 281 |
+
| 0.6274 | 5.42 | 233 | 0.5422 |
|
| 282 |
+
| 0.7024 | 5.44 | 234 | 0.5414 |
|
| 283 |
+
| 0.8223 | 5.47 | 235 | 0.5402 |
|
| 284 |
+
| 0.6441 | 5.49 | 236 | 0.5386 |
|
| 285 |
+
| 0.749 | 5.51 | 237 | 0.5368 |
|
| 286 |
+
| 0.6654 | 5.53 | 238 | 0.5357 |
|
| 287 |
+
| 0.8781 | 5.56 | 239 | 0.5346 |
|
| 288 |
+
| 0.7139 | 5.58 | 240 | 0.5340 |
|
| 289 |
+
| 0.587 | 5.6 | 241 | 0.5339 |
|
| 290 |
+
| 0.8308 | 5.63 | 242 | 0.5340 |
|
| 291 |
+
| 0.5613 | 5.65 | 243 | 0.5334 |
|
| 292 |
+
| 0.7108 | 5.67 | 244 | 0.5330 |
|
| 293 |
+
| 0.6884 | 5.7 | 245 | 0.5322 |
|
| 294 |
+
| 0.6955 | 5.72 | 246 | 0.5310 |
|
| 295 |
+
| 0.5989 | 5.74 | 247 | 0.5301 |
|
| 296 |
+
| 0.7517 | 5.77 | 248 | 0.5295 |
|
| 297 |
+
| 0.6765 | 5.79 | 249 | 0.5291 |
|
| 298 |
+
| 0.6223 | 5.81 | 250 | 0.5285 |
|
| 299 |
+
| 0.6694 | 5.84 | 251 | 0.5277 |
|
| 300 |
+
| 0.6235 | 5.86 | 252 | 0.5267 |
|
| 301 |
+
| 0.6591 | 5.88 | 253 | 0.5259 |
|
| 302 |
+
| 0.6832 | 5.91 | 254 | 0.5251 |
|
| 303 |
+
| 0.7346 | 5.93 | 255 | 0.5246 |
|
| 304 |
+
| 0.6574 | 5.95 | 256 | 0.5242 |
|
| 305 |
+
| 0.704 | 5.98 | 257 | 0.5236 |
|
| 306 |
+
| 0.7269 | 6.0 | 258 | 0.5234 |
|
| 307 |
+
| 0.6097 | 6.02 | 259 | 0.5231 |
|
| 308 |
+
| 0.5369 | 6.05 | 260 | 0.5224 |
|
| 309 |
+
| 0.7094 | 6.07 | 261 | 0.5214 |
|
| 310 |
+
| 0.608 | 6.09 | 262 | 0.5207 |
|
| 311 |
+
| 0.6112 | 6.12 | 263 | 0.5200 |
|
| 312 |
+
| 0.6414 | 6.14 | 264 | 0.5192 |
|
| 313 |
+
| 0.6254 | 6.16 | 265 | 0.5186 |
|
| 314 |
+
| 0.8219 | 6.19 | 266 | 0.5184 |
|
| 315 |
+
| 0.6536 | 6.21 | 267 | 0.5183 |
|
| 316 |
+
| 0.601 | 6.23 | 268 | 0.5184 |
|
| 317 |
+
| 0.672 | 6.26 | 269 | 0.5182 |
|
| 318 |
+
| 0.6646 | 6.28 | 270 | 0.5179 |
|
| 319 |
+
| 0.7228 | 6.3 | 271 | 0.5179 |
|
| 320 |
+
| 0.6542 | 6.33 | 272 | 0.5182 |
|
| 321 |
+
| 0.6003 | 6.35 | 273 | 0.5185 |
|
| 322 |
+
| 0.4799 | 6.37 | 274 | 0.5195 |
|
| 323 |
+
| 0.7062 | 6.4 | 275 | 0.5203 |
|
| 324 |
+
| 0.7557 | 6.42 | 276 | 0.5199 |
|
| 325 |
+
| 0.7419 | 6.44 | 277 | 0.5189 |
|
| 326 |
+
| 0.5468 | 6.47 | 278 | 0.5179 |
|
| 327 |
+
| 0.6142 | 6.49 | 279 | 0.5168 |
|
| 328 |
+
| 0.5953 | 6.51 | 280 | 0.5161 |
|
| 329 |
+
| 0.602 | 6.53 | 281 | 0.5152 |
|
| 330 |
+
| 0.6168 | 6.56 | 282 | 0.5146 |
|
| 331 |
+
| 0.815 | 6.58 | 283 | 0.5141 |
|
| 332 |
+
| 0.7738 | 6.6 | 284 | 0.5138 |
|
| 333 |
+
| 0.64 | 6.63 | 285 | 0.5136 |
|
| 334 |
+
| 0.6377 | 6.65 | 286 | 0.5133 |
|
| 335 |
+
| 0.7254 | 6.67 | 287 | 0.5131 |
|
| 336 |
+
| 0.6416 | 6.7 | 288 | 0.5128 |
|
| 337 |
+
| 0.6555 | 6.72 | 289 | 0.5123 |
|
| 338 |
+
| 0.6812 | 6.74 | 290 | 0.5118 |
|
| 339 |
+
| 0.7116 | 6.77 | 291 | 0.5113 |
|
| 340 |
+
| 0.6046 | 6.79 | 292 | 0.5104 |
|
| 341 |
+
| 0.7386 | 6.81 | 293 | 0.5095 |
|
| 342 |
+
| 0.733 | 6.84 | 294 | 0.5088 |
|
| 343 |
+
| 0.6579 | 6.86 | 295 | 0.5081 |
|
| 344 |
+
| 0.5418 | 6.88 | 296 | 0.5076 |
|
| 345 |
+
| 0.5853 | 6.91 | 297 | 0.5071 |
|
| 346 |
+
| 0.6488 | 6.93 | 298 | 0.5070 |
|
| 347 |
+
| 0.5726 | 6.95 | 299 | 0.5069 |
|
| 348 |
+
| 0.5821 | 6.98 | 300 | 0.5068 |
|
| 349 |
+
| 0.9157 | 7.0 | 301 | 0.5068 |
|
| 350 |
+
| 0.6769 | 7.02 | 302 | 0.5061 |
|
| 351 |
+
| 0.7632 | 7.05 | 303 | 0.5049 |
|
| 352 |
+
| 0.7479 | 7.07 | 304 | 0.5037 |
|
| 353 |
+
| 0.5632 | 7.09 | 305 | 0.5028 |
|
| 354 |
+
| 0.6493 | 7.12 | 306 | 0.5015 |
|
| 355 |
+
| 0.6517 | 7.14 | 307 | 0.5007 |
|
| 356 |
+
| 0.6944 | 7.16 | 308 | 0.5000 |
|
| 357 |
+
| 0.5862 | 7.19 | 309 | 0.4996 |
|
| 358 |
+
| 0.6161 | 7.21 | 310 | 0.4993 |
|
| 359 |
+
| 0.6396 | 7.23 | 311 | 0.4988 |
|
| 360 |
+
| 0.5506 | 7.26 | 312 | 0.4985 |
|
| 361 |
+
| 0.7518 | 7.28 | 313 | 0.4982 |
|
| 362 |
+
| 0.7445 | 7.3 | 314 | 0.4977 |
|
| 363 |
+
| 0.6228 | 7.33 | 315 | 0.4974 |
|
| 364 |
+
| 0.5555 | 7.35 | 316 | 0.4968 |
|
| 365 |
+
| 0.7457 | 7.37 | 317 | 0.4964 |
|
| 366 |
+
| 0.579 | 7.4 | 318 | 0.4961 |
|
| 367 |
+
| 0.528 | 7.42 | 319 | 0.4956 |
|
| 368 |
+
| 0.5286 | 7.44 | 320 | 0.4953 |
|
| 369 |
+
| 0.591 | 7.47 | 321 | 0.4952 |
|
| 370 |
+
| 0.5903 | 7.49 | 322 | 0.4953 |
|
| 371 |
+
| 0.6155 | 7.51 | 323 | 0.4955 |
|
| 372 |
+
| 0.5907 | 7.53 | 324 | 0.4954 |
|
| 373 |
+
| 0.6028 | 7.56 | 325 | 0.4949 |
|
| 374 |
+
| 0.5852 | 7.58 | 326 | 0.4943 |
|
| 375 |
+
| 0.6156 | 7.6 | 327 | 0.4934 |
|
| 376 |
+
| 0.582 | 7.63 | 328 | 0.4925 |
|
| 377 |
+
| 0.6091 | 7.65 | 329 | 0.4918 |
|
| 378 |
+
| 0.5877 | 7.67 | 330 | 0.4912 |
|
| 379 |
+
| 0.7017 | 7.7 | 331 | 0.4908 |
|
| 380 |
+
| 0.6496 | 7.72 | 332 | 0.4905 |
|
| 381 |
+
| 0.6089 | 7.74 | 333 | 0.4903 |
|
| 382 |
+
| 0.5807 | 7.77 | 334 | 0.4901 |
|
| 383 |
+
| 0.5553 | 7.79 | 335 | 0.4897 |
|
| 384 |
+
| 0.8058 | 7.81 | 336 | 0.4894 |
|
| 385 |
+
| 0.6147 | 7.84 | 337 | 0.4892 |
|
| 386 |
+
| 0.6289 | 7.86 | 338 | 0.4891 |
|
| 387 |
+
| 0.5883 | 7.88 | 339 | 0.4891 |
|
| 388 |
+
| 0.6048 | 7.91 | 340 | 0.4890 |
|
| 389 |
+
| 0.6411 | 7.93 | 341 | 0.4889 |
|
| 390 |
+
| 0.5575 | 7.95 | 342 | 0.4887 |
|
| 391 |
+
| 0.6509 | 7.98 | 343 | 0.4884 |
|
| 392 |
+
| 0.764 | 8.0 | 344 | 0.4882 |
|
| 393 |
+
| 0.6364 | 8.02 | 345 | 0.4880 |
|
| 394 |
+
| 0.561 | 8.05 | 346 | 0.4880 |
|
| 395 |
+
| 0.5949 | 8.07 | 347 | 0.4878 |
|
| 396 |
+
| 0.6904 | 8.09 | 348 | 0.4874 |
|
| 397 |
+
| 0.647 | 8.12 | 349 | 0.4868 |
|
| 398 |
+
| 0.6374 | 8.14 | 350 | 0.4862 |
|
| 399 |
+
| 0.7048 | 8.16 | 351 | 0.4859 |
|
| 400 |
+
| 0.6085 | 8.19 | 352 | 0.4854 |
|
| 401 |
+
| 0.5246 | 8.21 | 353 | 0.4852 |
|
| 402 |
+
| 0.531 | 8.23 | 354 | 0.4849 |
|
| 403 |
+
| 0.4605 | 8.26 | 355 | 0.4844 |
|
| 404 |
+
| 0.6132 | 8.28 | 356 | 0.4839 |
|
| 405 |
+
| 0.6378 | 8.3 | 357 | 0.4835 |
|
| 406 |
+
| 0.7885 | 8.33 | 358 | 0.4831 |
|
| 407 |
+
| 0.6008 | 8.35 | 359 | 0.4827 |
|
| 408 |
+
| 0.7118 | 8.37 | 360 | 0.4823 |
|
| 409 |
+
| 0.6792 | 8.4 | 361 | 0.4821 |
|
| 410 |
+
| 0.6317 | 8.42 | 362 | 0.4819 |
|
| 411 |
+
| 0.5942 | 8.44 | 363 | 0.4817 |
|
| 412 |
+
| 0.6184 | 8.47 | 364 | 0.4815 |
|
| 413 |
+
| 0.5902 | 8.49 | 365 | 0.4813 |
|
| 414 |
+
| 0.5353 | 8.51 | 366 | 0.4812 |
|
| 415 |
+
| 0.685 | 8.53 | 367 | 0.4812 |
|
| 416 |
+
| 0.5232 | 8.56 | 368 | 0.4811 |
|
| 417 |
+
| 0.6393 | 8.58 | 369 | 0.4812 |
|
| 418 |
+
| 0.5685 | 8.6 | 370 | 0.4812 |
|
| 419 |
+
| 0.6234 | 8.63 | 371 | 0.4813 |
|
| 420 |
+
| 0.5456 | 8.65 | 372 | 0.4810 |
|
| 421 |
+
| 0.6159 | 8.67 | 373 | 0.4807 |
|
| 422 |
+
| 0.6575 | 8.7 | 374 | 0.4804 |
|
| 423 |
+
| 0.5769 | 8.72 | 375 | 0.4803 |
|
| 424 |
+
| 0.5939 | 8.74 | 376 | 0.4801 |
|
| 425 |
+
| 0.5721 | 8.77 | 377 | 0.4800 |
|
| 426 |
+
| 0.5283 | 8.79 | 378 | 0.4797 |
|
| 427 |
+
| 0.5275 | 8.81 | 379 | 0.4795 |
|
| 428 |
+
| 0.5907 | 8.84 | 380 | 0.4794 |
|
| 429 |
+
| 0.6058 | 8.86 | 381 | 0.4792 |
|
| 430 |
+
| 0.7202 | 8.88 | 382 | 0.4790 |
|
| 431 |
+
| 0.6811 | 8.91 | 383 | 0.4787 |
|
| 432 |
+
| 0.5979 | 8.93 | 384 | 0.4785 |
|
| 433 |
+
| 0.5572 | 8.95 | 385 | 0.4783 |
|
| 434 |
+
| 0.5893 | 8.98 | 386 | 0.4781 |
|
| 435 |
+
| 0.6796 | 9.0 | 387 | 0.4779 |
|
| 436 |
+
| 0.5412 | 9.02 | 388 | 0.4780 |
|
| 437 |
+
| 0.5453 | 9.05 | 389 | 0.4781 |
|
| 438 |
+
| 0.7475 | 9.07 | 390 | 0.4782 |
|
| 439 |
+
| 0.6222 | 9.09 | 391 | 0.4781 |
|
| 440 |
+
| 0.5177 | 9.12 | 392 | 0.4778 |
|
| 441 |
+
| 0.6182 | 9.14 | 393 | 0.4775 |
|
| 442 |
+
| 0.6124 | 9.16 | 394 | 0.4772 |
|
| 443 |
+
| 0.6485 | 9.19 | 395 | 0.4769 |
|
| 444 |
+
| 0.5852 | 9.21 | 396 | 0.4765 |
|
| 445 |
+
| 0.5656 | 9.23 | 397 | 0.4761 |
|
| 446 |
+
| 0.6162 | 9.26 | 398 | 0.4758 |
|
| 447 |
+
| 0.6965 | 9.28 | 399 | 0.4755 |
|
| 448 |
+
| 0.5342 | 9.3 | 400 | 0.4753 |
|
| 449 |
+
| 0.718 | 9.33 | 401 | 0.4751 |
|
| 450 |
+
| 0.5089 | 9.35 | 402 | 0.4750 |
|
| 451 |
+
| 0.5738 | 9.37 | 403 | 0.4748 |
|
| 452 |
+
| 0.5612 | 9.4 | 404 | 0.4746 |
|
| 453 |
+
| 0.5628 | 9.42 | 405 | 0.4744 |
|
| 454 |
+
| 0.6512 | 9.44 | 406 | 0.4743 |
|
| 455 |
+
| 0.6717 | 9.47 | 407 | 0.4742 |
|
| 456 |
+
| 0.5937 | 9.49 | 408 | 0.4741 |
|
| 457 |
+
| 0.5906 | 9.51 | 409 | 0.4741 |
|
| 458 |
+
| 0.529 | 9.53 | 410 | 0.4741 |
|
| 459 |
+
| 0.6554 | 9.56 | 411 | 0.4741 |
|
| 460 |
+
| 0.5074 | 9.58 | 412 | 0.4741 |
|
| 461 |
+
| 0.6997 | 9.6 | 413 | 0.4741 |
|
| 462 |
+
| 0.5573 | 9.63 | 414 | 0.4741 |
|
| 463 |
+
| 0.6113 | 9.65 | 415 | 0.4741 |
|
| 464 |
+
| 0.5129 | 9.67 | 416 | 0.4741 |
|
| 465 |
+
| 0.5428 | 9.7 | 417 | 0.4740 |
|
| 466 |
+
| 0.5363 | 9.72 | 418 | 0.4739 |
|
| 467 |
+
| 0.5862 | 9.74 | 419 | 0.4739 |
|
| 468 |
+
| 0.6119 | 9.77 | 420 | 0.4738 |
|
| 469 |
+
| 0.6698 | 9.79 | 421 | 0.4738 |
|
| 470 |
+
| 0.5966 | 9.81 | 422 | 0.4737 |
|
| 471 |
+
| 0.5309 | 9.84 | 423 | 0.4737 |
|
| 472 |
+
| 0.5924 | 9.86 | 424 | 0.4736 |
|
| 473 |
+
| 0.6133 | 9.88 | 425 | 0.4736 |
|
| 474 |
+
| 0.6869 | 9.91 | 426 | 0.4736 |
|
| 475 |
+
| 0.5508 | 9.93 | 427 | 0.4735 |
|
| 476 |
+
| 0.6858 | 9.95 | 428 | 0.4735 |
|
| 477 |
+
| 0.5681 | 9.98 | 429 | 0.4735 |
|
| 478 |
+
| 0.7834 | 10.0 | 430 | 0.4735 |
|
| 479 |
+
|
| 480 |
+
|
| 481 |
+
### Framework versions
|
| 482 |
+
|
| 483 |
+
- Transformers 4.32.1
|
| 484 |
+
- Pytorch 2.0.1+cu118
|
| 485 |
+
- Datasets 2.14.4
|
| 486 |
+
- Tokenizers 0.13.3
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2-medium",
|
| 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": 1024,
|
| 16 |
+
"n_head": 16,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 24,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"n_special": 0,
|
| 21 |
+
"predict_special_tokens": true,
|
| 22 |
+
"reorder_and_upcast_attn": false,
|
| 23 |
+
"resid_pdrop": 0.1,
|
| 24 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 25 |
+
"scale_attn_weights": true,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.32.1",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 50257
|
| 41 |
+
}
|
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": "4.32.1"
|
| 6 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:864f98af794e6fa03ce9523118d9ae296b00f30d8573782ca72d2995cdadff41
|
| 3 |
+
size 1419387869
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24ca82a1d0f983b85b92649da7bccd86d26e7b6ab441398a5b6762f6b95a4182
|
| 3 |
+
size 4091
|