Fine-tuned GPT-2 on Wikitext-2
Browse files
README.md
CHANGED
|
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [cuba6112/orion](https://huggingface.co/cuba6112/orion) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
-
- Loss:
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -41,47 +41,357 @@ The following hyperparameters were used during training:
|
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- lr_scheduler_warmup_steps: 500
|
| 44 |
-
- num_epochs:
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
-
| Training Loss | Epoch
|
| 50 |
-
|
| 51 |
-
| No log | 0.0871
|
| 52 |
-
| 2.
|
| 53 |
-
| 1.
|
| 54 |
-
| 1.
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
| 2.
|
| 58 |
-
| 2.
|
| 59 |
-
| 2.
|
| 60 |
-
| 2.
|
| 61 |
-
| 2.
|
| 62 |
-
| 2.
|
| 63 |
-
| 2.
|
| 64 |
-
| 2.
|
| 65 |
-
| 2.
|
| 66 |
-
| 2.
|
| 67 |
-
| 2.
|
| 68 |
-
| 2.
|
| 69 |
-
| 2.
|
| 70 |
-
| 2.
|
| 71 |
-
| 2.
|
| 72 |
-
| 2.
|
| 73 |
-
| 2.
|
| 74 |
-
| 2.
|
| 75 |
-
| 2.
|
| 76 |
-
| 2.
|
| 77 |
-
| 2.
|
| 78 |
-
| 2.
|
| 79 |
-
| 2.
|
| 80 |
-
| 2.
|
| 81 |
-
| 2.
|
| 82 |
-
| 2.
|
| 83 |
-
| 2.
|
| 84 |
-
| 2.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
|
| 86 |
|
| 87 |
### Framework versions
|
|
|
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [cuba6112/orion](https://huggingface.co/cuba6112/orion) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 3.3813
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
- lr_scheduler_type: linear
|
| 43 |
- lr_scheduler_warmup_steps: 500
|
| 44 |
+
- num_epochs: 30
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-------:|:------:|:---------------:|
|
| 51 |
+
| No log | 0.0871 | 400 | 3.0498 |
|
| 52 |
+
| 2.1987 | 0.1743 | 800 | 3.2218 |
|
| 53 |
+
| 1.682 | 0.2614 | 1200 | 3.2123 |
|
| 54 |
+
| 1.7259 | 0.3486 | 1600 | 3.2036 |
|
| 55 |
+
| 1.996 | 0.4357 | 2000 | 3.0685 |
|
| 56 |
+
| 1.996 | 0.5229 | 2400 | 3.0753 |
|
| 57 |
+
| 2.1139 | 0.6100 | 2800 | 3.0261 |
|
| 58 |
+
| 2.1855 | 0.6972 | 3200 | 2.9876 |
|
| 59 |
+
| 2.3493 | 0.7843 | 3600 | 2.9616 |
|
| 60 |
+
| 2.4411 | 0.8715 | 4000 | 2.9416 |
|
| 61 |
+
| 2.4411 | 0.9586 | 4400 | 2.9191 |
|
| 62 |
+
| 2.5409 | 1.0458 | 4800 | 2.9867 |
|
| 63 |
+
| 2.3445 | 1.1329 | 5200 | 2.9837 |
|
| 64 |
+
| 2.3134 | 1.2200 | 5600 | 2.9847 |
|
| 65 |
+
| 2.312 | 1.3072 | 6000 | 2.9661 |
|
| 66 |
+
| 2.312 | 1.3943 | 6400 | 2.9673 |
|
| 67 |
+
| 2.3304 | 1.4815 | 6800 | 2.9659 |
|
| 68 |
+
| 2.3239 | 1.5686 | 7200 | 2.9541 |
|
| 69 |
+
| 2.3673 | 1.6558 | 7600 | 2.9694 |
|
| 70 |
+
| 2.3503 | 1.7429 | 8000 | 2.9608 |
|
| 71 |
+
| 2.3503 | 1.8301 | 8400 | 2.9436 |
|
| 72 |
+
| 2.411 | 1.9172 | 8800 | 2.9596 |
|
| 73 |
+
| 2.3752 | 2.0044 | 9200 | 2.9666 |
|
| 74 |
+
| 2.3068 | 2.0915 | 9600 | 2.9763 |
|
| 75 |
+
| 2.2758 | 2.1786 | 10000 | 2.9779 |
|
| 76 |
+
| 2.2758 | 2.2658 | 10400 | 2.9780 |
|
| 77 |
+
| 2.3147 | 2.3529 | 10800 | 2.9708 |
|
| 78 |
+
| 2.3042 | 2.4401 | 11200 | 2.9562 |
|
| 79 |
+
| 2.326 | 2.5272 | 11600 | 2.9669 |
|
| 80 |
+
| 2.3543 | 2.6144 | 12000 | 2.9586 |
|
| 81 |
+
| 2.3543 | 2.7015 | 12400 | 2.9503 |
|
| 82 |
+
| 2.3478 | 2.7887 | 12800 | 2.9551 |
|
| 83 |
+
| 2.3671 | 2.8758 | 13200 | 2.9495 |
|
| 84 |
+
| 2.3881 | 2.9630 | 13600 | 2.9487 |
|
| 85 |
+
| 2.3464 | 3.0501 | 14000 | 2.9822 |
|
| 86 |
+
| 2.3464 | 3.1373 | 14400 | 2.9787 |
|
| 87 |
+
| 2.2827 | 3.2244 | 14800 | 2.9811 |
|
| 88 |
+
| 2.3025 | 3.3115 | 15200 | 2.9744 |
|
| 89 |
+
| 2.3032 | 3.3987 | 15600 | 2.9633 |
|
| 90 |
+
| 2.2829 | 3.4858 | 16000 | 2.9682 |
|
| 91 |
+
| 2.2829 | 3.5730 | 16400 | 2.9691 |
|
| 92 |
+
| 2.3227 | 3.6601 | 16800 | 2.9705 |
|
| 93 |
+
| 2.304 | 3.7473 | 17200 | 2.9695 |
|
| 94 |
+
| 2.3249 | 3.8344 | 17600 | 2.9564 |
|
| 95 |
+
| 2.3228 | 3.9216 | 18000 | 2.9707 |
|
| 96 |
+
| 2.3228 | 4.0087 | 18400 | 2.9947 |
|
| 97 |
+
| 2.303 | 4.0959 | 18800 | 2.9898 |
|
| 98 |
+
| 2.2062 | 4.1830 | 19200 | 2.9936 |
|
| 99 |
+
| 2.2194 | 4.2702 | 19600 | 2.9913 |
|
| 100 |
+
| 2.2357 | 4.3573 | 20000 | 3.0012 |
|
| 101 |
+
| 2.2357 | 4.4444 | 20400 | 2.9915 |
|
| 102 |
+
| 2.2628 | 4.5316 | 20800 | 2.9880 |
|
| 103 |
+
| 2.26 | 4.6187 | 21200 | 2.9777 |
|
| 104 |
+
| 2.2893 | 4.7059 | 21600 | 2.9920 |
|
| 105 |
+
| 2.2587 | 4.7930 | 22000 | 2.9791 |
|
| 106 |
+
| 2.2587 | 4.8802 | 22400 | 2.9806 |
|
| 107 |
+
| 2.2752 | 4.9673 | 22800 | 2.9791 |
|
| 108 |
+
| 2.2541 | 5.0545 | 23200 | 3.0167 |
|
| 109 |
+
| 2.1708 | 5.1416 | 23600 | 3.0109 |
|
| 110 |
+
| 2.1866 | 5.2288 | 24000 | 3.0121 |
|
| 111 |
+
| 2.1866 | 5.3159 | 24400 | 3.0081 |
|
| 112 |
+
| 2.1906 | 5.4031 | 24800 | 3.0166 |
|
| 113 |
+
| 2.1882 | 5.4902 | 25200 | 3.0160 |
|
| 114 |
+
| 2.2057 | 5.5773 | 25600 | 3.0014 |
|
| 115 |
+
| 2.2106 | 5.6645 | 26000 | 3.0005 |
|
| 116 |
+
| 2.2106 | 5.7516 | 26400 | 3.0028 |
|
| 117 |
+
| 2.2293 | 5.8388 | 26800 | 3.0156 |
|
| 118 |
+
| 2.1999 | 5.9259 | 27200 | 3.0012 |
|
| 119 |
+
| 2.2221 | 6.0131 | 27600 | 3.0241 |
|
| 120 |
+
| 2.1506 | 6.1002 | 28000 | 3.0365 |
|
| 121 |
+
| 2.1506 | 6.1874 | 28400 | 3.0434 |
|
| 122 |
+
| 2.1511 | 6.2745 | 28800 | 3.0286 |
|
| 123 |
+
| 2.1449 | 6.3617 | 29200 | 3.0477 |
|
| 124 |
+
| 2.1298 | 6.4488 | 29600 | 3.0356 |
|
| 125 |
+
| 2.166 | 6.5359 | 30000 | 3.0365 |
|
| 126 |
+
| 2.166 | 6.6231 | 30400 | 3.0301 |
|
| 127 |
+
| 2.1646 | 6.7102 | 30800 | 3.0291 |
|
| 128 |
+
| 2.14 | 6.7974 | 31200 | 3.0259 |
|
| 129 |
+
| 2.1597 | 6.8845 | 31600 | 3.0171 |
|
| 130 |
+
| 2.1661 | 6.9717 | 32000 | 3.0316 |
|
| 131 |
+
| 2.1661 | 7.0588 | 32400 | 3.0620 |
|
| 132 |
+
| 2.1108 | 7.1460 | 32800 | 3.0650 |
|
| 133 |
+
| 2.1125 | 7.2331 | 33200 | 3.0554 |
|
| 134 |
+
| 2.112 | 7.3203 | 33600 | 3.0693 |
|
| 135 |
+
| 2.0923 | 7.4074 | 34000 | 3.0634 |
|
| 136 |
+
| 2.0923 | 7.4946 | 34400 | 3.0530 |
|
| 137 |
+
| 2.114 | 7.5817 | 34800 | 3.0421 |
|
| 138 |
+
| 2.1223 | 7.6688 | 35200 | 3.0439 |
|
| 139 |
+
| 2.1027 | 7.7560 | 35600 | 3.0478 |
|
| 140 |
+
| 2.1345 | 7.8431 | 36000 | 3.0432 |
|
| 141 |
+
| 2.1345 | 7.9303 | 36400 | 3.0441 |
|
| 142 |
+
| 2.1327 | 8.0174 | 36800 | 3.0732 |
|
| 143 |
+
| 2.0844 | 8.1046 | 37200 | 3.0709 |
|
| 144 |
+
| 2.0634 | 8.1917 | 37600 | 3.0767 |
|
| 145 |
+
| 2.0644 | 8.2789 | 38000 | 3.0821 |
|
| 146 |
+
| 2.0644 | 8.3660 | 38400 | 3.0742 |
|
| 147 |
+
| 2.0724 | 8.4532 | 38800 | 3.0888 |
|
| 148 |
+
| 2.0661 | 8.5403 | 39200 | 3.0760 |
|
| 149 |
+
| 2.0706 | 8.6275 | 39600 | 3.0767 |
|
| 150 |
+
| 2.0673 | 8.7146 | 40000 | 3.0632 |
|
| 151 |
+
| 2.0673 | 8.8017 | 40400 | 3.0682 |
|
| 152 |
+
| 2.0982 | 8.8889 | 40800 | 3.0741 |
|
| 153 |
+
| 2.0998 | 8.9760 | 41200 | 3.0715 |
|
| 154 |
+
| 2.0553 | 9.0632 | 41600 | 3.1081 |
|
| 155 |
+
| 2.0268 | 9.1503 | 42000 | 3.1013 |
|
| 156 |
+
| 2.0268 | 9.2375 | 42400 | 3.1060 |
|
| 157 |
+
| 2.0072 | 9.3246 | 42800 | 3.0983 |
|
| 158 |
+
| 2.0263 | 9.4118 | 43200 | 3.0981 |
|
| 159 |
+
| 2.0114 | 9.4989 | 43600 | 3.0915 |
|
| 160 |
+
| 2.0314 | 9.5861 | 44000 | 3.0973 |
|
| 161 |
+
| 2.0314 | 9.6732 | 44400 | 3.1053 |
|
| 162 |
+
| 2.0413 | 9.7603 | 44800 | 3.0982 |
|
| 163 |
+
| 2.0425 | 9.8475 | 45200 | 3.1079 |
|
| 164 |
+
| 2.0354 | 9.9346 | 45600 | 3.0982 |
|
| 165 |
+
| 2.0485 | 10.0218 | 46000 | 3.1200 |
|
| 166 |
+
| 2.0485 | 10.1089 | 46400 | 3.1409 |
|
| 167 |
+
| 1.9523 | 10.1961 | 46800 | 3.1287 |
|
| 168 |
+
| 1.9911 | 10.2832 | 47200 | 3.1222 |
|
| 169 |
+
| 1.9842 | 10.3704 | 47600 | 3.1362 |
|
| 170 |
+
| 1.9892 | 10.4575 | 48000 | 3.1157 |
|
| 171 |
+
| 1.9892 | 10.5447 | 48400 | 3.1314 |
|
| 172 |
+
| 1.9867 | 10.6318 | 48800 | 3.1089 |
|
| 173 |
+
| 2.0033 | 10.7190 | 49200 | 3.1138 |
|
| 174 |
+
| 2.0057 | 10.8061 | 49600 | 3.1332 |
|
| 175 |
+
| 1.9959 | 10.8932 | 50000 | 3.1280 |
|
| 176 |
+
| 1.9959 | 10.9804 | 50400 | 3.1232 |
|
| 177 |
+
| 1.9956 | 11.0675 | 50800 | 3.1424 |
|
| 178 |
+
| 1.951 | 11.1547 | 51200 | 3.1473 |
|
| 179 |
+
| 1.9491 | 11.2418 | 51600 | 3.1429 |
|
| 180 |
+
| 1.9612 | 11.3290 | 52000 | 3.1451 |
|
| 181 |
+
| 1.9612 | 11.4161 | 52400 | 3.1591 |
|
| 182 |
+
| 1.971 | 11.5033 | 52800 | 3.1558 |
|
| 183 |
+
| 1.9582 | 11.5904 | 53200 | 3.1337 |
|
| 184 |
+
| 1.9675 | 11.6776 | 53600 | 3.1459 |
|
| 185 |
+
| 1.9529 | 11.7647 | 54000 | 3.1416 |
|
| 186 |
+
| 1.9529 | 11.8519 | 54400 | 3.1484 |
|
| 187 |
+
| 1.9572 | 11.9390 | 54800 | 3.1465 |
|
| 188 |
+
| 1.989 | 12.0261 | 55200 | 3.1638 |
|
| 189 |
+
| 1.9232 | 12.1133 | 55600 | 3.1767 |
|
| 190 |
+
| 1.9115 | 12.2004 | 56000 | 3.1617 |
|
| 191 |
+
| 1.9115 | 12.2876 | 56400 | 3.1688 |
|
| 192 |
+
| 1.9082 | 12.3747 | 56800 | 3.1755 |
|
| 193 |
+
| 1.9193 | 12.4619 | 57200 | 3.1826 |
|
| 194 |
+
| 1.9188 | 12.5490 | 57600 | 3.1732 |
|
| 195 |
+
| 1.9367 | 12.6362 | 58000 | 3.1784 |
|
| 196 |
+
| 1.9367 | 12.7233 | 58400 | 3.1680 |
|
| 197 |
+
| 1.9442 | 12.8105 | 58800 | 3.1649 |
|
| 198 |
+
| 1.9402 | 12.8976 | 59200 | 3.1517 |
|
| 199 |
+
| 1.9426 | 12.9847 | 59600 | 3.1584 |
|
| 200 |
+
| 1.9087 | 13.0719 | 60000 | 3.1833 |
|
| 201 |
+
| 1.9087 | 13.1590 | 60400 | 3.1808 |
|
| 202 |
+
| 1.888 | 13.2462 | 60800 | 3.1818 |
|
| 203 |
+
| 1.8757 | 13.3333 | 61200 | 3.2008 |
|
| 204 |
+
| 1.8792 | 13.4205 | 61600 | 3.2086 |
|
| 205 |
+
| 1.8875 | 13.5076 | 62000 | 3.1938 |
|
| 206 |
+
| 1.8875 | 13.5948 | 62400 | 3.1910 |
|
| 207 |
+
| 1.8815 | 13.6819 | 62800 | 3.1948 |
|
| 208 |
+
| 1.9077 | 13.7691 | 63200 | 3.1791 |
|
| 209 |
+
| 1.9038 | 13.8562 | 63600 | 3.1817 |
|
| 210 |
+
| 1.9153 | 13.9434 | 64000 | 3.1879 |
|
| 211 |
+
| 1.9153 | 14.0305 | 64400 | 3.2086 |
|
| 212 |
+
| 1.8823 | 14.1176 | 64800 | 3.2081 |
|
| 213 |
+
| 1.8672 | 14.2048 | 65200 | 3.2079 |
|
| 214 |
+
| 1.8373 | 14.2919 | 65600 | 3.1995 |
|
| 215 |
+
| 1.8498 | 14.3791 | 66000 | 3.2020 |
|
| 216 |
+
| 1.8498 | 14.4662 | 66400 | 3.1984 |
|
| 217 |
+
| 1.8694 | 14.5534 | 66800 | 3.2120 |
|
| 218 |
+
| 1.8736 | 14.6405 | 67200 | 3.2019 |
|
| 219 |
+
| 1.8702 | 14.7277 | 67600 | 3.2145 |
|
| 220 |
+
| 1.8839 | 14.8148 | 68000 | 3.2128 |
|
| 221 |
+
| 1.8839 | 14.9020 | 68400 | 3.2141 |
|
| 222 |
+
| 1.8872 | 14.9891 | 68800 | 3.2037 |
|
| 223 |
+
| 1.8689 | 15.0763 | 69200 | 3.2270 |
|
| 224 |
+
| 1.8321 | 15.1634 | 69600 | 3.2363 |
|
| 225 |
+
| 1.8226 | 15.2505 | 70000 | 3.2272 |
|
| 226 |
+
| 1.8226 | 15.3377 | 70400 | 3.2378 |
|
| 227 |
+
| 1.8367 | 15.4248 | 70800 | 3.2220 |
|
| 228 |
+
| 1.8403 | 15.5120 | 71200 | 3.2190 |
|
| 229 |
+
| 1.8473 | 15.5991 | 71600 | 3.2261 |
|
| 230 |
+
| 1.83 | 15.6863 | 72000 | 3.2246 |
|
| 231 |
+
| 1.83 | 15.7734 | 72400 | 3.2292 |
|
| 232 |
+
| 1.8554 | 15.8606 | 72800 | 3.2194 |
|
| 233 |
+
| 1.8569 | 15.9477 | 73200 | 3.2239 |
|
| 234 |
+
| 1.8493 | 16.0349 | 73600 | 3.2449 |
|
| 235 |
+
| 1.8066 | 16.1220 | 74000 | 3.2532 |
|
| 236 |
+
| 1.8066 | 16.2092 | 74400 | 3.2525 |
|
| 237 |
+
| 1.7883 | 16.2963 | 74800 | 3.2499 |
|
| 238 |
+
| 1.8053 | 16.3834 | 75200 | 3.2533 |
|
| 239 |
+
| 1.8036 | 16.4706 | 75600 | 3.2437 |
|
| 240 |
+
| 1.8197 | 16.5577 | 76000 | 3.2443 |
|
| 241 |
+
| 1.8197 | 16.6449 | 76400 | 3.2466 |
|
| 242 |
+
| 1.8069 | 16.7320 | 76800 | 3.2301 |
|
| 243 |
+
| 1.8108 | 16.8192 | 77200 | 3.2422 |
|
| 244 |
+
| 1.83 | 16.9063 | 77600 | 3.2477 |
|
| 245 |
+
| 1.8424 | 16.9935 | 78000 | 3.2489 |
|
| 246 |
+
| 1.8424 | 17.0806 | 78400 | 3.2720 |
|
| 247 |
+
| 1.7802 | 17.1678 | 78800 | 3.2764 |
|
| 248 |
+
| 1.7698 | 17.2549 | 79200 | 3.2724 |
|
| 249 |
+
| 1.7883 | 17.3420 | 79600 | 3.2668 |
|
| 250 |
+
| 1.8066 | 17.4292 | 80000 | 3.2590 |
|
| 251 |
+
| 1.8066 | 17.5163 | 80400 | 3.2698 |
|
| 252 |
+
| 1.7783 | 17.6035 | 80800 | 3.2650 |
|
| 253 |
+
| 1.7753 | 17.6906 | 81200 | 3.2656 |
|
| 254 |
+
| 1.8071 | 17.7778 | 81600 | 3.2589 |
|
| 255 |
+
| 1.8148 | 17.8649 | 82000 | 3.2583 |
|
| 256 |
+
| 1.8148 | 17.9521 | 82400 | 3.2603 |
|
| 257 |
+
| 1.8088 | 18.0392 | 82800 | 3.2774 |
|
| 258 |
+
| 1.7732 | 18.1264 | 83200 | 3.2715 |
|
| 259 |
+
| 1.7401 | 18.2135 | 83600 | 3.2806 |
|
| 260 |
+
| 1.7522 | 18.3007 | 84000 | 3.2847 |
|
| 261 |
+
| 1.7522 | 18.3878 | 84400 | 3.2842 |
|
| 262 |
+
| 1.7704 | 18.4749 | 84800 | 3.2705 |
|
| 263 |
+
| 1.7778 | 18.5621 | 85200 | 3.2813 |
|
| 264 |
+
| 1.7811 | 18.6492 | 85600 | 3.2771 |
|
| 265 |
+
| 1.7706 | 18.7364 | 86000 | 3.2808 |
|
| 266 |
+
| 1.7706 | 18.8235 | 86400 | 3.2833 |
|
| 267 |
+
| 1.7669 | 18.9107 | 86800 | 3.2800 |
|
| 268 |
+
| 1.7831 | 18.9978 | 87200 | 3.2816 |
|
| 269 |
+
| 1.7559 | 19.0850 | 87600 | 3.3049 |
|
| 270 |
+
| 1.7288 | 19.1721 | 88000 | 3.2914 |
|
| 271 |
+
| 1.7288 | 19.2593 | 88400 | 3.2865 |
|
| 272 |
+
| 1.7625 | 19.3464 | 88800 | 3.3103 |
|
| 273 |
+
| 1.7507 | 19.4336 | 89200 | 3.2994 |
|
| 274 |
+
| 1.7422 | 19.5207 | 89600 | 3.3055 |
|
| 275 |
+
| 1.745 | 19.6078 | 90000 | 3.2948 |
|
| 276 |
+
| 1.745 | 19.6950 | 90400 | 3.2899 |
|
| 277 |
+
| 1.7514 | 19.7821 | 90800 | 3.3007 |
|
| 278 |
+
| 1.7674 | 19.8693 | 91200 | 3.2860 |
|
| 279 |
+
| 1.7584 | 19.9564 | 91600 | 3.2932 |
|
| 280 |
+
| 1.7563 | 20.0436 | 92000 | 3.2996 |
|
| 281 |
+
| 1.7563 | 20.1307 | 92400 | 3.3120 |
|
| 282 |
+
| 1.7272 | 20.2179 | 92800 | 3.3208 |
|
| 283 |
+
| 1.7268 | 20.3050 | 93200 | 3.3080 |
|
| 284 |
+
| 1.7156 | 20.3922 | 93600 | 3.3193 |
|
| 285 |
+
| 1.7437 | 20.4793 | 94000 | 3.3151 |
|
| 286 |
+
| 1.7437 | 20.5664 | 94400 | 3.2991 |
|
| 287 |
+
| 1.7282 | 20.6536 | 94800 | 3.3088 |
|
| 288 |
+
| 1.7532 | 20.7407 | 95200 | 3.3054 |
|
| 289 |
+
| 1.7394 | 20.8279 | 95600 | 3.3044 |
|
| 290 |
+
| 1.7238 | 20.9150 | 96000 | 3.3098 |
|
| 291 |
+
| 1.7238 | 21.0022 | 96400 | 3.3157 |
|
| 292 |
+
| 1.7179 | 21.0893 | 96800 | 3.3328 |
|
| 293 |
+
| 1.6887 | 21.1765 | 97200 | 3.3292 |
|
| 294 |
+
| 1.7301 | 21.2636 | 97600 | 3.3223 |
|
| 295 |
+
| 1.7126 | 21.3508 | 98000 | 3.3146 |
|
| 296 |
+
| 1.7126 | 21.4379 | 98400 | 3.3177 |
|
| 297 |
+
| 1.7163 | 21.5251 | 98800 | 3.3153 |
|
| 298 |
+
| 1.7132 | 21.6122 | 99200 | 3.3180 |
|
| 299 |
+
| 1.7128 | 21.6993 | 99600 | 3.3167 |
|
| 300 |
+
| 1.7088 | 21.7865 | 100000 | 3.3214 |
|
| 301 |
+
| 1.7088 | 21.8736 | 100400 | 3.3187 |
|
| 302 |
+
| 1.7205 | 21.9608 | 100800 | 3.3214 |
|
| 303 |
+
| 1.7121 | 22.0479 | 101200 | 3.3374 |
|
| 304 |
+
| 1.6778 | 22.1351 | 101600 | 3.3358 |
|
| 305 |
+
| 1.7013 | 22.2222 | 102000 | 3.3389 |
|
| 306 |
+
| 1.7013 | 22.3094 | 102400 | 3.3322 |
|
| 307 |
+
| 1.6742 | 22.3965 | 102800 | 3.3478 |
|
| 308 |
+
| 1.6972 | 22.4837 | 103200 | 3.3255 |
|
| 309 |
+
| 1.6951 | 22.5708 | 103600 | 3.3325 |
|
| 310 |
+
| 1.7017 | 22.6580 | 104000 | 3.3424 |
|
| 311 |
+
| 1.7017 | 22.7451 | 104400 | 3.3256 |
|
| 312 |
+
| 1.7041 | 22.8322 | 104800 | 3.3353 |
|
| 313 |
+
| 1.7165 | 22.9194 | 105200 | 3.3224 |
|
| 314 |
+
| 1.724 | 23.0065 | 105600 | 3.3278 |
|
| 315 |
+
| 1.6814 | 23.0937 | 106000 | 3.3438 |
|
| 316 |
+
| 1.6814 | 23.1808 | 106400 | 3.3510 |
|
| 317 |
+
| 1.6667 | 23.2680 | 106800 | 3.3436 |
|
| 318 |
+
| 1.6851 | 23.3551 | 107200 | 3.3529 |
|
| 319 |
+
| 1.692 | 23.4423 | 107600 | 3.3422 |
|
| 320 |
+
| 1.6977 | 23.5294 | 108000 | 3.3397 |
|
| 321 |
+
| 1.6977 | 23.6166 | 108400 | 3.3527 |
|
| 322 |
+
| 1.6783 | 23.7037 | 108800 | 3.3499 |
|
| 323 |
+
| 1.6655 | 23.7908 | 109200 | 3.3488 |
|
| 324 |
+
| 1.699 | 23.8780 | 109600 | 3.3396 |
|
| 325 |
+
| 1.6932 | 23.9651 | 110000 | 3.3543 |
|
| 326 |
+
| 1.6932 | 24.0523 | 110400 | 3.3645 |
|
| 327 |
+
| 1.6702 | 24.1394 | 110800 | 3.3517 |
|
| 328 |
+
| 1.6763 | 24.2266 | 111200 | 3.3539 |
|
| 329 |
+
| 1.6535 | 24.3137 | 111600 | 3.3473 |
|
| 330 |
+
| 1.6847 | 24.4009 | 112000 | 3.3527 |
|
| 331 |
+
| 1.6847 | 24.4880 | 112400 | 3.3483 |
|
| 332 |
+
| 1.6862 | 24.5752 | 112800 | 3.3540 |
|
| 333 |
+
| 1.6829 | 24.6623 | 113200 | 3.3592 |
|
| 334 |
+
| 1.6698 | 24.7495 | 113600 | 3.3534 |
|
| 335 |
+
| 1.671 | 24.8366 | 114000 | 3.3538 |
|
| 336 |
+
| 1.671 | 24.9237 | 114400 | 3.3509 |
|
| 337 |
+
| 1.6707 | 25.0109 | 114800 | 3.3563 |
|
| 338 |
+
| 1.6657 | 25.0980 | 115200 | 3.3647 |
|
| 339 |
+
| 1.6421 | 25.1852 | 115600 | 3.3676 |
|
| 340 |
+
| 1.6474 | 25.2723 | 116000 | 3.3669 |
|
| 341 |
+
| 1.6474 | 25.3595 | 116400 | 3.3651 |
|
| 342 |
+
| 1.6575 | 25.4466 | 116800 | 3.3681 |
|
| 343 |
+
| 1.657 | 25.5338 | 117200 | 3.3681 |
|
| 344 |
+
| 1.6709 | 25.6209 | 117600 | 3.3647 |
|
| 345 |
+
| 1.6699 | 25.7081 | 118000 | 3.3609 |
|
| 346 |
+
| 1.6699 | 25.7952 | 118400 | 3.3599 |
|
| 347 |
+
| 1.6567 | 25.8824 | 118800 | 3.3652 |
|
| 348 |
+
| 1.6683 | 25.9695 | 119200 | 3.3619 |
|
| 349 |
+
| 1.666 | 26.0566 | 119600 | 3.3621 |
|
| 350 |
+
| 1.6508 | 26.1438 | 120000 | 3.3709 |
|
| 351 |
+
| 1.6508 | 26.2309 | 120400 | 3.3687 |
|
| 352 |
+
| 1.6385 | 26.3181 | 120800 | 3.3709 |
|
| 353 |
+
| 1.6645 | 26.4052 | 121200 | 3.3708 |
|
| 354 |
+
| 1.637 | 26.4924 | 121600 | 3.3776 |
|
| 355 |
+
| 1.6475 | 26.5795 | 122000 | 3.3674 |
|
| 356 |
+
| 1.6475 | 26.6667 | 122400 | 3.3709 |
|
| 357 |
+
| 1.6593 | 26.7538 | 122800 | 3.3733 |
|
| 358 |
+
| 1.6528 | 26.8410 | 123200 | 3.3718 |
|
| 359 |
+
| 1.6492 | 26.9281 | 123600 | 3.3709 |
|
| 360 |
+
| 1.6668 | 27.0153 | 124000 | 3.3713 |
|
| 361 |
+
| 1.6668 | 27.1024 | 124400 | 3.3744 |
|
| 362 |
+
| 1.6439 | 27.1895 | 124800 | 3.3748 |
|
| 363 |
+
| 1.6504 | 27.2767 | 125200 | 3.3802 |
|
| 364 |
+
| 1.6262 | 27.3638 | 125600 | 3.3787 |
|
| 365 |
+
| 1.646 | 27.4510 | 126000 | 3.3718 |
|
| 366 |
+
| 1.646 | 27.5381 | 126400 | 3.3762 |
|
| 367 |
+
| 1.6387 | 27.6253 | 126800 | 3.3775 |
|
| 368 |
+
| 1.6484 | 27.7124 | 127200 | 3.3759 |
|
| 369 |
+
| 1.6446 | 27.7996 | 127600 | 3.3745 |
|
| 370 |
+
| 1.6625 | 27.8867 | 128000 | 3.3716 |
|
| 371 |
+
| 1.6625 | 27.9739 | 128400 | 3.3691 |
|
| 372 |
+
| 1.6485 | 28.0610 | 128800 | 3.3810 |
|
| 373 |
+
| 1.6339 | 28.1481 | 129200 | 3.3834 |
|
| 374 |
+
| 1.6157 | 28.2353 | 129600 | 3.3818 |
|
| 375 |
+
| 1.6309 | 28.3224 | 130000 | 3.3827 |
|
| 376 |
+
| 1.6309 | 28.4096 | 130400 | 3.3793 |
|
| 377 |
+
| 1.6439 | 28.4967 | 130800 | 3.3812 |
|
| 378 |
+
| 1.6351 | 28.5839 | 131200 | 3.3806 |
|
| 379 |
+
| 1.6375 | 28.6710 | 131600 | 3.3807 |
|
| 380 |
+
| 1.6395 | 28.7582 | 132000 | 3.3780 |
|
| 381 |
+
| 1.6395 | 28.8453 | 132400 | 3.3768 |
|
| 382 |
+
| 1.6576 | 28.9325 | 132800 | 3.3756 |
|
| 383 |
+
| 1.6431 | 29.0196 | 133200 | 3.3782 |
|
| 384 |
+
| 1.6308 | 29.1068 | 133600 | 3.3782 |
|
| 385 |
+
| 1.66 | 29.1939 | 134000 | 3.3769 |
|
| 386 |
+
| 1.66 | 29.2810 | 134400 | 3.3817 |
|
| 387 |
+
| 1.6188 | 29.3682 | 134800 | 3.3824 |
|
| 388 |
+
| 1.6435 | 29.4553 | 135200 | 3.3831 |
|
| 389 |
+
| 1.6169 | 29.5425 | 135600 | 3.3819 |
|
| 390 |
+
| 1.6506 | 29.6296 | 136000 | 3.3788 |
|
| 391 |
+
| 1.6506 | 29.7168 | 136400 | 3.3802 |
|
| 392 |
+
| 1.6318 | 29.8039 | 136800 | 3.3806 |
|
| 393 |
+
| 1.6155 | 29.8911 | 137200 | 3.3810 |
|
| 394 |
+
| 1.6292 | 29.9782 | 137600 | 3.3813 |
|
| 395 |
|
| 396 |
|
| 397 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497774208
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae0c3758ce92a6c84cd6735e7b6740e38f2b63a20b7b4f5e3c3a175efb3c858a
|
| 3 |
size 497774208
|
runs/Jul01_00-00-11_Delta6112/events.out.tfevents.1719806412.Delta6112.24560.6
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49aac77bcbe905d136e137e8b7c67ced0217b73bec075cd4d62ce62a35db4c72
|
| 3 |
+
size 159066
|
runs/Jul01_00-00-11_Delta6112/events.out.tfevents.1719835582.Delta6112.24560.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74367cf6baf04b3ab1193992f31b0bd6b09f8b8c493c1a4c6ca2eed6c7647e6f
|
| 3 |
+
size 364
|