Training in progress, epoch 1
Browse files- README.md +24 -191
- adapter_model.safetensors +1 -1
- all_results.json +11 -11
- eval_results.json +6 -6
- train_results.json +6 -6
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -5,18 +5,18 @@ base_model: gpt2
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
-
- name:
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
#
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss:
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
@@ -35,204 +35,37 @@ More information needed
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate:
|
| 39 |
-
- train_batch_size:
|
| 40 |
-
- eval_batch_size:
|
| 41 |
- seed: 42
|
| 42 |
- gradient_accumulation_steps: 4
|
| 43 |
-
- total_train_batch_size:
|
| 44 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_ratio: 0.03
|
| 47 |
-
- num_epochs:
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
-
| 3.
|
| 54 |
-
| 3.
|
| 55 |
-
|
|
| 56 |
-
|
|
| 57 |
-
|
|
| 58 |
-
|
|
| 59 |
-
|
|
| 60 |
-
|
|
| 61 |
-
|
|
| 62 |
-
|
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
| 1.
|
| 66 |
-
| 1.
|
| 67 |
-
| 1.
|
| 68 |
-
| 1.
|
| 69 |
-
| 1.5545 | 0.2783 | 340 | 1.3478 |
|
| 70 |
-
| 1.4609 | 0.2947 | 360 | 1.2741 |
|
| 71 |
-
| 1.3616 | 0.3111 | 380 | 1.2038 |
|
| 72 |
-
| 1.3137 | 0.3275 | 400 | 1.1477 |
|
| 73 |
-
| 1.2682 | 0.3438 | 420 | 1.1003 |
|
| 74 |
-
| 1.2262 | 0.3602 | 440 | 1.0645 |
|
| 75 |
-
| 1.2021 | 0.3766 | 460 | 1.0357 |
|
| 76 |
-
| 1.1659 | 0.3930 | 480 | 1.0129 |
|
| 77 |
-
| 1.1355 | 0.4093 | 500 | 0.9911 |
|
| 78 |
-
| 1.1085 | 0.4257 | 520 | 0.9732 |
|
| 79 |
-
| 1.0979 | 0.4421 | 540 | 0.9571 |
|
| 80 |
-
| 1.0775 | 0.4585 | 560 | 0.9420 |
|
| 81 |
-
| 1.0659 | 0.4748 | 580 | 0.9295 |
|
| 82 |
-
| 1.0356 | 0.4912 | 600 | 0.9158 |
|
| 83 |
-
| 1.0184 | 0.5076 | 620 | 0.9056 |
|
| 84 |
-
| 0.9979 | 0.5239 | 640 | 0.8965 |
|
| 85 |
-
| 0.988 | 0.5403 | 660 | 0.8879 |
|
| 86 |
-
| 0.9913 | 0.5567 | 680 | 0.8794 |
|
| 87 |
-
| 0.9681 | 0.5731 | 700 | 0.8734 |
|
| 88 |
-
| 0.959 | 0.5894 | 720 | 0.8670 |
|
| 89 |
-
| 0.9389 | 0.6058 | 740 | 0.8591 |
|
| 90 |
-
| 0.9363 | 0.6222 | 760 | 0.8556 |
|
| 91 |
-
| 0.9274 | 0.6386 | 780 | 0.8490 |
|
| 92 |
-
| 0.9265 | 0.6549 | 800 | 0.8472 |
|
| 93 |
-
| 0.9265 | 0.6713 | 820 | 0.8432 |
|
| 94 |
-
| 0.9033 | 0.6877 | 840 | 0.8404 |
|
| 95 |
-
| 0.912 | 0.7041 | 860 | 0.8372 |
|
| 96 |
-
| 0.9067 | 0.7204 | 880 | 0.8337 |
|
| 97 |
-
| 0.896 | 0.7368 | 900 | 0.8309 |
|
| 98 |
-
| 0.9061 | 0.7532 | 920 | 0.8280 |
|
| 99 |
-
| 0.8966 | 0.7695 | 940 | 0.8247 |
|
| 100 |
-
| 0.8871 | 0.7859 | 960 | 0.8233 |
|
| 101 |
-
| 0.8844 | 0.8023 | 980 | 0.8209 |
|
| 102 |
-
| 0.8903 | 0.8187 | 1000 | 0.8188 |
|
| 103 |
-
| 0.8938 | 0.8350 | 1020 | 0.8166 |
|
| 104 |
-
| 0.884 | 0.8514 | 1040 | 0.8143 |
|
| 105 |
-
| 0.8614 | 0.8678 | 1060 | 0.8128 |
|
| 106 |
-
| 0.8716 | 0.8842 | 1080 | 0.8100 |
|
| 107 |
-
| 0.8719 | 0.9005 | 1100 | 0.8082 |
|
| 108 |
-
| 0.8685 | 0.9169 | 1120 | 0.8063 |
|
| 109 |
-
| 0.8784 | 0.9333 | 1140 | 0.8049 |
|
| 110 |
-
| 0.8534 | 0.9497 | 1160 | 0.8037 |
|
| 111 |
-
| 0.8556 | 0.9660 | 1180 | 0.8021 |
|
| 112 |
-
| 0.862 | 0.9824 | 1200 | 0.8007 |
|
| 113 |
-
| 0.852 | 0.9988 | 1220 | 0.7989 |
|
| 114 |
-
| 0.857 | 1.0147 | 1240 | 0.7969 |
|
| 115 |
-
| 0.8562 | 1.0311 | 1260 | 0.7957 |
|
| 116 |
-
| 0.8508 | 1.0475 | 1280 | 0.7965 |
|
| 117 |
-
| 0.845 | 1.0639 | 1300 | 0.7952 |
|
| 118 |
-
| 0.839 | 1.0802 | 1320 | 0.7951 |
|
| 119 |
-
| 0.8472 | 1.0966 | 1340 | 0.7919 |
|
| 120 |
-
| 0.8425 | 1.1130 | 1360 | 0.7899 |
|
| 121 |
-
| 0.8285 | 1.1293 | 1380 | 0.7908 |
|
| 122 |
-
| 0.8287 | 1.1457 | 1400 | 0.7894 |
|
| 123 |
-
| 0.8371 | 1.1621 | 1420 | 0.7880 |
|
| 124 |
-
| 0.8281 | 1.1785 | 1440 | 0.7873 |
|
| 125 |
-
| 0.8468 | 1.1948 | 1460 | 0.7863 |
|
| 126 |
-
| 0.833 | 1.2112 | 1480 | 0.7851 |
|
| 127 |
-
| 0.8298 | 1.2276 | 1500 | 0.7854 |
|
| 128 |
-
| 0.8321 | 1.2440 | 1520 | 0.7841 |
|
| 129 |
-
| 0.823 | 1.2603 | 1540 | 0.7835 |
|
| 130 |
-
| 0.828 | 1.2767 | 1560 | 0.7832 |
|
| 131 |
-
| 0.8353 | 1.2931 | 1580 | 0.7830 |
|
| 132 |
-
| 0.8277 | 1.3095 | 1600 | 0.7814 |
|
| 133 |
-
| 0.8172 | 1.3258 | 1620 | 0.7815 |
|
| 134 |
-
| 0.8192 | 1.3422 | 1640 | 0.7814 |
|
| 135 |
-
| 0.8223 | 1.3586 | 1660 | 0.7800 |
|
| 136 |
-
| 0.8272 | 1.3749 | 1680 | 0.7789 |
|
| 137 |
-
| 0.8202 | 1.3913 | 1700 | 0.7785 |
|
| 138 |
-
| 0.8185 | 1.4077 | 1720 | 0.7769 |
|
| 139 |
-
| 0.8325 | 1.4241 | 1740 | 0.7778 |
|
| 140 |
-
| 0.8128 | 1.4404 | 1760 | 0.7760 |
|
| 141 |
-
| 0.8153 | 1.4568 | 1780 | 0.7767 |
|
| 142 |
-
| 0.8212 | 1.4732 | 1800 | 0.7772 |
|
| 143 |
-
| 0.8049 | 1.4896 | 1820 | 0.7753 |
|
| 144 |
-
| 0.825 | 1.5059 | 1840 | 0.7744 |
|
| 145 |
-
| 0.8175 | 1.5223 | 1860 | 0.7746 |
|
| 146 |
-
| 0.8218 | 1.5387 | 1880 | 0.7731 |
|
| 147 |
-
| 0.814 | 1.5551 | 1900 | 0.7730 |
|
| 148 |
-
| 0.8172 | 1.5714 | 1920 | 0.7723 |
|
| 149 |
-
| 0.8305 | 1.5878 | 1940 | 0.7717 |
|
| 150 |
-
| 0.8145 | 1.6042 | 1960 | 0.7728 |
|
| 151 |
-
| 0.7996 | 1.6205 | 1980 | 0.7710 |
|
| 152 |
-
| 0.809 | 1.6369 | 2000 | 0.7705 |
|
| 153 |
-
| 0.8013 | 1.6533 | 2020 | 0.7707 |
|
| 154 |
-
| 0.8106 | 1.6697 | 2040 | 0.7680 |
|
| 155 |
-
| 0.8235 | 1.6860 | 2060 | 0.7695 |
|
| 156 |
-
| 0.8075 | 1.7024 | 2080 | 0.7692 |
|
| 157 |
-
| 0.8098 | 1.7188 | 2100 | 0.7679 |
|
| 158 |
-
| 0.8036 | 1.7352 | 2120 | 0.7690 |
|
| 159 |
-
| 0.8119 | 1.7515 | 2140 | 0.7664 |
|
| 160 |
-
| 0.8111 | 1.7679 | 2160 | 0.7672 |
|
| 161 |
-
| 0.8052 | 1.7843 | 2180 | 0.7670 |
|
| 162 |
-
| 0.8084 | 1.8007 | 2200 | 0.7673 |
|
| 163 |
-
| 0.8102 | 1.8170 | 2220 | 0.7675 |
|
| 164 |
-
| 0.8099 | 1.8334 | 2240 | 0.7665 |
|
| 165 |
-
| 0.7982 | 1.8498 | 2260 | 0.7660 |
|
| 166 |
-
| 0.8052 | 1.8661 | 2280 | 0.7652 |
|
| 167 |
-
| 0.8096 | 1.8825 | 2300 | 0.7646 |
|
| 168 |
-
| 0.8099 | 1.8989 | 2320 | 0.7659 |
|
| 169 |
-
| 0.7973 | 1.9153 | 2340 | 0.7661 |
|
| 170 |
-
| 0.817 | 1.9316 | 2360 | 0.7650 |
|
| 171 |
-
| 0.7987 | 1.9480 | 2380 | 0.7646 |
|
| 172 |
-
| 0.8112 | 1.9644 | 2400 | 0.7630 |
|
| 173 |
-
| 0.8051 | 1.9808 | 2420 | 0.7635 |
|
| 174 |
-
| 0.797 | 1.9971 | 2440 | 0.7635 |
|
| 175 |
-
| 0.7871 | 2.0131 | 2460 | 0.7629 |
|
| 176 |
-
| 0.8124 | 2.0295 | 2480 | 0.7633 |
|
| 177 |
-
| 0.7969 | 2.0458 | 2500 | 0.7642 |
|
| 178 |
-
| 0.7906 | 2.0622 | 2520 | 0.7634 |
|
| 179 |
-
| 0.8032 | 2.0786 | 2540 | 0.7632 |
|
| 180 |
-
| 0.806 | 2.0950 | 2560 | 0.7625 |
|
| 181 |
-
| 0.8019 | 2.1113 | 2580 | 0.7628 |
|
| 182 |
-
| 0.8017 | 2.1277 | 2600 | 0.7614 |
|
| 183 |
-
| 0.8106 | 2.1441 | 2620 | 0.7623 |
|
| 184 |
-
| 0.7996 | 2.1605 | 2640 | 0.7622 |
|
| 185 |
-
| 0.8038 | 2.1768 | 2660 | 0.7621 |
|
| 186 |
-
| 0.8036 | 2.1932 | 2680 | 0.7607 |
|
| 187 |
-
| 0.8032 | 2.2096 | 2700 | 0.7618 |
|
| 188 |
-
| 0.797 | 2.2260 | 2720 | 0.7608 |
|
| 189 |
-
| 0.8031 | 2.2423 | 2740 | 0.7607 |
|
| 190 |
-
| 0.8004 | 2.2587 | 2760 | 0.7606 |
|
| 191 |
-
| 0.8043 | 2.2751 | 2780 | 0.7604 |
|
| 192 |
-
| 0.7971 | 2.2914 | 2800 | 0.7614 |
|
| 193 |
-
| 0.7982 | 2.3078 | 2820 | 0.7607 |
|
| 194 |
-
| 0.7972 | 2.3242 | 2840 | 0.7601 |
|
| 195 |
-
| 0.8071 | 2.3406 | 2860 | 0.7609 |
|
| 196 |
-
| 0.8094 | 2.3569 | 2880 | 0.7605 |
|
| 197 |
-
| 0.7994 | 2.3733 | 2900 | 0.7600 |
|
| 198 |
-
| 0.7918 | 2.3897 | 2920 | 0.7596 |
|
| 199 |
-
| 0.7978 | 2.4061 | 2940 | 0.7597 |
|
| 200 |
-
| 0.8026 | 2.4224 | 2960 | 0.7599 |
|
| 201 |
-
| 0.7981 | 2.4388 | 2980 | 0.7593 |
|
| 202 |
-
| 0.7957 | 2.4552 | 3000 | 0.7600 |
|
| 203 |
-
| 0.8089 | 2.4716 | 3020 | 0.7601 |
|
| 204 |
-
| 0.801 | 2.4879 | 3040 | 0.7598 |
|
| 205 |
-
| 0.8044 | 2.5043 | 3060 | 0.7592 |
|
| 206 |
-
| 0.7967 | 2.5207 | 3080 | 0.7591 |
|
| 207 |
-
| 0.803 | 2.5370 | 3100 | 0.7589 |
|
| 208 |
-
| 0.8006 | 2.5534 | 3120 | 0.7591 |
|
| 209 |
-
| 0.7933 | 2.5698 | 3140 | 0.7599 |
|
| 210 |
-
| 0.7954 | 2.5862 | 3160 | 0.7590 |
|
| 211 |
-
| 0.7996 | 2.6025 | 3180 | 0.7592 |
|
| 212 |
-
| 0.7931 | 2.6189 | 3200 | 0.7597 |
|
| 213 |
-
| 0.8034 | 2.6353 | 3220 | 0.7595 |
|
| 214 |
-
| 0.7954 | 2.6517 | 3240 | 0.7606 |
|
| 215 |
-
| 0.801 | 2.6680 | 3260 | 0.7592 |
|
| 216 |
-
| 0.7973 | 2.6844 | 3280 | 0.7595 |
|
| 217 |
-
| 0.7976 | 2.7008 | 3300 | 0.7601 |
|
| 218 |
-
| 0.8014 | 2.7172 | 3320 | 0.7606 |
|
| 219 |
-
| 0.8052 | 2.7335 | 3340 | 0.7590 |
|
| 220 |
-
| 0.7898 | 2.7499 | 3360 | 0.7609 |
|
| 221 |
-
| 0.794 | 2.7663 | 3380 | 0.7598 |
|
| 222 |
-
| 0.7984 | 2.7826 | 3400 | 0.7609 |
|
| 223 |
-
| 0.7905 | 2.7990 | 3420 | 0.7587 |
|
| 224 |
-
| 0.7994 | 2.8154 | 3440 | 0.7595 |
|
| 225 |
-
| 0.8083 | 2.8318 | 3460 | 0.7588 |
|
| 226 |
-
| 0.7979 | 2.8481 | 3480 | 0.7585 |
|
| 227 |
-
| 0.7947 | 2.8645 | 3500 | 0.7596 |
|
| 228 |
-
| 0.8081 | 2.8809 | 3520 | 0.7592 |
|
| 229 |
-
| 0.801 | 2.8973 | 3540 | 0.7615 |
|
| 230 |
-
| 0.7959 | 2.9136 | 3560 | 0.7590 |
|
| 231 |
-
| 0.8081 | 2.9300 | 3580 | 0.7594 |
|
| 232 |
-
| 0.7927 | 2.9464 | 3600 | 0.7589 |
|
| 233 |
-
| 0.8006 | 2.9628 | 3620 | 0.7594 |
|
| 234 |
-
| 0.7933 | 2.9791 | 3640 | 0.7591 |
|
| 235 |
-
| 0.7896 | 2.9955 | 3660 | 0.7591 |
|
| 236 |
|
| 237 |
|
| 238 |
### Framework versions
|
|
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
model-index:
|
| 8 |
+
- name: Se124M10KInfPrompt_WT_EOS
|
| 9 |
results: []
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
+
# Se124M10KInfPrompt_WT_EOS
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.0978
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 5e-05
|
| 39 |
+
- train_batch_size: 64
|
| 40 |
+
- eval_batch_size: 64
|
| 41 |
- seed: 42
|
| 42 |
- gradient_accumulation_steps: 4
|
| 43 |
+
- total_train_batch_size: 256
|
| 44 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_ratio: 0.03
|
| 47 |
+
- num_epochs: 10
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 3.2645 | 0.5970 | 20 | 2.8750 |
|
| 54 |
+
| 3.0103 | 1.1791 | 40 | 2.6534 |
|
| 55 |
+
| 2.7014 | 1.7761 | 60 | 2.3720 |
|
| 56 |
+
| 2.3851 | 2.3582 | 80 | 2.1090 |
|
| 57 |
+
| 2.1288 | 2.9552 | 100 | 1.8650 |
|
| 58 |
+
| 1.9062 | 3.5373 | 120 | 1.6703 |
|
| 59 |
+
| 1.739 | 4.1194 | 140 | 1.5153 |
|
| 60 |
+
| 1.6033 | 4.7164 | 160 | 1.3879 |
|
| 61 |
+
| 1.5039 | 5.2985 | 180 | 1.2845 |
|
| 62 |
+
| 1.4219 | 5.8955 | 200 | 1.2122 |
|
| 63 |
+
| 1.357 | 6.4776 | 220 | 1.1649 |
|
| 64 |
+
| 1.3201 | 7.0597 | 240 | 1.1304 |
|
| 65 |
+
| 1.2923 | 7.6567 | 260 | 1.1101 |
|
| 66 |
+
| 1.2831 | 8.2388 | 280 | 1.1035 |
|
| 67 |
+
| 1.2715 | 8.8358 | 300 | 1.1007 |
|
| 68 |
+
| 1.2721 | 9.4179 | 320 | 1.0986 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
|
| 71 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 309980480
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:988a0855d45e3695e95b55aaeea2226c042bce5ce609146fbde0c0d06b7d7954
|
| 3 |
size 309980480
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second":
|
| 7 |
-
"perplexity": 2.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 1.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.716417910447761,
|
| 3 |
+
"eval_loss": 1.0977526903152466,
|
| 4 |
+
"eval_runtime": 1.7342,
|
| 5 |
+
"eval_samples_per_second": 1054.072,
|
| 6 |
+
"eval_steps_per_second": 16.722,
|
| 7 |
+
"perplexity": 2.9974223129878887,
|
| 8 |
+
"total_flos": 5406457244811264.0,
|
| 9 |
+
"train_loss": 1.8237198396162553,
|
| 10 |
+
"train_runtime": 182.316,
|
| 11 |
+
"train_samples_per_second": 467.759,
|
| 12 |
+
"train_steps_per_second": 1.81
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples_per_second":
|
| 6 |
-
"eval_steps_per_second":
|
| 7 |
-
"perplexity": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.716417910447761,
|
| 3 |
+
"eval_loss": 1.0977526903152466,
|
| 4 |
+
"eval_runtime": 1.7342,
|
| 5 |
+
"eval_samples_per_second": 1054.072,
|
| 6 |
+
"eval_steps_per_second": 16.722,
|
| 7 |
+
"perplexity": 2.9974223129878887
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 1.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.716417910447761,
|
| 3 |
+
"total_flos": 5406457244811264.0,
|
| 4 |
+
"train_loss": 1.8237198396162553,
|
| 5 |
+
"train_runtime": 182.316,
|
| 6 |
+
"train_samples_per_second": 467.759,
|
| 7 |
+
"train_steps_per_second": 1.81
|
| 8 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58259ea51d9add808365a7fb5410f4bdcc0e1fae3d72e4d1227b28002ba9f9cb
|
| 3 |
size 5432
|