<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
metal-graphcodebert-base-gpt4-v2
This model is a fine-tuned version of on the None dataset. It achieves the following results on the evaluation set:
- Loss: 5.8479
- Accuracy: 0.7289
- Text Start Acc: 0.7159
- Text End Acc: 0.6831
- Code Start Acc: 0.7602
- Code End Acc: 0.7565
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 28
- eval_batch_size: 28
- seed: 1337
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | Text Start Acc | Text End Acc | Code Start Acc | Code End Acc |
---|---|---|---|---|---|---|---|---|
8.3971 | 0.02 | 100 | 6.7316 | 0.3450 | 0.3354 | 0.3555 | 0.3508 | 0.3385 |
6.9776 | 0.04 | 200 | 6.3918 | 0.3317 | 0.3607 | 0.3607 | 0.2892 | 0.3161 |
6.7246 | 0.05 | 300 | 6.4021 | 0.2950 | 0.3098 | 0.3588 | 0.2861 | 0.2253 |
6.2857 | 0.07 | 400 | 6.4514 | 0.2544 | 0.3112 | 0.3147 | 0.1952 | 0.1965 |
5.6849 | 0.09 | 500 | 6.8546 | 0.2111 | 0.1829 | 0.2111 | 0.2242 | 0.2263 |
5.2509 | 0.11 | 600 | 6.6644 | 0.2578 | 0.2362 | 0.2369 | 0.2918 | 0.2664 |
4.7871 | 0.13 | 700 | 6.2825 | 0.3287 | 0.3252 | 0.3182 | 0.3412 | 0.3302 |
4.5091 | 0.14 | 800 | 6.6473 | 0.3498 | 0.3174 | 0.3213 | 0.3717 | 0.3890 |
4.2741 | 0.16 | 900 | 6.9305 | 0.3409 | 0.3046 | 0.3140 | 0.3685 | 0.3765 |
4.0916 | 0.18 | 1000 | 6.9337 | 0.3729 | 0.3892 | 0.3541 | 0.3695 | 0.3789 |
3.9533 | 0.2 | 1100 | 6.4524 | 0.4331 | 0.4411 | 0.3891 | 0.4630 | 0.4392 |
3.7737 | 0.22 | 1200 | 6.9752 | 0.4375 | 0.4372 | 0.3867 | 0.4670 | 0.4592 |
3.6482 | 0.23 | 1300 | 6.5678 | 0.4796 | 0.4856 | 0.4361 | 0.5141 | 0.4826 |
3.5602 | 0.25 | 1400 | 6.1688 | 0.5299 | 0.5260 | 0.4741 | 0.5569 | 0.5627 |
3.4698 | 0.27 | 1500 | 6.8455 | 0.4851 | 0.4801 | 0.4559 | 0.5056 | 0.4987 |
3.3788 | 0.29 | 1600 | 6.4223 | 0.5420 | 0.5168 | 0.4904 | 0.5809 | 0.5799 |
3.3251 | 0.31 | 1700 | 6.8447 | 0.5318 | 0.5374 | 0.4958 | 0.5393 | 0.5550 |
3.2756 | 0.32 | 1800 | 6.6636 | 0.5328 | 0.5289 | 0.4806 | 0.5676 | 0.5540 |
3.2408 | 0.34 | 1900 | 6.9432 | 0.5282 | 0.5139 | 0.4744 | 0.5732 | 0.5513 |
3.1621 | 0.36 | 2000 | 6.5627 | 0.5485 | 0.5462 | 0.5275 | 0.5585 | 0.5618 |
3.1129 | 0.38 | 2100 | 6.4573 | 0.5837 | 0.5588 | 0.5337 | 0.6266 | 0.6158 |
3.0736 | 0.4 | 2200 | 6.5341 | 0.5745 | 0.5407 | 0.5285 | 0.6187 | 0.6101 |
3.1045 | 0.42 | 2300 | 6.5989 | 0.5637 | 0.5541 | 0.5294 | 0.5906 | 0.5806 |
2.9869 | 0.43 | 2400 | 5.9950 | 0.6288 | 0.6510 | 0.6143 | 0.6286 | 0.6213 |
3.031 | 0.45 | 2500 | 6.0789 | 0.6228 | 0.6292 | 0.5977 | 0.6376 | 0.6268 |
2.9777 | 0.47 | 2600 | 6.5276 | 0.5798 | 0.5589 | 0.5255 | 0.6207 | 0.6140 |
2.9349 | 0.49 | 2700 | 6.8991 | 0.5739 | 0.5494 | 0.5251 | 0.6085 | 0.6125 |
2.9124 | 0.51 | 2800 | 6.5091 | 0.6107 | 0.5949 | 0.5815 | 0.6333 | 0.6331 |
2.8915 | 0.52 | 2900 | 6.5923 | 0.5845 | 0.6001 | 0.5595 | 0.5938 | 0.5846 |
2.8751 | 0.54 | 3000 | 6.5511 | 0.6096 | 0.5879 | 0.5700 | 0.6367 | 0.6439 |
2.8601 | 0.56 | 3100 | 6.3659 | 0.6199 | 0.6034 | 0.5669 | 0.6493 | 0.6598 |
2.8456 | 0.58 | 3200 | 6.4313 | 0.6036 | 0.5800 | 0.5632 | 0.6358 | 0.6354 |
2.8159 | 0.6 | 3300 | 6.4739 | 0.6275 | 0.6061 | 0.6005 | 0.6579 | 0.6453 |
2.7855 | 0.61 | 3400 | 6.2978 | 0.6346 | 0.6622 | 0.5956 | 0.6549 | 0.6257 |
2.7855 | 0.63 | 3500 | 6.3657 | 0.6196 | 0.6127 | 0.5731 | 0.6633 | 0.6293 |
2.7661 | 0.65 | 3600 | 6.0560 | 0.6541 | 0.6664 | 0.6242 | 0.6779 | 0.6481 |
2.767 | 0.67 | 3700 | 6.4933 | 0.6305 | 0.5995 | 0.5815 | 0.6770 | 0.6640 |
2.729 | 0.69 | 3800 | 5.9295 | 0.6679 | 0.6615 | 0.6292 | 0.7063 | 0.6748 |
2.7618 | 0.7 | 3900 | 6.1942 | 0.6567 | 0.6397 | 0.6347 | 0.6870 | 0.6655 |
2.71 | 0.72 | 4000 | 6.3116 | 0.6487 | 0.6382 | 0.5967 | 0.6951 | 0.6649 |
2.6885 | 0.74 | 4100 | 6.4091 | 0.6324 | 0.6167 | 0.5838 | 0.6734 | 0.6555 |
2.6836 | 0.76 | 4200 | 6.1200 | 0.6698 | 0.6710 | 0.6424 | 0.6940 | 0.6717 |
2.6377 | 0.78 | 4300 | 6.2637 | 0.6623 | 0.6715 | 0.6492 | 0.6722 | 0.6563 |
2.637 | 0.79 | 4400 | 5.9594 | 0.6834 | 0.6762 | 0.6608 | 0.7179 | 0.6787 |
2.6328 | 0.81 | 4500 | 6.3686 | 0.6437 | 0.6240 | 0.6216 | 0.6741 | 0.6549 |
2.6071 | 0.83 | 4600 | 6.2973 | 0.6590 | 0.6201 | 0.6371 | 0.6951 | 0.6835 |
2.633 | 0.85 | 4700 | 6.4171 | 0.6366 | 0.6061 | 0.5995 | 0.6824 | 0.6583 |
2.61 | 0.87 | 4800 | 6.2193 | 0.6555 | 0.6441 | 0.6416 | 0.6891 | 0.6472 |
2.6009 | 0.88 | 4900 | 6.2767 | 0.6449 | 0.6457 | 0.6373 | 0.6643 | 0.6324 |
2.6197 | 0.9 | 5000 | 6.2614 | 0.6677 | 0.6624 | 0.6324 | 0.6863 | 0.6899 |
2.5735 | 0.92 | 5100 | 6.2180 | 0.6688 | 0.6586 | 0.6209 | 0.7093 | 0.6863 |
2.5512 | 0.94 | 5200 | 5.9750 | 0.6846 | 0.6702 | 0.6490 | 0.7297 | 0.6894 |
2.5685 | 0.96 | 5300 | 5.8572 | 0.7053 | 0.7120 | 0.6648 | 0.7302 | 0.7142 |
2.5614 | 0.97 | 5400 | 6.3916 | 0.6566 | 0.6565 | 0.6030 | 0.6959 | 0.6708 |
2.5365 | 0.99 | 5500 | 6.2022 | 0.6796 | 0.6803 | 0.6622 | 0.6886 | 0.6872 |
2.5137 | 1.01 | 5600 | 6.1598 | 0.6761 | 0.6635 | 0.6453 | 0.7047 | 0.6910 |
2.4921 | 1.03 | 5700 | 6.0222 | 0.6818 | 0.6528 | 0.6502 | 0.7180 | 0.7063 |
2.4955 | 1.05 | 5800 | 6.1344 | 0.6762 | 0.6616 | 0.6250 | 0.7163 | 0.7018 |
2.4384 | 1.06 | 5900 | 6.2503 | 0.6726 | 0.6751 | 0.6596 | 0.6799 | 0.6759 |
2.4571 | 1.08 | 6000 | 6.3051 | 0.6637 | 0.6435 | 0.6192 | 0.7025 | 0.6894 |
2.455 | 1.1 | 6100 | 6.0680 | 0.6799 | 0.6896 | 0.6430 | 0.7052 | 0.6816 |
2.4189 | 1.12 | 6200 | 6.2017 | 0.6742 | 0.6631 | 0.6318 | 0.7145 | 0.6875 |
2.4405 | 1.14 | 6300 | 6.1502 | 0.6773 | 0.6631 | 0.6395 | 0.7011 | 0.7054 |
2.4469 | 1.16 | 6400 | 6.1243 | 0.6800 | 0.6772 | 0.6390 | 0.7092 | 0.6948 |
2.4166 | 1.17 | 6500 | 6.0812 | 0.6819 | 0.6639 | 0.6391 | 0.7141 | 0.7106 |
2.4241 | 1.19 | 6600 | 5.6822 | 0.7309 | 0.7273 | 0.7163 | 0.7426 | 0.7376 |
2.412 | 1.21 | 6700 | 6.1815 | 0.6781 | 0.6598 | 0.6544 | 0.7128 | 0.6855 |
2.4207 | 1.23 | 6800 | 5.9485 | 0.6983 | 0.7056 | 0.6681 | 0.7193 | 0.7001 |
2.3856 | 1.25 | 6900 | 6.2165 | 0.6769 | 0.6538 | 0.6242 | 0.7227 | 0.7068 |
2.3837 | 1.26 | 7000 | 6.2255 | 0.6784 | 0.6531 | 0.6288 | 0.7208 | 0.7108 |
2.4406 | 1.28 | 7100 | 6.0703 | 0.6964 | 0.6972 | 0.6630 | 0.7098 | 0.7155 |
2.3832 | 1.3 | 7200 | 6.0778 | 0.6867 | 0.6864 | 0.6563 | 0.7102 | 0.6939 |
2.4194 | 1.32 | 7300 | 6.1522 | 0.6804 | 0.6654 | 0.6349 | 0.7144 | 0.7069 |
2.4214 | 1.34 | 7400 | 6.2848 | 0.6664 | 0.6660 | 0.6218 | 0.6998 | 0.6781 |
2.3598 | 1.35 | 7500 | 6.0278 | 0.7073 | 0.6869 | 0.6610 | 0.7400 | 0.7413 |
2.3669 | 1.37 | 7600 | 5.9456 | 0.7121 | 0.7083 | 0.6921 | 0.7264 | 0.7217 |
2.4028 | 1.39 | 7700 | 6.1055 | 0.6827 | 0.6846 | 0.6357 | 0.7085 | 0.7018 |
2.3922 | 1.41 | 7800 | 5.9995 | 0.6972 | 0.6770 | 0.6487 | 0.7351 | 0.7281 |
2.3867 | 1.43 | 7900 | 6.2460 | 0.6816 | 0.6672 | 0.6363 | 0.7096 | 0.7135 |
2.371 | 1.44 | 8000 | 5.9551 | 0.7072 | 0.6980 | 0.6734 | 0.7318 | 0.7256 |
2.3553 | 1.46 | 8100 | 5.9955 | 0.7052 | 0.7135 | 0.6651 | 0.7256 | 0.7168 |
2.4089 | 1.48 | 8200 | 6.1565 | 0.6869 | 0.6769 | 0.6335 | 0.7102 | 0.7270 |
2.3822 | 1.5 | 8300 | 6.2396 | 0.6817 | 0.6722 | 0.6434 | 0.7130 | 0.6982 |
2.3743 | 1.52 | 8400 | 5.9867 | 0.6964 | 0.6853 | 0.6573 | 0.7236 | 0.7195 |
2.3818 | 1.53 | 8500 | 6.1663 | 0.6839 | 0.6549 | 0.6340 | 0.7371 | 0.7094 |
2.3467 | 1.55 | 8600 | 6.3287 | 0.6657 | 0.6509 | 0.6116 | 0.7034 | 0.6968 |
2.3544 | 1.57 | 8700 | 5.9424 | 0.7101 | 0.7074 | 0.6769 | 0.7346 | 0.7213 |
2.3138 | 1.59 | 8800 | 6.1324 | 0.6859 | 0.6778 | 0.6387 | 0.7278 | 0.6994 |
2.3574 | 1.61 | 8900 | 6.0064 | 0.6995 | 0.6850 | 0.6600 | 0.7350 | 0.7179 |
2.3234 | 1.62 | 9000 | 5.9436 | 0.7048 | 0.6848 | 0.6644 | 0.7450 | 0.7251 |
2.3546 | 1.64 | 9100 | 6.0459 | 0.6933 | 0.6701 | 0.6415 | 0.7306 | 0.7311 |
2.3518 | 1.66 | 9200 | 6.0300 | 0.6976 | 0.6831 | 0.6657 | 0.7208 | 0.7209 |
2.3474 | 1.68 | 9300 | 6.2438 | 0.6880 | 0.6584 | 0.6192 | 0.7376 | 0.7366 |
2.3079 | 1.7 | 9400 | 6.1013 | 0.6922 | 0.6720 | 0.6398 | 0.7326 | 0.7242 |
2.3718 | 1.71 | 9500 | 5.9430 | 0.7004 | 0.6996 | 0.6597 | 0.7316 | 0.7109 |
2.3153 | 1.73 | 9600 | 6.0077 | 0.7016 | 0.6941 | 0.6597 | 0.7359 | 0.7166 |
2.2929 | 1.75 | 9700 | 6.0677 | 0.6997 | 0.6787 | 0.6448 | 0.7424 | 0.7327 |
2.3055 | 1.77 | 9800 | 6.1334 | 0.6887 | 0.6659 | 0.6466 | 0.7252 | 0.7170 |
2.327 | 1.79 | 9900 | 5.8188 | 0.7274 | 0.7217 | 0.6932 | 0.7538 | 0.7407 |
2.2936 | 1.81 | 10000 | 5.9292 | 0.7172 | 0.7042 | 0.6836 | 0.7497 | 0.7313 |
2.2941 | 1.82 | 10100 | 6.2885 | 0.6812 | 0.6610 | 0.6220 | 0.7321 | 0.7098 |
2.3006 | 1.84 | 10200 | 5.8766 | 0.7159 | 0.7171 | 0.6864 | 0.7352 | 0.7250 |
2.3093 | 1.86 | 10300 | 5.8775 | 0.7189 | 0.7182 | 0.6820 | 0.7436 | 0.7319 |
2.3366 | 1.88 | 10400 | 6.1641 | 0.6916 | 0.6679 | 0.6407 | 0.7321 | 0.7255 |
2.3077 | 1.9 | 10500 | 5.8684 | 0.7198 | 0.6958 | 0.6744 | 0.7584 | 0.7505 |
2.317 | 1.91 | 10600 | 5.9451 | 0.7119 | 0.6781 | 0.6581 | 0.7507 | 0.7608 |
2.2959 | 1.93 | 10700 | 6.0043 | 0.7100 | 0.6915 | 0.6526 | 0.7512 | 0.7448 |
2.3102 | 1.95 | 10800 | 5.9453 | 0.7171 | 0.7025 | 0.6803 | 0.7504 | 0.7351 |
2.2915 | 1.97 | 10900 | 6.0021 | 0.7087 | 0.6753 | 0.6582 | 0.7421 | 0.7591 |
2.3239 | 1.99 | 11000 | 6.0865 | 0.6927 | 0.6744 | 0.6382 | 0.7313 | 0.7270 |
2.2721 | 2.0 | 11100 | 5.9036 | 0.7169 | 0.7026 | 0.6824 | 0.7435 | 0.7393 |
2.2238 | 2.02 | 11200 | 6.0722 | 0.7050 | 0.6864 | 0.6488 | 0.7471 | 0.7376 |
2.2447 | 2.04 | 11300 | 6.1078 | 0.6991 | 0.6627 | 0.6440 | 0.7452 | 0.7445 |
2.2241 | 2.06 | 11400 | 5.9561 | 0.7144 | 0.7061 | 0.6706 | 0.7502 | 0.7307 |
2.2261 | 2.08 | 11500 | 5.7849 | 0.7248 | 0.7244 | 0.6917 | 0.7359 | 0.7474 |
2.231 | 2.09 | 11600 | 6.0342 | 0.7090 | 0.6958 | 0.6485 | 0.7486 | 0.7432 |
2.1898 | 2.11 | 11700 | 5.9014 | 0.7201 | 0.7069 | 0.6768 | 0.7484 | 0.7483 |
2.2201 | 2.13 | 11800 | 5.9044 | 0.7174 | 0.7009 | 0.6657 | 0.7542 | 0.7486 |
2.2307 | 2.15 | 11900 | 5.9123 | 0.7155 | 0.7054 | 0.6746 | 0.7407 | 0.7413 |
2.1999 | 2.17 | 12000 | 6.2262 | 0.6832 | 0.6482 | 0.6148 | 0.7354 | 0.7345 |
2.2209 | 2.18 | 12100 | 5.9494 | 0.7107 | 0.6891 | 0.6654 | 0.7408 | 0.7474 |
2.2259 | 2.2 | 12200 | 5.9214 | 0.7109 | 0.7052 | 0.6571 | 0.7392 | 0.7422 |
2.2245 | 2.22 | 12300 | 5.8257 | 0.7295 | 0.7212 | 0.6841 | 0.7600 | 0.7528 |
2.2082 | 2.24 | 12400 | 6.0086 | 0.7081 | 0.7012 | 0.6534 | 0.7507 | 0.7271 |
2.2245 | 2.26 | 12500 | 5.9757 | 0.7081 | 0.6949 | 0.6458 | 0.7426 | 0.7493 |
2.2237 | 2.27 | 12600 | 5.8529 | 0.7212 | 0.7150 | 0.6687 | 0.7589 | 0.7423 |
2.2003 | 2.29 | 12700 | 6.0264 | 0.7004 | 0.6798 | 0.6391 | 0.7405 | 0.7422 |
2.1977 | 2.31 | 12800 | 5.8916 | 0.7227 | 0.7137 | 0.6774 | 0.7574 | 0.7424 |
2.22 | 2.33 | 12900 | 5.9524 | 0.7153 | 0.6999 | 0.6703 | 0.7442 | 0.7467 |
2.1917 | 2.35 | 13000 | 5.9550 | 0.7142 | 0.6964 | 0.6694 | 0.7464 | 0.7446 |
2.215 | 2.36 | 13100 | 5.9686 | 0.7090 | 0.6853 | 0.6596 | 0.7478 | 0.7433 |
2.2258 | 2.38 | 13200 | 5.7851 | 0.7321 | 0.7214 | 0.6929 | 0.7594 | 0.7548 |
2.2281 | 2.4 | 13300 | 5.9139 | 0.7193 | 0.6966 | 0.6765 | 0.7526 | 0.7514 |
2.2055 | 2.42 | 13400 | 5.9116 | 0.7197 | 0.7077 | 0.6696 | 0.7534 | 0.7483 |
2.1781 | 2.44 | 13500 | 5.9780 | 0.7117 | 0.6918 | 0.6603 | 0.7450 | 0.7495 |
2.2239 | 2.45 | 13600 | 5.9471 | 0.7110 | 0.6875 | 0.6655 | 0.7435 | 0.7476 |
2.2284 | 2.47 | 13700 | 5.9708 | 0.7082 | 0.6934 | 0.6694 | 0.7384 | 0.7317 |
2.1786 | 2.49 | 13800 | 5.8479 | 0.7290 | 0.7189 | 0.6845 | 0.7604 | 0.7523 |
2.1944 | 2.51 | 13900 | 5.8999 | 0.7194 | 0.7051 | 0.6831 | 0.7456 | 0.7437 |
2.1895 | 2.53 | 14000 | 5.9709 | 0.7107 | 0.6936 | 0.6660 | 0.7466 | 0.7364 |
2.1995 | 2.55 | 14100 | 5.7951 | 0.7333 | 0.7223 | 0.6908 | 0.7612 | 0.7588 |
2.1989 | 2.56 | 14200 | 5.8615 | 0.7252 | 0.7102 | 0.6743 | 0.7595 | 0.7570 |
2.2218 | 2.58 | 14300 | 5.8684 | 0.7246 | 0.7161 | 0.6939 | 0.7445 | 0.7438 |
2.192 | 2.6 | 14400 | 5.9905 | 0.7132 | 0.6884 | 0.6538 | 0.7593 | 0.7512 |
2.1772 | 2.62 | 14500 | 5.9371 | 0.7145 | 0.7012 | 0.6554 | 0.7591 | 0.7422 |
2.1891 | 2.64 | 14600 | 5.9154 | 0.7187 | 0.7056 | 0.6669 | 0.7560 | 0.7462 |
2.1816 | 2.65 | 14700 | 5.9592 | 0.7126 | 0.6936 | 0.6633 | 0.7475 | 0.7460 |
2.2013 | 2.67 | 14800 | 5.9243 | 0.7151 | 0.6980 | 0.6649 | 0.7497 | 0.7480 |
2.208 | 2.69 | 14900 | 5.8249 | 0.7250 | 0.7113 | 0.6717 | 0.7603 | 0.7565 |
2.2053 | 2.71 | 15000 | 5.8508 | 0.7286 | 0.7130 | 0.6840 | 0.7596 | 0.7577 |
2.1609 | 2.73 | 15100 | 5.9201 | 0.7207 | 0.7042 | 0.6770 | 0.7542 | 0.7475 |
2.1801 | 2.74 | 15200 | 5.8693 | 0.7275 | 0.7084 | 0.6880 | 0.7593 | 0.7545 |
2.1972 | 2.76 | 15300 | 5.8483 | 0.7285 | 0.7166 | 0.6874 | 0.7596 | 0.7502 |
2.2134 | 2.78 | 15400 | 5.8746 | 0.7275 | 0.7164 | 0.6826 | 0.7603 | 0.7507 |
2.1707 | 2.8 | 15500 | 5.8845 | 0.7246 | 0.7121 | 0.6821 | 0.7550 | 0.7494 |
2.1909 | 2.82 | 15600 | 5.8627 | 0.7269 | 0.7073 | 0.6849 | 0.7598 | 0.7556 |
2.2049 | 2.83 | 15700 | 5.8539 | 0.7291 | 0.7080 | 0.6856 | 0.7652 | 0.7575 |
2.1588 | 2.85 | 15800 | 5.9037 | 0.7214 | 0.7028 | 0.6820 | 0.7519 | 0.7488 |
2.1796 | 2.87 | 15900 | 5.8557 | 0.7263 | 0.7118 | 0.6844 | 0.7565 | 0.7524 |
2.216 | 2.89 | 16000 | 5.8732 | 0.7261 | 0.7103 | 0.6777 | 0.7608 | 0.7556 |
2.1994 | 2.91 | 16100 | 5.8283 | 0.7304 | 0.7202 | 0.6854 | 0.7615 | 0.7543 |
2.168 | 2.92 | 16200 | 5.8564 | 0.7274 | 0.7156 | 0.6822 | 0.7570 | 0.7547 |
2.1989 | 2.94 | 16300 | 5.8409 | 0.7293 | 0.7179 | 0.6839 | 0.7595 | 0.7560 |
2.22 | 2.96 | 16400 | 5.8212 | 0.7317 | 0.7211 | 0.6851 | 0.7632 | 0.7575 |
2.1602 | 2.98 | 16500 | 5.8388 | 0.7303 | 0.7171 | 0.6840 | 0.7623 | 0.7577 |
2.1948 | 3.0 | 16600 | 5.8484 | 0.7289 | 0.7157 | 0.6831 | 0.7603 | 0.7566 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3