--- library_name: transformers tags: - generated_from_trainer metrics: - accuracy model-index: - name: ht-finbert-cls-v5_ftis_noPretrain_tdso-smlo results: [] --- # ht-finbert-cls-v5_ftis_noPretrain_tdso-smlo This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.3715 - Accuracy: 0.8266 - Macro F1: 0.5992 ## 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: 0.0001 - train_batch_size: 8 - eval_batch_size: 4 - seed: 42 - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 6700 - training_steps: 134000 ### Training results | Training Loss | Epoch | Step | Accuracy | Validation Loss | Macro F1 | |:-------------:|:--------:|:-----:|:--------:|:---------------:|:--------:| | 60.146 | 2.0002 | 100 | 0.0640 | 35.7626 | 0.0348 | | 22.4431 | 5.0002 | 200 | 0.1551 | 12.0966 | 0.0558 | | 9.1164 | 8.0002 | 300 | 0.4586 | 8.6968 | 0.1167 | | 7.3706 | 11.0002 | 400 | 0.5270 | 7.5573 | 0.1403 | | 6.6822 | 14.0002 | 500 | 0.5649 | 6.5449 | 0.1518 | | 6.0983 | 17.0002 | 600 | 0.5862 | 6.4116 | 0.1598 | | 5.6519 | 20.0001 | 700 | 0.6059 | 5.4930 | 0.1812 | | 4.7887 | 23.0001 | 800 | 0.6211 | 4.5238 | 0.2028 | | 4.1287 | 26.0001 | 900 | 0.6375 | 3.5454 | 0.2293 | | 3.485 | 29.0001 | 1000 | 0.6426 | 3.2262 | 0.2329 | | 3.0592 | 32.0001 | 1100 | 0.6658 | 2.7347 | 0.2600 | | 2.5414 | 35.0001 | 1200 | 0.6698 | 2.4810 | 0.2876 | | 2.2536 | 38.0001 | 1300 | 0.6887 | 2.3174 | 0.2978 | | 1.9944 | 41.0000 | 1400 | 0.6704 | 2.3076 | 0.3220 | | 1.745 | 44.0000 | 1500 | 0.7091 | 2.1667 | 0.3509 | | 1.5825 | 47.0000 | 1600 | 0.7221 | 2.1587 | 0.3731 | | 1.4019 | 49.0003 | 1700 | 0.7227 | 2.1903 | 0.3770 | | 1.3098 | 52.0002 | 1800 | 0.7305 | 2.0639 | 0.4022 | | 1.1999 | 55.0002 | 1900 | 0.7165 | 2.2811 | 0.3997 | | 1.1357 | 58.0002 | 2000 | 0.7364 | 2.0456 | 0.4397 | | 1.0099 | 61.0002 | 2100 | 0.7463 | 2.1184 | 0.4433 | | 0.9511 | 64.0002 | 2200 | 0.7430 | 2.1943 | 0.4562 | | 0.9267 | 67.0002 | 2300 | 0.7430 | 2.1426 | 0.4567 | | 0.8538 | 70.0001 | 2400 | 0.7555 | 2.1494 | 0.4734 | | 0.8137 | 73.0001 | 2500 | 0.7543 | 2.1069 | 0.4870 | | 0.7565 | 76.0001 | 2600 | 0.7582 | 2.0830 | 0.4944 | | 0.7137 | 79.0001 | 2700 | 0.7635 | 2.0783 | 0.4961 | | 0.6768 | 82.0001 | 2800 | 0.7625 | 2.2560 | 0.4857 | | 0.6767 | 85.0001 | 2900 | 0.7586 | 2.2191 | 0.5000 | | 0.655 | 88.0001 | 3000 | 0.7595 | 2.3385 | 0.4860 | | 0.6107 | 91.0000 | 3100 | 0.7669 | 2.2185 | 0.5104 | | 0.5909 | 94.0000 | 3200 | 0.7664 | 2.1933 | 0.5069 | | 0.5825 | 97.0000 | 3300 | 0.7715 | 2.2201 | 0.5207 | | 0.5517 | 99.0003 | 3400 | 0.7718 | 2.2094 | 0.5193 | | 0.5291 | 102.0002 | 3500 | 0.7754 | 2.1411 | 0.5165 | | 0.5179 | 105.0002 | 3600 | 0.7727 | 2.2621 | 0.5181 | | 0.5068 | 108.0002 | 3700 | 0.7736 | 2.3722 | 0.5186 | | 0.485 | 111.0002 | 3800 | 0.7747 | 2.2727 | 0.5169 | | 0.4685 | 114.0002 | 3900 | 0.7788 | 2.2356 | 0.5215 | | 0.4455 | 117.0002 | 4000 | 0.7835 | 2.3099 | 0.5318 | | 0.4417 | 120.0001 | 4100 | 0.7809 | 2.2780 | 0.5176 | | 0.4239 | 123.0001 | 4200 | 0.7803 | 2.2974 | 0.5274 | | 0.4138 | 126.0001 | 4300 | 0.7856 | 2.3263 | 0.5306 | | 0.4161 | 129.0001 | 4400 | 0.7857 | 2.4421 | 0.5291 | | 0.407 | 132.0001 | 4500 | 0.7851 | 2.2520 | 0.5298 | | 0.3937 | 135.0001 | 4600 | 0.7822 | 2.4370 | 0.5258 | | 0.3955 | 138.0001 | 4700 | 0.7822 | 2.4754 | 0.5208 | | 0.3958 | 141.0000 | 4800 | 0.7850 | 2.4944 | 0.5228 | | 0.371 | 144.0000 | 4900 | 0.7930 | 2.2718 | 0.5393 | | 0.3631 | 147.0000 | 5000 | 0.7980 | 2.1747 | 0.5545 | | 0.357 | 149.0003 | 5100 | 0.7967 | 2.1777 | 0.5547 | | 0.3535 | 152.0002 | 5200 | 0.7931 | 2.3164 | 0.5407 | | 0.3494 | 155.0002 | 5300 | 0.7970 | 2.2375 | 0.5521 | | 0.337 | 158.0002 | 5400 | 0.7939 | 2.3545 | 0.5430 | | 0.3341 | 161.0002 | 5500 | 0.7999 | 2.3440 | 0.5439 | | 0.3304 | 164.0002 | 5600 | 0.7992 | 2.3232 | 0.5477 | | 0.3301 | 167.0002 | 5700 | 0.7973 | 2.3870 | 0.5482 | | 0.3147 | 170.0001 | 5800 | 0.7932 | 2.4424 | 0.5387 | | 0.3156 | 173.0001 | 5900 | 0.8022 | 2.2992 | 0.5511 | | 0.3097 | 176.0001 | 6000 | 0.8056 | 2.3754 | 0.5553 | | 0.3153 | 179.0001 | 6100 | 0.8045 | 2.2373 | 0.5511 | | 0.3324 | 182.0001 | 6200 | 0.8021 | 2.3703 | 0.5464 | | 0.3229 | 185.0001 | 6300 | 0.8066 | 2.2643 | 0.5585 | | 0.3278 | 188.0001 | 6400 | 0.8022 | 2.3330 | 0.5587 | | 0.3033 | 191.0000 | 6500 | 0.8034 | 2.4422 | 0.5515 | | 0.2962 | 194.0000 | 6600 | 0.8091 | 2.3543 | 0.5600 | | 0.2981 | 197.0000 | 6700 | 0.8086 | 2.3194 | 0.5666 | | 0.2938 | 199.0003 | 6800 | 0.8112 | 2.3451 | 0.5690 | | 0.2905 | 202.0002 | 6900 | 0.8099 | 2.4594 | 0.5635 | | 0.2864 | 205.0002 | 7000 | 0.8019 | 2.4190 | 0.5570 | | 0.2841 | 208.0002 | 7100 | 0.8082 | 2.4058 | 0.5649 | | 0.281 | 211.0002 | 7200 | 0.8040 | 2.4430 | 0.5604 | | 0.2858 | 214.0002 | 7300 | 0.8044 | 2.4068 | 0.5622 | | 0.2855 | 217.0002 | 7400 | 0.8063 | 2.6108 | 0.5662 | | 0.294 | 220.0001 | 7500 | 0.7997 | 2.6127 | 0.5564 | | 0.2861 | 223.0001 | 7600 | 0.8056 | 2.4765 | 0.5706 | | 0.2727 | 226.0001 | 7700 | 0.8049 | 2.5476 | 0.5655 | | 0.2739 | 229.0001 | 7800 | 0.8096 | 2.4457 | 0.5695 | | 0.2692 | 232.0001 | 7900 | 0.8122 | 2.3098 | 0.5774 | | 0.2871 | 235.0001 | 8000 | 0.8031 | 2.5063 | 0.5765 | | 0.2782 | 238.0001 | 8100 | 0.8114 | 2.4428 | 0.5673 | | 0.2756 | 241.0000 | 8200 | 0.7937 | 2.3776 | 0.5673 | | 0.2724 | 244.0000 | 8300 | 0.8139 | 2.3966 | 0.5692 | | 0.264 | 247.0000 | 8400 | 0.8137 | 2.4945 | 0.5717 | | 0.2607 | 249.0003 | 8500 | 0.8092 | 2.3385 | 0.5645 | | 0.2607 | 252.0002 | 8600 | 0.8136 | 2.3088 | 0.5719 | | 0.2549 | 255.0002 | 8700 | 0.8150 | 2.4480 | 0.5743 | | 0.2498 | 258.0002 | 8800 | 0.8150 | 2.5000 | 0.5809 | | 0.2531 | 261.0002 | 8900 | 0.8147 | 2.4216 | 0.5753 | | 0.2533 | 264.0002 | 9000 | 0.8124 | 2.5209 | 0.5746 | | 0.2595 | 267.0002 | 9100 | 0.8134 | 2.4882 | 0.5802 | | 0.2592 | 270.0001 | 9200 | 0.8038 | 2.6653 | 0.5583 | | 0.2538 | 273.0001 | 9300 | 0.8154 | 2.3961 | 0.5755 | | 0.2467 | 276.0001 | 9400 | 0.8166 | 2.4694 | 0.5796 | | 0.246 | 279.0001 | 9500 | 0.8144 | 2.6904 | 0.5726 | | 0.2457 | 282.0001 | 9600 | 0.8162 | 2.3962 | 0.5816 | | 0.2481 | 285.0001 | 9700 | 0.8166 | 2.5073 | 0.5764 | | 0.2446 | 288.0001 | 9800 | 0.8113 | 2.5453 | 0.5742 | | 0.2432 | 291.0000 | 9900 | 0.8151 | 2.5354 | 0.5832 | | 0.2433 | 294.0000 | 10000 | 0.8171 | 2.4146 | 0.5827 | | 0.249 | 297.0000 | 10100 | 0.8029 | 2.6529 | 0.5491 | | 0.2548 | 299.0003 | 10200 | 0.8131 | 2.4793 | 0.5793 | | 0.2649 | 302.0002 | 10300 | 0.8053 | 2.5708 | 0.5797 | | 0.2844 | 305.0002 | 10400 | 0.8155 | 2.3701 | 0.5871 | | 0.2615 | 308.0002 | 10500 | 0.8134 | 2.2351 | 0.5769 | | 0.2404 | 311.0002 | 10600 | 0.8209 | 2.3267 | 0.5823 | | 0.2374 | 314.0002 | 10700 | 0.8210 | 2.5221 | 0.5865 | | 0.2336 | 317.0002 | 10800 | 0.8207 | 2.3691 | 0.5841 | | 0.2353 | 320.0001 | 10900 | 0.8216 | 2.3595 | 0.5864 | | 0.2325 | 323.0001 | 11000 | 0.8204 | 2.3844 | 0.5928 | | 0.2308 | 326.0001 | 11100 | 0.8217 | 2.5118 | 0.5889 | | 0.2297 | 329.0001 | 11200 | 0.8186 | 2.5145 | 0.5839 | | 0.228 | 332.0001 | 11300 | 0.8210 | 2.5383 | 0.5890 | | 0.2277 | 335.0001 | 11400 | 0.8193 | 2.5202 | 0.5842 | | 0.2411 | 338.0001 | 11500 | 0.8174 | 2.4485 | 0.5882 | | 0.2385 | 341.0000 | 11600 | 0.8095 | 2.5662 | 0.5775 | | 0.2326 | 344.0000 | 11700 | 0.8186 | 2.6191 | 0.5804 | | 0.2276 | 347.0000 | 11800 | 0.8197 | 2.3903 | 0.5883 | | 0.2314 | 349.0003 | 11900 | 0.8187 | 2.5956 | 0.5761 | | 0.2247 | 352.0002 | 12000 | 0.8231 | 2.5574 | 0.5837 | | 0.2221 | 355.0002 | 12100 | 0.8216 | 2.5241 | 0.5876 | | 0.2222 | 358.0002 | 12200 | 0.8190 | 2.5069 | 0.5853 | | 0.2252 | 361.0002 | 12300 | 0.8214 | 2.4055 | 0.5890 | | 0.2258 | 364.0002 | 12400 | 0.8219 | 2.4567 | 0.5886 | | 0.2241 | 367.0002 | 12500 | 0.8222 | 2.4780 | 0.5971 | | 0.2236 | 370.0001 | 12600 | 0.8174 | 2.3867 | 0.5860 | | 0.2228 | 373.0001 | 12700 | 0.8250 | 2.4244 | 0.5971 | | 0.2206 | 376.0001 | 12800 | 0.8196 | 2.4699 | 0.5885 | | 0.2228 | 379.0001 | 12900 | 0.8198 | 2.5620 | 0.5894 | | 0.2168 | 382.0001 | 13000 | 0.8222 | 2.5460 | 0.5934 | | 0.2186 | 385.0001 | 13100 | 0.8244 | 2.4516 | 0.5940 | | 0.2197 | 388.0001 | 13200 | 0.8190 | 2.6875 | 0.5848 | | 0.216 | 391.0000 | 13300 | 0.8205 | 2.5740 | 0.5863 | | 0.2386 | 394.0000 | 13400 | 0.8141 | 2.6024 | 0.5791 | | 0.2657 | 397.0000 | 13500 | 0.8161 | 2.5998 | 0.5836 | | 0.2661 | 399.0003 | 13600 | 0.8150 | 2.3760 | 0.5849 | | 0.2206 | 402.0002 | 13700 | 0.8243 | 2.5276 | 0.5866 | | 0.2151 | 405.0002 | 13800 | 0.8264 | 2.3444 | 0.6009 | | 0.2121 | 408.0002 | 13900 | 0.8246 | 2.4449 | 0.5966 | | 0.2127 | 411.0002 | 14000 | 0.8239 | 2.3422 | 0.5923 | ### Framework versions - Transformers 4.46.0 - Pytorch 2.3.1+cu121 - Datasets 2.20.0 - Tokenizers 0.20.1