--- library_name: transformers license: bsd-3-clause base_model: Salesforce/blip-image-captioning-base tags: - generated_from_trainer metrics: - accuracy model-index: - name: smiles_llava results: [] --- <!-- 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. --> # smiles_llava This model is a fine-tuned version of [Salesforce/blip-image-captioning-base](https://huggingface.co/Salesforce/blip-image-captioning-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0064 - Accuracy: 0.9674 ## 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: 6e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 64 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.05 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:| | 4.8969 | 0.0224 | 100 | 4.4867 | 0.0 | | 4.1587 | 0.0448 | 200 | 3.4584 | 0.0014 | | 3.0055 | 0.0672 | 300 | 2.5821 | 0.0014 | | 1.5994 | 0.0896 | 400 | 1.5937 | 0.0027 | | 0.9106 | 0.1120 | 500 | 0.9564 | 0.0068 | | 0.649 | 0.1344 | 600 | 0.6497 | 0.0109 | | 0.4068 | 0.1568 | 700 | 0.4567 | 0.0163 | | 0.3836 | 0.1792 | 800 | 0.3997 | 0.0394 | | 0.3197 | 0.2016 | 900 | 0.3010 | 0.0516 | | 0.2139 | 0.2240 | 1000 | 0.2531 | 0.0774 | | 0.1888 | 0.2464 | 1100 | 0.2234 | 0.1196 | | 0.1511 | 0.2688 | 1200 | 0.2089 | 0.1467 | | 0.1664 | 0.2912 | 1300 | 0.1664 | 0.2296 | | 0.1342 | 0.3136 | 1400 | 0.1551 | 0.2772 | | 0.1287 | 0.3360 | 1500 | 0.1390 | 0.2554 | | 0.1254 | 0.3584 | 1600 | 0.1224 | 0.3247 | | 0.1017 | 0.3808 | 1700 | 0.1148 | 0.3859 | | 0.1017 | 0.4032 | 1800 | 0.1000 | 0.4212 | | 0.0604 | 0.4256 | 1900 | 0.0919 | 0.4022 | | 0.0962 | 0.4480 | 2000 | 0.1015 | 0.3546 | | 0.1066 | 0.4704 | 2100 | 0.0895 | 0.4361 | | 0.0995 | 0.4928 | 2200 | 0.0897 | 0.4266 | | 0.0502 | 0.5152 | 2300 | 0.0781 | 0.5041 | | 0.0554 | 0.5376 | 2400 | 0.0759 | 0.5190 | | 0.0782 | 0.5600 | 2500 | 0.0689 | 0.5163 | | 0.0653 | 0.5824 | 2600 | 0.0673 | 0.5842 | | 0.0522 | 0.6048 | 2700 | 0.0561 | 0.6318 | | 0.0417 | 0.6272 | 2800 | 0.0576 | 0.5788 | | 0.0504 | 0.6496 | 2900 | 0.0532 | 0.6481 | | 0.0533 | 0.6720 | 3000 | 0.0407 | 0.7242 | | 0.0424 | 0.6944 | 3100 | 0.0430 | 0.7052 | | 0.035 | 0.7168 | 3200 | 0.0514 | 0.6359 | | 0.0393 | 0.7392 | 3300 | 0.0467 | 0.6549 | | 0.058 | 0.7616 | 3400 | 0.0436 | 0.6821 | | 0.0628 | 0.7840 | 3500 | 0.0395 | 0.6970 | | 0.0285 | 0.8064 | 3600 | 0.0443 | 0.6889 | | 0.023 | 0.8288 | 3700 | 0.0449 | 0.7120 | | 0.0361 | 0.8512 | 3800 | 0.0392 | 0.7283 | | 0.0302 | 0.8736 | 3900 | 0.0383 | 0.6957 | | 0.0258 | 0.8960 | 4000 | 0.0347 | 0.7147 | | 0.0494 | 0.9184 | 4100 | 0.0486 | 0.6603 | | 0.022 | 0.9408 | 4200 | 0.0335 | 0.7473 | | 0.0116 | 0.9632 | 4300 | 0.0288 | 0.8016 | | 0.0389 | 0.9856 | 4400 | 0.0320 | 0.7717 | | 0.0222 | 1.0078 | 4500 | 0.0286 | 0.7894 | | 0.0201 | 1.0302 | 4600 | 0.0272 | 0.8003 | | 0.0171 | 1.0526 | 4700 | 0.0246 | 0.8261 | | 0.0237 | 1.0750 | 4800 | 0.0250 | 0.7962 | | 0.0152 | 1.0974 | 4900 | 0.0296 | 0.7826 | | 0.0272 | 1.1198 | 5000 | 0.0295 | 0.7799 | | 0.0325 | 1.1422 | 5100 | 0.0291 | 0.7894 | | 0.0221 | 1.1646 | 5200 | 0.0271 | 0.8016 | | 0.0177 | 1.1870 | 5300 | 0.0270 | 0.8193 | | 0.0197 | 1.2094 | 5400 | 0.0257 | 0.8111 | | 0.0369 | 1.2318 | 5500 | 0.0256 | 0.7799 | | 0.0167 | 1.2542 | 5600 | 0.0267 | 0.7880 | | 0.013 | 1.2766 | 5700 | 0.0334 | 0.7663 | | 0.0252 | 1.2990 | 5800 | 0.0359 | 0.7826 | | 0.0106 | 1.3214 | 5900 | 0.0283 | 0.7853 | | 0.0167 | 1.3438 | 6000 | 0.0263 | 0.7799 | | 0.0234 | 1.3662 | 6100 | 0.0245 | 0.8152 | | 0.0138 | 1.3886 | 6200 | 0.0223 | 0.8302 | | 0.0184 | 1.4110 | 6300 | 0.0231 | 0.8043 | | 0.0189 | 1.4334 | 6400 | 0.0329 | 0.75 | | 0.0156 | 1.4558 | 6500 | 0.0259 | 0.8274 | | 0.0301 | 1.4782 | 6600 | 0.0210 | 0.8424 | | 0.017 | 1.5006 | 6700 | 0.0226 | 0.8573 | | 0.0217 | 1.5230 | 6800 | 0.0236 | 0.8573 | | 0.0156 | 1.5454 | 6900 | 0.0204 | 0.8519 | | 0.0249 | 1.5678 | 7000 | 0.0246 | 0.8098 | | 0.0152 | 1.5902 | 7100 | 0.0209 | 0.8220 | | 0.0149 | 1.6126 | 7200 | 0.0306 | 0.8016 | | 0.0123 | 1.6350 | 7300 | 0.0218 | 0.8288 | | 0.0189 | 1.6574 | 7400 | 0.0256 | 0.8084 | | 0.0244 | 1.6798 | 7500 | 0.0232 | 0.8098 | | 0.0131 | 1.7022 | 7600 | 0.0185 | 0.8329 | | 0.0241 | 1.7246 | 7700 | 0.0195 | 0.8886 | | 0.0155 | 1.7470 | 7800 | 0.0291 | 0.8193 | | 0.0081 | 1.7694 | 7900 | 0.0191 | 0.8478 | | 0.0047 | 1.7918 | 8000 | 0.0224 | 0.8220 | | 0.0092 | 1.8142 | 8100 | 0.0247 | 0.8424 | | 0.0147 | 1.8366 | 8200 | 0.0229 | 0.8736 | | 0.0084 | 1.8590 | 8300 | 0.0211 | 0.8736 | | 0.0125 | 1.8814 | 8400 | 0.0283 | 0.8288 | | 0.0145 | 1.9038 | 8500 | 0.0235 | 0.8302 | | 0.0144 | 1.9262 | 8600 | 0.0204 | 0.8465 | | 0.0055 | 1.9486 | 8700 | 0.0190 | 0.8587 | | 0.0134 | 1.9710 | 8800 | 0.0222 | 0.8451 | | 0.0058 | 1.9934 | 8900 | 0.0200 | 0.8791 | | 0.0141 | 2.0157 | 9000 | 0.0206 | 0.8451 | | 0.0103 | 2.0381 | 9100 | 0.0189 | 0.8587 | | 0.0106 | 2.0605 | 9200 | 0.0150 | 0.8818 | | 0.0056 | 2.0829 | 9300 | 0.0139 | 0.8845 | | 0.0148 | 2.1053 | 9400 | 0.0117 | 0.9144 | | 0.0072 | 2.1277 | 9500 | 0.0137 | 0.8872 | | 0.0082 | 2.1501 | 9600 | 0.0197 | 0.8641 | | 0.0104 | 2.1725 | 9700 | 0.0163 | 0.8736 | | 0.0082 | 2.1949 | 9800 | 0.0176 | 0.8791 | | 0.0236 | 2.2173 | 9900 | 0.0222 | 0.8410 | | 0.0119 | 2.2397 | 10000 | 0.0206 | 0.8668 | | 0.0263 | 2.2621 | 10100 | 0.0133 | 0.9144 | | 0.0136 | 2.2845 | 10200 | 0.0215 | 0.8641 | | 0.0096 | 2.3069 | 10300 | 0.0163 | 0.8927 | | 0.0076 | 2.3293 | 10400 | 0.0170 | 0.875 | | 0.0138 | 2.3517 | 10500 | 0.0180 | 0.8804 | | 0.0139 | 2.3741 | 10600 | 0.0196 | 0.8696 | | 0.025 | 2.3965 | 10700 | 0.0183 | 0.8573 | | 0.0038 | 2.4189 | 10800 | 0.0180 | 0.8804 | | 0.0082 | 2.4413 | 10900 | 0.0228 | 0.8261 | | 0.0097 | 2.4637 | 11000 | 0.0219 | 0.8519 | | 0.0076 | 2.4861 | 11100 | 0.0185 | 0.8913 | | 0.0122 | 2.5085 | 11200 | 0.0212 | 0.8818 | | 0.013 | 2.5309 | 11300 | 0.0199 | 0.8533 | | 0.0087 | 2.5533 | 11400 | 0.0126 | 0.9103 | | 0.0087 | 2.5757 | 11500 | 0.0154 | 0.8682 | | 0.0097 | 2.5981 | 11600 | 0.0245 | 0.8410 | | 0.0133 | 2.6205 | 11700 | 0.0195 | 0.8832 | | 0.0088 | 2.6428 | 11800 | 0.0134 | 0.9022 | | 0.0152 | 2.6652 | 11900 | 0.0153 | 0.8764 | | 0.0026 | 2.6876 | 12000 | 0.0193 | 0.8818 | | 0.0097 | 2.7100 | 12100 | 0.0222 | 0.8696 | | 0.0113 | 2.7324 | 12200 | 0.0153 | 0.8845 | | 0.0057 | 2.7548 | 12300 | 0.0188 | 0.8940 | | 0.0092 | 2.7772 | 12400 | 0.0185 | 0.8872 | | 0.0025 | 2.7996 | 12500 | 0.0167 | 0.8967 | | 0.0158 | 2.8220 | 12600 | 0.0243 | 0.8451 | | 0.0065 | 2.8444 | 12700 | 0.0186 | 0.8777 | | 0.0044 | 2.8668 | 12800 | 0.0157 | 0.9049 | | 0.0061 | 2.8892 | 12900 | 0.0148 | 0.8859 | | 0.0058 | 2.9116 | 13000 | 0.0126 | 0.9062 | | 0.0033 | 2.9340 | 13100 | 0.0121 | 0.9334 | | 0.0084 | 2.9564 | 13200 | 0.0138 | 0.9171 | | 0.0082 | 2.9788 | 13300 | 0.0202 | 0.8560 | | 0.0049 | 3.0011 | 13400 | 0.0233 | 0.8478 | | 0.0056 | 3.0235 | 13500 | 0.0255 | 0.8709 | | 0.0054 | 3.0459 | 13600 | 0.0148 | 0.9049 | | 0.0008 | 3.0683 | 13700 | 0.0153 | 0.8940 | | 0.0029 | 3.0907 | 13800 | 0.0191 | 0.8777 | | 0.0011 | 3.1131 | 13900 | 0.0165 | 0.9049 | | 0.0052 | 3.1355 | 14000 | 0.0178 | 0.8913 | | 0.0056 | 3.1579 | 14100 | 0.0163 | 0.9022 | | 0.0069 | 3.1803 | 14200 | 0.0175 | 0.9103 | | 0.0069 | 3.2027 | 14300 | 0.0209 | 0.9049 | | 0.0066 | 3.2251 | 14400 | 0.0213 | 0.9062 | | 0.0048 | 3.2475 | 14500 | 0.0186 | 0.8981 | | 0.0029 | 3.2699 | 14600 | 0.0118 | 0.9158 | | 0.0035 | 3.2923 | 14700 | 0.0155 | 0.9185 | | 0.0137 | 3.3147 | 14800 | 0.0136 | 0.9117 | | 0.0031 | 3.3371 | 14900 | 0.0161 | 0.9062 | | 0.003 | 3.3595 | 15000 | 0.0151 | 0.8886 | | 0.0025 | 3.3819 | 15100 | 0.0134 | 0.9239 | | 0.0058 | 3.4043 | 15200 | 0.0115 | 0.9130 | | 0.0166 | 3.4267 | 15300 | 0.0181 | 0.8899 | | 0.0035 | 3.4491 | 15400 | 0.0173 | 0.8940 | | 0.0042 | 3.4715 | 15500 | 0.0165 | 0.9049 | | 0.001 | 3.4939 | 15600 | 0.0151 | 0.9049 | | 0.0021 | 3.5163 | 15700 | 0.0180 | 0.8913 | | 0.0034 | 3.5387 | 15800 | 0.0158 | 0.9239 | | 0.0009 | 3.5611 | 15900 | 0.0126 | 0.9171 | | 0.0025 | 3.5835 | 16000 | 0.0173 | 0.8940 | | 0.0021 | 3.6059 | 16100 | 0.0172 | 0.8818 | | 0.0033 | 3.6283 | 16200 | 0.0111 | 0.9416 | | 0.0057 | 3.6507 | 16300 | 0.0120 | 0.9266 | | 0.0051 | 3.6731 | 16400 | 0.0177 | 0.8804 | | 0.0077 | 3.6955 | 16500 | 0.0166 | 0.8804 | | 0.0016 | 3.7179 | 16600 | 0.0115 | 0.9361 | | 0.0062 | 3.7403 | 16700 | 0.0161 | 0.9293 | | 0.0064 | 3.7627 | 16800 | 0.0173 | 0.8832 | | 0.0028 | 3.7851 | 16900 | 0.0053 | 0.9429 | | 0.0038 | 3.8075 | 17000 | 0.0167 | 0.8981 | | 0.0086 | 3.8299 | 17100 | 0.0122 | 0.9008 | | 0.0008 | 3.8523 | 17200 | 0.0088 | 0.9185 | | 0.0027 | 3.8747 | 17300 | 0.0156 | 0.8899 | | 0.0017 | 3.8971 | 17400 | 0.0107 | 0.9171 | | 0.0037 | 3.9195 | 17500 | 0.0101 | 0.9457 | | 0.0113 | 3.9419 | 17600 | 0.0091 | 0.9348 | | 0.004 | 3.9643 | 17700 | 0.0072 | 0.9429 | | 0.0061 | 3.9867 | 17800 | 0.0143 | 0.9117 | | 0.0011 | 4.0090 | 17900 | 0.0106 | 0.9185 | | 0.0053 | 4.0314 | 18000 | 0.0137 | 0.9239 | | 0.0059 | 4.0538 | 18100 | 0.0115 | 0.9022 | | 0.0039 | 4.0762 | 18200 | 0.0070 | 0.9443 | | 0.0074 | 4.0986 | 18300 | 0.0099 | 0.9266 | | 0.001 | 4.1210 | 18400 | 0.0104 | 0.9280 | | 0.0085 | 4.1434 | 18500 | 0.0113 | 0.9117 | | 0.0054 | 4.1658 | 18600 | 0.0135 | 0.8886 | | 0.006 | 4.1882 | 18700 | 0.0111 | 0.9185 | | 0.0019 | 4.2105 | 18800 | 0.0083 | 0.9321 | | 0.0074 | 4.2329 | 18900 | 0.0144 | 0.8981 | | 0.0044 | 4.2553 | 19000 | 0.0123 | 0.9348 | | 0.0021 | 4.2777 | 19100 | 0.0146 | 0.9158 | | 0.0031 | 4.3001 | 19200 | 0.0140 | 0.8927 | | 0.0045 | 4.3225 | 19300 | 0.0123 | 0.9117 | | 0.0028 | 4.3449 | 19400 | 0.0113 | 0.9198 | | 0.0018 | 4.3673 | 19500 | 0.0157 | 0.9049 | | 0.0012 | 4.3897 | 19600 | 0.0078 | 0.9470 | | 0.0035 | 4.4121 | 19700 | 0.0132 | 0.9307 | | 0.0057 | 4.4345 | 19800 | 0.0107 | 0.9212 | | 0.0016 | 4.4569 | 19900 | 0.0164 | 0.9022 | | 0.0048 | 4.4793 | 20000 | 0.0118 | 0.9226 | | 0.0072 | 4.5017 | 20100 | 0.0094 | 0.9158 | | 0.0024 | 4.5241 | 20200 | 0.0077 | 0.9402 | | 0.0112 | 4.5465 | 20300 | 0.0073 | 0.9334 | | 0.0032 | 4.5689 | 20400 | 0.0126 | 0.9253 | | 0.0048 | 4.5913 | 20500 | 0.0114 | 0.9361 | | 0.0081 | 4.6137 | 20600 | 0.0157 | 0.9171 | | 0.0013 | 4.6361 | 20700 | 0.0147 | 0.9103 | | 0.0016 | 4.6585 | 20800 | 0.0109 | 0.9307 | | 0.0016 | 4.6809 | 20900 | 0.0107 | 0.9307 | | 0.0038 | 4.7033 | 21000 | 0.0118 | 0.9321 | | 0.0027 | 4.7257 | 21100 | 0.0105 | 0.9334 | | 0.0077 | 4.7481 | 21200 | 0.0103 | 0.9226 | | 0.0024 | 4.7705 | 21300 | 0.0117 | 0.9348 | | 0.0037 | 4.7929 | 21400 | 0.0091 | 0.9443 | | 0.0017 | 4.8153 | 21500 | 0.0084 | 0.9457 | | 0.0048 | 4.8377 | 21600 | 0.0097 | 0.9321 | | 0.0021 | 4.8601 | 21700 | 0.0108 | 0.9416 | | 0.0025 | 4.8825 | 21800 | 0.0118 | 0.9171 | | 0.0026 | 4.9049 | 21900 | 0.0099 | 0.9198 | | 0.0012 | 4.9273 | 22000 | 0.0062 | 0.9606 | | 0.0015 | 4.9497 | 22100 | 0.0085 | 0.9389 | | 0.0034 | 4.9721 | 22200 | 0.0151 | 0.9185 | | 0.0003 | 4.9945 | 22300 | 0.0100 | 0.9171 | | 0.0021 | 5.0168 | 22400 | 0.0087 | 0.9321 | | 0.0006 | 5.0392 | 22500 | 0.0082 | 0.9606 | | 0.0006 | 5.0616 | 22600 | 0.0115 | 0.9239 | | 0.006 | 5.0840 | 22700 | 0.0098 | 0.9348 | | 0.0022 | 5.1064 | 22800 | 0.0149 | 0.9117 | | 0.0004 | 5.1288 | 22900 | 0.0075 | 0.9538 | | 0.0003 | 5.1512 | 23000 | 0.0147 | 0.9280 | | 0.0097 | 5.1736 | 23100 | 0.0130 | 0.9239 | | 0.0012 | 5.1960 | 23200 | 0.0114 | 0.9470 | | 0.0003 | 5.2184 | 23300 | 0.0094 | 0.9402 | | 0.0039 | 5.2408 | 23400 | 0.0072 | 0.9429 | | 0.0012 | 5.2632 | 23500 | 0.0068 | 0.9579 | | 0.0001 | 5.2856 | 23600 | 0.0150 | 0.9280 | | 0.001 | 5.3080 | 23700 | 0.0103 | 0.9470 | | 0.0005 | 5.3304 | 23800 | 0.0136 | 0.9171 | | 0.0004 | 5.3528 | 23900 | 0.0111 | 0.9389 | | 0.0008 | 5.3752 | 24000 | 0.0130 | 0.9212 | | 0.0046 | 5.3976 | 24100 | 0.0139 | 0.9375 | | 0.004 | 5.4200 | 24200 | 0.0080 | 0.9497 | | 0.0032 | 5.4424 | 24300 | 0.0089 | 0.9484 | | 0.0004 | 5.4648 | 24400 | 0.0085 | 0.9552 | | 0.0001 | 5.4872 | 24500 | 0.0081 | 0.9552 | | 0.0008 | 5.5096 | 24600 | 0.0087 | 0.9565 | | 0.0007 | 5.5320 | 24700 | 0.0093 | 0.9606 | | 0.0002 | 5.5544 | 24800 | 0.0108 | 0.9307 | | 0.0036 | 5.5768 | 24900 | 0.0099 | 0.9524 | | 0.0006 | 5.5992 | 25000 | 0.0131 | 0.9117 | | 0.003 | 5.6216 | 25100 | 0.0095 | 0.9429 | | 0.0026 | 5.6440 | 25200 | 0.0108 | 0.9348 | | 0.0002 | 5.6664 | 25300 | 0.0069 | 0.9660 | | 0.0006 | 5.6888 | 25400 | 0.0080 | 0.9497 | | 0.0001 | 5.7112 | 25500 | 0.0075 | 0.9633 | | 0.0014 | 5.7336 | 25600 | 0.0064 | 0.9674 | | 0.0004 | 5.7560 | 25700 | 0.0081 | 0.9606 | | 0.0031 | 5.7784 | 25800 | 0.0071 | 0.9647 | | 0.0009 | 5.8008 | 25900 | 0.0074 | 0.9579 | | 0.0003 | 5.8232 | 26000 | 0.0094 | 0.9470 | | 0.0003 | 5.8456 | 26100 | 0.0116 | 0.9416 | | 0.0009 | 5.8680 | 26200 | 0.0082 | 0.9579 | | 0.0025 | 5.8904 | 26300 | 0.0078 | 0.9524 | | 0.0002 | 5.9128 | 26400 | 0.0104 | 0.9484 | | 0.0003 | 5.9352 | 26500 | 0.0090 | 0.9484 | | 0.0001 | 5.9576 | 26600 | 0.0115 | 0.9334 | | 0.0008 | 5.9800 | 26700 | 0.0098 | 0.9307 | | 0.0015 | 6.0022 | 26800 | 0.0083 | 0.9606 | | 0.0001 | 6.0246 | 26900 | 0.0085 | 0.9524 | | 0.0007 | 6.0470 | 27000 | 0.0080 | 0.9457 | | 0.0007 | 6.0694 | 27100 | 0.0081 | 0.9484 | | 0.0001 | 6.0918 | 27200 | 0.0058 | 0.9620 | | 0.0001 | 6.1142 | 27300 | 0.0065 | 0.9565 | | 0.0 | 6.1366 | 27400 | 0.0053 | 0.9715 | | 0.0012 | 6.1590 | 27500 | 0.0078 | 0.9565 | | 0.0017 | 6.1814 | 27600 | 0.0102 | 0.9497 | | 0.0001 | 6.2038 | 27700 | 0.0079 | 0.9660 | | 0.0004 | 6.2262 | 27800 | 0.0091 | 0.9457 | | 0.0001 | 6.2486 | 27900 | 0.0102 | 0.9565 | | 0.0 | 6.2710 | 28000 | 0.0080 | 0.9620 | | 0.0011 | 6.2934 | 28100 | 0.0093 | 0.9497 | | 0.0019 | 6.3158 | 28200 | 0.0097 | 0.9470 | | 0.0032 | 6.3382 | 28300 | 0.0062 | 0.9647 | | 0.0032 | 6.3606 | 28400 | 0.0091 | 0.9524 | | 0.0001 | 6.3830 | 28500 | 0.0074 | 0.9443 | | 0.0051 | 6.4054 | 28600 | 0.0095 | 0.9470 | | 0.0001 | 6.4278 | 28700 | 0.0093 | 0.9565 | | 0.0001 | 6.4502 | 28800 | 0.0089 | 0.9565 | | 0.0004 | 6.4726 | 28900 | 0.0110 | 0.9375 | | 0.001 | 6.4950 | 29000 | 0.0137 | 0.9321 | | 0.0014 | 6.5174 | 29100 | 0.0113 | 0.9375 | | 0.0001 | 6.5398 | 29200 | 0.0113 | 0.9348 | | 0.0001 | 6.5622 | 29300 | 0.0108 | 0.9361 | | 0.0001 | 6.5846 | 29400 | 0.0125 | 0.9375 | | 0.0003 | 6.6070 | 29500 | 0.0084 | 0.9565 | | 0.0009 | 6.6294 | 29600 | 0.0080 | 0.9389 | | 0.0001 | 6.6518 | 29700 | 0.0108 | 0.9416 | | 0.0002 | 6.6742 | 29800 | 0.0109 | 0.9375 | | 0.0001 | 6.6966 | 29900 | 0.0070 | 0.9647 | | 0.0001 | 6.7190 | 30000 | 0.0087 | 0.9674 | | 0.0002 | 6.7414 | 30100 | 0.0086 | 0.9538 | | 0.0003 | 6.7638 | 30200 | 0.0108 | 0.9524 | | 0.0001 | 6.7862 | 30300 | 0.0105 | 0.9443 | | 0.0002 | 6.8086 | 30400 | 0.0122 | 0.9429 | | 0.0007 | 6.8310 | 30500 | 0.0117 | 0.9389 | | 0.0001 | 6.8534 | 30600 | 0.0105 | 0.9429 | | 0.0001 | 6.8758 | 30700 | 0.0100 | 0.9606 | | 0.003 | 6.8982 | 30800 | 0.0084 | 0.9674 | | 0.001 | 6.9206 | 30900 | 0.0074 | 0.9606 | | 0.0 | 6.9430 | 31000 | 0.0099 | 0.9552 | | 0.0002 | 6.9654 | 31100 | 0.0081 | 0.9552 | | 0.0001 | 6.9878 | 31200 | 0.0093 | 0.9647 | | 0.0002 | 7.0101 | 31300 | 0.0092 | 0.9660 | | 0.0021 | 7.0325 | 31400 | 0.0077 | 0.9620 | | 0.0 | 7.0549 | 31500 | 0.0090 | 0.9552 | | 0.0 | 7.0773 | 31600 | 0.0075 | 0.9633 | | 0.0002 | 7.0997 | 31700 | 0.0082 | 0.9606 | | 0.0002 | 7.1221 | 31800 | 0.0077 | 0.9674 | | 0.0002 | 7.1445 | 31900 | 0.0083 | 0.9620 | | 0.0 | 7.1669 | 32000 | 0.0072 | 0.9701 | | 0.0004 | 7.1893 | 32100 | 0.0077 | 0.9470 | | 0.0006 | 7.2117 | 32200 | 0.0097 | 0.9620 | | 0.0001 | 7.2341 | 32300 | 0.0096 | 0.9579 | | 0.0001 | 7.2565 | 32400 | 0.0102 | 0.9579 | | 0.0 | 7.2789 | 32500 | 0.0091 | 0.9592 | | 0.0001 | 7.3013 | 32600 | 0.0073 | 0.9606 | | 0.0013 | 7.3237 | 32700 | 0.0091 | 0.9538 | | 0.0001 | 7.3461 | 32800 | 0.0086 | 0.9470 | | 0.0024 | 7.3685 | 32900 | 0.0059 | 0.9660 | | 0.0 | 7.3909 | 33000 | 0.0115 | 0.9565 | | 0.0 | 7.4133 | 33100 | 0.0063 | 0.9633 | | 0.0 | 7.4357 | 33200 | 0.0059 | 0.9701 | | 0.0006 | 7.4581 | 33300 | 0.0076 | 0.9606 | | 0.0 | 7.4805 | 33400 | 0.0047 | 0.9674 | | 0.0 | 7.5029 | 33500 | 0.0049 | 0.9701 | | 0.0 | 7.5253 | 33600 | 0.0067 | 0.9688 | | 0.0001 | 7.5477 | 33700 | 0.0067 | 0.9688 | | 0.0027 | 7.5701 | 33800 | 0.0074 | 0.9620 | | 0.0 | 7.5925 | 33900 | 0.0064 | 0.9633 | | 0.0001 | 7.6149 | 34000 | 0.0055 | 0.9620 | | 0.0015 | 7.6372 | 34100 | 0.0062 | 0.9755 | | 0.0 | 7.6596 | 34200 | 0.0072 | 0.9660 | | 0.0 | 7.6820 | 34300 | 0.0085 | 0.9633 | | 0.0 | 7.7044 | 34400 | 0.0095 | 0.9524 | | 0.004 | 7.7268 | 34500 | 0.0090 | 0.9484 | | 0.0011 | 7.7492 | 34600 | 0.0101 | 0.9511 | | 0.0 | 7.7716 | 34700 | 0.0115 | 0.9457 | | 0.0 | 7.7940 | 34800 | 0.0115 | 0.9511 | | 0.0 | 7.8164 | 34900 | 0.0101 | 0.9429 | | 0.0 | 7.8388 | 35000 | 0.0079 | 0.9538 | | 0.0 | 7.8612 | 35100 | 0.0071 | 0.9620 | | 0.0 | 7.8836 | 35200 | 0.0072 | 0.9606 | | 0.0001 | 7.9060 | 35300 | 0.0064 | 0.9674 | | 0.0 | 7.9284 | 35400 | 0.0086 | 0.9565 | | 0.0 | 7.9508 | 35500 | 0.0115 | 0.9579 | | 0.0 | 7.9732 | 35600 | 0.0087 | 0.9606 | | 0.0 | 7.9956 | 35700 | 0.0096 | 0.9620 | | 0.0 | 8.0179 | 35800 | 0.0101 | 0.9579 | | 0.0 | 8.0403 | 35900 | 0.0093 | 0.9592 | | 0.0 | 8.0627 | 36000 | 0.0093 | 0.9633 | | 0.0 | 8.0851 | 36100 | 0.0079 | 0.9647 | | 0.0 | 8.1075 | 36200 | 0.0079 | 0.9688 | | 0.0 | 8.1299 | 36300 | 0.0080 | 0.9647 | | 0.0 | 8.1523 | 36400 | 0.0082 | 0.9633 | | 0.0 | 8.1747 | 36500 | 0.0084 | 0.9647 | | 0.0 | 8.1971 | 36600 | 0.0088 | 0.9620 | | 0.0004 | 8.2195 | 36700 | 0.0123 | 0.9524 | | 0.0 | 8.2419 | 36800 | 0.0079 | 0.9647 | | 0.0 | 8.2643 | 36900 | 0.0085 | 0.9606 | | 0.0 | 8.2867 | 37000 | 0.0098 | 0.9633 | | 0.0 | 8.3091 | 37100 | 0.0085 | 0.9579 | | 0.0 | 8.3315 | 37200 | 0.0091 | 0.9429 | | 0.0002 | 8.3539 | 37300 | 0.0084 | 0.9565 | | 0.0 | 8.3763 | 37400 | 0.0082 | 0.9579 | | 0.0 | 8.3987 | 37500 | 0.0100 | 0.9565 | | 0.0 | 8.4211 | 37600 | 0.0087 | 0.9565 | | 0.0 | 8.4435 | 37700 | 0.0075 | 0.9606 | | 0.0 | 8.4659 | 37800 | 0.0076 | 0.9592 | | 0.0 | 8.4883 | 37900 | 0.0078 | 0.9552 | | 0.0 | 8.5107 | 38000 | 0.0068 | 0.9606 | | 0.0 | 8.5331 | 38100 | 0.0067 | 0.9660 | | 0.0 | 8.5555 | 38200 | 0.0066 | 0.9674 | | 0.0 | 8.5779 | 38300 | 0.0070 | 0.9633 | | 0.0 | 8.6003 | 38400 | 0.0069 | 0.9633 | | 0.0 | 8.6227 | 38500 | 0.0070 | 0.9633 | | 0.0 | 8.6451 | 38600 | 0.0073 | 0.9620 | | 0.0 | 8.6675 | 38700 | 0.0073 | 0.9633 | | 0.0 | 8.6899 | 38800 | 0.0085 | 0.9633 | | 0.0 | 8.7123 | 38900 | 0.0085 | 0.9633 | | 0.0 | 8.7347 | 39000 | 0.0087 | 0.9660 | | 0.0 | 8.7571 | 39100 | 0.0081 | 0.9674 | | 0.0 | 8.7795 | 39200 | 0.0077 | 0.9688 | | 0.0 | 8.8019 | 39300 | 0.0071 | 0.9701 | | 0.0002 | 8.8243 | 39400 | 0.0067 | 0.9701 | | 0.0 | 8.8467 | 39500 | 0.0072 | 0.9688 | | 0.0 | 8.8691 | 39600 | 0.0078 | 0.9674 | | 0.0 | 8.8915 | 39700 | 0.0082 | 0.9660 | | 0.0 | 8.9139 | 39800 | 0.0083 | 0.9674 | | 0.0 | 8.9363 | 39900 | 0.0084 | 0.9674 | | 0.0 | 8.9587 | 40000 | 0.0078 | 0.9701 | | 0.0 | 8.9811 | 40100 | 0.0074 | 0.9660 | | 0.0 | 9.0034 | 40200 | 0.0077 | 0.9660 | | 0.0 | 9.0258 | 40300 | 0.0075 | 0.9688 | | 0.0 | 9.0482 | 40400 | 0.0073 | 0.9674 | | 0.0 | 9.0706 | 40500 | 0.0076 | 0.9674 | | 0.0 | 9.0930 | 40600 | 0.0067 | 0.9688 | | 0.0 | 9.1154 | 40700 | 0.0060 | 0.9715 | | 0.0 | 9.1378 | 40800 | 0.0057 | 0.9728 | | 0.0 | 9.1602 | 40900 | 0.0057 | 0.9728 | | 0.0 | 9.1826 | 41000 | 0.0058 | 0.9728 | | 0.0 | 9.2050 | 41100 | 0.0059 | 0.9715 | | 0.0 | 9.2273 | 41200 | 0.0062 | 0.9701 | | 0.0 | 9.2497 | 41300 | 0.0063 | 0.9701 | | 0.0 | 9.2721 | 41400 | 0.0063 | 0.9701 | | 0.0 | 9.2945 | 41500 | 0.0063 | 0.9701 | | 0.0 | 9.3169 | 41600 | 0.0063 | 0.9701 | | 0.0 | 9.3393 | 41700 | 0.0063 | 0.9701 | | 0.0 | 9.3617 | 41800 | 0.0063 | 0.9701 | | 0.0 | 9.3841 | 41900 | 0.0063 | 0.9701 | | 0.0 | 9.4065 | 42000 | 0.0063 | 0.9701 | | 0.0 | 9.4289 | 42100 | 0.0064 | 0.9701 | | 0.0 | 9.4513 | 42200 | 0.0064 | 0.9701 | | 0.0 | 9.4737 | 42300 | 0.0065 | 0.9688 | | 0.0 | 9.4961 | 42400 | 0.0065 | 0.9674 | | 0.0 | 9.5185 | 42500 | 0.0065 | 0.9674 | | 0.0 | 9.5409 | 42600 | 0.0065 | 0.9674 | | 0.0 | 9.5633 | 42700 | 0.0065 | 0.9688 | | 0.0 | 9.5857 | 42800 | 0.0065 | 0.9688 | | 0.0 | 9.6081 | 42900 | 0.0065 | 0.9688 | | 0.0 | 9.6305 | 43000 | 0.0065 | 0.9688 | | 0.0 | 9.6529 | 43100 | 0.0064 | 0.9688 | | 0.0 | 9.6753 | 43200 | 0.0064 | 0.9688 | | 0.0 | 9.6977 | 43300 | 0.0064 | 0.9688 | | 0.0 | 9.7201 | 43400 | 0.0064 | 0.9674 | | 0.0 | 9.7425 | 43500 | 0.0064 | 0.9674 | | 0.0 | 9.7649 | 43600 | 0.0064 | 0.9688 | | 0.0 | 9.7873 | 43700 | 0.0064 | 0.9688 | | 0.0 | 9.8097 | 43800 | 0.0064 | 0.9688 | | 0.0 | 9.8321 | 43900 | 0.0064 | 0.9674 | | 0.0 | 9.8545 | 44000 | 0.0064 | 0.9674 | | 0.0 | 9.8769 | 44100 | 0.0064 | 0.9674 | | 0.0 | 9.8993 | 44200 | 0.0064 | 0.9674 | | 0.0 | 9.9217 | 44300 | 0.0064 | 0.9674 | | 0.0 | 9.9441 | 44400 | 0.0064 | 0.9674 | | 0.0 | 9.9665 | 44500 | 0.0064 | 0.9688 | | 0.0 | 9.9889 | 44600 | 0.0064 | 0.9674 | ### Framework versions - Transformers 4.49.0 - Pytorch 2.5.1+cu124 - Datasets 3.3.2 - Tokenizers 0.21.0