--- license: apache-2.0 base_model: facebook/wav2vec2-large-xlsr-53 tags: - generated_from_trainer datasets: - ascend metrics: - wer model-index: - name: wav2vec2-large-xlsr-53-codemix-gpu0 results: - task: name: Automatic Speech Recognition type: automatic-speech-recognition dataset: name: ascend type: ascend config: main split: test args: main metrics: - name: Wer type: wer value: 0.5028735632183908 --- # wav2vec2-large-xlsr-53-codemix-gpu0 This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the ascend dataset. It achieves the following results on the evaluation set: - Loss: 2.4142 - Wer: 0.5029 - Cer: 0.2095 ## 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: 13 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 26 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 300 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |:-------------:|:------:|:------:|:---------------:|:------:|:------:| | No log | 0.94 | 400 | 17.8810 | 1.0 | 1.0 | | 39.8704 | 1.89 | 800 | 5.6649 | 1.0 | 1.0 | | 5.6783 | 2.83 | 1200 | 5.3852 | 1.0 | 1.0 | | 5.2781 | 3.78 | 1600 | 4.9545 | 1.0 | 1.0 | | 4.8306 | 4.72 | 2000 | 4.6591 | 1.0 | 1.0 | | 4.8306 | 5.67 | 2400 | 4.3414 | 1.0 | 1.0 | | 4.5061 | 6.61 | 2800 | 3.6204 | 0.9716 | 0.8151 | | 3.6227 | 7.56 | 3200 | 2.4748 | 0.8693 | 0.4801 | | 2.3991 | 8.5 | 3600 | 2.1247 | 0.7435 | 0.3907 | | 1.8352 | 9.45 | 4000 | 1.9019 | 0.6853 | 0.3474 | | 1.8352 | 10.39 | 4400 | 1.7681 | 0.6706 | 0.3272 | | 1.5545 | 11.33 | 4800 | 1.7038 | 0.6487 | 0.3095 | | 1.3323 | 12.28 | 5200 | 1.6353 | 0.6272 | 0.2992 | | 1.1949 | 13.22 | 5600 | 1.5671 | 0.6189 | 0.2871 | | 1.0377 | 14.17 | 6000 | 1.6160 | 0.6099 | 0.2853 | | 1.0377 | 15.11 | 6400 | 1.5205 | 0.5887 | 0.2793 | | 0.9246 | 16.06 | 6800 | 1.4538 | 0.5999 | 0.2710 | | 0.8484 | 17.0 | 7200 | 1.4279 | 0.5823 | 0.2646 | | 0.7414 | 17.95 | 7600 | 1.4470 | 0.5754 | 0.2555 | | 0.6947 | 18.89 | 8000 | 1.4676 | 0.5794 | 0.2611 | | 0.6947 | 19.83 | 8400 | 1.4599 | 0.5726 | 0.2599 | | 0.6213 | 20.78 | 8800 | 1.4639 | 0.5718 | 0.2578 | | 0.5613 | 21.72 | 9200 | 1.4544 | 0.5675 | 0.2523 | | 0.5154 | 22.67 | 9600 | 1.4663 | 0.5866 | 0.2504 | | 0.4656 | 23.61 | 10000 | 1.5221 | 0.5575 | 0.2432 | | 0.4656 | 24.56 | 10400 | 1.4894 | 0.5726 | 0.2450 | | 0.4375 | 25.5 | 10800 | 1.4671 | 0.5686 | 0.2449 | | 0.3928 | 26.45 | 11200 | 1.5376 | 0.5621 | 0.2451 | | 0.3654 | 27.39 | 11600 | 1.5160 | 0.5603 | 0.2422 | | 0.3188 | 28.34 | 12000 | 1.6036 | 0.5575 | 0.2425 | | 0.3188 | 29.28 | 12400 | 1.5975 | 0.5575 | 0.2391 | | 0.3054 | 30.22 | 12800 | 1.5988 | 0.5560 | 0.2424 | | 0.2826 | 31.17 | 13200 | 1.6094 | 0.5524 | 0.2402 | | 0.2632 | 32.11 | 13600 | 1.6833 | 0.5596 | 0.2394 | | 0.2356 | 33.06 | 14000 | 1.6503 | 0.5445 | 0.2317 | | 0.2356 | 34.0 | 14400 | 1.6318 | 0.5463 | 0.2314 | | 0.2165 | 34.95 | 14800 | 1.7002 | 0.5535 | 0.2359 | | 0.2085 | 35.89 | 15200 | 1.6683 | 0.5499 | 0.2332 | | 0.1806 | 36.84 | 15600 | 1.7490 | 0.5384 | 0.2298 | | 0.177 | 37.78 | 16000 | 1.7325 | 0.5510 | 0.2368 | | 0.177 | 38.72 | 16400 | 1.7853 | 0.5542 | 0.2415 | | 0.1624 | 39.67 | 16800 | 1.6703 | 0.5431 | 0.2281 | | 0.1624 | 40.61 | 17200 | 1.8425 | 0.5514 | 0.2339 | | 0.1421 | 41.56 | 17600 | 1.7714 | 0.5399 | 0.2319 | | 0.13 | 42.5 | 18000 | 1.7403 | 0.5388 | 0.2295 | | 0.13 | 43.45 | 18400 | 1.7871 | 0.5392 | 0.2318 | | 0.1135 | 44.39 | 18800 | 1.7677 | 0.5316 | 0.2266 | | 0.1077 | 45.34 | 19200 | 1.8119 | 0.5431 | 0.2363 | | 0.1106 | 46.28 | 19600 | 1.8375 | 0.5348 | 0.2264 | | 0.0996 | 47.23 | 20000 | 1.7923 | 0.5330 | 0.2315 | | 0.0996 | 48.17 | 20400 | 1.7852 | 0.5284 | 0.2245 | | 0.0931 | 49.11 | 20800 | 1.8031 | 0.5248 | 0.2223 | | 0.0922 | 50.06 | 21200 | 1.8541 | 0.5417 | 0.2319 | | 0.0967 | 51.0 | 21600 | 1.8455 | 0.5406 | 0.2293 | | 0.0755 | 51.95 | 22000 | 1.8984 | 0.5291 | 0.2240 | | 0.0755 | 52.89 | 22400 | 1.8003 | 0.5352 | 0.2222 | | 0.0811 | 53.84 | 22800 | 1.9022 | 0.5524 | 0.2288 | | 0.0771 | 54.78 | 23200 | 1.9080 | 0.5338 | 0.2229 | | 0.0754 | 55.73 | 23600 | 1.8981 | 0.5460 | 0.2292 | | 0.0708 | 56.67 | 24000 | 1.8118 | 0.5277 | 0.2204 | | 0.0708 | 57.62 | 24400 | 1.8570 | 0.5287 | 0.2241 | | 0.0738 | 58.56 | 24800 | 1.9806 | 0.5399 | 0.2230 | | 0.0646 | 59.5 | 25200 | 1.9899 | 0.5399 | 0.2281 | | 0.055 | 60.45 | 25600 | 2.0234 | 0.5302 | 0.2227 | | 0.0602 | 61.39 | 26000 | 1.8967 | 0.5266 | 0.2223 | | 0.0602 | 62.34 | 26400 | 2.0122 | 0.5323 | 0.2204 | | 0.058 | 63.28 | 26800 | 1.9054 | 0.5320 | 0.2205 | | 0.052 | 64.23 | 27200 | 1.9543 | 0.5305 | 0.2213 | | 0.0489 | 65.17 | 27600 | 1.8892 | 0.5280 | 0.2192 | | 0.0591 | 66.12 | 28000 | 1.9432 | 0.5356 | 0.2238 | | 0.0591 | 67.06 | 28400 | 1.9314 | 0.5309 | 0.2244 | | 0.0559 | 68.0 | 28800 | 2.0145 | 0.5284 | 0.2206 | | 0.0489 | 68.95 | 29200 | 1.9624 | 0.5327 | 0.2228 | | 0.0532 | 69.89 | 29600 | 2.0026 | 0.5251 | 0.2243 | | 0.042 | 70.84 | 30000 | 2.0111 | 0.5305 | 0.2202 | | 0.042 | 71.78 | 30400 | 2.0058 | 0.5320 | 0.2227 | | 0.0464 | 72.73 | 30800 | 1.9390 | 0.5226 | 0.2166 | | 0.0477 | 73.67 | 31200 | 1.9187 | 0.5338 | 0.2199 | | 0.0379 | 74.62 | 31600 | 1.9747 | 0.5323 | 0.2252 | | 0.0376 | 75.56 | 32000 | 2.0026 | 0.5305 | 0.2288 | | 0.0376 | 76.51 | 32400 | 2.0456 | 0.5320 | 0.2244 | | 0.0359 | 77.45 | 32800 | 2.1259 | 0.5255 | 0.2202 | | 0.0389 | 78.39 | 33200 | 2.0762 | 0.5295 | 0.2236 | | 0.0359 | 79.34 | 33600 | 2.0339 | 0.5302 | 0.2308 | | 0.0336 | 80.28 | 34000 | 2.0412 | 0.5338 | 0.2214 | | 0.0336 | 81.23 | 34400 | 2.0328 | 0.5244 | 0.2231 | | 0.04 | 82.17 | 34800 | 2.0155 | 0.5273 | 0.2204 | | 0.0315 | 83.12 | 35200 | 2.1555 | 0.5320 | 0.2234 | | 0.0297 | 84.06 | 35600 | 2.0178 | 0.5237 | 0.2168 | | 0.0333 | 85.01 | 36000 | 2.0469 | 0.5309 | 0.2240 | | 0.0333 | 85.95 | 36400 | 2.0885 | 0.5348 | 0.2208 | | 0.0376 | 86.89 | 36800 | 2.1829 | 0.5277 | 0.2243 | | 0.0341 | 87.84 | 37200 | 2.1781 | 0.5298 | 0.2242 | | 0.0326 | 88.78 | 37600 | 2.0283 | 0.5241 | 0.2174 | | 0.0309 | 89.73 | 38000 | 2.0074 | 0.5140 | 0.2183 | | 0.0309 | 90.67 | 38400 | 2.0938 | 0.5194 | 0.2210 | | 0.0298 | 91.62 | 38800 | 2.0011 | 0.5251 | 0.2201 | | 0.0261 | 92.56 | 39200 | 1.9834 | 0.5262 | 0.2174 | | 0.028 | 93.51 | 39600 | 1.9964 | 0.5201 | 0.2210 | | 0.0249 | 94.45 | 40000 | 2.0909 | 0.5327 | 0.2216 | | 0.0249 | 95.4 | 40400 | 2.1145 | 0.5280 | 0.2196 | | 0.0235 | 96.34 | 40800 | 2.0568 | 0.5216 | 0.2210 | | 0.0207 | 97.28 | 41200 | 2.1006 | 0.5136 | 0.2148 | | 0.0229 | 98.23 | 41600 | 2.1488 | 0.5262 | 0.2226 | | 0.03 | 99.17 | 42000 | 2.2123 | 0.5251 | 0.2181 | | 0.03 | 100.12 | 42400 | 2.1388 | 0.5205 | 0.2210 | | 0.029 | 101.06 | 42800 | 2.1480 | 0.5226 | 0.2141 | | 0.0277 | 102.01 | 43200 | 2.1999 | 0.5136 | 0.2190 | | 0.0207 | 102.95 | 43600 | 2.1723 | 0.5212 | 0.2188 | | 0.0298 | 103.9 | 44000 | 2.1314 | 0.5230 | 0.2176 | | 0.0298 | 104.84 | 44400 | 2.2185 | 0.5212 | 0.2194 | | 0.0196 | 105.79 | 44800 | 2.1399 | 0.5241 | 0.2216 | | 0.0339 | 106.73 | 45200 | 2.1360 | 0.5216 | 0.2194 | | 0.0188 | 107.67 | 45600 | 2.2099 | 0.5284 | 0.2191 | | 0.0219 | 108.62 | 46000 | 2.2325 | 0.5262 | 0.2235 | | 0.0219 | 109.56 | 46400 | 2.2137 | 0.5205 | 0.2202 | | 0.0197 | 110.51 | 46800 | 2.2480 | 0.5208 | 0.2216 | | 0.0185 | 111.45 | 47200 | 2.1687 | 0.5208 | 0.2210 | | 0.0252 | 112.4 | 47600 | 2.1374 | 0.5241 | 0.2204 | | 0.018 | 113.34 | 48000 | 2.1948 | 0.5133 | 0.2238 | | 0.018 | 114.29 | 48400 | 2.1851 | 0.5172 | 0.2181 | | 0.0472 | 115.23 | 48800 | 2.2225 | 0.5312 | 0.2274 | | 0.0166 | 116.17 | 49200 | 2.2063 | 0.5136 | 0.2162 | | 0.0163 | 117.12 | 49600 | 2.2021 | 0.5183 | 0.2166 | | 0.0174 | 118.06 | 50000 | 2.1958 | 0.5144 | 0.2171 | | 0.0174 | 119.01 | 50400 | 2.2010 | 0.5226 | 0.2168 | | 0.022 | 119.95 | 50800 | 2.1710 | 0.5287 | 0.2172 | | 0.0161 | 120.9 | 51200 | 2.1413 | 0.5230 | 0.2176 | | 0.0205 | 121.84 | 51600 | 2.1558 | 0.5180 | 0.2158 | | 0.0176 | 122.79 | 52000 | 2.1222 | 0.5226 | 0.2185 | | 0.0176 | 123.73 | 52400 | 2.0850 | 0.5223 | 0.2194 | | 0.0179 | 124.68 | 52800 | 2.0551 | 0.5212 | 0.2190 | | 0.0168 | 125.62 | 53200 | 2.2350 | 0.5205 | 0.2185 | | 0.0181 | 126.56 | 53600 | 2.1468 | 0.5183 | 0.2182 | | 0.0185 | 127.51 | 54000 | 2.1373 | 0.5201 | 0.2205 | | 0.0185 | 128.45 | 54400 | 2.1399 | 0.5208 | 0.2173 | | 0.017 | 129.4 | 54800 | 2.2898 | 0.5280 | 0.2190 | | 0.0172 | 130.34 | 55200 | 2.2841 | 0.5183 | 0.2188 | | 0.0171 | 131.29 | 55600 | 2.1375 | 0.5129 | 0.2203 | | 0.0148 | 132.23 | 56000 | 2.2004 | 0.5136 | 0.2151 | | 0.0148 | 133.18 | 56400 | 2.2068 | 0.5165 | 0.2160 | | 0.0172 | 134.12 | 56800 | 2.2018 | 0.5126 | 0.2141 | | 0.0143 | 135.06 | 57200 | 2.2044 | 0.5233 | 0.2153 | | 0.0179 | 136.01 | 57600 | 2.3219 | 0.5259 | 0.2186 | | 0.0167 | 136.95 | 58000 | 2.2770 | 0.5266 | 0.2191 | | 0.0167 | 137.9 | 58400 | 2.2735 | 0.5144 | 0.2182 | | 0.018 | 138.84 | 58800 | 2.3331 | 0.5341 | 0.2236 | | 0.0141 | 139.79 | 59200 | 2.3517 | 0.5316 | 0.2222 | | 0.0124 | 140.73 | 59600 | 2.3140 | 0.5330 | 0.2223 | | 0.0184 | 141.68 | 60000 | 2.3398 | 0.5244 | 0.2192 | | 0.0184 | 142.62 | 60400 | 2.2294 | 0.5273 | 0.2191 | | 0.0138 | 143.57 | 60800 | 2.2740 | 0.5244 | 0.2213 | | 0.0141 | 144.51 | 61200 | 2.3127 | 0.5291 | 0.2192 | | 0.0127 | 145.45 | 61600 | 2.2401 | 0.5176 | 0.2163 | | 0.0156 | 146.4 | 62000 | 2.2034 | 0.5126 | 0.2146 | | 0.0156 | 147.34 | 62400 | 2.2117 | 0.5162 | 0.2160 | | 0.0146 | 148.29 | 62800 | 2.2384 | 0.5208 | 0.2161 | | 0.0107 | 149.23 | 63200 | 2.2461 | 0.5187 | 0.2170 | | 0.0128 | 150.18 | 63600 | 2.2797 | 0.5226 | 0.2145 | | 0.011 | 151.12 | 64000 | 2.2011 | 0.5154 | 0.2170 | | 0.011 | 152.07 | 64400 | 2.2867 | 0.5230 | 0.2189 | | 0.014 | 153.01 | 64800 | 2.2458 | 0.5158 | 0.2138 | | 0.0143 | 153.96 | 65200 | 2.3514 | 0.5298 | 0.2176 | | 0.0108 | 154.9 | 65600 | 2.2746 | 0.5183 | 0.2158 | | 0.0149 | 155.84 | 66000 | 2.2356 | 0.5223 | 0.2159 | | 0.0149 | 156.79 | 66400 | 2.3048 | 0.5165 | 0.2194 | | 0.014 | 157.73 | 66800 | 2.2453 | 0.5183 | 0.2146 | | 0.015 | 158.68 | 67200 | 2.3483 | 0.5248 | 0.2181 | | 0.0111 | 159.62 | 67600 | 2.2445 | 0.5205 | 0.2151 | | 0.0112 | 160.57 | 68000 | 2.3657 | 0.5201 | 0.2180 | | 0.0112 | 161.51 | 68400 | 2.3159 | 0.5223 | 0.2193 | | 0.0114 | 162.46 | 68800 | 2.3097 | 0.5119 | 0.2170 | | 0.0236 | 163.4 | 69200 | 2.3455 | 0.5198 | 0.2143 | | 0.0094 | 164.34 | 69600 | 2.3474 | 0.5190 | 0.2186 | | 0.0146 | 165.29 | 70000 | 2.3095 | 0.5165 | 0.2145 | | 0.0146 | 166.23 | 70400 | 2.3445 | 0.5140 | 0.2130 | | 0.0085 | 167.18 | 70800 | 2.3123 | 0.5180 | 0.2158 | | 0.009 | 168.12 | 71200 | 2.3232 | 0.5212 | 0.2217 | | 0.0094 | 169.07 | 71600 | 2.3938 | 0.5165 | 0.2155 | | 0.0119 | 170.01 | 72000 | 2.3336 | 0.5248 | 0.2160 | | 0.0119 | 170.96 | 72400 | 2.2819 | 0.5172 | 0.2157 | | 0.0087 | 171.9 | 72800 | 2.3174 | 0.5133 | 0.2156 | | 0.0116 | 172.85 | 73200 | 2.3225 | 0.5093 | 0.2149 | | 0.0081 | 173.79 | 73600 | 2.2715 | 0.5079 | 0.2148 | | 0.0083 | 174.73 | 74000 | 2.2454 | 0.5129 | 0.2129 | | 0.0083 | 175.68 | 74400 | 2.2992 | 0.5190 | 0.2177 | | 0.0137 | 176.62 | 74800 | 2.2487 | 0.5104 | 0.2156 | | 0.0149 | 177.57 | 75200 | 2.2963 | 0.5190 | 0.2153 | | 0.0082 | 178.51 | 75600 | 2.3329 | 0.5169 | 0.2148 | | 0.0082 | 179.46 | 76000 | 2.3725 | 0.5194 | 0.2155 | | 0.0082 | 180.4 | 76400 | 2.3200 | 0.5190 | 0.2197 | | 0.008 | 181.35 | 76800 | 2.3551 | 0.5226 | 0.2173 | | 0.0091 | 182.29 | 77200 | 2.3861 | 0.5201 | 0.2123 | | 0.0094 | 183.23 | 77600 | 2.3033 | 0.5129 | 0.2108 | | 0.0081 | 184.18 | 78000 | 2.3498 | 0.5115 | 0.2148 | | 0.0081 | 185.12 | 78400 | 2.4158 | 0.5162 | 0.2200 | | 0.0097 | 186.07 | 78800 | 2.3857 | 0.5194 | 0.2163 | | 0.008 | 187.01 | 79200 | 2.3744 | 0.5140 | 0.2107 | | 0.0082 | 187.96 | 79600 | 2.3297 | 0.5144 | 0.2125 | | 0.0114 | 188.9 | 80000 | 2.2988 | 0.5183 | 0.2097 | | 0.0114 | 189.85 | 80400 | 2.3056 | 0.5187 | 0.2134 | | 0.0128 | 190.79 | 80800 | 2.3505 | 0.5158 | 0.2128 | | 0.0077 | 191.74 | 81200 | 2.3267 | 0.5187 | 0.2126 | | 0.0071 | 192.68 | 81600 | 2.3242 | 0.5216 | 0.2158 | | 0.0085 | 193.62 | 82000 | 2.3454 | 0.5162 | 0.2130 | | 0.0085 | 194.57 | 82400 | 2.2598 | 0.5151 | 0.2107 | | 0.008 | 195.51 | 82800 | 2.3276 | 0.5158 | 0.2132 | | 0.0084 | 196.46 | 83200 | 2.2328 | 0.5172 | 0.2135 | | 0.0101 | 197.4 | 83600 | 2.2749 | 0.5165 | 0.2113 | | 0.006 | 198.35 | 84000 | 2.3034 | 0.5147 | 0.2142 | | 0.006 | 199.29 | 84400 | 2.3225 | 0.5104 | 0.2124 | | 0.0064 | 200.24 | 84800 | 2.3010 | 0.5180 | 0.2139 | | 0.0073 | 201.18 | 85200 | 2.3142 | 0.5126 | 0.2110 | | 0.0071 | 202.13 | 85600 | 2.2778 | 0.5097 | 0.2111 | | 0.0056 | 203.07 | 86000 | 2.3066 | 0.5083 | 0.2144 | | 0.0056 | 204.01 | 86400 | 2.3355 | 0.5129 | 0.2127 | | 0.0054 | 204.96 | 86800 | 2.3253 | 0.5151 | 0.2142 | | 0.0074 | 205.9 | 87200 | 2.3698 | 0.5133 | 0.2130 | | 0.0055 | 206.85 | 87600 | 2.3500 | 0.5090 | 0.2140 | | 0.0066 | 207.79 | 88000 | 2.3585 | 0.5043 | 0.2104 | | 0.0066 | 208.74 | 88400 | 2.3482 | 0.5119 | 0.2142 | | 0.0043 | 209.68 | 88800 | 2.3157 | 0.5086 | 0.2139 | | 0.0072 | 210.63 | 89200 | 2.3450 | 0.5140 | 0.2131 | | 0.0065 | 211.57 | 89600 | 2.3420 | 0.5093 | 0.2130 | | 0.0057 | 212.51 | 90000 | 2.3196 | 0.5025 | 0.2091 | | 0.0057 | 213.46 | 90400 | 2.2695 | 0.5040 | 0.2070 | | 0.0058 | 214.4 | 90800 | 2.3159 | 0.5014 | 0.2073 | | 0.0059 | 215.35 | 91200 | 2.3003 | 0.5165 | 0.2101 | | 0.0072 | 216.29 | 91600 | 2.3027 | 0.5057 | 0.2085 | | 0.008 | 217.24 | 92000 | 2.3013 | 0.4996 | 0.2086 | | 0.008 | 218.18 | 92400 | 2.2358 | 0.5043 | 0.2101 | | 0.0068 | 219.13 | 92800 | 2.2319 | 0.5086 | 0.2093 | | 0.0081 | 220.07 | 93200 | 2.2096 | 0.5025 | 0.2093 | | 0.007 | 221.02 | 93600 | 2.2037 | 0.5022 | 0.2080 | | 0.0075 | 221.96 | 94000 | 2.2277 | 0.5083 | 0.2112 | | 0.0075 | 222.9 | 94400 | 2.2409 | 0.5068 | 0.2089 | | 0.005 | 223.85 | 94800 | 2.2466 | 0.5101 | 0.2109 | | 0.0045 | 224.79 | 95200 | 2.2922 | 0.5018 | 0.2082 | | 0.0045 | 225.74 | 95600 | 2.3045 | 0.5040 | 0.2143 | | 0.0043 | 226.68 | 96000 | 2.3546 | 0.5065 | 0.2128 | | 0.0043 | 227.63 | 96400 | 2.2876 | 0.5036 | 0.2113 | | 0.0076 | 228.57 | 96800 | 2.3149 | 0.5083 | 0.2127 | | 0.0052 | 229.52 | 97200 | 2.3272 | 0.5075 | 0.2089 | | 0.0069 | 230.46 | 97600 | 2.2869 | 0.5119 | 0.2097 | | 0.0067 | 231.4 | 98000 | 2.3168 | 0.5108 | 0.2125 | | 0.0067 | 232.35 | 98400 | 2.3802 | 0.5115 | 0.2143 | | 0.0049 | 233.29 | 98800 | 2.3419 | 0.5075 | 0.2151 | | 0.0061 | 234.24 | 99200 | 2.3651 | 0.5079 | 0.2132 | | 0.0045 | 235.18 | 99600 | 2.3841 | 0.5054 | 0.2135 | | 0.0043 | 236.13 | 100000 | 2.4073 | 0.5061 | 0.2131 | | 0.0043 | 237.07 | 100400 | 2.3851 | 0.5079 | 0.2141 | | 0.0041 | 238.02 | 100800 | 2.3834 | 0.5036 | 0.2112 | | 0.0055 | 238.96 | 101200 | 2.3981 | 0.5057 | 0.2114 | | 0.0042 | 239.91 | 101600 | 2.4412 | 0.5050 | 0.2121 | | 0.006 | 240.85 | 102000 | 2.4280 | 0.5036 | 0.2126 | | 0.006 | 241.79 | 102400 | 2.4465 | 0.5047 | 0.2116 | | 0.0041 | 242.74 | 102800 | 2.4130 | 0.5040 | 0.2126 | | 0.0117 | 243.68 | 103200 | 2.4477 | 0.5054 | 0.2123 | | 0.0047 | 244.63 | 103600 | 2.5122 | 0.5079 | 0.2138 | | 0.0031 | 245.57 | 104000 | 2.4971 | 0.5101 | 0.2117 | | 0.0031 | 246.52 | 104400 | 2.4521 | 0.5101 | 0.2136 | | 0.0052 | 247.46 | 104800 | 2.4590 | 0.5007 | 0.2103 | | 0.0041 | 248.41 | 105200 | 2.4725 | 0.5108 | 0.2115 | | 0.0053 | 249.35 | 105600 | 2.4557 | 0.5093 | 0.2113 | | 0.0041 | 250.3 | 106000 | 2.4377 | 0.5093 | 0.2130 | | 0.0041 | 251.24 | 106400 | 2.4383 | 0.5108 | 0.2122 | | 0.0069 | 252.18 | 106800 | 2.4570 | 0.5050 | 0.2121 | | 0.0028 | 253.13 | 107200 | 2.4544 | 0.5057 | 0.2135 | | 0.0039 | 254.07 | 107600 | 2.4487 | 0.5140 | 0.2145 | | 0.0032 | 255.02 | 108000 | 2.4256 | 0.5079 | 0.2139 | | 0.0032 | 255.96 | 108400 | 2.4174 | 0.5043 | 0.2128 | | 0.0048 | 256.91 | 108800 | 2.4341 | 0.5050 | 0.2131 | | 0.0035 | 257.85 | 109200 | 2.4111 | 0.5090 | 0.2122 | | 0.0042 | 258.8 | 109600 | 2.4191 | 0.5108 | 0.2116 | | 0.0039 | 259.74 | 110000 | 2.4173 | 0.5043 | 0.2107 | | 0.0039 | 260.68 | 110400 | 2.4195 | 0.5054 | 0.2100 | | 0.0029 | 261.63 | 110800 | 2.4397 | 0.5054 | 0.2110 | | 0.0036 | 262.57 | 111200 | 2.4165 | 0.5050 | 0.2126 | | 0.003 | 263.52 | 111600 | 2.4057 | 0.5061 | 0.2095 | | 0.0038 | 264.46 | 112000 | 2.3734 | 0.5029 | 0.2108 | | 0.0038 | 265.41 | 112400 | 2.3847 | 0.5029 | 0.2100 | | 0.0034 | 266.35 | 112800 | 2.3959 | 0.5007 | 0.2090 | | 0.0057 | 267.3 | 113200 | 2.4000 | 0.5014 | 0.2097 | | 0.0064 | 268.24 | 113600 | 2.4070 | 0.5032 | 0.2099 | | 0.0048 | 269.19 | 114000 | 2.3990 | 0.5029 | 0.2093 | | 0.0048 | 270.13 | 114400 | 2.4165 | 0.5022 | 0.2097 | | 0.0041 | 271.07 | 114800 | 2.4088 | 0.5050 | 0.2092 | | 0.0031 | 272.02 | 115200 | 2.3946 | 0.5043 | 0.2098 | | 0.0039 | 272.96 | 115600 | 2.3970 | 0.5022 | 0.2103 | | 0.0044 | 273.91 | 116000 | 2.4102 | 0.5022 | 0.2093 | | 0.0044 | 274.85 | 116400 | 2.4244 | 0.5040 | 0.2099 | | 0.0037 | 275.8 | 116800 | 2.4146 | 0.5014 | 0.2089 | | 0.0054 | 276.74 | 117200 | 2.3832 | 0.5029 | 0.2102 | | 0.0049 | 277.69 | 117600 | 2.4004 | 0.5057 | 0.2097 | | 0.003 | 278.63 | 118000 | 2.4024 | 0.5050 | 0.2102 | | 0.003 | 279.57 | 118400 | 2.4038 | 0.5065 | 0.2109 | | 0.0051 | 280.52 | 118800 | 2.4086 | 0.5040 | 0.2101 | | 0.0028 | 281.46 | 119200 | 2.4124 | 0.5036 | 0.2095 | | 0.0038 | 282.41 | 119600 | 2.3978 | 0.5054 | 0.2106 | | 0.003 | 283.35 | 120000 | 2.3903 | 0.5054 | 0.2099 | | 0.003 | 284.3 | 120400 | 2.3989 | 0.5032 | 0.2087 | | 0.0038 | 285.24 | 120800 | 2.4043 | 0.5029 | 0.2084 | | 0.0024 | 286.19 | 121200 | 2.4167 | 0.5047 | 0.2092 | | 0.0023 | 287.13 | 121600 | 2.4140 | 0.5022 | 0.2100 | | 0.0031 | 288.08 | 122000 | 2.4046 | 0.5036 | 0.2110 | | 0.0031 | 289.02 | 122400 | 2.3840 | 0.5047 | 0.2100 | | 0.0038 | 289.96 | 122800 | 2.3865 | 0.5057 | 0.2090 | | 0.0036 | 290.91 | 123200 | 2.3852 | 0.5068 | 0.2092 | | 0.0026 | 291.85 | 123600 | 2.3938 | 0.5040 | 0.2096 | | 0.002 | 292.8 | 124000 | 2.3988 | 0.5029 | 0.2091 | | 0.002 | 293.74 | 124400 | 2.3968 | 0.5032 | 0.2091 | | 0.0049 | 294.69 | 124800 | 2.4075 | 0.5025 | 0.2093 | | 0.0028 | 295.63 | 125200 | 2.4129 | 0.5036 | 0.2097 | | 0.002 | 296.58 | 125600 | 2.4119 | 0.5014 | 0.2092 | | 0.0042 | 297.52 | 126000 | 2.4118 | 0.5025 | 0.2097 | | 0.0042 | 298.47 | 126400 | 2.4128 | 0.5022 | 0.2093 | | 0.003 | 299.41 | 126800 | 2.4142 | 0.5029 | 0.2095 | ### Framework versions - Transformers 4.31.0 - Pytorch 1.13.1+cu117 - Datasets 2.13.1 - Tokenizers 0.13.3