|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-xls-r-300m |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- ascend |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: wav2vec2-large-xls-r-300m-codemix-gpu1 |
|
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: 0.5050287356321839 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# wav2vec2-large-xls-r-300m-codemix-gpu1 |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the ascend dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.2061 |
|
- Wer: 0.5050 |
|
- Cer: 0.1982 |
|
|
|
## 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 | 21.9000 | 1.0 | 1.0 | |
|
| 38.4951 | 1.89 | 800 | 5.6544 | 1.0 | 1.0 | |
|
| 5.8527 | 2.83 | 1200 | 5.4920 | 1.0 | 1.0 | |
|
| 5.4391 | 3.78 | 1600 | 5.3156 | 1.0 | 1.0 | |
|
| 5.1782 | 4.72 | 2000 | 5.0525 | 1.0 | 1.0 | |
|
| 5.1782 | 5.67 | 2400 | 4.9258 | 1.0 | 1.0 | |
|
| 4.9333 | 6.61 | 2800 | 4.7009 | 1.0 | 1.0 | |
|
| 4.7205 | 7.56 | 3200 | 4.4642 | 1.0 | 1.0 | |
|
| 4.4312 | 8.5 | 3600 | 3.9080 | 0.9634 | 0.9246 | |
|
| 3.5483 | 9.45 | 4000 | 2.9466 | 0.9271 | 0.7290 | |
|
| 3.5483 | 10.39 | 4400 | 2.3584 | 0.9159 | 0.5206 | |
|
| 2.5687 | 11.33 | 4800 | 2.0802 | 0.8114 | 0.3977 | |
|
| 1.9323 | 12.28 | 5200 | 1.8289 | 0.7421 | 0.3429 | |
|
| 1.5981 | 13.22 | 5600 | 1.7033 | 0.6835 | 0.3166 | |
|
| 1.3129 | 14.17 | 6000 | 1.5895 | 0.6491 | 0.3017 | |
|
| 1.3129 | 15.11 | 6400 | 1.5779 | 0.6433 | 0.3033 | |
|
| 1.1235 | 16.06 | 6800 | 1.4794 | 0.6131 | 0.2863 | |
|
| 0.9964 | 17.0 | 7200 | 1.4897 | 0.6182 | 0.2960 | |
|
| 0.8708 | 17.95 | 7600 | 1.4468 | 0.6114 | 0.2659 | |
|
| 0.7861 | 18.89 | 8000 | 1.4461 | 0.5995 | 0.2614 | |
|
| 0.7861 | 19.83 | 8400 | 1.4869 | 0.5952 | 0.2678 | |
|
| 0.6926 | 20.78 | 8800 | 1.4592 | 0.5833 | 0.2549 | |
|
| 0.6153 | 21.72 | 9200 | 1.4053 | 0.5855 | 0.2530 | |
|
| 0.5642 | 22.67 | 9600 | 1.3772 | 0.5787 | 0.2409 | |
|
| 0.5081 | 23.61 | 10000 | 1.4347 | 0.5833 | 0.2423 | |
|
| 0.5081 | 24.56 | 10400 | 1.3555 | 0.5690 | 0.2427 | |
|
| 0.4667 | 25.5 | 10800 | 1.3732 | 0.5657 | 0.2381 | |
|
| 0.4062 | 26.45 | 11200 | 1.4353 | 0.5726 | 0.2373 | |
|
| 0.3684 | 27.39 | 11600 | 1.3958 | 0.5661 | 0.2351 | |
|
| 0.326 | 28.34 | 12000 | 1.5068 | 0.5797 | 0.2361 | |
|
| 0.326 | 29.28 | 12400 | 1.4500 | 0.5546 | 0.2291 | |
|
| 0.305 | 30.22 | 12800 | 1.4933 | 0.5560 | 0.2329 | |
|
| 0.2743 | 31.17 | 13200 | 1.4684 | 0.5463 | 0.2295 | |
|
| 0.2529 | 32.11 | 13600 | 1.4816 | 0.5629 | 0.2310 | |
|
| 0.2231 | 33.06 | 14000 | 1.4672 | 0.5370 | 0.2251 | |
|
| 0.2231 | 34.0 | 14400 | 1.5095 | 0.5514 | 0.2274 | |
|
| 0.1979 | 34.95 | 14800 | 1.5443 | 0.5514 | 0.2288 | |
|
| 0.184 | 35.89 | 15200 | 1.5431 | 0.5442 | 0.2241 | |
|
| 0.1663 | 36.84 | 15600 | 1.5377 | 0.5471 | 0.2221 | |
|
| 0.1597 | 37.78 | 16000 | 1.5782 | 0.5496 | 0.2261 | |
|
| 0.1597 | 38.72 | 16400 | 1.6236 | 0.5578 | 0.2246 | |
|
| 0.1371 | 39.67 | 16800 | 1.6783 | 0.5550 | 0.2256 | |
|
| 0.1348 | 40.61 | 17200 | 1.7202 | 0.5589 | 0.2276 | |
|
| 0.1215 | 41.56 | 17600 | 1.6399 | 0.5485 | 0.2237 | |
|
| 0.1138 | 42.5 | 18000 | 1.6724 | 0.5445 | 0.2210 | |
|
| 0.1138 | 43.45 | 18400 | 1.7090 | 0.5374 | 0.2217 | |
|
| 0.0992 | 44.39 | 18800 | 1.6476 | 0.5503 | 0.2264 | |
|
| 0.1001 | 45.34 | 19200 | 1.6959 | 0.5524 | 0.2251 | |
|
| 0.0925 | 46.28 | 19600 | 1.8083 | 0.5639 | 0.2270 | |
|
| 0.0848 | 47.23 | 20000 | 1.7361 | 0.5506 | 0.2229 | |
|
| 0.0848 | 48.17 | 20400 | 1.7499 | 0.5471 | 0.2231 | |
|
| 0.0852 | 49.11 | 20800 | 1.7702 | 0.5510 | 0.2254 | |
|
| 0.0792 | 50.06 | 21200 | 1.7595 | 0.5467 | 0.2230 | |
|
| 0.0717 | 51.0 | 21600 | 1.7661 | 0.5535 | 0.2196 | |
|
| 0.0669 | 51.95 | 22000 | 1.6757 | 0.5603 | 0.2307 | |
|
| 0.0669 | 52.89 | 22400 | 1.7932 | 0.5596 | 0.2222 | |
|
| 0.0689 | 53.84 | 22800 | 1.7859 | 0.5535 | 0.2192 | |
|
| 0.066 | 54.78 | 23200 | 1.7322 | 0.5463 | 0.2195 | |
|
| 0.0721 | 55.73 | 23600 | 1.7828 | 0.5517 | 0.2235 | |
|
| 0.057 | 56.67 | 24000 | 1.8470 | 0.5420 | 0.2170 | |
|
| 0.057 | 57.62 | 24400 | 1.8273 | 0.5471 | 0.2219 | |
|
| 0.0615 | 58.56 | 24800 | 1.8081 | 0.5453 | 0.2226 | |
|
| 0.0584 | 59.5 | 25200 | 1.8340 | 0.5388 | 0.2145 | |
|
| 0.048 | 60.45 | 25600 | 1.8584 | 0.5424 | 0.2202 | |
|
| 0.0545 | 61.39 | 26000 | 1.8483 | 0.5420 | 0.2176 | |
|
| 0.0545 | 62.34 | 26400 | 1.8932 | 0.5585 | 0.2259 | |
|
| 0.0525 | 63.28 | 26800 | 1.8906 | 0.5427 | 0.2215 | |
|
| 0.0458 | 64.23 | 27200 | 1.7618 | 0.5431 | 0.2160 | |
|
| 0.0421 | 65.17 | 27600 | 2.0073 | 0.5377 | 0.2168 | |
|
| 0.0435 | 66.12 | 28000 | 1.8957 | 0.5463 | 0.2190 | |
|
| 0.0435 | 67.06 | 28400 | 1.8931 | 0.5352 | 0.2176 | |
|
| 0.0449 | 68.0 | 28800 | 1.9795 | 0.5435 | 0.2225 | |
|
| 0.0458 | 68.95 | 29200 | 1.9299 | 0.5560 | 0.2190 | |
|
| 0.0458 | 69.89 | 29600 | 1.9310 | 0.5427 | 0.2154 | |
|
| 0.037 | 70.84 | 30000 | 1.9183 | 0.5427 | 0.2211 | |
|
| 0.037 | 71.78 | 30400 | 1.8506 | 0.5374 | 0.2153 | |
|
| 0.0417 | 72.73 | 30800 | 1.8749 | 0.5546 | 0.2239 | |
|
| 0.0441 | 73.67 | 31200 | 1.9007 | 0.5492 | 0.2194 | |
|
| 0.0331 | 74.62 | 31600 | 2.0232 | 0.5603 | 0.2237 | |
|
| 0.0315 | 75.56 | 32000 | 1.9655 | 0.5445 | 0.2201 | |
|
| 0.0315 | 76.51 | 32400 | 1.9662 | 0.5384 | 0.2129 | |
|
| 0.0322 | 77.45 | 32800 | 1.9437 | 0.5402 | 0.2166 | |
|
| 0.0352 | 78.39 | 33200 | 1.9171 | 0.5370 | 0.2164 | |
|
| 0.0329 | 79.34 | 33600 | 1.9477 | 0.5320 | 0.2190 | |
|
| 0.0345 | 80.28 | 34000 | 1.9378 | 0.5359 | 0.2188 | |
|
| 0.0345 | 81.23 | 34400 | 1.9537 | 0.5449 | 0.2209 | |
|
| 0.0368 | 82.17 | 34800 | 1.8541 | 0.5463 | 0.2195 | |
|
| 0.0314 | 83.12 | 35200 | 1.9304 | 0.5521 | 0.2148 | |
|
| 0.0247 | 84.06 | 35600 | 1.9365 | 0.5374 | 0.2190 | |
|
| 0.0314 | 85.01 | 36000 | 1.9683 | 0.5395 | 0.2183 | |
|
| 0.0314 | 85.95 | 36400 | 2.0073 | 0.5338 | 0.2202 | |
|
| 0.0324 | 86.89 | 36800 | 1.9907 | 0.5291 | 0.2161 | |
|
| 0.0265 | 87.84 | 37200 | 1.9969 | 0.5359 | 0.2172 | |
|
| 0.0303 | 88.78 | 37600 | 2.0443 | 0.5496 | 0.2209 | |
|
| 0.026 | 89.73 | 38000 | 2.0565 | 0.5413 | 0.2175 | |
|
| 0.026 | 90.67 | 38400 | 2.0716 | 0.5341 | 0.2173 | |
|
| 0.0269 | 91.62 | 38800 | 2.0431 | 0.5312 | 0.2211 | |
|
| 0.0241 | 92.56 | 39200 | 1.9598 | 0.5359 | 0.2176 | |
|
| 0.0256 | 93.51 | 39600 | 2.0544 | 0.5381 | 0.2187 | |
|
| 0.025 | 94.45 | 40000 | 2.1567 | 0.5424 | 0.2176 | |
|
| 0.025 | 95.4 | 40400 | 1.9953 | 0.5348 | 0.2218 | |
|
| 0.0232 | 96.34 | 40800 | 2.0090 | 0.5298 | 0.2170 | |
|
| 0.0186 | 97.28 | 41200 | 2.1091 | 0.5384 | 0.2172 | |
|
| 0.0226 | 98.23 | 41600 | 2.0469 | 0.5406 | 0.2232 | |
|
| 0.0231 | 99.17 | 42000 | 1.9422 | 0.5266 | 0.2148 | |
|
| 0.0231 | 100.12 | 42400 | 1.9989 | 0.5208 | 0.2125 | |
|
| 0.0229 | 101.06 | 42800 | 2.0184 | 0.5269 | 0.2137 | |
|
| 0.0223 | 102.01 | 43200 | 2.0628 | 0.5499 | 0.2202 | |
|
| 0.0217 | 102.95 | 43600 | 2.1697 | 0.5456 | 0.2231 | |
|
| 0.0246 | 103.9 | 44000 | 2.0539 | 0.5341 | 0.2194 | |
|
| 0.0246 | 104.84 | 44400 | 2.0108 | 0.5420 | 0.2205 | |
|
| 0.0188 | 105.79 | 44800 | 2.0435 | 0.5442 | 0.2179 | |
|
| 0.0232 | 106.73 | 45200 | 1.9907 | 0.5338 | 0.2209 | |
|
| 0.0181 | 107.67 | 45600 | 2.0283 | 0.5463 | 0.2182 | |
|
| 0.0196 | 108.62 | 46000 | 2.0573 | 0.5377 | 0.2168 | |
|
| 0.0196 | 109.56 | 46400 | 2.0870 | 0.5363 | 0.2213 | |
|
| 0.014 | 110.51 | 46800 | 2.0414 | 0.5370 | 0.2169 | |
|
| 0.019 | 111.45 | 47200 | 2.0856 | 0.5392 | 0.2202 | |
|
| 0.0222 | 112.4 | 47600 | 2.0484 | 0.5298 | 0.2119 | |
|
| 0.0196 | 113.34 | 48000 | 2.0621 | 0.5298 | 0.2139 | |
|
| 0.0196 | 114.29 | 48400 | 2.0678 | 0.5334 | 0.2148 | |
|
| 0.019 | 115.23 | 48800 | 2.0594 | 0.5381 | 0.2171 | |
|
| 0.0222 | 116.17 | 49200 | 2.0287 | 0.5323 | 0.2098 | |
|
| 0.0157 | 117.12 | 49600 | 2.0198 | 0.5312 | 0.2159 | |
|
| 0.0138 | 118.06 | 50000 | 2.0889 | 0.5273 | 0.2147 | |
|
| 0.0138 | 119.01 | 50400 | 2.0316 | 0.5287 | 0.2133 | |
|
| 0.0149 | 119.95 | 50800 | 2.0093 | 0.5345 | 0.2186 | |
|
| 0.0144 | 120.9 | 51200 | 2.0363 | 0.5352 | 0.2201 | |
|
| 0.0214 | 121.84 | 51600 | 1.9881 | 0.5352 | 0.2149 | |
|
| 0.0203 | 122.79 | 52000 | 2.0539 | 0.5334 | 0.2172 | |
|
| 0.0203 | 123.73 | 52400 | 2.0060 | 0.5277 | 0.2142 | |
|
| 0.0155 | 124.68 | 52800 | 2.0310 | 0.5273 | 0.2163 | |
|
| 0.0152 | 125.62 | 53200 | 2.1064 | 0.5377 | 0.2204 | |
|
| 0.0153 | 126.56 | 53600 | 1.9753 | 0.5320 | 0.2107 | |
|
| 0.0169 | 127.51 | 54000 | 2.0713 | 0.5198 | 0.2129 | |
|
| 0.0169 | 128.45 | 54400 | 2.0593 | 0.5233 | 0.2127 | |
|
| 0.0145 | 129.4 | 54800 | 1.9994 | 0.5190 | 0.2093 | |
|
| 0.016 | 130.34 | 55200 | 2.0760 | 0.5312 | 0.2158 | |
|
| 0.0145 | 131.29 | 55600 | 2.0213 | 0.5305 | 0.2157 | |
|
| 0.0157 | 132.23 | 56000 | 2.0769 | 0.5241 | 0.2108 | |
|
| 0.0157 | 133.18 | 56400 | 2.0819 | 0.5266 | 0.2132 | |
|
| 0.0147 | 134.12 | 56800 | 2.0268 | 0.5248 | 0.2124 | |
|
| 0.015 | 135.06 | 57200 | 2.0261 | 0.5158 | 0.2098 | |
|
| 0.016 | 136.01 | 57600 | 1.9948 | 0.5126 | 0.2096 | |
|
| 0.015 | 136.95 | 58000 | 2.0358 | 0.5237 | 0.2107 | |
|
| 0.015 | 137.9 | 58400 | 2.0809 | 0.5262 | 0.2160 | |
|
| 0.0182 | 138.84 | 58800 | 2.1024 | 0.5251 | 0.2158 | |
|
| 0.0123 | 139.79 | 59200 | 2.0872 | 0.5208 | 0.2132 | |
|
| 0.0114 | 140.73 | 59600 | 2.0152 | 0.5255 | 0.2145 | |
|
| 0.0111 | 141.68 | 60000 | 2.0423 | 0.5241 | 0.2111 | |
|
| 0.0111 | 142.62 | 60400 | 2.1610 | 0.5251 | 0.2108 | |
|
| 0.015 | 143.57 | 60800 | 2.0061 | 0.5126 | 0.2089 | |
|
| 0.0106 | 144.51 | 61200 | 1.9854 | 0.5194 | 0.2110 | |
|
| 0.0126 | 145.45 | 61600 | 2.1059 | 0.5230 | 0.2166 | |
|
| 0.0122 | 146.4 | 62000 | 2.0353 | 0.5183 | 0.2084 | |
|
| 0.0122 | 147.34 | 62400 | 1.9908 | 0.5194 | 0.2087 | |
|
| 0.0114 | 148.29 | 62800 | 2.0102 | 0.5158 | 0.2112 | |
|
| 0.0102 | 149.23 | 63200 | 2.0733 | 0.5244 | 0.2147 | |
|
| 0.0137 | 150.18 | 63600 | 1.9885 | 0.5219 | 0.2128 | |
|
| 0.0119 | 151.12 | 64000 | 2.1361 | 0.5384 | 0.2133 | |
|
| 0.0119 | 152.07 | 64400 | 2.1052 | 0.5151 | 0.2089 | |
|
| 0.0122 | 153.01 | 64800 | 2.0875 | 0.5205 | 0.2087 | |
|
| 0.0108 | 153.96 | 65200 | 2.1429 | 0.5190 | 0.2070 | |
|
| 0.0111 | 154.9 | 65600 | 2.0868 | 0.5172 | 0.2081 | |
|
| 0.0168 | 155.84 | 66000 | 2.0705 | 0.5244 | 0.2085 | |
|
| 0.0168 | 156.79 | 66400 | 2.0395 | 0.5154 | 0.2061 | |
|
| 0.0104 | 157.73 | 66800 | 2.0649 | 0.5219 | 0.2104 | |
|
| 0.0134 | 158.68 | 67200 | 2.0947 | 0.5208 | 0.2079 | |
|
| 0.0138 | 159.62 | 67600 | 2.0279 | 0.5172 | 0.2068 | |
|
| 0.0108 | 160.57 | 68000 | 2.0735 | 0.5219 | 0.2093 | |
|
| 0.0108 | 161.51 | 68400 | 2.1113 | 0.5241 | 0.2118 | |
|
| 0.0108 | 162.46 | 68800 | 2.0902 | 0.5201 | 0.2099 | |
|
| 0.0097 | 163.4 | 69200 | 2.1501 | 0.5216 | 0.2087 | |
|
| 0.0094 | 164.34 | 69600 | 2.0897 | 0.5180 | 0.2092 | |
|
| 0.0134 | 165.29 | 70000 | 2.0759 | 0.5176 | 0.2095 | |
|
| 0.0134 | 166.23 | 70400 | 2.1005 | 0.5198 | 0.2116 | |
|
| 0.0075 | 167.18 | 70800 | 2.1269 | 0.5262 | 0.2093 | |
|
| 0.0121 | 168.12 | 71200 | 2.1036 | 0.5198 | 0.2090 | |
|
| 0.006 | 169.07 | 71600 | 2.1189 | 0.5144 | 0.2086 | |
|
| 0.0084 | 170.01 | 72000 | 2.2502 | 0.5119 | 0.2065 | |
|
| 0.0084 | 170.96 | 72400 | 2.0946 | 0.5144 | 0.2075 | |
|
| 0.0101 | 171.9 | 72800 | 2.0551 | 0.5111 | 0.2072 | |
|
| 0.0111 | 172.85 | 73200 | 2.1882 | 0.5126 | 0.2101 | |
|
| 0.0084 | 173.79 | 73600 | 2.1289 | 0.5140 | 0.2087 | |
|
| 0.0081 | 174.73 | 74000 | 2.1833 | 0.5187 | 0.2071 | |
|
| 0.0081 | 175.68 | 74400 | 2.1543 | 0.5198 | 0.2064 | |
|
| 0.0095 | 176.62 | 74800 | 2.0642 | 0.5104 | 0.2066 | |
|
| 0.0114 | 177.57 | 75200 | 2.1615 | 0.5147 | 0.2080 | |
|
| 0.0075 | 178.51 | 75600 | 2.1834 | 0.5108 | 0.2076 | |
|
| 0.0088 | 179.46 | 76000 | 2.0629 | 0.5065 | 0.2052 | |
|
| 0.0088 | 180.4 | 76400 | 2.1611 | 0.5172 | 0.2111 | |
|
| 0.007 | 181.35 | 76800 | 2.1460 | 0.5136 | 0.2084 | |
|
| 0.0081 | 182.29 | 77200 | 2.1669 | 0.5216 | 0.2061 | |
|
| 0.0063 | 183.23 | 77600 | 2.1599 | 0.5266 | 0.2125 | |
|
| 0.008 | 184.18 | 78000 | 2.1681 | 0.5219 | 0.2093 | |
|
| 0.008 | 185.12 | 78400 | 2.1855 | 0.5219 | 0.2114 | |
|
| 0.0085 | 186.07 | 78800 | 2.2260 | 0.5190 | 0.2066 | |
|
| 0.0067 | 187.01 | 79200 | 2.3088 | 0.5119 | 0.2116 | |
|
| 0.0078 | 187.96 | 79600 | 2.1148 | 0.5101 | 0.2051 | |
|
| 0.0103 | 188.9 | 80000 | 2.1095 | 0.5122 | 0.2058 | |
|
| 0.0103 | 189.85 | 80400 | 2.0761 | 0.5198 | 0.2065 | |
|
| 0.0131 | 190.79 | 80800 | 2.1673 | 0.5136 | 0.2087 | |
|
| 0.0077 | 191.74 | 81200 | 2.1062 | 0.5165 | 0.2090 | |
|
| 0.0083 | 192.68 | 81600 | 2.0541 | 0.5158 | 0.2070 | |
|
| 0.0054 | 193.62 | 82000 | 2.1153 | 0.5151 | 0.2054 | |
|
| 0.0054 | 194.57 | 82400 | 2.0986 | 0.5151 | 0.2066 | |
|
| 0.0083 | 195.51 | 82800 | 2.1527 | 0.5208 | 0.2064 | |
|
| 0.0052 | 196.46 | 83200 | 2.1105 | 0.5241 | 0.2094 | |
|
| 0.0095 | 197.4 | 83600 | 2.1886 | 0.5169 | 0.2070 | |
|
| 0.0054 | 198.35 | 84000 | 2.1499 | 0.5198 | 0.2093 | |
|
| 0.0054 | 199.29 | 84400 | 2.1341 | 0.5154 | 0.2050 | |
|
| 0.0056 | 200.24 | 84800 | 2.1335 | 0.5126 | 0.2044 | |
|
| 0.0067 | 201.18 | 85200 | 2.1063 | 0.5158 | 0.2067 | |
|
| 0.0062 | 202.13 | 85600 | 2.2441 | 0.5305 | 0.2091 | |
|
| 0.0046 | 203.07 | 86000 | 2.3026 | 0.5144 | 0.2068 | |
|
| 0.0046 | 204.01 | 86400 | 2.2769 | 0.5136 | 0.2072 | |
|
| 0.0057 | 204.96 | 86800 | 2.1965 | 0.5230 | 0.2082 | |
|
| 0.0094 | 205.9 | 87200 | 2.2242 | 0.5140 | 0.2051 | |
|
| 0.0038 | 206.85 | 87600 | 2.2546 | 0.5169 | 0.2065 | |
|
| 0.0045 | 207.79 | 88000 | 2.2832 | 0.5169 | 0.2048 | |
|
| 0.0045 | 208.74 | 88400 | 2.2217 | 0.5104 | 0.2050 | |
|
| 0.0051 | 209.68 | 88800 | 2.1853 | 0.5172 | 0.2080 | |
|
| 0.0059 | 210.63 | 89200 | 2.3355 | 0.5122 | 0.2074 | |
|
| 0.0072 | 211.57 | 89600 | 2.2551 | 0.5133 | 0.2084 | |
|
| 0.0054 | 212.51 | 90000 | 2.2100 | 0.5122 | 0.2066 | |
|
| 0.0054 | 213.46 | 90400 | 2.2089 | 0.5040 | 0.2064 | |
|
| 0.0055 | 214.4 | 90800 | 2.1626 | 0.5086 | 0.2049 | |
|
| 0.0059 | 215.35 | 91200 | 2.0619 | 0.5093 | 0.2030 | |
|
| 0.0066 | 216.29 | 91600 | 2.1264 | 0.5086 | 0.2018 | |
|
| 0.0052 | 217.24 | 92000 | 2.1548 | 0.5104 | 0.2035 | |
|
| 0.0052 | 218.18 | 92400 | 2.1520 | 0.5004 | 0.2007 | |
|
| 0.0039 | 219.13 | 92800 | 2.1095 | 0.5068 | 0.2060 | |
|
| 0.0056 | 220.07 | 93200 | 2.1674 | 0.5122 | 0.2065 | |
|
| 0.0056 | 221.02 | 93600 | 2.0891 | 0.5162 | 0.2065 | |
|
| 0.0047 | 221.96 | 94000 | 2.1217 | 0.5144 | 0.2047 | |
|
| 0.0047 | 222.9 | 94400 | 2.1482 | 0.5104 | 0.2015 | |
|
| 0.0041 | 223.85 | 94800 | 2.0938 | 0.5122 | 0.2062 | |
|
| 0.0039 | 224.79 | 95200 | 2.1521 | 0.5040 | 0.2038 | |
|
| 0.0046 | 225.74 | 95600 | 2.0902 | 0.5151 | 0.2045 | |
|
| 0.0038 | 226.68 | 96000 | 2.2018 | 0.5176 | 0.2047 | |
|
| 0.0038 | 227.63 | 96400 | 2.1789 | 0.5212 | 0.2063 | |
|
| 0.0066 | 228.57 | 96800 | 2.2180 | 0.5190 | 0.2055 | |
|
| 0.0043 | 229.52 | 97200 | 2.1474 | 0.5180 | 0.2039 | |
|
| 0.0058 | 230.46 | 97600 | 2.1442 | 0.5205 | 0.2053 | |
|
| 0.0049 | 231.4 | 98000 | 2.2504 | 0.5248 | 0.2057 | |
|
| 0.0049 | 232.35 | 98400 | 2.2156 | 0.5251 | 0.2061 | |
|
| 0.0035 | 233.29 | 98800 | 2.2306 | 0.5158 | 0.2047 | |
|
| 0.0047 | 234.24 | 99200 | 2.2065 | 0.5176 | 0.2070 | |
|
| 0.0037 | 235.18 | 99600 | 2.1740 | 0.5126 | 0.2045 | |
|
| 0.0035 | 236.13 | 100000 | 2.1977 | 0.5079 | 0.2033 | |
|
| 0.0035 | 237.07 | 100400 | 2.1814 | 0.5136 | 0.2047 | |
|
| 0.003 | 238.02 | 100800 | 2.1884 | 0.5057 | 0.2028 | |
|
| 0.0032 | 238.96 | 101200 | 2.1905 | 0.5162 | 0.2032 | |
|
| 0.0032 | 239.91 | 101600 | 2.1615 | 0.5187 | 0.2036 | |
|
| 0.0049 | 240.85 | 102000 | 2.1595 | 0.5147 | 0.2043 | |
|
| 0.0049 | 241.79 | 102400 | 2.1762 | 0.5187 | 0.2022 | |
|
| 0.0057 | 242.74 | 102800 | 2.1740 | 0.5219 | 0.2035 | |
|
| 0.0093 | 243.68 | 103200 | 2.1495 | 0.5126 | 0.2044 | |
|
| 0.0045 | 244.63 | 103600 | 2.1512 | 0.5172 | 0.2048 | |
|
| 0.0035 | 245.57 | 104000 | 2.1849 | 0.5187 | 0.2044 | |
|
| 0.0035 | 246.52 | 104400 | 2.1989 | 0.5183 | 0.2030 | |
|
| 0.0033 | 247.46 | 104800 | 2.2341 | 0.5183 | 0.2032 | |
|
| 0.0031 | 248.41 | 105200 | 2.1902 | 0.5140 | 0.2032 | |
|
| 0.0043 | 249.35 | 105600 | 2.1945 | 0.5172 | 0.2034 | |
|
| 0.002 | 250.3 | 106000 | 2.2070 | 0.5162 | 0.2033 | |
|
| 0.002 | 251.24 | 106400 | 2.2130 | 0.5144 | 0.2019 | |
|
| 0.0066 | 252.18 | 106800 | 2.2191 | 0.5136 | 0.2025 | |
|
| 0.0019 | 253.13 | 107200 | 2.2326 | 0.5129 | 0.2025 | |
|
| 0.003 | 254.07 | 107600 | 2.2271 | 0.5097 | 0.2010 | |
|
| 0.0024 | 255.02 | 108000 | 2.2429 | 0.5090 | 0.2007 | |
|
| 0.0024 | 255.96 | 108400 | 2.1557 | 0.5093 | 0.2003 | |
|
| 0.0034 | 256.91 | 108800 | 2.1615 | 0.5101 | 0.2021 | |
|
| 0.003 | 257.85 | 109200 | 2.2049 | 0.5126 | 0.2003 | |
|
| 0.0032 | 258.8 | 109600 | 2.2107 | 0.5136 | 0.1996 | |
|
| 0.0026 | 259.74 | 110000 | 2.1887 | 0.5104 | 0.2007 | |
|
| 0.0026 | 260.68 | 110400 | 2.2254 | 0.5115 | 0.2002 | |
|
| 0.0022 | 261.63 | 110800 | 2.1952 | 0.5140 | 0.1999 | |
|
| 0.0022 | 262.57 | 111200 | 2.1954 | 0.5115 | 0.1991 | |
|
| 0.0019 | 263.52 | 111600 | 2.2104 | 0.5111 | 0.1997 | |
|
| 0.0037 | 264.46 | 112000 | 2.1438 | 0.5122 | 0.2001 | |
|
| 0.0037 | 265.41 | 112400 | 2.2171 | 0.5151 | 0.2001 | |
|
| 0.0031 | 266.35 | 112800 | 2.2432 | 0.5104 | 0.2012 | |
|
| 0.0041 | 267.3 | 113200 | 2.2321 | 0.5119 | 0.2005 | |
|
| 0.0066 | 268.24 | 113600 | 2.2066 | 0.5086 | 0.1995 | |
|
| 0.004 | 269.19 | 114000 | 2.1904 | 0.5111 | 0.2003 | |
|
| 0.004 | 270.13 | 114400 | 2.2114 | 0.5119 | 0.1994 | |
|
| 0.0028 | 271.07 | 114800 | 2.2074 | 0.5065 | 0.1992 | |
|
| 0.0034 | 272.02 | 115200 | 2.2172 | 0.5097 | 0.1995 | |
|
| 0.0032 | 272.96 | 115600 | 2.1759 | 0.5086 | 0.1987 | |
|
| 0.0031 | 273.91 | 116000 | 2.1870 | 0.5104 | 0.1993 | |
|
| 0.0031 | 274.85 | 116400 | 2.1658 | 0.5097 | 0.1993 | |
|
| 0.0033 | 275.8 | 116800 | 2.2122 | 0.5097 | 0.1994 | |
|
| 0.0042 | 276.74 | 117200 | 2.2084 | 0.5079 | 0.2000 | |
|
| 0.0041 | 277.69 | 117600 | 2.2042 | 0.5025 | 0.1995 | |
|
| 0.0019 | 278.63 | 118000 | 2.2102 | 0.5072 | 0.2000 | |
|
| 0.0019 | 279.57 | 118400 | 2.2238 | 0.5061 | 0.1994 | |
|
| 0.0024 | 280.52 | 118800 | 2.2299 | 0.5086 | 0.1989 | |
|
| 0.0017 | 281.46 | 119200 | 2.2374 | 0.5043 | 0.1982 | |
|
| 0.0026 | 282.41 | 119600 | 2.2307 | 0.5090 | 0.1994 | |
|
| 0.004 | 283.35 | 120000 | 2.2176 | 0.5057 | 0.1977 | |
|
| 0.004 | 284.3 | 120400 | 2.2064 | 0.5040 | 0.1972 | |
|
| 0.0028 | 285.24 | 120800 | 2.2228 | 0.5097 | 0.1977 | |
|
| 0.0024 | 286.19 | 121200 | 2.2224 | 0.5083 | 0.1986 | |
|
| 0.0018 | 287.13 | 121600 | 2.2182 | 0.5057 | 0.1995 | |
|
| 0.0025 | 288.08 | 122000 | 2.2210 | 0.5068 | 0.1993 | |
|
| 0.0025 | 289.02 | 122400 | 2.2164 | 0.5079 | 0.1995 | |
|
| 0.0022 | 289.96 | 122800 | 2.2034 | 0.5068 | 0.2000 | |
|
| 0.0022 | 290.91 | 123200 | 2.1867 | 0.5057 | 0.1996 | |
|
| 0.0021 | 291.85 | 123600 | 2.1855 | 0.5065 | 0.2000 | |
|
| 0.0016 | 292.8 | 124000 | 2.1897 | 0.5061 | 0.1996 | |
|
| 0.0016 | 293.74 | 124400 | 2.2099 | 0.5047 | 0.1989 | |
|
| 0.0032 | 294.69 | 124800 | 2.2018 | 0.5050 | 0.1988 | |
|
| 0.0019 | 295.63 | 125200 | 2.1945 | 0.5054 | 0.1992 | |
|
| 0.0014 | 296.58 | 125600 | 2.2012 | 0.5040 | 0.1985 | |
|
| 0.0018 | 297.52 | 126000 | 2.2040 | 0.5050 | 0.1983 | |
|
| 0.0018 | 298.47 | 126400 | 2.2039 | 0.5054 | 0.1984 | |
|
| 0.0023 | 299.41 | 126800 | 2.2061 | 0.5050 | 0.1982 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0.dev0 |
|
- Pytorch 1.13.1+cu117 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
