update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,309 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
model-index:
|
| 5 |
+
- name: pixel-tiny-cont
|
| 6 |
+
results: []
|
| 7 |
---
|
| 8 |
+
|
| 9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 10 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 11 |
+
|
| 12 |
+
# pixel-tiny-cont
|
| 13 |
+
|
| 14 |
+
This model was trained from scratch on the None dataset.
|
| 15 |
+
It achieves the following results on the evaluation set:
|
| 16 |
+
- Loss: 0.8016
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 0.0006
|
| 36 |
+
- train_batch_size: 128
|
| 37 |
+
- eval_batch_size: 8
|
| 38 |
+
- seed: 42
|
| 39 |
+
- distributed_type: multi-GPU
|
| 40 |
+
- num_devices: 8
|
| 41 |
+
- total_train_batch_size: 1024
|
| 42 |
+
- total_eval_batch_size: 64
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: cosine
|
| 45 |
+
- lr_scheduler_warmup_ratio: 0.05
|
| 46 |
+
- training_steps: 250000
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 51 |
+
|:-------------:|:-----:|:------:|:---------------:|
|
| 52 |
+
| 0.7411 | 0.06 | 1000 | 0.9070 |
|
| 53 |
+
| 0.7395 | 0.12 | 2000 | 0.9064 |
|
| 54 |
+
| 0.7387 | 0.18 | 3000 | 0.9047 |
|
| 55 |
+
| 0.7382 | 0.25 | 4000 | 0.9015 |
|
| 56 |
+
| 0.7381 | 0.31 | 5000 | 0.9044 |
|
| 57 |
+
| 0.7379 | 0.37 | 6000 | 0.9042 |
|
| 58 |
+
| 0.7379 | 0.43 | 7000 | 0.9054 |
|
| 59 |
+
| 0.7378 | 0.49 | 8000 | 0.9035 |
|
| 60 |
+
| 0.7378 | 0.55 | 9000 | 0.9026 |
|
| 61 |
+
| 0.7371 | 0.61 | 10000 | 0.9038 |
|
| 62 |
+
| 0.7369 | 0.67 | 11000 | 0.9027 |
|
| 63 |
+
| 0.7368 | 0.74 | 12000 | 0.9022 |
|
| 64 |
+
| 0.7368 | 0.8 | 13000 | 0.8987 |
|
| 65 |
+
| 0.7374 | 0.86 | 14000 | 0.9014 |
|
| 66 |
+
| 0.7369 | 0.92 | 15000 | 0.9002 |
|
| 67 |
+
| 0.7369 | 0.98 | 16000 | 0.9002 |
|
| 68 |
+
| 0.7372 | 1.04 | 17000 | 0.9019 |
|
| 69 |
+
| 0.737 | 1.1 | 18000 | 0.9001 |
|
| 70 |
+
| 0.737 | 1.16 | 19000 | 0.9006 |
|
| 71 |
+
| 0.7369 | 1.23 | 20000 | 0.9007 |
|
| 72 |
+
| 0.7365 | 1.29 | 21000 | 0.8698 |
|
| 73 |
+
| 0.7363 | 1.35 | 22000 | 0.8700 |
|
| 74 |
+
| 0.7366 | 1.41 | 23000 | 0.9021 |
|
| 75 |
+
| 0.7362 | 1.47 | 24000 | 0.8763 |
|
| 76 |
+
| 0.7082 | 1.53 | 25000 | 0.8719 |
|
| 77 |
+
| 0.6774 | 1.59 | 26000 | 0.8876 |
|
| 78 |
+
| 0.6525 | 1.65 | 27000 | 0.8905 |
|
| 79 |
+
| 0.6022 | 1.72 | 28000 | 0.8856 |
|
| 80 |
+
| 0.5874 | 1.78 | 29000 | 0.8794 |
|
| 81 |
+
| 0.5765 | 1.84 | 30000 | 0.8806 |
|
| 82 |
+
| 0.5685 | 1.9 | 31000 | 0.8747 |
|
| 83 |
+
| 0.564 | 1.96 | 32000 | 0.8779 |
|
| 84 |
+
| 0.5606 | 2.02 | 33000 | 0.8762 |
|
| 85 |
+
| 0.5574 | 2.08 | 34000 | 0.8703 |
|
| 86 |
+
| 0.5528 | 2.14 | 35000 | 0.8664 |
|
| 87 |
+
| 0.5494 | 2.21 | 36000 | 0.8717 |
|
| 88 |
+
| 0.5448 | 2.27 | 37000 | 0.8673 |
|
| 89 |
+
| 0.5419 | 2.33 | 38000 | 0.8637 |
|
| 90 |
+
| 0.5385 | 2.39 | 39000 | 0.8634 |
|
| 91 |
+
| 0.536 | 2.45 | 40000 | 0.8661 |
|
| 92 |
+
| 0.5336 | 2.51 | 41000 | 0.8631 |
|
| 93 |
+
| 0.5316 | 2.57 | 42000 | 0.8606 |
|
| 94 |
+
| 0.5297 | 2.63 | 43000 | 0.8589 |
|
| 95 |
+
| 0.5305 | 2.7 | 44000 | 0.8570 |
|
| 96 |
+
| 0.5262 | 2.76 | 45000 | 0.8559 |
|
| 97 |
+
| 0.5247 | 2.82 | 46000 | 0.8634 |
|
| 98 |
+
| 0.5235 | 2.88 | 47000 | 0.8606 |
|
| 99 |
+
| 0.5227 | 2.94 | 48000 | 0.8610 |
|
| 100 |
+
| 0.5206 | 3.0 | 49000 | 0.8610 |
|
| 101 |
+
| 0.5194 | 3.06 | 50000 | 0.8611 |
|
| 102 |
+
| 0.5183 | 3.12 | 51000 | 0.8579 |
|
| 103 |
+
| 0.5175 | 3.19 | 52000 | 0.8598 |
|
| 104 |
+
| 0.5163 | 3.25 | 53000 | 0.8521 |
|
| 105 |
+
| 0.5156 | 3.31 | 54000 | 0.8550 |
|
| 106 |
+
| 0.5148 | 3.37 | 55000 | 0.8504 |
|
| 107 |
+
| 0.5139 | 3.43 | 56000 | 0.8530 |
|
| 108 |
+
| 0.5133 | 3.49 | 57000 | 0.8589 |
|
| 109 |
+
| 0.5126 | 3.55 | 58000 | 0.8561 |
|
| 110 |
+
| 0.5119 | 3.62 | 59000 | 0.8574 |
|
| 111 |
+
| 0.5127 | 3.68 | 60000 | 0.8624 |
|
| 112 |
+
| 0.5105 | 3.74 | 61000 | 0.8522 |
|
| 113 |
+
| 0.5099 | 3.8 | 62000 | 0.8550 |
|
| 114 |
+
| 0.5094 | 3.86 | 63000 | 0.8537 |
|
| 115 |
+
| 0.509 | 3.92 | 64000 | 0.8535 |
|
| 116 |
+
| 0.5091 | 3.98 | 65000 | 0.8592 |
|
| 117 |
+
| 0.5079 | 4.04 | 66000 | 0.8554 |
|
| 118 |
+
| 0.5074 | 4.11 | 67000 | 0.8516 |
|
| 119 |
+
| 0.5069 | 4.17 | 68000 | 0.8491 |
|
| 120 |
+
| 0.5066 | 4.23 | 69000 | 0.8571 |
|
| 121 |
+
| 0.5068 | 4.29 | 70000 | 0.8536 |
|
| 122 |
+
| 0.5066 | 4.35 | 71000 | 0.9288 |
|
| 123 |
+
| 0.5051 | 4.41 | 72000 | 0.8597 |
|
| 124 |
+
| 0.5045 | 4.47 | 73000 | 0.8555 |
|
| 125 |
+
| 0.5043 | 4.53 | 74000 | 0.8547 |
|
| 126 |
+
| 0.5039 | 4.6 | 75000 | 0.8561 |
|
| 127 |
+
| 0.504 | 4.66 | 76000 | 0.8541 |
|
| 128 |
+
| 0.5026 | 4.72 | 77000 | 0.8490 |
|
| 129 |
+
| 0.5024 | 4.78 | 78000 | 0.8499 |
|
| 130 |
+
| 0.5019 | 4.84 | 79000 | 0.8522 |
|
| 131 |
+
| 0.5014 | 4.9 | 80000 | 0.8508 |
|
| 132 |
+
| 0.5008 | 4.96 | 81000 | 0.8512 |
|
| 133 |
+
| 0.5002 | 5.02 | 82000 | 0.8470 |
|
| 134 |
+
| 0.4995 | 5.09 | 83000 | 0.8462 |
|
| 135 |
+
| 0.4991 | 5.15 | 84000 | 0.8455 |
|
| 136 |
+
| 0.4982 | 5.21 | 85000 | 0.8465 |
|
| 137 |
+
| 0.4978 | 5.27 | 86000 | 0.8434 |
|
| 138 |
+
| 0.4969 | 5.33 | 87000 | 0.8432 |
|
| 139 |
+
| 0.4964 | 5.39 | 88000 | 0.8417 |
|
| 140 |
+
| 0.4957 | 5.45 | 89000 | 0.8363 |
|
| 141 |
+
| 0.495 | 5.51 | 90000 | 0.8392 |
|
| 142 |
+
| 0.4946 | 5.58 | 91000 | 0.8401 |
|
| 143 |
+
| 0.4935 | 5.64 | 92000 | 0.8373 |
|
| 144 |
+
| 0.4929 | 5.7 | 93000 | 0.8401 |
|
| 145 |
+
| 0.492 | 5.76 | 94000 | 0.8356 |
|
| 146 |
+
| 0.4912 | 5.82 | 95000 | 0.8334 |
|
| 147 |
+
| 0.4904 | 5.88 | 96000 | 0.8281 |
|
| 148 |
+
| 0.4898 | 5.94 | 97000 | 0.8338 |
|
| 149 |
+
| 0.4891 | 6.0 | 98000 | 0.8300 |
|
| 150 |
+
| 0.4882 | 6.07 | 99000 | 0.8262 |
|
| 151 |
+
| 0.4876 | 6.13 | 100000 | 0.8172 |
|
| 152 |
+
| 0.4868 | 6.19 | 101000 | 0.8240 |
|
| 153 |
+
| 0.4861 | 6.25 | 102000 | 0.8212 |
|
| 154 |
+
| 0.4854 | 6.31 | 103000 | 0.8243 |
|
| 155 |
+
| 0.4847 | 6.37 | 104000 | 0.8228 |
|
| 156 |
+
| 0.4841 | 6.43 | 105000 | 0.8185 |
|
| 157 |
+
| 0.4837 | 6.5 | 106000 | 0.8177 |
|
| 158 |
+
| 0.4827 | 6.56 | 107000 | 0.8140 |
|
| 159 |
+
| 0.4819 | 6.62 | 108000 | 0.8147 |
|
| 160 |
+
| 0.4813 | 6.68 | 109000 | 0.8172 |
|
| 161 |
+
| 0.4807 | 6.74 | 110000 | 0.8149 |
|
| 162 |
+
| 0.4801 | 6.8 | 111000 | 0.8152 |
|
| 163 |
+
| 0.4792 | 6.86 | 112000 | 0.8089 |
|
| 164 |
+
| 0.4785 | 6.92 | 113000 | 0.8084 |
|
| 165 |
+
| 0.4777 | 6.99 | 114000 | 0.8103 |
|
| 166 |
+
| 0.477 | 7.05 | 115000 | 0.8104 |
|
| 167 |
+
| 0.4772 | 7.11 | 116000 | 0.8142 |
|
| 168 |
+
| 0.4754 | 7.17 | 117000 | 0.8159 |
|
| 169 |
+
| 0.4748 | 7.23 | 118000 | 0.8092 |
|
| 170 |
+
| 0.4738 | 7.29 | 119000 | 0.8036 |
|
| 171 |
+
| 0.473 | 7.35 | 120000 | 0.8085 |
|
| 172 |
+
| 0.4724 | 7.41 | 121000 | 0.8084 |
|
| 173 |
+
| 0.4714 | 7.48 | 122000 | 0.8066 |
|
| 174 |
+
| 0.4705 | 7.54 | 123000 | 0.8094 |
|
| 175 |
+
| 0.4699 | 7.6 | 124000 | 0.8095 |
|
| 176 |
+
| 0.4693 | 7.66 | 125000 | 0.8101 |
|
| 177 |
+
| 0.4685 | 7.72 | 126000 | 0.8092 |
|
| 178 |
+
| 0.4679 | 7.78 | 127000 | 0.8025 |
|
| 179 |
+
| 0.4672 | 7.84 | 128000 | 0.8000 |
|
| 180 |
+
| 0.4665 | 7.9 | 129000 | 0.8020 |
|
| 181 |
+
| 0.4659 | 7.97 | 130000 | 0.8022 |
|
| 182 |
+
| 0.4653 | 8.03 | 131000 | 0.8071 |
|
| 183 |
+
| 0.4647 | 8.09 | 132000 | 0.7994 |
|
| 184 |
+
| 0.4639 | 8.15 | 133000 | 0.8034 |
|
| 185 |
+
| 0.4634 | 8.21 | 134000 | 0.8022 |
|
| 186 |
+
| 0.4656 | 8.27 | 135000 | 0.8052 |
|
| 187 |
+
| 0.4623 | 8.33 | 136000 | 0.7989 |
|
| 188 |
+
| 0.4617 | 8.39 | 137000 | 0.7993 |
|
| 189 |
+
| 0.4612 | 8.46 | 138000 | 0.8003 |
|
| 190 |
+
| 0.4608 | 8.52 | 139000 | 0.7990 |
|
| 191 |
+
| 0.4603 | 8.58 | 140000 | 0.8074 |
|
| 192 |
+
| 0.4597 | 8.64 | 141000 | 0.8089 |
|
| 193 |
+
| 0.4591 | 8.7 | 142000 | 0.8040 |
|
| 194 |
+
| 0.4586 | 8.76 | 143000 | 0.7993 |
|
| 195 |
+
| 0.4584 | 8.82 | 144000 | 0.8004 |
|
| 196 |
+
| 0.4594 | 8.88 | 145000 | 0.7991 |
|
| 197 |
+
| 0.4574 | 8.95 | 146000 | 0.7956 |
|
| 198 |
+
| 0.4571 | 9.01 | 147000 | 0.7948 |
|
| 199 |
+
| 0.4565 | 9.07 | 148000 | 0.7982 |
|
| 200 |
+
| 0.4563 | 9.13 | 149000 | 0.7960 |
|
| 201 |
+
| 0.4555 | 9.19 | 150000 | 0.8043 |
|
| 202 |
+
| 0.4551 | 9.25 | 151000 | 0.8021 |
|
| 203 |
+
| 0.4549 | 9.31 | 152000 | 0.7972 |
|
| 204 |
+
| 0.4545 | 9.38 | 153000 | 0.8003 |
|
| 205 |
+
| 0.4542 | 9.44 | 154000 | 0.8000 |
|
| 206 |
+
| 0.4539 | 9.5 | 155000 | 0.7960 |
|
| 207 |
+
| 0.4533 | 9.56 | 156000 | 0.8035 |
|
| 208 |
+
| 0.453 | 9.62 | 157000 | 0.7953 |
|
| 209 |
+
| 0.4527 | 9.68 | 158000 | 0.7937 |
|
| 210 |
+
| 0.4524 | 9.74 | 159000 | 0.8021 |
|
| 211 |
+
| 0.4519 | 9.8 | 160000 | 0.8028 |
|
| 212 |
+
| 0.4517 | 9.87 | 161000 | 0.8006 |
|
| 213 |
+
| 0.4514 | 9.93 | 162000 | 0.8067 |
|
| 214 |
+
| 0.4512 | 9.99 | 163000 | 0.7990 |
|
| 215 |
+
| 0.4508 | 10.05 | 164000 | 0.8041 |
|
| 216 |
+
| 0.4504 | 10.11 | 165000 | 0.7995 |
|
| 217 |
+
| 0.4501 | 10.17 | 166000 | 0.7979 |
|
| 218 |
+
| 0.4499 | 10.23 | 167000 | 0.7969 |
|
| 219 |
+
| 0.4497 | 10.29 | 168000 | 0.8041 |
|
| 220 |
+
| 0.4495 | 10.36 | 169000 | 0.8050 |
|
| 221 |
+
| 0.4492 | 10.42 | 170000 | 0.7999 |
|
| 222 |
+
| 0.4494 | 10.48 | 171000 | 0.7992 |
|
| 223 |
+
| 0.4486 | 10.54 | 172000 | 0.8019 |
|
| 224 |
+
| 0.4485 | 10.6 | 173000 | 0.8026 |
|
| 225 |
+
| 0.4483 | 10.66 | 174000 | 0.8009 |
|
| 226 |
+
| 0.448 | 10.72 | 175000 | 0.8022 |
|
| 227 |
+
| 0.4479 | 10.78 | 176000 | 0.8016 |
|
| 228 |
+
| 0.4476 | 10.85 | 177000 | 0.7988 |
|
| 229 |
+
| 0.4474 | 10.91 | 178000 | 0.8025 |
|
| 230 |
+
| 0.4471 | 10.97 | 179000 | 0.8035 |
|
| 231 |
+
| 0.4471 | 11.03 | 180000 | 0.7983 |
|
| 232 |
+
| 0.4467 | 11.09 | 181000 | 0.8010 |
|
| 233 |
+
| 0.4463 | 11.15 | 182000 | 0.8035 |
|
| 234 |
+
| 0.4463 | 11.21 | 183000 | 0.8049 |
|
| 235 |
+
| 0.4462 | 11.27 | 184000 | 0.7998 |
|
| 236 |
+
| 0.4459 | 11.34 | 185000 | 0.7988 |
|
| 237 |
+
| 0.4457 | 11.4 | 186000 | 0.8064 |
|
| 238 |
+
| 0.4456 | 11.46 | 187000 | 0.8042 |
|
| 239 |
+
| 0.4454 | 11.52 | 188000 | 0.7998 |
|
| 240 |
+
| 0.4453 | 11.58 | 189000 | 0.8026 |
|
| 241 |
+
| 0.4449 | 11.64 | 190000 | 0.7993 |
|
| 242 |
+
| 0.4448 | 11.7 | 191000 | 0.8037 |
|
| 243 |
+
| 0.4448 | 11.76 | 192000 | 0.8038 |
|
| 244 |
+
| 0.4445 | 11.83 | 193000 | 0.8010 |
|
| 245 |
+
| 0.4442 | 11.89 | 194000 | 0.7977 |
|
| 246 |
+
| 0.4443 | 11.95 | 195000 | 0.8008 |
|
| 247 |
+
| 0.4441 | 12.01 | 196000 | 0.8048 |
|
| 248 |
+
| 0.4439 | 12.07 | 197000 | 0.8034 |
|
| 249 |
+
| 0.4438 | 12.13 | 198000 | 0.8052 |
|
| 250 |
+
| 0.4437 | 12.19 | 199000 | 0.8041 |
|
| 251 |
+
| 0.4434 | 12.25 | 200000 | 0.8001 |
|
| 252 |
+
| 0.4434 | 12.32 | 201000 | 0.8013 |
|
| 253 |
+
| 0.4432 | 12.38 | 202000 | 0.7987 |
|
| 254 |
+
| 0.443 | 12.44 | 203000 | 0.7962 |
|
| 255 |
+
| 0.443 | 12.5 | 204000 | 0.8017 |
|
| 256 |
+
| 0.4429 | 12.56 | 205000 | 0.7996 |
|
| 257 |
+
| 0.4428 | 12.62 | 206000 | 0.7997 |
|
| 258 |
+
| 0.4425 | 12.68 | 207000 | 0.8017 |
|
| 259 |
+
| 0.4424 | 12.75 | 208000 | 0.8008 |
|
| 260 |
+
| 0.4424 | 12.81 | 209000 | 0.8052 |
|
| 261 |
+
| 0.4422 | 12.87 | 210000 | 0.8004 |
|
| 262 |
+
| 0.4421 | 12.93 | 211000 | 0.8023 |
|
| 263 |
+
| 0.4421 | 12.99 | 212000 | 0.8014 |
|
| 264 |
+
| 0.442 | 13.05 | 213000 | 0.7999 |
|
| 265 |
+
| 0.4418 | 13.11 | 214000 | 0.8019 |
|
| 266 |
+
| 0.4417 | 13.17 | 215000 | 0.7996 |
|
| 267 |
+
| 0.4416 | 13.24 | 216000 | 0.8007 |
|
| 268 |
+
| 0.4414 | 13.3 | 217000 | 0.8029 |
|
| 269 |
+
| 0.4415 | 13.36 | 218000 | 0.7990 |
|
| 270 |
+
| 0.4413 | 13.42 | 219000 | 0.7997 |
|
| 271 |
+
| 0.4413 | 13.48 | 220000 | 0.7997 |
|
| 272 |
+
| 0.4412 | 13.54 | 221000 | 0.7996 |
|
| 273 |
+
| 0.4411 | 13.6 | 222000 | 0.8003 |
|
| 274 |
+
| 0.4411 | 13.66 | 223000 | 0.7993 |
|
| 275 |
+
| 0.4411 | 13.73 | 224000 | 0.8005 |
|
| 276 |
+
| 0.4409 | 13.79 | 225000 | 0.8013 |
|
| 277 |
+
| 0.4409 | 13.85 | 226000 | 0.8016 |
|
| 278 |
+
| 0.4409 | 13.91 | 227000 | 0.7994 |
|
| 279 |
+
| 0.4408 | 13.97 | 228000 | 0.8023 |
|
| 280 |
+
| 0.4407 | 14.03 | 229000 | 0.8013 |
|
| 281 |
+
| 0.4406 | 14.09 | 230000 | 0.8038 |
|
| 282 |
+
| 0.4408 | 14.15 | 231000 | 0.7994 |
|
| 283 |
+
| 0.4406 | 14.22 | 232000 | 0.8007 |
|
| 284 |
+
| 0.4404 | 14.28 | 233000 | 0.8006 |
|
| 285 |
+
| 0.4403 | 14.34 | 234000 | 0.7987 |
|
| 286 |
+
| 0.4405 | 14.4 | 235000 | 0.8010 |
|
| 287 |
+
| 0.4404 | 14.46 | 236000 | 0.7982 |
|
| 288 |
+
| 0.4404 | 14.52 | 237000 | 0.7985 |
|
| 289 |
+
| 0.4403 | 14.58 | 238000 | 0.8016 |
|
| 290 |
+
| 0.4402 | 14.64 | 239000 | 0.8025 |
|
| 291 |
+
| 0.4402 | 14.71 | 240000 | 0.8020 |
|
| 292 |
+
| 0.4401 | 14.77 | 241000 | 0.8009 |
|
| 293 |
+
| 0.4401 | 14.83 | 242000 | 0.8015 |
|
| 294 |
+
| 0.4401 | 14.89 | 243000 | 0.8010 |
|
| 295 |
+
| 0.44 | 14.95 | 244000 | 0.7996 |
|
| 296 |
+
| 0.4402 | 15.01 | 245000 | 0.8014 |
|
| 297 |
+
| 0.44 | 15.07 | 246000 | 0.8007 |
|
| 298 |
+
| 0.44 | 15.13 | 247000 | 0.7984 |
|
| 299 |
+
| 0.44 | 15.2 | 248000 | 0.8009 |
|
| 300 |
+
| 0.4399 | 15.26 | 249000 | 0.8006 |
|
| 301 |
+
| 0.4399 | 15.32 | 250000 | 0.8016 |
|
| 302 |
+
|
| 303 |
+
|
| 304 |
+
### Framework versions
|
| 305 |
+
|
| 306 |
+
- Transformers 4.17.0
|
| 307 |
+
- Pytorch 1.11.0
|
| 308 |
+
- Datasets 2.1.1.dev0
|
| 309 |
+
- Tokenizers 0.12.1
|