End of training
Browse files
README.md
CHANGED
|
@@ -21,8 +21,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the gg_ds dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss:
|
| 25 |
-
- Cer: 26.
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
@@ -48,113 +48,313 @@ The following hyperparameters were used during training:
|
|
| 48 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
- lr_scheduler_warmup_steps: 500
|
| 51 |
-
- training_steps:
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 57 |
|:-------------:|:-----:|:------:|:---------------:|:-------:|
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
| 61 |
-
| 0.
|
| 62 |
-
| 0.
|
| 63 |
-
| 0.
|
| 64 |
-
| 0.
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
-
| 0.
|
| 87 |
-
| 0.
|
| 88 |
-
| 0.
|
| 89 |
-
| 0.
|
| 90 |
-
| 0.
|
| 91 |
-
| 0.
|
| 92 |
-
| 0.
|
| 93 |
-
| 0.
|
| 94 |
-
| 0.
|
| 95 |
-
| 0.
|
| 96 |
-
| 0.0007 | 31.2 | 39000 | 1.
|
| 97 |
-
| 0.
|
| 98 |
-
| 0.001 | 32.8 | 41000 | 1.
|
| 99 |
-
| 0.
|
| 100 |
-
| 0.
|
| 101 |
-
| 0.
|
| 102 |
-
| 0.
|
| 103 |
-
| 0.
|
| 104 |
-
| 0.
|
| 105 |
-
| 0.
|
| 106 |
-
| 0.
|
| 107 |
-
| 0.
|
| 108 |
-
| 0.
|
| 109 |
-
| 0.
|
| 110 |
-
| 0.
|
| 111 |
-
| 0.
|
| 112 |
-
| 0.
|
| 113 |
-
| 0.
|
| 114 |
-
| 0.
|
| 115 |
-
| 0.
|
| 116 |
-
| 0.
|
| 117 |
-
| 0.
|
| 118 |
-
| 0.
|
| 119 |
-
| 0.
|
| 120 |
-
| 0.
|
| 121 |
-
| 0.
|
| 122 |
-
| 0.
|
| 123 |
-
| 0.
|
| 124 |
-
| 0.
|
| 125 |
-
| 0.
|
| 126 |
-
| 0.
|
| 127 |
-
| 0.
|
| 128 |
-
| 0.
|
| 129 |
-
| 0.
|
| 130 |
-
| 0.
|
| 131 |
-
| 0.
|
| 132 |
-
| 0.
|
| 133 |
-
| 0.
|
| 134 |
-
| 0.
|
| 135 |
-
| 0.
|
| 136 |
-
| 0.
|
| 137 |
-
| 0.
|
| 138 |
-
| 0.
|
| 139 |
-
| 0.
|
| 140 |
-
| 0.
|
| 141 |
-
| 0.
|
| 142 |
-
| 0.
|
| 143 |
-
| 0.
|
| 144 |
-
| 0.
|
| 145 |
-
| 0.
|
| 146 |
-
| 0.
|
| 147 |
-
| 0.
|
| 148 |
-
| 0.
|
| 149 |
-
| 0.
|
| 150 |
-
| 0.
|
| 151 |
-
| 0.
|
| 152 |
-
| 0.
|
| 153 |
-
| 0.
|
| 154 |
-
| 0.
|
| 155 |
-
| 0.
|
| 156 |
-
| 0.
|
| 157 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 158 |
|
| 159 |
|
| 160 |
### Framework versions
|
|
|
|
| 21 |
|
| 22 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the gg_ds dataset.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 2.0181
|
| 25 |
+
- Cer: 26.4902
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 48 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
- lr_scheduler_warmup_steps: 500
|
| 51 |
+
- training_steps: 300000
|
| 52 |
- mixed_precision_training: Native AMP
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 57 |
|:-------------:|:-----:|:------:|:---------------:|:-------:|
|
| 58 |
+
| 0.0028 | 0.8 | 1000 | 1.5737 | 27.8905 |
|
| 59 |
+
| 0.0059 | 1.6 | 2000 | 1.5694 | 27.5053 |
|
| 60 |
+
| 0.0039 | 2.4 | 3000 | 1.5481 | 27.8554 |
|
| 61 |
+
| 0.0042 | 3.2 | 4000 | 1.5456 | 27.6774 |
|
| 62 |
+
| 0.0029 | 4.0 | 5000 | 1.5568 | 26.8684 |
|
| 63 |
+
| 0.0072 | 4.8 | 6000 | 1.5703 | 27.7266 |
|
| 64 |
+
| 0.0026 | 5.6 | 7000 | 1.5721 | 30.2872 |
|
| 65 |
+
| 0.002 | 6.4 | 8000 | 1.5597 | 27.0569 |
|
| 66 |
+
| 0.0077 | 7.2 | 9000 | 1.5680 | 27.3742 |
|
| 67 |
+
| 0.0059 | 8.0 | 10000 | 1.5891 | 28.6492 |
|
| 68 |
+
| 0.0023 | 8.8 | 11000 | 1.5614 | 26.9854 |
|
| 69 |
+
| 0.0043 | 9.6 | 12000 | 1.5679 | 26.9480 |
|
| 70 |
+
| 0.0027 | 10.4 | 13000 | 1.5807 | 26.9257 |
|
| 71 |
+
| 0.0024 | 11.2 | 14000 | 1.5903 | 26.1460 |
|
| 72 |
+
| 0.0028 | 12.0 | 15000 | 1.5812 | 30.4265 |
|
| 73 |
+
| 0.0043 | 12.8 | 16000 | 1.5962 | 28.9115 |
|
| 74 |
+
| 0.0019 | 13.6 | 17000 | 1.5915 | 28.0895 |
|
| 75 |
+
| 0.0066 | 14.4 | 18000 | 1.6038 | 27.1283 |
|
| 76 |
+
| 0.0052 | 15.2 | 19000 | 1.6088 | 27.0370 |
|
| 77 |
+
| 0.0015 | 16.0 | 20000 | 1.6055 | 26.7782 |
|
| 78 |
+
| 0.0076 | 16.8 | 21000 | 1.6063 | 26.5745 |
|
| 79 |
+
| 0.0074 | 17.6 | 22000 | 1.5864 | 26.1214 |
|
| 80 |
+
| 0.0009 | 18.4 | 23000 | 1.6042 | 28.1539 |
|
| 81 |
+
| 0.0025 | 19.2 | 24000 | 1.6047 | 27.0206 |
|
| 82 |
+
| 0.0041 | 20.0 | 25000 | 1.6130 | 26.9737 |
|
| 83 |
+
| 0.0031 | 20.8 | 26000 | 1.6087 | 28.4068 |
|
| 84 |
+
| 0.0014 | 21.6 | 27000 | 1.5997 | 27.6739 |
|
| 85 |
+
| 0.0003 | 22.4 | 28000 | 1.6045 | 26.3309 |
|
| 86 |
+
| 0.006 | 23.2 | 29000 | 1.6061 | 27.3074 |
|
| 87 |
+
| 0.0031 | 24.0 | 30000 | 1.6221 | 29.8739 |
|
| 88 |
+
| 0.0015 | 24.8 | 31000 | 1.6350 | 27.4784 |
|
| 89 |
+
| 0.0028 | 25.6 | 32000 | 1.6271 | 26.8274 |
|
| 90 |
+
| 0.0015 | 26.4 | 33000 | 1.6386 | 28.1504 |
|
| 91 |
+
| 0.0007 | 27.2 | 34000 | 1.6262 | 26.5054 |
|
| 92 |
+
| 0.0035 | 28.0 | 35000 | 1.6441 | 30.8761 |
|
| 93 |
+
| 0.0029 | 28.8 | 36000 | 1.6650 | 27.3988 |
|
| 94 |
+
| 0.0014 | 29.6 | 37000 | 1.6366 | 27.2957 |
|
| 95 |
+
| 0.0051 | 30.4 | 38000 | 1.6433 | 26.0230 |
|
| 96 |
+
| 0.0007 | 31.2 | 39000 | 1.6476 | 27.1224 |
|
| 97 |
+
| 0.0042 | 32.0 | 40000 | 1.6526 | 27.3367 |
|
| 98 |
+
| 0.001 | 32.8 | 41000 | 1.6606 | 26.5113 |
|
| 99 |
+
| 0.0005 | 33.6 | 42000 | 1.6455 | 28.5239 |
|
| 100 |
+
| 0.0064 | 34.4 | 43000 | 1.6537 | 28.2324 |
|
| 101 |
+
| 0.0005 | 35.2 | 44000 | 1.6589 | 26.0980 |
|
| 102 |
+
| 0.0035 | 36.0 | 45000 | 1.6617 | 26.6412 |
|
| 103 |
+
| 0.0014 | 36.8 | 46000 | 1.6698 | 27.2606 |
|
| 104 |
+
| 0.0007 | 37.6 | 47000 | 1.6751 | 26.9726 |
|
| 105 |
+
| 0.0036 | 38.4 | 48000 | 1.6790 | 26.9620 |
|
| 106 |
+
| 0.0049 | 39.2 | 49000 | 1.6914 | 26.9222 |
|
| 107 |
+
| 0.002 | 40.0 | 50000 | 1.7004 | 27.1728 |
|
| 108 |
+
| 0.0032 | 40.8 | 51000 | 1.7019 | 26.6096 |
|
| 109 |
+
| 0.0012 | 41.6 | 52000 | 1.7076 | 27.5006 |
|
| 110 |
+
| 0.0004 | 42.4 | 53000 | 1.7054 | 26.6553 |
|
| 111 |
+
| 0.0029 | 43.2 | 54000 | 1.6880 | 27.3952 |
|
| 112 |
+
| 0.0013 | 44.0 | 55000 | 1.6983 | 27.7722 |
|
| 113 |
+
| 0.0021 | 44.8 | 56000 | 1.7000 | 28.0275 |
|
| 114 |
+
| 0.0007 | 45.6 | 57000 | 1.6831 | 27.9268 |
|
| 115 |
+
| 0.0007 | 46.4 | 58000 | 1.6989 | 26.1284 |
|
| 116 |
+
| 0.0025 | 47.2 | 59000 | 1.6858 | 27.2372 |
|
| 117 |
+
| 0.0003 | 48.0 | 60000 | 1.7004 | 29.3213 |
|
| 118 |
+
| 0.0011 | 48.8 | 61000 | 1.7122 | 26.9433 |
|
| 119 |
+
| 0.0017 | 49.6 | 62000 | 1.7014 | 25.8474 |
|
| 120 |
+
| 0.0023 | 50.4 | 63000 | 1.7186 | 26.5546 |
|
| 121 |
+
| 0.0031 | 51.2 | 64000 | 1.6963 | 27.2735 |
|
| 122 |
+
| 0.0023 | 52.0 | 65000 | 1.7043 | 26.9117 |
|
| 123 |
+
| 0.0004 | 52.8 | 66000 | 1.7068 | 26.3064 |
|
| 124 |
+
| 0.0003 | 53.6 | 67000 | 1.7196 | 27.1517 |
|
| 125 |
+
| 0.0012 | 54.4 | 68000 | 1.7213 | 26.9737 |
|
| 126 |
+
| 0.0013 | 55.2 | 69000 | 1.7114 | 26.5347 |
|
| 127 |
+
| 0.0007 | 56.0 | 70000 | 1.7245 | 28.1001 |
|
| 128 |
+
| 0.0002 | 56.8 | 71000 | 1.7138 | 27.8788 |
|
| 129 |
+
| 0.0001 | 57.6 | 72000 | 1.7182 | 27.3543 |
|
| 130 |
+
| 0.0009 | 58.4 | 73000 | 1.7354 | 28.0942 |
|
| 131 |
+
| 0.0023 | 59.2 | 74000 | 1.7314 | 27.0077 |
|
| 132 |
+
| 0.0013 | 60.0 | 75000 | 1.7350 | 28.0439 |
|
| 133 |
+
| 0.0019 | 60.8 | 76000 | 1.7322 | 27.7512 |
|
| 134 |
+
| 0.0025 | 61.6 | 77000 | 1.7620 | 27.5978 |
|
| 135 |
+
| 0.0005 | 62.4 | 78000 | 1.7201 | 27.7102 |
|
| 136 |
+
| 0.0043 | 63.2 | 79000 | 1.7405 | 27.8565 |
|
| 137 |
+
| 0.0006 | 64.0 | 80000 | 1.7550 | 29.4407 |
|
| 138 |
+
| 0.0004 | 64.8 | 81000 | 1.7410 | 27.6189 |
|
| 139 |
+
| 0.0002 | 65.6 | 82000 | 1.7312 | 29.3189 |
|
| 140 |
+
| 0.0006 | 66.4 | 83000 | 1.7476 | 26.5312 |
|
| 141 |
+
| 0.0033 | 67.2 | 84000 | 1.7571 | 26.8098 |
|
| 142 |
+
| 0.0041 | 68.0 | 85000 | 1.7463 | 27.2512 |
|
| 143 |
+
| 0.0014 | 68.8 | 86000 | 1.7401 | 26.3485 |
|
| 144 |
+
| 0.0001 | 69.6 | 87000 | 1.7465 | 27.6622 |
|
| 145 |
+
| 0.0011 | 70.4 | 88000 | 1.7494 | 26.9468 |
|
| 146 |
+
| 0.0001 | 71.2 | 89000 | 1.7423 | 28.5684 |
|
| 147 |
+
| 0.0037 | 72.0 | 90000 | 1.7728 | 29.7896 |
|
| 148 |
+
| 0.0002 | 72.8 | 91000 | 1.7555 | 26.9140 |
|
| 149 |
+
| 0.0006 | 73.6 | 92000 | 1.7685 | 26.7606 |
|
| 150 |
+
| 0.0014 | 74.4 | 93000 | 1.7494 | 26.8204 |
|
| 151 |
+
| 0.001 | 75.2 | 94000 | 1.7719 | 26.7150 |
|
| 152 |
+
| 0.0005 | 76.0 | 95000 | 1.7754 | 26.6892 |
|
| 153 |
+
| 0.0022 | 76.8 | 96000 | 1.7698 | 27.4807 |
|
| 154 |
+
| 0.0017 | 77.6 | 97000 | 1.7830 | 27.7465 |
|
| 155 |
+
| 0.0001 | 78.4 | 98000 | 1.7751 | 27.0487 |
|
| 156 |
+
| 0.0025 | 79.2 | 99000 | 1.7768 | 27.1505 |
|
| 157 |
+
| 0.0001 | 80.0 | 100000 | 1.7671 | 27.2805 |
|
| 158 |
+
| 0.0019 | 80.8 | 101000 | 1.7910 | 27.3027 |
|
| 159 |
+
| 0.0031 | 81.6 | 102000 | 1.7965 | 27.6809 |
|
| 160 |
+
| 0.0016 | 82.4 | 103000 | 1.7893 | 28.0146 |
|
| 161 |
+
| 0.0002 | 83.2 | 104000 | 1.7939 | 26.7384 |
|
| 162 |
+
| 0.0001 | 84.0 | 105000 | 1.7925 | 27.3156 |
|
| 163 |
+
| 0.0001 | 84.8 | 106000 | 1.7866 | 27.8718 |
|
| 164 |
+
| 0.0001 | 85.6 | 107000 | 1.7789 | 27.0171 |
|
| 165 |
+
| 0.0001 | 86.4 | 108000 | 1.7738 | 26.3977 |
|
| 166 |
+
| 0.0005 | 87.2 | 109000 | 1.7748 | 27.8577 |
|
| 167 |
+
| 0.0015 | 88.0 | 110000 | 1.7922 | 26.6611 |
|
| 168 |
+
| 0.0003 | 88.8 | 111000 | 1.7987 | 28.0486 |
|
| 169 |
+
| 0.0017 | 89.6 | 112000 | 1.7901 | 28.0860 |
|
| 170 |
+
| 0.0001 | 90.4 | 113000 | 1.8013 | 27.7523 |
|
| 171 |
+
| 0.0001 | 91.2 | 114000 | 1.8045 | 26.9796 |
|
| 172 |
+
| 0.0005 | 92.0 | 115000 | 1.7989 | 27.0112 |
|
| 173 |
+
| 0.0024 | 92.8 | 116000 | 1.8068 | 26.9597 |
|
| 174 |
+
| 0.0001 | 93.6 | 117000 | 1.8033 | 29.2651 |
|
| 175 |
+
| 0.0001 | 94.4 | 118000 | 1.7955 | 28.6984 |
|
| 176 |
+
| 0.0004 | 95.2 | 119000 | 1.7956 | 27.0920 |
|
| 177 |
+
| 0.0005 | 96.0 | 120000 | 1.7868 | 27.3426 |
|
| 178 |
+
| 0.0011 | 96.8 | 121000 | 1.8209 | 26.8005 |
|
| 179 |
+
| 0.0005 | 97.6 | 122000 | 1.8152 | 29.9816 |
|
| 180 |
+
| 0.002 | 98.4 | 123000 | 1.8174 | 26.7255 |
|
| 181 |
+
| 0.0001 | 99.2 | 124000 | 1.8194 | 26.9164 |
|
| 182 |
+
| 0.0004 | 100.0 | 125000 | 1.8307 | 27.7289 |
|
| 183 |
+
| 0.0001 | 100.8 | 126000 | 1.8151 | 26.9609 |
|
| 184 |
+
| 0.0001 | 101.6 | 127000 | 1.8080 | 28.0158 |
|
| 185 |
+
| 0.0001 | 102.4 | 128000 | 1.8349 | 26.7571 |
|
| 186 |
+
| 0.0002 | 103.2 | 129000 | 1.8371 | 27.0686 |
|
| 187 |
+
| 0.0006 | 104.0 | 130000 | 1.8133 | 27.4842 |
|
| 188 |
+
| 0.0001 | 104.8 | 131000 | 1.8246 | 26.5768 |
|
| 189 |
+
| 0.0005 | 105.6 | 132000 | 1.8180 | 26.7489 |
|
| 190 |
+
| 0.0001 | 106.4 | 133000 | 1.8261 | 27.4409 |
|
| 191 |
+
| 0.0001 | 107.2 | 134000 | 1.8101 | 26.7443 |
|
| 192 |
+
| 0.0003 | 108.0 | 135000 | 1.8164 | 27.3800 |
|
| 193 |
+
| 0.0001 | 108.8 | 136000 | 1.8152 | 26.9679 |
|
| 194 |
+
| 0.0001 | 109.6 | 137000 | 1.8121 | 26.6775 |
|
| 195 |
+
| 0.0001 | 110.4 | 138000 | 1.8317 | 27.7968 |
|
| 196 |
+
| 0.0 | 111.2 | 139000 | 1.8266 | 26.6869 |
|
| 197 |
+
| 0.0001 | 112.0 | 140000 | 1.8331 | 27.2067 |
|
| 198 |
+
| 0.0045 | 112.8 | 141000 | 1.8353 | 27.0276 |
|
| 199 |
+
| 0.0024 | 113.6 | 142000 | 1.8416 | 28.0345 |
|
| 200 |
+
| 0.0005 | 114.4 | 143000 | 1.8359 | 27.8460 |
|
| 201 |
+
| 0.0 | 115.2 | 144000 | 1.8390 | 27.1892 |
|
| 202 |
+
| 0.0 | 116.0 | 145000 | 1.8311 | 27.2934 |
|
| 203 |
+
| 0.0 | 116.8 | 146000 | 1.8473 | 27.4386 |
|
| 204 |
+
| 0.0016 | 117.6 | 147000 | 1.8554 | 27.3964 |
|
| 205 |
+
| 0.0001 | 118.4 | 148000 | 1.8608 | 26.5148 |
|
| 206 |
+
| 0.0021 | 119.2 | 149000 | 1.8582 | 26.9058 |
|
| 207 |
+
| 0.0003 | 120.0 | 150000 | 1.8574 | 26.9269 |
|
| 208 |
+
| 0.0002 | 120.8 | 151000 | 1.8568 | 27.2079 |
|
| 209 |
+
| 0.0 | 121.6 | 152000 | 1.8623 | 26.5417 |
|
| 210 |
+
| 0.0001 | 122.4 | 153000 | 1.8500 | 27.2009 |
|
| 211 |
+
| 0.0 | 123.2 | 154000 | 1.8604 | 27.6236 |
|
| 212 |
+
| 0.0 | 124.0 | 155000 | 1.8739 | 27.8203 |
|
| 213 |
+
| 0.0001 | 124.8 | 156000 | 1.8705 | 26.8215 |
|
| 214 |
+
| 0.0 | 125.6 | 157000 | 1.8521 | 27.1283 |
|
| 215 |
+
| 0.0 | 126.4 | 158000 | 1.8607 | 26.5241 |
|
| 216 |
+
| 0.0 | 127.2 | 159000 | 1.8646 | 27.1423 |
|
| 217 |
+
| 0.0001 | 128.0 | 160000 | 1.8665 | 26.9538 |
|
| 218 |
+
| 0.0002 | 128.8 | 161000 | 1.8768 | 26.7841 |
|
| 219 |
+
| 0.0002 | 129.6 | 162000 | 1.8722 | 26.7864 |
|
| 220 |
+
| 0.0005 | 130.4 | 163000 | 1.8626 | 27.3695 |
|
| 221 |
+
| 0.0 | 131.2 | 164000 | 1.8646 | 27.8425 |
|
| 222 |
+
| 0.0 | 132.0 | 165000 | 1.8758 | 27.8062 |
|
| 223 |
+
| 0.0002 | 132.8 | 166000 | 1.8780 | 28.5110 |
|
| 224 |
+
| 0.0 | 133.6 | 167000 | 1.8672 | 26.1319 |
|
| 225 |
+
| 0.0 | 134.4 | 168000 | 1.8833 | 26.4422 |
|
| 226 |
+
| 0.0009 | 135.2 | 169000 | 1.8828 | 27.4421 |
|
| 227 |
+
| 0.0 | 136.0 | 170000 | 1.8933 | 27.2243 |
|
| 228 |
+
| 0.0001 | 136.8 | 171000 | 1.8913 | 27.2302 |
|
| 229 |
+
| 0.0 | 137.6 | 172000 | 1.8941 | 27.2746 |
|
| 230 |
+
| 0.0001 | 138.4 | 173000 | 1.8873 | 26.5089 |
|
| 231 |
+
| 0.0004 | 139.2 | 174000 | 1.8966 | 26.7969 |
|
| 232 |
+
| 0.0 | 140.0 | 175000 | 1.8916 | 26.6611 |
|
| 233 |
+
| 0.0 | 140.8 | 176000 | 1.8890 | 26.4199 |
|
| 234 |
+
| 0.0 | 141.6 | 177000 | 1.8991 | 28.7066 |
|
| 235 |
+
| 0.0 | 142.4 | 178000 | 1.8963 | 27.2021 |
|
| 236 |
+
| 0.0 | 143.2 | 179000 | 1.8996 | 27.7231 |
|
| 237 |
+
| 0.0001 | 144.0 | 180000 | 1.9000 | 28.4513 |
|
| 238 |
+
| 0.0 | 144.8 | 181000 | 1.9029 | 27.0428 |
|
| 239 |
+
| 0.0 | 145.6 | 182000 | 1.9119 | 27.1540 |
|
| 240 |
+
| 0.0 | 146.4 | 183000 | 1.8947 | 26.8684 |
|
| 241 |
+
| 0.0 | 147.2 | 184000 | 1.9096 | 27.1131 |
|
| 242 |
+
| 0.0 | 148.0 | 185000 | 1.9065 | 25.9961 |
|
| 243 |
+
| 0.0 | 148.8 | 186000 | 1.9112 | 27.3004 |
|
| 244 |
+
| 0.0013 | 149.6 | 187000 | 1.9016 | 27.0182 |
|
| 245 |
+
| 0.0 | 150.4 | 188000 | 1.9075 | 26.8637 |
|
| 246 |
+
| 0.0 | 151.2 | 189000 | 1.9189 | 27.3016 |
|
| 247 |
+
| 0.0 | 152.0 | 190000 | 1.9179 | 28.9431 |
|
| 248 |
+
| 0.0 | 152.8 | 191000 | 1.9277 | 27.1283 |
|
| 249 |
+
| 0.0 | 153.6 | 192000 | 1.9123 | 27.5463 |
|
| 250 |
+
| 0.0001 | 154.4 | 193000 | 1.9066 | 26.6459 |
|
| 251 |
+
| 0.0002 | 155.2 | 194000 | 1.9222 | 26.8168 |
|
| 252 |
+
| 0.0 | 156.0 | 195000 | 1.9263 | 27.1435 |
|
| 253 |
+
| 0.0 | 156.8 | 196000 | 1.9363 | 26.9187 |
|
| 254 |
+
| 0.0 | 157.6 | 197000 | 1.9299 | 26.0546 |
|
| 255 |
+
| 0.0 | 158.4 | 198000 | 1.9429 | 27.1704 |
|
| 256 |
+
| 0.0014 | 159.2 | 199000 | 1.9413 | 26.4609 |
|
| 257 |
+
| 0.0 | 160.0 | 200000 | 1.9294 | 26.8567 |
|
| 258 |
+
| 0.0 | 160.8 | 201000 | 1.9351 | 27.6727 |
|
| 259 |
+
| 0.0 | 161.6 | 202000 | 1.9396 | 26.8297 |
|
| 260 |
+
| 0.0 | 162.4 | 203000 | 1.9388 | 26.9292 |
|
| 261 |
+
| 0.0 | 163.2 | 204000 | 1.9436 | 26.8531 |
|
| 262 |
+
| 0.0 | 164.0 | 205000 | 1.9439 | 27.5486 |
|
| 263 |
+
| 0.0 | 164.8 | 206000 | 1.9380 | 27.5252 |
|
| 264 |
+
| 0.0 | 165.6 | 207000 | 1.9396 | 26.4843 |
|
| 265 |
+
| 0.0 | 166.4 | 208000 | 1.9379 | 26.1846 |
|
| 266 |
+
| 0.0011 | 167.2 | 209000 | 1.9598 | 27.2407 |
|
| 267 |
+
| 0.0 | 168.0 | 210000 | 1.9474 | 26.6834 |
|
| 268 |
+
| 0.0 | 168.8 | 211000 | 1.9509 | 27.3367 |
|
| 269 |
+
| 0.0 | 169.6 | 212000 | 1.9567 | 27.4948 |
|
| 270 |
+
| 0.0 | 170.4 | 213000 | 1.9584 | 27.3671 |
|
| 271 |
+
| 0.0009 | 171.2 | 214000 | 1.9578 | 26.8168 |
|
| 272 |
+
| 0.0 | 172.0 | 215000 | 1.9477 | 27.9362 |
|
| 273 |
+
| 0.0007 | 172.8 | 216000 | 1.9651 | 27.3484 |
|
| 274 |
+
| 0.0 | 173.6 | 217000 | 1.9491 | 26.4515 |
|
| 275 |
+
| 0.0 | 174.4 | 218000 | 1.9434 | 27.3507 |
|
| 276 |
+
| 0.0001 | 175.2 | 219000 | 1.9572 | 27.3133 |
|
| 277 |
+
| 0.0 | 176.0 | 220000 | 1.9570 | 27.3812 |
|
| 278 |
+
| 0.0 | 176.8 | 221000 | 1.9577 | 27.4339 |
|
| 279 |
+
| 0.0 | 177.6 | 222000 | 1.9655 | 27.4924 |
|
| 280 |
+
| 0.0 | 178.4 | 223000 | 1.9625 | 27.2021 |
|
| 281 |
+
| 0.0 | 179.2 | 224000 | 1.9601 | 27.0346 |
|
| 282 |
+
| 0.0 | 180.0 | 225000 | 1.9703 | 26.8988 |
|
| 283 |
+
| 0.0 | 180.8 | 226000 | 1.9747 | 26.4539 |
|
| 284 |
+
| 0.0 | 181.6 | 227000 | 1.9728 | 26.4106 |
|
| 285 |
+
| 0.0 | 182.4 | 228000 | 1.9776 | 27.2372 |
|
| 286 |
+
| 0.0 | 183.2 | 229000 | 1.9866 | 26.7969 |
|
| 287 |
+
| 0.0 | 184.0 | 230000 | 1.9857 | 26.9164 |
|
| 288 |
+
| 0.0 | 184.8 | 231000 | 1.9847 | 26.5113 |
|
| 289 |
+
| 0.0 | 185.6 | 232000 | 1.9850 | 27.0897 |
|
| 290 |
+
| 0.0004 | 186.4 | 233000 | 1.9967 | 27.4749 |
|
| 291 |
+
| 0.0 | 187.2 | 234000 | 1.9906 | 26.5464 |
|
| 292 |
+
| 0.0 | 188.0 | 235000 | 2.0016 | 27.7336 |
|
| 293 |
+
| 0.0 | 188.8 | 236000 | 2.0036 | 26.6775 |
|
| 294 |
+
| 0.0 | 189.6 | 237000 | 1.9978 | 26.6119 |
|
| 295 |
+
| 0.0 | 190.4 | 238000 | 1.9968 | 27.2711 |
|
| 296 |
+
| 0.0 | 191.2 | 239000 | 1.9970 | 26.6319 |
|
| 297 |
+
| 0.0 | 192.0 | 240000 | 1.9969 | 26.8812 |
|
| 298 |
+
| 0.0 | 192.8 | 241000 | 2.0076 | 27.1201 |
|
| 299 |
+
| 0.0 | 193.6 | 242000 | 2.0073 | 26.4644 |
|
| 300 |
+
| 0.0 | 194.4 | 243000 | 2.0097 | 26.0371 |
|
| 301 |
+
| 0.0 | 195.2 | 244000 | 2.0108 | 25.8544 |
|
| 302 |
+
| 0.0 | 196.0 | 245000 | 2.0138 | 26.1998 |
|
| 303 |
+
| 0.0 | 196.8 | 246000 | 2.0177 | 26.4761 |
|
| 304 |
+
| 0.0 | 197.6 | 247000 | 2.0226 | 26.4925 |
|
| 305 |
+
| 0.0 | 198.4 | 248000 | 2.0277 | 27.0194 |
|
| 306 |
+
| 0.0 | 199.2 | 249000 | 2.0331 | 26.4059 |
|
| 307 |
+
| 0.0 | 200.0 | 250000 | 2.0388 | 26.0980 |
|
| 308 |
+
| 0.0 | 200.8 | 251000 | 2.0451 | 26.4562 |
|
| 309 |
+
| 0.0 | 201.6 | 252000 | 2.0527 | 26.1085 |
|
| 310 |
+
| 0.0 | 202.4 | 253000 | 2.0578 | 26.6529 |
|
| 311 |
+
| 0.0 | 203.2 | 254000 | 2.0631 | 26.5195 |
|
| 312 |
+
| 0.0 | 204.0 | 255000 | 2.0665 | 26.2314 |
|
| 313 |
+
| 0.0 | 204.8 | 256000 | 2.0711 | 26.5312 |
|
| 314 |
+
| 0.0 | 205.6 | 257000 | 2.0749 | 26.7021 |
|
| 315 |
+
| 0.0 | 206.4 | 258000 | 2.0747 | 26.2525 |
|
| 316 |
+
| 0.0 | 207.2 | 259000 | 2.0755 | 26.0277 |
|
| 317 |
+
| 0.0 | 208.0 | 260000 | 2.0746 | 25.9457 |
|
| 318 |
+
| 0.0 | 208.8 | 261000 | 2.0739 | 25.8404 |
|
| 319 |
+
| 0.0 | 209.6 | 262000 | 2.0720 | 25.7151 |
|
| 320 |
+
| 0.0 | 210.4 | 263000 | 2.0695 | 25.7151 |
|
| 321 |
+
| 0.0 | 211.2 | 264000 | 2.0669 | 25.6156 |
|
| 322 |
+
| 0.0 | 212.0 | 265000 | 2.0652 | 25.9130 |
|
| 323 |
+
| 0.0 | 212.8 | 266000 | 2.0625 | 25.7795 |
|
| 324 |
+
| 0.0 | 213.6 | 267000 | 2.0598 | 26.0827 |
|
| 325 |
+
| 0.0 | 214.4 | 268000 | 2.0576 | 25.6928 |
|
| 326 |
+
| 0.0 | 215.2 | 269000 | 2.0546 | 26.0628 |
|
| 327 |
+
| 0.0 | 216.0 | 270000 | 2.0530 | 25.6472 |
|
| 328 |
+
| 0.0 | 216.8 | 271000 | 2.0506 | 25.8076 |
|
| 329 |
+
| 0.0 | 217.6 | 272000 | 2.0476 | 25.9200 |
|
| 330 |
+
| 0.0 | 218.4 | 273000 | 2.0452 | 26.2595 |
|
| 331 |
+
| 0.0 | 219.2 | 274000 | 2.0437 | 26.0816 |
|
| 332 |
+
| 0.0 | 220.0 | 275000 | 2.0422 | 26.0382 |
|
| 333 |
+
| 0.0 | 220.8 | 276000 | 2.0401 | 26.0078 |
|
| 334 |
+
| 0.0 | 221.6 | 277000 | 2.0380 | 26.5440 |
|
| 335 |
+
| 0.0 | 222.4 | 278000 | 2.0358 | 26.1401 |
|
| 336 |
+
| 0.0 | 223.2 | 279000 | 2.0347 | 26.5487 |
|
| 337 |
+
| 0.0 | 224.0 | 280000 | 2.0334 | 26.1623 |
|
| 338 |
+
| 0.0 | 224.8 | 281000 | 2.0321 | 26.3743 |
|
| 339 |
+
| 0.0 | 225.6 | 282000 | 2.0303 | 26.2630 |
|
| 340 |
+
| 0.0 | 226.4 | 283000 | 2.0290 | 26.5604 |
|
| 341 |
+
| 0.0 | 227.2 | 284000 | 2.0280 | 26.7618 |
|
| 342 |
+
| 0.0 | 228.0 | 285000 | 2.0269 | 26.8859 |
|
| 343 |
+
| 0.0 | 228.8 | 286000 | 2.0256 | 26.7279 |
|
| 344 |
+
| 0.0 | 229.6 | 287000 | 2.0243 | 26.3871 |
|
| 345 |
+
| 0.0 | 230.4 | 288000 | 2.0238 | 26.6049 |
|
| 346 |
+
| 0.0 | 231.2 | 289000 | 2.0223 | 26.5452 |
|
| 347 |
+
| 0.0 | 232.0 | 290000 | 2.0222 | 26.4761 |
|
| 348 |
+
| 0.0 | 232.8 | 291000 | 2.0215 | 26.3497 |
|
| 349 |
+
| 0.0 | 233.6 | 292000 | 2.0206 | 26.4024 |
|
| 350 |
+
| 0.0 | 234.4 | 293000 | 2.0202 | 26.7899 |
|
| 351 |
+
| 0.0 | 235.2 | 294000 | 2.0196 | 26.8051 |
|
| 352 |
+
| 0.0 | 236.0 | 295000 | 2.0192 | 26.7466 |
|
| 353 |
+
| 0.0 | 236.8 | 296000 | 2.0187 | 26.5686 |
|
| 354 |
+
| 0.0 | 237.6 | 297000 | 2.0185 | 26.5956 |
|
| 355 |
+
| 0.0 | 238.4 | 298000 | 2.0183 | 26.2747 |
|
| 356 |
+
| 0.0 | 239.2 | 299000 | 2.0182 | 26.5253 |
|
| 357 |
+
| 0.0 | 240.0 | 300000 | 2.0181 | 26.4902 |
|
| 358 |
|
| 359 |
|
| 360 |
### Framework versions
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 290403936
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c99a66092ded50a85d8bf0d777ef26af03f452c6e9053b95409a0eb4f433fa28
|
| 3 |
size 290403936
|
runs/Nov30_11-41-09_DESKTOP-BCLBGEN/events.out.tfevents.1732934490.DESKTOP-BCLBGEN
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6cce9ec35dbb1dd2cf31ad462a40fac40c2a59ee225610e6a85e546f387cdb9
|
| 3 |
+
size 2680527
|