End of training
Browse files
README.md
CHANGED
|
@@ -44,7 +44,7 @@ The following hyperparameters were used during training:
|
|
| 44 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_steps: 1000
|
| 47 |
-
- training_steps:
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
### Training results
|
|
@@ -66,6 +66,21 @@ The following hyperparameters were used during training:
|
|
| 66 |
| 3.0465 | 0.4622 | 13000 | nan |
|
| 67 |
| 3.0446 | 0.4978 | 14000 | nan |
|
| 68 |
| 3.0422 | 0.5333 | 15000 | nan |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 69 |
|
| 70 |
|
| 71 |
### Framework versions
|
|
|
|
| 44 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_steps: 1000
|
| 47 |
+
- training_steps: 30000
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
### Training results
|
|
|
|
| 66 |
| 3.0465 | 0.4622 | 13000 | nan |
|
| 67 |
| 3.0446 | 0.4978 | 14000 | nan |
|
| 68 |
| 3.0422 | 0.5333 | 15000 | nan |
|
| 69 |
+
| 3.0986 | 0.5689 | 16000 | nan |
|
| 70 |
+
| 3.1074 | 0.6044 | 17000 | nan |
|
| 71 |
+
| 3.1088 | 0.64 | 18000 | nan |
|
| 72 |
+
| 3.0854 | 0.6756 | 19000 | nan |
|
| 73 |
+
| 3.0752 | 0.7111 | 20000 | nan |
|
| 74 |
+
| 3.065 | 0.7467 | 21000 | nan |
|
| 75 |
+
| 3.0527 | 0.7822 | 22000 | nan |
|
| 76 |
+
| 3.0428 | 0.8178 | 23000 | nan |
|
| 77 |
+
| 3.0357 | 0.8533 | 24000 | nan |
|
| 78 |
+
| 3.0295 | 0.8889 | 25000 | nan |
|
| 79 |
+
| 3.0149 | 0.9244 | 26000 | nan |
|
| 80 |
+
| 3.0146 | 0.96 | 27000 | nan |
|
| 81 |
+
| 3.0148 | 0.9956 | 28000 | nan |
|
| 82 |
+
| 2.9621 | 1.0311 | 29000 | nan |
|
| 83 |
+
| 2.9542 | 1.0667 | 30000 | nan |
|
| 84 |
|
| 85 |
|
| 86 |
### Framework versions
|