Update README.md
Browse files
README.md
CHANGED
|
@@ -50,9 +50,12 @@ The following hyperparameters were used during training:
|
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
Training steps: 1025/1025; time- 2:45:21
|
| 53 |
-
|
| 54 |
-
|
|
| 55 |
-
|
|
|
|
|
|
|
|
|
|
|
| 56 |
TrainOutput(global_step=1025, training_loss=1.1994486794820647, metrics={'train_runtime': 9932.0844, 'train_samples_per_second': 1.652, 'train_steps_per_second': 0.103, 'total_flos': 3.2484758758785024e+16, 'train_loss': 1.1994486794820647, 'epoch': 1.0})
|
| 57 |
|
| 58 |
### Framework versions
|
|
|
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
Training steps: 1025/1025; time- 2:45:21
|
| 53 |
+
|
| 54 |
+
| Steps | Training_loss |
|
| 55 |
+
|-------|---------------|
|
| 56 |
+
| 500 | 1.273800 |
|
| 57 |
+
| 1000 | 1.133000 |
|
| 58 |
+
|
| 59 |
TrainOutput(global_step=1025, training_loss=1.1994486794820647, metrics={'train_runtime': 9932.0844, 'train_samples_per_second': 1.652, 'train_steps_per_second': 0.103, 'total_flos': 3.2484758758785024e+16, 'train_loss': 1.1994486794820647, 'epoch': 1.0})
|
| 60 |
|
| 61 |
### Framework versions
|