End of training
Browse files
README.md
CHANGED
|
@@ -37,9 +37,11 @@ More information needed
|
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
- learning_rate: 0.0005
|
| 40 |
-
- train_batch_size:
|
| 41 |
-
- eval_batch_size:
|
| 42 |
- seed: 42
|
|
|
|
|
|
|
| 43 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 44 |
- lr_scheduler_type: cosine
|
| 45 |
- lr_scheduler_warmup_steps: 30
|
|
@@ -52,7 +54,7 @@ The following hyperparameters were used during training:
|
|
| 52 |
### Framework versions
|
| 53 |
|
| 54 |
- PEFT 0.17.1
|
| 55 |
-
- Transformers 4.56.
|
| 56 |
- Pytorch 2.8.0+cu126
|
| 57 |
- Datasets 4.0.0
|
| 58 |
- Tokenizers 0.22.0
|
|
|
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
- learning_rate: 0.0005
|
| 40 |
+
- train_batch_size: 1
|
| 41 |
+
- eval_batch_size: 1
|
| 42 |
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 16
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
- lr_scheduler_type: cosine
|
| 47 |
- lr_scheduler_warmup_steps: 30
|
|
|
|
| 54 |
### Framework versions
|
| 55 |
|
| 56 |
- PEFT 0.17.1
|
| 57 |
+
- Transformers 4.56.1
|
| 58 |
- Pytorch 2.8.0+cu126
|
| 59 |
- Datasets 4.0.0
|
| 60 |
- Tokenizers 0.22.0
|