End of training
Browse files- README.md +5 -5
- adapter.bam.safetensors +1 -1
README.md
CHANGED
|
@@ -33,16 +33,16 @@ More information needed
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
-
- learning_rate: 0.
|
| 37 |
- train_batch_size: 16
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
-
- gradient_accumulation_steps:
|
| 41 |
-
- total_train_batch_size:
|
| 42 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
-
- lr_scheduler_type:
|
| 44 |
- lr_scheduler_warmup_ratio: 0.1
|
| 45 |
-
- num_epochs:
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
### Training results
|
|
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 0.001
|
| 37 |
- train_batch_size: 16
|
| 38 |
- eval_batch_size: 8
|
| 39 |
- seed: 42
|
| 40 |
+
- gradient_accumulation_steps: 2
|
| 41 |
+
- total_train_batch_size: 32
|
| 42 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
+
- lr_scheduler_type: cosine
|
| 44 |
- lr_scheduler_warmup_ratio: 0.1
|
| 45 |
+
- num_epochs: 4
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
### Training results
|
adapter.bam.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8813904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:112505b001809d887d445f175e602cafc0be6243a8249f24ac52e7b3ad4371cd
|
| 3 |
size 8813904
|