Update README.md
Browse files
README.md
CHANGED
|
@@ -15,4 +15,34 @@ Hello world!<|im_end|>
|
|
| 15 |
|
| 16 |
## Model Description
|
| 17 |
|
| 18 |
-
More information needed
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
## Model Description
|
| 17 |
|
| 18 |
+
More information needed
|
| 19 |
+
|
| 20 |
+
## Training procedure
|
| 21 |
+
|
| 22 |
+
### Training hyperparameters
|
| 23 |
+
|
| 24 |
+
The following hyperparameters were used during training:
|
| 25 |
+
- learning_rate: 2e-06
|
| 26 |
+
- train_batch_size: 2
|
| 27 |
+
- eval_batch_size: 2
|
| 28 |
+
- seed: 42
|
| 29 |
+
- distributed_type: multi-GPU
|
| 30 |
+
- num_devices: 4
|
| 31 |
+
- gradient_accumulation_steps: 4
|
| 32 |
+
- total_train_batch_size: 32
|
| 33 |
+
- total_eval_batch_size: 8
|
| 34 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 35 |
+
- lr_scheduler_type: cosine
|
| 36 |
+
- lr_scheduler_warmup_steps: 100
|
| 37 |
+
- num_epochs: 1
|
| 38 |
+
|
| 39 |
+
### Training results
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
### Framework versions
|
| 44 |
+
|
| 45 |
+
- Transformers 4.34.1
|
| 46 |
+
- Pytorch 2.0.1+cu118
|
| 47 |
+
- Datasets 2.14.6
|
| 48 |
+
- Tokenizers 0.14.1
|