Commit
•
7985f9f
1
Parent(s):
3f9f66d
Update README.md
Browse files
README.md
CHANGED
|
@@ -11,7 +11,12 @@ tags:
|
|
| 11 |
- trl
|
| 12 |
- dpo
|
| 13 |
---
|
| 14 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
# Uploaded model
|
| 16 |
|
| 17 |
- **Developed by:** sonthenguyen
|
|
|
|
| 11 |
- trl
|
| 12 |
- dpo
|
| 13 |
---
|
| 14 |
+
TrainOutput(global_step=252, training_loss=0.0682461416144461, metrics={'train_runtime': 2060.2317, 'train_samples_per_second': 1.953, 'train_steps_per_second': 0.122, 'total_flos': 0.0, 'train_loss': 0.0682461416144461, 'epoch': 0.5009940357852882})
|
| 15 |
+
==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1
|
| 16 |
+
\\ /| Num examples = 8,046 | Num Epochs = 1
|
| 17 |
+
O^O/ \_/ \ Batch size per device = 4 | Gradient Accumulation steps = 4
|
| 18 |
+
\ / Total batch size = 16 | Total steps = 252
|
| 19 |
+
"-____-" Number of trainable parameters = 41,943,040
|
| 20 |
# Uploaded model
|
| 21 |
|
| 22 |
- **Developed by:** sonthenguyen
|