model checkpoint updated
Browse files- README.md +1 -1
- pytorch_model.bin +1 -1
README.md
CHANGED
|
@@ -61,7 +61,7 @@ The following hyperparameters were used during training:
|
|
| 61 |
- optimizer: adamw_bnb_8bit
|
| 62 |
- lr_scheduler_type: linear
|
| 63 |
- lr_scheduler_warmup_steps: 17500
|
| 64 |
-
- training_steps:
|
| 65 |
- mixed_precision_training: True
|
| 66 |
|
| 67 |
## Acknowledgement
|
|
|
|
| 61 |
- optimizer: adamw_bnb_8bit
|
| 62 |
- lr_scheduler_type: linear
|
| 63 |
- lr_scheduler_warmup_steps: 17500
|
| 64 |
+
- training_steps: 33892 (Initially set to 84730 steps)
|
| 65 |
- mixed_precision_training: True
|
| 66 |
|
| 67 |
## Acknowledgement
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3055748571
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e54e23c21b0d61d6256fe8bc6f772f103dbc883743733d5f181894a560f81e0d
|
| 3 |
size 3055748571
|