DheerajNalapat
commited on
Commit
•
c1a9a79
1
Parent(s):
ef1e626
End of training
Browse files
README.md
CHANGED
@@ -41,7 +41,8 @@ The following hyperparameters were used during training:
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
-
- training_steps:
|
|
|
45 |
|
46 |
### Training results
|
47 |
|
@@ -51,6 +52,6 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
- PEFT 0.8.2
|
53 |
- Transformers 4.39.0.dev0
|
54 |
-
- Pytorch 2.
|
55 |
- Datasets 2.17.1
|
56 |
- Tokenizers 0.15.2
|
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: cosine
|
44 |
+
- training_steps: 750
|
45 |
+
- mixed_precision_training: Native AMP
|
46 |
|
47 |
### Training results
|
48 |
|
|
|
52 |
|
53 |
- PEFT 0.8.2
|
54 |
- Transformers 4.39.0.dev0
|
55 |
+
- Pytorch 2.2.0
|
56 |
- Datasets 2.17.1
|
57 |
- Tokenizers 0.15.2
|