Hugging Face's logo

qazisaad
/
results

Generated from Trainer
Model card Files Community
qazisaad commited on
Commit
5237202
•
1 Parent(s): e030eef

End of training

Browse files
Files changed (2) hide show
  1. README.md +4 -4
  2. training_args.bin +1 -1
README.md CHANGED
@@ -32,11 +32,11 @@ More information needed
32
 
33
  The following hyperparameters were used during training:
34
  - learning_rate: 0.0002
35
- - train_batch_size: 5
36
- - eval_batch_size: 8
37
  - seed: 42
38
- - gradient_accumulation_steps: 10
39
- - total_train_batch_size: 50
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: constant
42
  - lr_scheduler_warmup_ratio: 0.03
 
32
 
33
  The following hyperparameters were used during training:
34
  - learning_rate: 0.0002
35
+ - train_batch_size: 10
36
+ - eval_batch_size: 10
37
  - seed: 42
38
+ - gradient_accumulation_steps: 4
39
+ - total_train_batch_size: 40
40
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
  - lr_scheduler_type: constant
42
  - lr_scheduler_warmup_ratio: 0.03
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a305511b474ab7b57a1edfb9a6b9dc884f408996f04d6f0996d5138346229cc
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ad36f9681797a132d980d5db2e3b8ef2da3383fa79821e0352d2c438b37e263
3
  size 4091