Menouar commited on
Commit
de294f2
1 Parent(s): 27c6674

Model save

Browse files
README.md CHANGED
@@ -36,15 +36,15 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0002
39
- - train_batch_size: 1
40
- - eval_batch_size: 1
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
- - total_train_batch_size: 2
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: constant
46
  - lr_scheduler_warmup_ratio: 0.03
47
- - training_steps: 10
48
 
49
  ### Training results
50
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0002
39
+ - train_batch_size: 42
40
+ - eval_batch_size: 8
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 84
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: constant
46
  - lr_scheduler_warmup_ratio: 0.03
47
+ - num_epochs: 10
48
 
49
  ### Training results
50
 
runs/Feb06_13-37-06_9e08d37cdcdf/events.out.tfevents.1707226635.9e08d37cdcdf.2041.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03e780cf4d7023fc7ea84da8d3cb90d69e6d4a5b05575ec5dc4e264f116fa52e
3
- size 19036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39d6842d48cc48eee1cca159470cc348428b3ec194b17526be3b0c25111f60b1
3
+ size 19390