SashaSheykina commited on
Commit
c792171
1 Parent(s): fc07df2

Training complete

Browse files
README.md CHANGED
@@ -19,14 +19,14 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [Salesforce/codet5-base](https://huggingface.co/Salesforce/codet5-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.3273
23
- - Rouge1: 0.4998
24
- - Rouge2: 0.3260
25
- - Rougel: 0.4806
26
- - Bleu: 20.0579
27
- - Meteor: 0.5318
28
- - Codebleu: 0.2414
29
- - Em: 0.14
30
 
31
  ## Model description
32
 
@@ -46,9 +46,11 @@ More information needed
46
 
47
  The following hyperparameters were used during training:
48
  - learning_rate: 5e-05
49
- - train_batch_size: 4
50
- - eval_batch_size: 4
51
  - seed: 42
 
 
52
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
53
  - lr_scheduler_type: linear
54
  - num_epochs: 3
 
19
 
20
  This model is a fine-tuned version of [Salesforce/codet5-base](https://huggingface.co/Salesforce/codet5-base) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.4358
23
+ - Rouge1: 0.3457
24
+ - Rouge2: 0.1202
25
+ - Rougel: 0.3148
26
+ - Bleu: 12.8425
27
+ - Meteor: 0.3899
28
+ - Codebleu: 0.1722
29
+ - Em: 0.02
30
 
31
  ## Model description
32
 
 
46
 
47
  The following hyperparameters were used during training:
48
  - learning_rate: 5e-05
49
+ - train_batch_size: 6
50
+ - eval_batch_size: 12
51
  - seed: 42
52
+ - gradient_accumulation_steps: 2
53
+ - total_train_batch_size: 12
54
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
  - lr_scheduler_type: linear
56
  - num_epochs: 3
runs/Aug05_14-52-35_cb69df8c9ea7/events.out.tfevents.1722870420.cb69df8c9ea7.4878.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8e668e7dc4a0e8e430ebab433486072ebf115115a114aeedb33439671273adb
3
+ size 693