varun-v-rao commited on
Commit
826eb4c
1 Parent(s): b42f859

End of training

Browse files
Files changed (1) hide show
  1. README.md +12 -12
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
- value: 0.9129242023978866
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -29,8 +29,8 @@ should probably proofread and complete it, then remove this comment. -->
29
 
30
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the snli dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 0.2576
33
- - Accuracy: 0.9129
34
 
35
  ## Model description
36
 
@@ -50,25 +50,25 @@ More information needed
50
 
51
  The following hyperparameters were used during training:
52
  - learning_rate: 2e-05
53
- - train_batch_size: 64
54
- - eval_batch_size: 32
55
- - seed: 58
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
  - num_epochs: 3
59
 
60
  ### Training results
61
 
62
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
- |:-------------:|:-----:|:-----:|:---------------:|:--------:|
64
- | 0.3378 | 1.0 | 8584 | 0.2729 | 0.9033 |
65
- | 0.2912 | 2.0 | 17168 | 0.2589 | 0.9100 |
66
- | 0.2516 | 3.0 | 25752 | 0.2576 | 0.9129 |
67
 
68
 
69
  ### Framework versions
70
 
71
  - Transformers 4.35.2
72
- - Pytorch 2.0.1+cu118
73
  - Datasets 2.15.0
74
  - Tokenizers 0.15.0
 
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
+ value: 0.9108920951026214
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
29
 
30
  This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the snli dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 0.2573
33
+ - Accuracy: 0.9109
34
 
35
  ## Model description
36
 
 
50
 
51
  The following hyperparameters were used during training:
52
  - learning_rate: 2e-05
53
+ - train_batch_size: 256
54
+ - eval_batch_size: 128
55
+ - seed: 81
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
  - num_epochs: 3
59
 
60
  ### Training results
61
 
62
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
+ | 0.367 | 1.0 | 2146 | 0.2850 | 0.8987 |
65
+ | 0.3208 | 2.0 | 4292 | 0.2633 | 0.9064 |
66
+ | 0.2926 | 3.0 | 6438 | 0.2573 | 0.9109 |
67
 
68
 
69
  ### Framework versions
70
 
71
  - Transformers 4.35.2
72
+ - Pytorch 2.1.1+cu121
73
  - Datasets 2.15.0
74
  - Tokenizers 0.15.0