varun-v-rao commited on
Commit
abe87ea
1 Parent(s): 3eb103d

End of training

Browse files
README.md CHANGED
@@ -8,7 +8,7 @@ datasets:
8
  metrics:
9
  - accuracy
10
  model-index:
11
- - name: roberta-base-sick
12
  results:
13
  - task:
14
  name: Text Classification
@@ -22,18 +22,18 @@ model-index:
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
- value: 0.3995
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
- # roberta-base-sick
32
 
33
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the snli-cf-kaushik dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 2.0984
36
- - Accuracy: 0.3995
37
 
38
  ## Model description
39
 
@@ -55,7 +55,7 @@ The following hyperparameters were used during training:
55
  - learning_rate: 2e-05
56
  - train_batch_size: 64
57
  - eval_batch_size: 32
58
- - seed: 14
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - num_epochs: 3
@@ -64,9 +64,9 @@ The following hyperparameters were used during training:
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
- | No log | 1.0 | 70 | 0.4301 | 0.8242 |
68
- | No log | 2.0 | 140 | 0.3366 | 0.8707 |
69
- | No log | 3.0 | 210 | 0.3695 | 0.8687 |
70
 
71
 
72
  ### Framework versions
 
8
  metrics:
9
  - accuracy
10
  model-index:
11
+ - name: roberta-base-fp-sick
12
  results:
13
  - task:
14
  name: Text Classification
 
22
  metrics:
23
  - name: Accuracy
24
  type: accuracy
25
+ value: 0.4395
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
  should probably proofread and complete it, then remove this comment. -->
30
 
31
+ # roberta-base-fp-sick
32
 
33
  This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the snli-cf-kaushik dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 2.1373
36
+ - Accuracy: 0.4395
37
 
38
  ## Model description
39
 
 
55
  - learning_rate: 2e-05
56
  - train_batch_size: 64
57
  - eval_batch_size: 32
58
+ - seed: 33
59
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
  - lr_scheduler_type: linear
61
  - num_epochs: 3
 
64
 
65
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
66
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
67
+ | No log | 1.0 | 70 | 0.4164 | 0.8485 |
68
+ | No log | 2.0 | 140 | 0.3497 | 0.8747 |
69
+ | No log | 3.0 | 210 | 0.3346 | 0.8727 |
70
 
71
 
72
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9e49d177223f0836f629c1b4da404386abd88e3ddbfb91a658dc9b133ad17a6
3
  size 498615900
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:974e47d62e26b31a9deac5e9fcf8fdefdb2194a3316dd211448b8d21c89cd349
3
  size 498615900
runs/Jun05_10-39-02_gl1523.arc-ts.umich.edu/events.out.tfevents.1717598425.gl1523.arc-ts.umich.edu.360242.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd89e78eaf0deb6336a50889d03a6dfd43bc8b8958b22883e3826014146fa7f
3
+ size 1380