Hugging Face's logo

varun-v-rao
/
gpt2-large-snli-model2

Text Classification
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
varun-v-rao commited on
Commit
2e3d5ce
•
1 Parent(s): 3969f8d

End of training

Browse files
Files changed (3) hide show
  1. README.md +7 -7
  2. model.safetensors +1 -1
  3. runs/Jun24_08-25-35_gl1520.arc-ts.umich.edu/events.out.tfevents.1719231951.gl1520.arc-ts.umich.edu.3698056.1 +2 -2
README.md CHANGED
@@ -19,7 +19,7 @@ model-index:
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
- value: 0.9158707579760211
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 [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on the snli dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 0.2900
33
- - Accuracy: 0.9159
34
 
35
  ## Model description
36
 
@@ -52,7 +52,7 @@ The following hyperparameters were used during training:
52
  - learning_rate: 2e-05
53
  - train_batch_size: 128
54
  - eval_batch_size: 128
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
@@ -61,9 +61,9 @@ The following hyperparameters were used during training:
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
64
- | 0.3105 | 1.0 | 4292 | 0.2489 | 0.9095 |
65
- | 0.2245 | 2.0 | 8584 | 0.2458 | 0.9172 |
66
- | 0.1436 | 3.0 | 12876 | 0.2900 | 0.9159 |
67
 
68
 
69
  ### Framework versions
 
19
  metrics:
20
  - name: Accuracy
21
  type: accuracy
22
+ value: 0.9134322292217029
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 [openai-community/gpt2-large](https://huggingface.co/openai-community/gpt2-large) on the snli dataset.
31
  It achieves the following results on the evaluation set:
32
+ - Loss: 0.2969
33
+ - Accuracy: 0.9134
34
 
35
  ## Model description
36
 
 
52
  - learning_rate: 2e-05
53
  - train_batch_size: 128
54
  - eval_batch_size: 128
55
+ - seed: 19
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: linear
58
  - num_epochs: 3
 
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
  |:-------------:|:-----:|:-----:|:---------------:|:--------:|
64
+ | 0.3148 | 1.0 | 4292 | 0.2557 | 0.9114 |
65
+ | 0.222 | 2.0 | 8584 | 0.2544 | 0.9141 |
66
+ | 0.1416 | 3.0 | 12876 | 0.2969 | 0.9134 |
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5b336aaa92062bc8c39362d9812ea72defcc0e69c63fec68a054ebca3fbf3f8
3
  size 3096181368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04319b8b9d7839689b34280e5070bb90c325536e6a3bd9fe804f407e3e07e909
3
  size 3096181368
runs/Jun24_08-25-35_gl1520.arc-ts.umich.edu/events.out.tfevents.1719231951.gl1520.arc-ts.umich.edu.3698056.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7652123e88c7d3b385baa361b6f0978996c37cb31703e958bf962494bcf937e8
3
- size 9918
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25ca8e1a9ef99f6d0df85fc54e8714580608e60887ca33cfb76230ef6e1c22e3
3
+ size 10272