Hugging Face's logo

vishnun
/
distilgpt2-finetuned-distilgpt2-med_articles

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
generated_from_trainer
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
1
vishnun25 commited on
Commit
c1946ff
•
1 Parent(s): d2346ef

add model

Browse files
Files changed (10) hide show
  1. README.md +7 -7
  2. config.json +3 -1
  3. pytorch_model.bin +1 -1
  4. runs/Aug19_10-11-15_a08bd7a25748/1629367894.5506911/events.out.tfevents.1629367894.a08bd7a25748.75.4 +3 -0
  5. runs/Aug19_10-11-15_a08bd7a25748/events.out.tfevents.1629367894.a08bd7a25748.75.3 +3 -0
  6. runs/Aug19_10-13-56_a08bd7a25748/1629368049.1363611/events.out.tfevents.1629368049.a08bd7a25748.75.6 +3 -0
  7. runs/Aug19_10-13-56_a08bd7a25748/events.out.tfevents.1629368049.a08bd7a25748.75.5 +3 -0
  8. runs/Aug19_10-13-56_a08bd7a25748/events.out.tfevents.1629368588.a08bd7a25748.75.7 +3 -0
  9. tokenizer_config.json +1 -1
  10. training_args.bin +1 -1
README.md CHANGED
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  # distilgpt2-finetuned-distilgpt2-med_articles
19
 
20
- This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 3.5189
23
 
24
  ## Model description
25
 
@@ -50,11 +50,11 @@ The following hyperparameters were used during training:
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
- | No log | 1.0 | 260 | 3.6093 |
54
- | 3.7297 | 2.0 | 520 | 3.5603 |
55
- | 3.7297 | 3.0 | 780 | 3.5338 |
56
- | 3.5313 | 4.0 | 1040 | 3.5232 |
57
- | 3.5313 | 5.0 | 1300 | 3.5189 |
58
 
59
 
60
  ### Framework versions
 
17
 
18
  # distilgpt2-finetuned-distilgpt2-med_articles
19
 
20
+ This model is a fine-tuned version of [vishnun/distilgpt2-finetuned-distilgpt2-med_articles](https://huggingface.co/vishnun/distilgpt2-finetuned-distilgpt2-med_articles) on the None dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 3.3171
23
 
24
  ## Model description
25
 
 
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-----:|:----:|:---------------:|
53
+ | No log | 1.0 | 65 | 3.3417 |
54
+ | No log | 2.0 | 130 | 3.3300 |
55
+ | No log | 3.0 | 195 | 3.3231 |
56
+ | No log | 4.0 | 260 | 3.3172 |
57
+ | No log | 5.0 | 325 | 3.3171 |
58
 
59
 
60
  ### Framework versions
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "distilgpt2",
3
  "_num_labels": 1,
4
  "activation_function": "gelu_new",
5
  "architectures": [
@@ -7,6 +7,7 @@
7
  ],
8
  "attn_pdrop": 0.1,
9
  "bos_token_id": 50256,
 
10
  "embd_pdrop": 0.1,
11
  "eos_token_id": 50256,
12
  "gradient_checkpointing": false,
@@ -18,6 +19,7 @@
18
  "LABEL_0": 0
19
  },
20
  "layer_norm_epsilon": 1e-05,
 
21
  "model_type": "gpt2",
22
  "n_ctx": 1024,
23
  "n_embd": 768,
 
1
  {
2
+ "_name_or_path": "vishnun/distilgpt2-finetuned-distilgpt2-med_articles",
3
  "_num_labels": 1,
4
  "activation_function": "gelu_new",
5
  "architectures": [
 
7
  ],
8
  "attn_pdrop": 0.1,
9
  "bos_token_id": 50256,
10
+ "do_sample": true,
11
  "embd_pdrop": 0.1,
12
  "eos_token_id": 50256,
13
  "gradient_checkpointing": false,
 
19
  "LABEL_0": 0
20
  },
21
  "layer_norm_epsilon": 1e-05,
22
+ "max_length": 50,
23
  "model_type": "gpt2",
24
  "n_ctx": 1024,
25
  "n_embd": 768,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f47bdd9cc0f58241e8c3723535e1d140733ebdbdacb62fa8bb46ce5635eb176e
3
  size 333972957
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf07f157ab32d63a4f5b38f8a35d99942b7238f8fa6942c2f5b6baff7c030f4
3
  size 333972957
runs/Aug19_10-11-15_a08bd7a25748/1629367894.5506911/events.out.tfevents.1629367894.a08bd7a25748.75.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3d90fe2bfc78c5d9160eda570682b316c0af8ea2f9290578936934c46b3c25
3
+ size 4205
runs/Aug19_10-11-15_a08bd7a25748/events.out.tfevents.1629367894.a08bd7a25748.75.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2de0ab23b294092cccf96814687e15e31e2457274557a7565b8554188c26df8
3
+ size 3375
runs/Aug19_10-13-56_a08bd7a25748/1629368049.1363611/events.out.tfevents.1629368049.a08bd7a25748.75.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d090efcef9e0f0eb6c14bce900722caf36b59ef95dfdaff7e029bfcef70cab
3
+ size 4205
runs/Aug19_10-13-56_a08bd7a25748/events.out.tfevents.1629368049.a08bd7a25748.75.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34face3efbf357ecd3930c490a42fc88fa98185be0dd05983a54af725d77630a
3
+ size 5079
runs/Aug19_10-13-56_a08bd7a25748/events.out.tfevents.1629368588.a08bd7a25748.75.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85654bb00d9b16efc98d373a4e26816aa8ca0b03884fa0d33f6067b10faa2043
3
+ size 311
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "distilgpt2", "tokenizer_class": "GPT2Tokenizer"}
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "vishnun/distilgpt2-finetuned-distilgpt2-med_articles", "tokenizer_class": "GPT2Tokenizer"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0405174ec65f57997442cf28a7725916e28a12529b30095d35752bd25f6282c5
3
  size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b96e6e0eca55c7c95c3a94a4b717f44b22126fbf53b33be361b11b18bf3964
3
  size 2671