Hugging Face's logo

jarod0411
/
stage1

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
jarod0411 commited on
Commit
eae97bf
·
verified ·
1 Parent(s): b5b721e

Model save

Browse files
Files changed (3) hide show
  1. README.md +22 -23
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -1,5 +1,4 @@
1
  ---
2
- license: mit
3
  base_model: jarod0411/zinc10M_gpt2_SMILES_bpe_combined_step1
4
  tags:
5
  - generated_from_trainer
@@ -15,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # stage1
17
 
18
- This model is a fine-tuned version of [jarod0411/zinc10M_gpt2_SMILES_bpe_combined_step1](https://huggingface.co/jarod0411/zinc10M_gpt2_SMILES_bpe_combined_step1) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.2469
21
- - Accuracy: 0.9158
22
 
23
  ## Model description
24
 
@@ -38,13 +37,13 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 5e-05
41
- - train_batch_size: 16
42
- - eval_batch_size: 16
43
  - seed: 1
44
  - distributed_type: multi-GPU
45
- - num_devices: 8
46
- - total_train_batch_size: 128
47
- - total_eval_batch_size: 128
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - num_epochs: 10.0
@@ -53,21 +52,21 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:-----:|:------:|:---------------:|:--------:|
56
- | 0.3374 | 1.0 | 16956 | 0.2982 | 0.9016 |
57
- | 0.2955 | 2.0 | 33912 | 0.2682 | 0.9104 |
58
- | 0.2795 | 3.0 | 50868 | 0.2593 | 0.9126 |
59
- | 0.2713 | 4.0 | 67824 | 0.2549 | 0.9137 |
60
- | 0.2661 | 5.0 | 84780 | 0.2522 | 0.9144 |
61
- | 0.2626 | 6.0 | 101736 | 0.2501 | 0.9150 |
62
- | 0.2602 | 7.0 | 118692 | 0.2488 | 0.9153 |
63
- | 0.2585 | 8.0 | 135648 | 0.2478 | 0.9156 |
64
- | 0.2574 | 9.0 | 152604 | 0.2471 | 0.9158 |
65
- | 0.2569 | 10.0 | 169560 | 0.2469 | 0.9158 |
66
 
67
 
68
  ### Framework versions
69
 
70
- - Transformers 4.36.0.dev0
71
- - Pytorch 2.1.1+cu121
72
- - Datasets 2.15.0
73
- - Tokenizers 0.15.0
 
1
  ---
 
2
  base_model: jarod0411/zinc10M_gpt2_SMILES_bpe_combined_step1
3
  tags:
4
  - generated_from_trainer
 
14
 
15
  # stage1
16
 
17
+ This model is a fine-tuned version of [jarod0411/zinc10M_gpt2_SMILES_bpe_combined_step1](https://huggingface.co/jarod0411/zinc10M_gpt2_SMILES_bpe_combined_step1) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.3311
20
+ - Accuracy: 0.8936
21
 
22
  ## Model description
23
 
 
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 5e-05
40
+ - train_batch_size: 24
41
+ - eval_batch_size: 24
42
  - seed: 1
43
  - distributed_type: multi-GPU
44
+ - num_devices: 6
45
+ - total_train_batch_size: 144
46
+ - total_eval_batch_size: 144
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - num_epochs: 10.0
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:------:|:---------------:|:--------:|
55
+ | 0.375 | 1.0 | 23931 | 0.3615 | 0.8853 |
56
+ | 0.3609 | 2.0 | 47862 | 0.3494 | 0.8887 |
57
+ | 0.3533 | 3.0 | 71793 | 0.3432 | 0.8904 |
58
+ | 0.3486 | 4.0 | 95724 | 0.3394 | 0.8914 |
59
+ | 0.3456 | 5.0 | 119655 | 0.3367 | 0.8921 |
60
+ | 0.3432 | 6.0 | 143586 | 0.3346 | 0.8927 |
61
+ | 0.3412 | 7.0 | 167517 | 0.3333 | 0.8930 |
62
+ | 0.3397 | 8.0 | 191448 | 0.3322 | 0.8933 |
63
+ | 0.339 | 9.0 | 215379 | 0.3314 | 0.8935 |
64
+ | 0.3383 | 10.0 | 239310 | 0.3311 | 0.8936 |
65
 
66
 
67
  ### Framework versions
68
 
69
+ - Transformers 4.38.0.dev0
70
+ - Pytorch 2.2.0+cu121
71
+ - Datasets 2.17.0
72
+ - Tokenizers 0.15.2
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
- "transformers_version": "4.36.0.dev0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
+ "transformers_version": "4.38.0.dev0"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:078d2870da4d63f1311470fa5e5fc2d5f983f85b110f8e4afd3886e16cfcc4be
3
  size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c152ca75c2c4a2cc62abcdd39c8e9ddfc98d22cf20aa7e503c7285c1bc580c3
3
  size 497774208