yunzliang commited on
Commit
e854820
·
verified ·
1 Parent(s): ad0f043

End of training

Browse files
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on the eli5_category dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 3.5890
22
 
23
  ## Model description
24
 
@@ -38,25 +38,25 @@ More information needed
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
- - train_batch_size: 32
42
- - eval_batch_size: 32
43
  - seed: 42
44
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
- - num_epochs: 3
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
- | 3.5937 | 1.0 | 2000 | 3.5904 |
53
- | 3.4515 | 2.0 | 4000 | 3.5851 |
54
- | 3.3591 | 3.0 | 6000 | 3.5890 |
55
 
56
 
57
  ### Framework versions
58
 
59
- - Transformers 4.46.2
60
  - Pytorch 2.5.1+cu121
61
  - Datasets 3.1.0
62
  - Tokenizers 0.20.3
 
18
 
19
  This model is a fine-tuned version of [EleutherAI/gpt-neo-125M](https://huggingface.co/EleutherAI/gpt-neo-125M) on the eli5_category dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 3.6474
22
 
23
  ## Model description
24
 
 
38
 
39
  The following hyperparameters were used during training:
40
  - learning_rate: 2e-05
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
  - seed: 42
44
  - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 3.0
47
 
48
  ### Training results
49
 
50
  | Training Loss | Epoch | Step | Validation Loss |
51
  |:-------------:|:-----:|:----:|:---------------:|
52
+ | 3.6611 | 1.0 | 1301 | 3.6505 |
53
+ | 3.5104 | 2.0 | 2602 | 3.6461 |
54
+ | 3.4318 | 3.0 | 3903 | 3.6474 |
55
 
56
 
57
  ### Framework versions
58
 
59
+ - Transformers 4.46.3
60
  - Pytorch 2.5.1+cu121
61
  - Datasets 3.1.0
62
  - Tokenizers 0.20.3
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": "4.46.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
+ "transformers_version": "4.46.3"
6
  }
runs/Dec10_12-05-42_31f25b1feafd/events.out.tfevents.1733832354.31f25b1feafd.3818.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9850c359068b1a76cbfb259119addf62f1d37a370e48dec64c3e1936586cc63
3
- size 7535
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25fd732ede9856f2d561c492cc1c020eb48f07af08e4df4c743aa7a38b2ba6f3
3
+ size 8160
runs/Dec10_12-05-42_31f25b1feafd/events.out.tfevents.1733833181.31f25b1feafd.3818.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07f46b73042e2725808f4c4947b54b45dbcb0c28de54c07fb35007ffb72c7a5
3
+ size 359