Hugging Face's logo

Aravindan
/
gpt2out

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Aravindan commited on
Commit
491f952
·
verified ·
1 Parent(s): 469b7b3

End of training

Browse files
Files changed (4) hide show
  1. README.md +8 -32
  2. model.safetensors +1 -1
  3. runs/Jun04_12-47-51_5f46b0e4b719/events.out.tfevents.1717505271.5f46b0e4b719.25.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: Aravindan/gpt2out
6
  model-index:
7
  - name: gpt2coder-8epochs
8
  results: []
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [Aravindan/gpt2out](https://huggingface.co/Aravindan/gpt2out) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.9270
19
 
20
  ## Model description
21
 
@@ -38,42 +38,18 @@ The following hyperparameters were used during training:
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
41
- - gradient_accumulation_steps: 10
42
- - total_train_batch_size: 80
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_ratio: 0.1
46
- - num_epochs: 25
47
 
48
  ### Training results
49
 
50
- | Training Loss | Epoch | Step | Validation Loss |
51
- |:-------------:|:-------:|:----:|:---------------:|
52
- | No log | 0.9810 | 31 | 3.2508 |
53
- | No log | 1.9937 | 63 | 2.6920 |
54
- | No log | 2.9747 | 94 | 2.3769 |
55
- | No log | 3.9873 | 126 | 2.1444 |
56
- | No log | 5.0 | 158 | 1.9673 |
57
- | No log | 5.9810 | 189 | 1.8320 |
58
- | No log | 6.9937 | 221 | 1.7097 |
59
- | No log | 7.9747 | 252 | 1.6159 |
60
- | No log | 8.9873 | 284 | 1.5231 |
61
- | No log | 10.0 | 316 | 1.4535 |
62
- | No log | 10.9810 | 347 | 1.3788 |
63
- | No log | 11.9937 | 379 | 1.3109 |
64
- | No log | 12.9747 | 410 | 1.2496 |
65
- | No log | 13.9873 | 442 | 1.1989 |
66
- | No log | 14.9810 | 465 | 1.1647 |
67
- | No log | 15.9937 | 497 | 1.1208 |
68
- | 1.3856 | 16.9747 | 528 | 1.0841 |
69
- | 1.3856 | 17.9873 | 560 | 1.0464 |
70
- | 1.3856 | 19.0 | 592 | 1.0180 |
71
- | 1.3856 | 19.9810 | 623 | 0.9928 |
72
- | 1.3856 | 20.9937 | 655 | 0.9689 |
73
- | 1.3856 | 21.9747 | 686 | 0.9517 |
74
- | 1.3856 | 22.9873 | 718 | 0.9390 |
75
- | 1.3856 | 24.0 | 750 | 0.9298 |
76
- | 1.3856 | 24.7911 | 775 | 0.9270 |
77
 
78
 
79
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: Aravindan/gpt2out
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: gpt2coder-8epochs
8
  results: []
 
15
 
16
  This model is a fine-tuned version of [Aravindan/gpt2out](https://huggingface.co/Aravindan/gpt2out) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 2.0309
19
 
20
  ## Model description
21
 
 
38
  - train_batch_size: 8
39
  - eval_batch_size: 8
40
  - seed: 42
41
+ - gradient_accumulation_steps: 16
42
+ - total_train_batch_size: 128
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_ratio: 0.1
46
+ - num_epochs: 1
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:------:|:----:|:---------------:|
52
+ | 2.2389 | 0.9998 | 1739 | 2.0309 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d29ced89a6423e2315431bff8b01bf9452b60607d050fb307ccb939435a8470b
3
  size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db5ed9c70628f43009980c4fd88939d66c16dec74f5d068c1f6ff9a974b1e663
3
  size 497774208
runs/Jun04_12-47-51_5f46b0e4b719/events.out.tfevents.1717505271.5f46b0e4b719.25.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:079de7dd737ab6143197e7840833df31196b7468c162fa593d659f7067cbadde
3
+ size 6353
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08ead8923aaaf05f683a0f272f9e8c5877c5d68113c2f6f34fbc69f833fffcc0
3
  size 5112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c41c320c81744d1d2af38cb685c1228f0782b20aeb38f5c3a9cd0b7042c804
3
  size 5112