Hugging Face's logo

mdroth
/
codeparrot-ds-model

Text Generation
Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files Community
mdroth commited on
Commit
bc4acfd
·
verified ·
1 Parent(s): 6008d66

End of training

Browse files
Files changed (3) hide show
  1. README.md +11 -31
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,12 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.9517
 
 
 
 
 
20
 
21
  ## Model description
22
 
@@ -36,42 +41,17 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0005
39
- - train_batch_size: 32
40
- - eval_batch_size: 32
41
  - seed: 42
42
- - gradient_accumulation_steps: 8
43
- - total_train_batch_size: 256
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: cosine
46
- - lr_scheduler_warmup_steps: 5000
47
  - num_epochs: 3
48
  - mixed_precision_training: Native AMP
49
 
50
- ### Training results
51
-
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:------:|:------:|:---------------:|
54
- | 2.4181 | 0.1533 | 10000 | 1.5849 |
55
- | 1.5361 | 0.3065 | 20000 | 1.4070 |
56
- | 1.4242 | 0.4598 | 30000 | 1.3356 |
57
- | 1.3721 | 0.6131 | 40000 | 1.2948 |
58
- | 1.3327 | 0.7664 | 50000 | 1.2638 |
59
- | 1.3053 | 0.9196 | 60000 | 1.2403 |
60
- | 1.2751 | 1.0729 | 70000 | 1.2146 |
61
- | 1.2491 | 1.2262 | 80000 | 1.1876 |
62
- | 1.2258 | 1.3795 | 90000 | 1.1642 |
63
- | 1.1997 | 1.5327 | 100000 | 1.1374 |
64
- | 1.1724 | 1.6860 | 110000 | 1.1113 |
65
- | 1.1444 | 1.8393 | 120000 | 1.0826 |
66
- | 1.1157 | 1.9926 | 130000 | 1.0551 |
67
- | 1.0762 | 2.1458 | 140000 | 1.0298 |
68
- | 1.0513 | 2.2991 | 150000 | 1.0042 |
69
- | 1.0275 | 2.4524 | 160000 | 0.9827 |
70
- | 1.0067 | 2.6056 | 170000 | 0.9662 |
71
- | 0.9906 | 2.7589 | 180000 | 0.9556 |
72
- | 0.9827 | 2.9122 | 190000 | 0.9517 |
73
-
74
-
75
  ### Framework versions
76
 
77
  - Transformers 4.48.3
 
16
 
17
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - eval_loss: 1.7598
20
+ - eval_runtime: 364.6427
21
+ - eval_samples_per_second: 255.494
22
+ - eval_steps_per_second: 15.969
23
+ - epoch: 0.0766
24
+ - step: 20000
25
 
26
  ## Model description
27
 
 
41
 
42
  The following hyperparameters were used during training:
43
  - learning_rate: 0.0005
44
+ - train_batch_size: 16
45
+ - eval_batch_size: 16
46
  - seed: 42
47
+ - gradient_accumulation_steps: 4
48
+ - total_train_batch_size: 64
49
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
50
  - lr_scheduler_type: cosine
51
+ - lr_scheduler_warmup_steps: 1000
52
  - num_epochs: 3
53
  - mixed_precision_training: Native AMP
54
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  ### Framework versions
56
 
57
  - Transformers 4.48.3
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e1467f88537d221fe26ae721db3ac69cc0ed9e261713823d0e0b69e9eae880d
3
  size 496984704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42a2a49483da280d2380cbb11f613a5eb8bb89ddbf9a5eb670a0575e9bf4092f
3
  size 496984704
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dcef805671c5cd07413ed54f02867f0c0d960d31fae1dfe656538f6f3bb285ea
3
  size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e518a33692ffeead2f83c3d97e15b6a9dca9612df1fcb9a40b051d51655c878
3
  size 5304