Hugging Face's logo

suku9
/
pretrain_gpt2___

Transformers
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Community
suku9 commited on
Commit
d59ae25
·
verified ·
1 Parent(s): f56d2b1

Model save

Browse files
Files changed (3) hide show
  1. README.md +83 -0
  2. generation_config.json +7 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: pretrain_gpt2___
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # pretrain_gpt2___
14
+
15
+ This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 0.5927
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 5e-05
37
+ - train_batch_size: 512
38
+ - eval_batch_size: 512
39
+ - seed: 42
40
+ - optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
+ - lr_scheduler_type: cosine
42
+ - lr_scheduler_warmup_steps: 312500
43
+ - num_epochs: 10
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:------:|:-----:|:---------------:|
50
+ | 0.408 | 0.3775 | 1000 | 1.5666 |
51
+ | 0.3475 | 0.7550 | 2000 | 1.3169 |
52
+ | 0.3182 | 1.1325 | 3000 | 1.1971 |
53
+ | 0.293 | 1.5100 | 4000 | 1.0951 |
54
+ | 0.2728 | 1.8875 | 5000 | 1.0073 |
55
+ | 0.2552 | 2.2650 | 6000 | 0.9333 |
56
+ | 0.2417 | 2.6425 | 7000 | 0.8703 |
57
+ | 0.227 | 3.0200 | 8000 | 0.8206 |
58
+ | 0.2185 | 3.3975 | 9000 | 0.7925 |
59
+ | 0.2103 | 3.7750 | 10000 | 0.7635 |
60
+ | 0.2034 | 4.1525 | 11000 | 0.7346 |
61
+ | 0.1967 | 4.5300 | 12000 | 0.7210 |
62
+ | 0.1895 | 4.9075 | 13000 | 0.7079 |
63
+ | 0.1875 | 5.2850 | 14000 | 0.6897 |
64
+ | 0.1844 | 5.6625 | 15000 | 0.6761 |
65
+ | 0.1782 | 6.0400 | 16000 | 0.6619 |
66
+ | 0.1758 | 6.4175 | 17000 | 0.6534 |
67
+ | 0.1744 | 6.7950 | 18000 | 0.6451 |
68
+ | 0.1732 | 7.1725 | 19000 | 0.6344 |
69
+ | 0.1672 | 7.5500 | 20000 | 0.6276 |
70
+ | 0.168 | 7.9275 | 21000 | 0.6197 |
71
+ | 0.1661 | 8.3050 | 22000 | 0.6124 |
72
+ | 0.1627 | 8.6825 | 23000 | 0.6080 |
73
+ | 0.1593 | 9.0600 | 24000 | 0.6042 |
74
+ | 0.1586 | 9.4375 | 25000 | 0.5978 |
75
+ | 0.1589 | 9.8150 | 26000 | 0.5927 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.51.1
81
+ - Pytorch 2.6.0+cu124
82
+ - Datasets 3.5.0
83
+ - Tokenizers 0.21.1
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 3,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.51.1"
7
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12d878fd068c6fdaaa72f9d9d6138dfa44178b40ec2888e6cc9f96915f0f2656
3
  size 340724352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97f9588fef662b1d7f605431d7632b92fc8e2bac3a45bb7215e40d902ca2d399
3
  size 340724352