Hugging Face's logo

e-hossam96
/
arabic-nano-gpt-v0

Text Generation
Transformers
Safetensors
Arabic
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
e-hossam96 commited on
Commit
b19a398
•
1 Parent(s): a64684d

End of training

Browse files
Files changed (6) hide show
  1. README.md +21 -8
  2. merges.txt +0 -0
  3. model.safetensors +1 -1
  4. tokenizer.json +0 -0
  5. training_args.bin +1 -1
  6. vocab.json +0 -0
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 6.7561
20
 
21
  ## Model description
22
 
@@ -35,21 +35,34 @@ More information needed
35
  ### Training hyperparameters
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
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
- - num_epochs: 100
45
 
46
  ### Training results
47
 
48
- | Training Loss | Epoch | Step | Validation Loss |
49
- |:-------------:|:-------:|:----:|:---------------:|
50
- | 3.9323 | 33.3333 | 100 | 6.6959 |
51
- | 1.7608 | 66.6667 | 200 | 6.7001 |
52
- | 1.0962 | 100.0 | 300 | 6.7561 |
 
 
 
 
 
 
 
 
 
 
 
53
 
54
 
55
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 4.7743
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.001
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - num_epochs: 2
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss |
51
+ |:-------------:|:------:|:----:|:---------------:|
52
+ | 7.3768 | 0.1422 | 100 | 6.7464 |
53
+ | 6.5028 | 0.2844 | 200 | 6.2504 |
54
+ | 6.0865 | 0.4266 | 300 | 5.8534 |
55
+ | 5.7563 | 0.5688 | 400 | 5.5491 |
56
+ | 5.5138 | 0.7110 | 500 | 5.3476 |
57
+ | 5.3615 | 0.8532 | 600 | 5.2035 |
58
+ | 5.2481 | 0.9954 | 700 | 5.0965 |
59
+ | 5.1406 | 1.1376 | 800 | 5.0118 |
60
+ | 5.0665 | 1.2798 | 900 | 4.9467 |
61
+ | 5.015 | 1.4220 | 1000 | 4.8900 |
62
+ | 4.9767 | 1.5642 | 1100 | 4.8476 |
63
+ | 4.9434 | 1.7064 | 1200 | 4.8122 |
64
+ | 4.9137 | 1.8486 | 1300 | 4.7864 |
65
+ | 4.9069 | 1.9908 | 1400 | 4.7743 |
66
 
67
 
68
  ### Framework versions
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e436710d521e6b7a63363fcdbf0f809934864e7a02edab3e6f8115fba67822f6
3
  size 22080496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef03bee4cdac781668e18b4eb3ac55e84d6086f3b666d99a7211dc1499c90b7
3
  size 22080496
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7dc7ec1ed83b3496ca7f0d18310e9ca6d0e5afaf432a54bc535d3d7aa6b0d97
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12e57a589058865d432b375c24c25ef67764e80778f2e51d8c95b8b5339317dc
3
  size 5240
vocab.json CHANGED
The diff for this file is too large to render. See raw diff