Hugging Face's logo

ninagroot
/
GPT2-705-RUN1

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
ninagroot commited on
Commit
16c2aa2
·
verified ·
1 Parent(s): 144179c

ninagroot/GPT2-705Mtest

Browse files
Files changed (4) hide show
  1. README.md +9 -25
  2. model.safetensors +1 -1
  3. runs/Apr16_13-55-28_gcn38.local.snellius.surf.nl/events.out.tfevents.1713268535.gcn38.local.snellius.surf.nl.410095.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
- - Loss: 6.0614
17
 
18
  ## Model description
19
 
@@ -33,41 +33,25 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.00025
36
- - train_batch_size: 8
37
  - eval_batch_size: 8
38
  - seed: 42
39
- - gradient_accumulation_steps: 4
40
- - total_train_batch_size: 32
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 50
44
- - num_epochs: 20
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 8.8224 | 1.0 | 7 | 7.6832 |
52
- | 7.4858 | 2.0 | 14 | 7.1509 |
53
- | 6.0862 | 3.0 | 21 | 6.5037 |
54
- | 5.6017 | 4.0 | 28 | 5.9130 |
55
- | 4.6362 | 5.0 | 35 | 5.7221 |
56
- | 4.2618 | 6.0 | 42 | 5.3891 |
57
- | 3.9715 | 7.0 | 49 | 5.3131 |
58
- | 3.5012 | 8.0 | 56 | 5.4218 |
59
- | 3.29 | 9.0 | 63 | 5.4657 |
60
- | 2.8687 | 10.0 | 70 | 5.4606 |
61
- | 2.6341 | 11.0 | 77 | 5.5206 |
62
- | 2.6041 | 12.0 | 84 | 5.7237 |
63
- | 2.2504 | 13.0 | 91 | 5.7820 |
64
- | 2.0707 | 14.0 | 98 | 5.8230 |
65
- | 1.8755 | 15.0 | 105 | 5.9205 |
66
- | 1.7089 | 16.0 | 112 | 5.9806 |
67
- | 1.6494 | 17.0 | 119 | 6.0164 |
68
- | 1.4828 | 18.0 | 126 | 6.0369 |
69
- | 1.3989 | 19.0 | 133 | 6.0577 |
70
- | 1.3667 | 20.0 | 140 | 6.0614 |
71
 
72
 
73
  ### Framework versions
 
13
 
14
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
15
  It achieves the following results on the evaluation set:
16
+ - Loss: 8.2338
17
 
18
  ## Model description
19
 
 
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.00025
36
+ - train_batch_size: 16
37
  - eval_batch_size: 8
38
  - seed: 42
39
+ - gradient_accumulation_steps: 8
40
+ - total_train_batch_size: 128
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: cosine
43
  - lr_scheduler_warmup_steps: 50
44
+ - num_epochs: 7
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | No log | 0.57 | 1 | 9.6467 |
52
+ | No log | 1.71 | 3 | 9.2986 |
53
+ | 8.859 | 2.86 | 5 | 8.2412 |
54
+ | 8.859 | 4.0 | 7 | 8.2338 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
 
56
 
57
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e5d79cd8946236db58f0963e9396cd82746d86aa096f5fb318c36e789bd5a3f
3
  size 2796386080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74c56106065c30430444b5d8f7c6f8818cdf7c13d35ff929b4d6086f5671989b
3
  size 2796386080
runs/Apr16_13-55-28_gcn38.local.snellius.surf.nl/events.out.tfevents.1713268535.gcn38.local.snellius.surf.nl.410095.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c40a465e424baa5a5abe2fac1e806c61c827c1bab2d352e110d3d6d94f58b50
3
+ size 6296
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f6b02ba198741c9abb6b2a702173cca3abfc60f62553972603e016427f2da79
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:291dd62c59e352bed154923a6e1726aa39f76b84f3074d31fbc9d294eed6cc5e
3
  size 4984