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
cd5ea68
·
verified ·
1 Parent(s): b2b54a8

ninagroot/GPT2-705Mtest

Browse files
Files changed (4) hide show
  1. README.md +31 -25
  2. model.safetensors +1 -1
  3. runs/Apr17_14-39-08_gcn53.local.snellius.surf.nl/events.out.tfevents.1713357559.gcn53.local.snellius.surf.nl.4133403.0 +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: 5.2910
17
 
18
  ## Model description
19
 
@@ -41,36 +41,42 @@ The following hyperparameters were used during training:
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: 40
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 9.7067 | 0.57 | 1 | 9.7226 |
52
- | 8.0571 | 1.71 | 3 | 9.2898 |
53
- | 8.3374 | 2.86 | 5 | 8.5986 |
54
- | 7.5982 | 4.0 | 7 | 7.8459 |
55
- | 7.2482 | 4.57 | 8 | 7.8008 |
56
- | 6.9285 | 5.71 | 10 | 7.3997 |
57
- | 6.4908 | 6.86 | 12 | 8.3017 |
58
- | 6.3109 | 8.0 | 14 | 6.9692 |
59
- | 6.2177 | 8.57 | 15 | 6.9043 |
60
- | 5.9262 | 9.71 | 17 | 6.5565 |
61
- | 5.6466 | 10.86 | 19 | 6.4155 |
62
- | 5.3065 | 12.0 | 21 | 6.1934 |
63
- | 5.1914 | 12.57 | 22 | 6.0177 |
64
- | 4.9555 | 13.71 | 24 | 6.0827 |
65
- | 4.7476 | 14.86 | 26 | 5.8534 |
66
- | 4.6724 | 16.0 | 28 | 5.7760 |
67
- | 4.4796 | 16.57 | 29 | 5.6058 |
68
- | 4.2379 | 17.71 | 31 | 5.4230 |
69
- | 4.1798 | 18.86 | 33 | 5.4227 |
70
- | 3.9092 | 20.0 | 35 | 5.3294 |
71
- | 3.8306 | 20.57 | 36 | 5.2938 |
72
- | 3.735 | 21.71 | 38 | 5.5156 |
73
- | 3.4544 | 22.86 | 40 | 5.2910 |
 
 
 
 
 
 
74
 
75
 
76
  ### 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: 5.5538
17
 
18
  ## Model description
19
 
 
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: 50
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 9.7407 | 0.57 | 1 | 9.7354 |
52
+ | 8.0949 | 1.71 | 3 | 9.2987 |
53
+ | 8.037 | 2.86 | 5 | 7.9942 |
54
+ | 8.4143 | 4.0 | 7 | 8.3825 |
55
+ | 7.7196 | 4.57 | 8 | 8.7978 |
56
+ | 7.2632 | 5.71 | 10 | 7.6261 |
57
+ | 6.9715 | 6.86 | 12 | 7.4135 |
58
+ | 6.4835 | 8.0 | 14 | 8.2776 |
59
+ | 7.1529 | 8.57 | 15 | 7.0085 |
60
+ | 6.1255 | 9.71 | 17 | 6.8228 |
61
+ | 5.9176 | 10.86 | 19 | 6.5603 |
62
+ | 5.5785 | 12.0 | 21 | 6.3862 |
63
+ | 5.4833 | 12.57 | 22 | 6.3011 |
64
+ | 5.1483 | 13.71 | 24 | 6.0480 |
65
+ | 4.9268 | 14.86 | 26 | 6.0532 |
66
+ | 4.6602 | 16.0 | 28 | 5.7750 |
67
+ | 4.5647 | 16.57 | 29 | 5.7046 |
68
+ | 4.3202 | 17.71 | 31 | 5.5333 |
69
+ | 4.1764 | 18.86 | 33 | 5.5809 |
70
+ | 4.1745 | 20.0 | 35 | 5.4089 |
71
+ | 4.0056 | 20.57 | 36 | 5.3978 |
72
+ | 3.8024 | 21.71 | 38 | 5.4085 |
73
+ | 3.5845 | 22.86 | 40 | 5.3279 |
74
+ | 3.4378 | 24.0 | 42 | 5.3881 |
75
+ | 3.3361 | 24.57 | 43 | 5.2754 |
76
+ | 3.2585 | 25.71 | 45 | 5.2913 |
77
+ | 3.168 | 26.86 | 47 | 5.4232 |
78
+ | 2.9045 | 28.0 | 49 | 5.5044 |
79
+ | 2.8709 | 28.57 | 50 | 5.5538 |
80
 
81
 
82
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bbe64cdd1fd57e3973cc244d9926375ebc01e1d458a14e400e45939441ddfc5
3
  size 2796386080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67a0ad96fd61d062481d2585b4b609b1352e057b1abfad475518de3e3e7a92fa
3
  size 2796386080
runs/Apr17_14-39-08_gcn53.local.snellius.surf.nl/events.out.tfevents.1713357559.gcn53.local.snellius.surf.nl.4133403.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e820e6647d03c6ab72ff3c33a7673f486461751c2af756c36d13f8666cdaa193
3
+ size 23090
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d61ff082ec6c42f1e6bcb30e984b2a470071df3df92a3b469ceb01b0d1cf6f3
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b71557a365487e867c53d02efcefd6b9c9702d6f5d94e2929a4f315cc59c4f
3
  size 4984