Hugging Face's logo

ninagroot
/
GPT2-705M-ORIGINAL

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
ninagroot commited on
Commit
a43035f
·
verified ·
1 Parent(s): 01b5ee1

ninagroot/GPT2-705M

Browse files
Files changed (4) hide show
  1. README.md +20 -38
  2. model.safetensors +1 -1
  3. runs/Apr22_21-01-20_gcn22.local.snellius.surf.nl/events.out.tfevents.1713812489.gcn22.local.snellius.surf.nl.1486285.0 +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: 4.8747
17
 
18
  ## Model description
19
 
@@ -41,49 +41,31 @@ 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
- | 8.6484 | 0.89 | 2 | 7.5910 |
52
- | 7.4125 | 1.78 | 4 | 7.3845 |
53
- | 7.177 | 2.67 | 6 | 8.4543 |
54
- | 6.8693 | 4.0 | 9 | 7.1517 |
55
- | 6.7375 | 4.89 | 11 | 6.7577 |
56
- | 6.4793 | 5.78 | 13 | 6.3863 |
57
- | 6.155 | 6.67 | 15 | 6.1743 |
58
- | 5.8146 | 8.0 | 18 | 5.8802 |
59
- | 5.5765 | 8.89 | 20 | 5.6410 |
60
- | 5.1699 | 9.78 | 22 | 5.4458 |
61
- | 5.1785 | 10.67 | 24 | 5.3271 |
62
- | 4.854 | 12.0 | 27 | 5.0277 |
63
- | 4.8076 | 12.89 | 29 | 4.9158 |
64
- | 4.5975 | 13.78 | 31 | 4.9445 |
65
- | 4.385 | 14.67 | 33 | 4.8140 |
66
- | 4.4167 | 16.0 | 36 | 4.6747 |
67
- | 4.3464 | 16.89 | 38 | 4.5966 |
68
- | 4.1645 | 17.78 | 40 | 4.4547 |
69
- | 3.9958 | 18.67 | 42 | 4.4993 |
70
- | 3.8152 | 20.0 | 45 | 4.4591 |
71
- | 3.6949 | 20.89 | 47 | 4.4364 |
72
- | 3.6767 | 21.78 | 49 | 4.4040 |
73
- | 3.5244 | 22.67 | 51 | 4.4034 |
74
- | 3.3385 | 24.0 | 54 | 4.4621 |
75
- | 3.2586 | 24.89 | 56 | 4.5152 |
76
- | 3.1222 | 25.78 | 58 | 4.5277 |
77
- | 2.8846 | 26.67 | 60 | 4.5638 |
78
- | 2.7718 | 28.0 | 63 | 4.6443 |
79
- | 2.5681 | 28.89 | 65 | 4.6683 |
80
- | 2.5383 | 29.78 | 67 | 4.7204 |
81
- | 2.4544 | 30.67 | 69 | 4.7512 |
82
- | 2.2336 | 32.0 | 72 | 4.7927 |
83
- | 2.1591 | 32.89 | 74 | 4.8253 |
84
- | 2.1328 | 33.78 | 76 | 4.8684 |
85
- | 2.1649 | 34.67 | 78 | 4.8750 |
86
- | 2.1091 | 35.56 | 80 | 4.8747 |
87
 
88
 
89
  ### 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: 4.5594
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: 20
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 8.705 | 0.89 | 2 | 7.8398 |
52
+ | 7.9084 | 1.78 | 4 | 7.9095 |
53
+ | 7.5512 | 2.67 | 6 | 7.0537 |
54
+ | 6.877 | 4.0 | 9 | 6.8957 |
55
+ | 6.6817 | 4.89 | 11 | 6.6244 |
56
+ | 6.3264 | 5.78 | 13 | 7.6667 |
57
+ | 6.044 | 6.67 | 15 | 6.2046 |
58
+ | 5.7734 | 8.0 | 18 | 5.8704 |
59
+ | 5.6256 | 8.89 | 20 | 5.7477 |
60
+ | 5.3341 | 9.78 | 22 | 5.5244 |
61
+ | 5.3234 | 10.67 | 24 | 5.3057 |
62
+ | 5.1621 | 12.0 | 27 | 5.2336 |
63
+ | 4.9043 | 12.89 | 29 | 5.0179 |
64
+ | 4.7566 | 13.78 | 31 | 4.8456 |
65
+ | 4.4543 | 14.67 | 33 | 4.7870 |
66
+ | 4.3777 | 16.0 | 36 | 4.5766 |
67
+ | 4.3737 | 16.89 | 38 | 4.5429 |
68
+ | 4.2825 | 17.78 | 40 | 4.5594 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59f9b32e01cb286bf7b3f5bf3c4452b35c89854ce4edeb937cbd1a3f0e29c890
3
  size 2747965216
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:797679ee0881ea87b6a748dc92f78b550162f5e8a89e08438223ef1fc30b9cfc
3
  size 2747965216
runs/Apr22_21-01-20_gcn22.local.snellius.surf.nl/events.out.tfevents.1713812489.gcn22.local.snellius.surf.nl.1486285.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:442a83a839dd67b77ebabd3de48f81e2372ffce89003a9a3ed7fb529b7f6e604
3
+ size 18093
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0e8c7544a44d2168b581b5ef35f1b96ca96f33b184b742628c864897f209e2f
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f94d5f797a871e76244808734bd8d84c2dc7ef3a7650697947ce1b69e151588c
3
  size 4984