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
6dc355e
·
verified ·
1 Parent(s): fccc788

ninagroot/GPT2-705Mtest

Browse files
Files changed (4) hide show
  1. README.md +62 -27
  2. model.safetensors +1 -1
  3. runs/Apr17_12-24-48_gcn61.local.snellius.surf.nl/events.out.tfevents.1713349497.gcn61.local.snellius.surf.nl.3984517.0 +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: 5.3613
17
 
18
  ## Model description
19
 
@@ -33,44 +33,79 @@ More information needed
33
 
34
  The following hyperparameters were used during training:
35
  - learning_rate: 0.00025
36
- - train_batch_size: 32
37
  - eval_batch_size: 8
38
  - seed: 42
39
- - gradient_accumulation_steps: 4
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: 40
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 9.7393 | 0.57 | 1 | 9.7595 |
52
- | 7.9692 | 1.71 | 3 | 8.8893 |
53
- | 7.9553 | 2.86 | 5 | 8.2940 |
54
- | 8.7602 | 4.0 | 7 | 8.8014 |
55
- | 8.2186 | 4.57 | 8 | 7.8900 |
56
- | 7.1745 | 5.71 | 10 | 7.5816 |
57
- | 7.1837 | 6.86 | 12 | 7.3890 |
58
- | 6.5593 | 8.0 | 14 | 7.1178 |
59
- | 6.387 | 8.57 | 15 | 8.4858 |
60
- | 6.4743 | 9.71 | 17 | 6.9945 |
61
- | 6.1188 | 10.86 | 19 | 6.8243 |
62
- | 5.9195 | 12.0 | 21 | 6.5761 |
63
- | 5.7847 | 12.57 | 22 | 6.4606 |
64
- | 5.4622 | 13.71 | 24 | 6.2584 |
65
- | 5.2573 | 14.86 | 26 | 6.1843 |
66
- | 5.0353 | 16.0 | 28 | 5.9988 |
67
- | 4.8916 | 16.57 | 29 | 5.9437 |
68
- | 4.6798 | 17.71 | 31 | 5.8515 |
69
- | 4.6879 | 18.86 | 33 | 5.6935 |
70
- | 4.3026 | 20.0 | 35 | 5.6336 |
71
- | 4.2853 | 20.57 | 36 | 5.5061 |
72
- | 4.0243 | 21.71 | 38 | 5.4732 |
73
- | 3.819 | 22.86 | 40 | 5.3613 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: 6.2845
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: 100
45
  - mixed_precision_training: Native AMP
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 9.7065 | 0.57 | 1 | 9.7011 |
52
+ | 7.9846 | 1.71 | 3 | 8.5445 |
53
+ | 7.6607 | 2.86 | 5 | 8.0972 |
54
+ | 7.5687 | 4.0 | 7 | 8.4841 |
55
+ | 8.0293 | 4.57 | 8 | 7.9394 |
56
+ | 7.0027 | 5.71 | 10 | 7.7385 |
57
+ | 6.8649 | 6.86 | 12 | 7.3423 |
58
+ | 6.4228 | 8.0 | 14 | 7.0662 |
59
+ | 6.259 | 8.57 | 15 | 6.9541 |
60
+ | 6.1205 | 9.71 | 17 | 6.6782 |
61
+ | 5.8029 | 10.86 | 19 | 6.5614 |
62
+ | 5.4672 | 12.0 | 21 | 6.2749 |
63
+ | 5.4032 | 12.57 | 22 | 6.2083 |
64
+ | 5.166 | 13.71 | 24 | 6.0910 |
65
+ | 4.9317 | 14.86 | 26 | 5.9103 |
66
+ | 4.71 | 16.0 | 28 | 5.8250 |
67
+ | 4.6227 | 16.57 | 29 | 5.7667 |
68
+ | 4.317 | 17.71 | 31 | 5.5216 |
69
+ | 4.375 | 18.86 | 33 | 5.4968 |
70
+ | 4.2285 | 20.0 | 35 | 5.4314 |
71
+ | 4.0816 | 20.57 | 36 | 5.3738 |
72
+ | 3.8132 | 21.71 | 38 | 5.4058 |
73
+ | 3.5336 | 22.86 | 40 | 5.5456 |
74
+ | 3.5355 | 24.0 | 42 | 5.3319 |
75
+ | 3.3558 | 24.57 | 43 | 5.3172 |
76
+ | 3.2986 | 25.71 | 45 | 5.3937 |
77
+ | 3.0968 | 26.86 | 47 | 5.3438 |
78
+ | 2.9288 | 28.0 | 49 | 5.4855 |
79
+ | 2.8645 | 28.57 | 50 | 5.4153 |
80
+ | 2.6979 | 29.71 | 52 | 5.5391 |
81
+ | 2.6357 | 30.86 | 54 | 5.6242 |
82
+ | 2.5271 | 32.0 | 56 | 5.6653 |
83
+ | 2.4606 | 32.57 | 57 | 5.7393 |
84
+ | 2.3441 | 33.71 | 59 | 5.8189 |
85
+ | 2.2027 | 34.86 | 61 | 5.7873 |
86
+ | 2.1467 | 36.0 | 63 | 5.7625 |
87
+ | 2.0218 | 36.57 | 64 | 5.7930 |
88
+ | 1.9145 | 37.71 | 66 | 5.9998 |
89
+ | 1.8427 | 38.86 | 68 | 5.9277 |
90
+ | 1.7795 | 40.0 | 70 | 5.9826 |
91
+ | 1.6823 | 40.57 | 71 | 6.0166 |
92
+ | 1.5936 | 41.71 | 73 | 6.0393 |
93
+ | 1.5114 | 42.86 | 75 | 6.1086 |
94
+ | 1.4313 | 44.0 | 77 | 6.1522 |
95
+ | 1.3536 | 44.57 | 78 | 6.1280 |
96
+ | 1.2649 | 45.71 | 80 | 6.1950 |
97
+ | 1.1631 | 46.86 | 82 | 6.2132 |
98
+ | 1.1196 | 48.0 | 84 | 6.2504 |
99
+ | 1.038 | 48.57 | 85 | 6.2654 |
100
+ | 0.9875 | 49.71 | 87 | 6.2609 |
101
+ | 0.9314 | 50.86 | 89 | 6.2622 |
102
+ | 0.9101 | 52.0 | 91 | 6.2624 |
103
+ | 0.8854 | 52.57 | 92 | 6.2676 |
104
+ | 0.8441 | 53.71 | 94 | 6.2807 |
105
+ | 0.8359 | 54.86 | 96 | 6.2855 |
106
+ | 0.8137 | 56.0 | 98 | 6.2849 |
107
+ | 0.815 | 56.57 | 99 | 6.2846 |
108
+ | 0.8284 | 57.14 | 100 | 6.2845 |
109
 
110
 
111
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d021d2d8676458c20960a472cdf7297e746755aabd78d27641db72c358c8a3a
3
  size 2796386080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17c1efb0068e09265d973c531ad4e0911372742a468e28c8842abc4358905829
3
  size 2796386080
runs/Apr17_12-24-48_gcn61.local.snellius.surf.nl/events.out.tfevents.1713349497.gcn61.local.snellius.surf.nl.3984517.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6f3d980b23d33ec2f66c7aa4389002abb105341cef143cc8b2622ea84f13474
3
+ size 41155
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed32b3d5b0def93391e72339d891569ab53ae8dd8b365dbfdf72094aee89a01c
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86662ece6d6f843dd83dc719cbd6d726ba4d67990a8b8eec336560c941979997
3
  size 4984