Hugging Face's logo

BluebrainAI
/
parallel-mean-bottleneck-gpt2-medium-wikitext

Feature Extraction
Transformers
Safetensors
parallel-gpt2
Generated from Trainer
custom_code
Model card Files Community
shivanandmn commited on
Commit
37eb7f1
·
verified ·
1 Parent(s): 12eeb00

Model save

Browse files
Files changed (2) hide show
  1. README.md +23 -23
  2. model.safetensors +1 -1
README.md CHANGED
@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 3.1859
21
- - Accuracy: 0.4194
22
- - Perplexity: 24.1889
23
- - Bleu: 0.1461
24
 
25
  ## Model description
26
 
@@ -50,25 +50,25 @@ The following hyperparameters were used during training:
50
 
51
  ### Training results
52
 
53
- | Training Loss | Epoch | Step | Accuracy | Bleu | Validation Loss | Perplexity |
54
- |:-------------:|:------:|:----:|:--------:|:------:|:---------------:|:----------:|
55
- | 6.0432 | 0.2806 | 500 | 0.1909 | 0.0378 | 5.9180 | 371.6605 |
56
- | 5.0476 | 0.5612 | 1000 | 0.2633 | 0.0612 | 4.8985 | 134.0910 |
57
- | 4.3528 | 0.8418 | 1500 | 0.3182 | 0.0834 | 4.2398 | 69.3933 |
58
- | 3.9497 | 1.1223 | 2000 | 0.3520 | 0.1054 | 3.8879 | 48.8078 |
59
- | 3.7614 | 1.4029 | 2500 | 0.3674 | 0.1207 | 3.7128 | 40.9670 |
60
- | 3.6543 | 1.6835 | 3000 | 0.3780 | 0.1310 | 3.5902 | 36.2404 |
61
- | 3.5527 | 1.9641 | 3500 | 0.3864 | 0.1337 | 3.5048 | 33.2757 |
62
- | 3.4348 | 2.2447 | 4000 | 0.3923 | 0.1361 | 3.4401 | 31.1898 |
63
- | 3.3739 | 2.5253 | 4500 | 3.3868 | 0.3974 | 29.5718 | 0.1419 |
64
- | 3.3441 | 2.8058 | 5000 | 3.3419 | 0.4020 | 28.2718 | 0.1394 |
65
- | 3.2252 | 3.0864 | 5500 | 3.3067 | 0.4057 | 27.2940 | 0.1432 |
66
- | 3.2188 | 3.3670 | 6000 | 3.2775 | 0.4088 | 26.5107 | 0.1421 |
67
- | 3.1971 | 3.6476 | 6500 | 3.2502 | 0.4115 | 25.7958 | 0.1426 |
68
- | 3.1722 | 3.9282 | 7000 | 3.2266 | 0.4143 | 25.1936 | 0.1446 |
69
- | 3.1052 | 4.2088 | 7500 | 3.2103 | 0.4163 | 24.7864 | 0.1433 |
70
- | 3.0672 | 4.4893 | 8000 | 3.1967 | 0.4180 | 24.4514 | 0.1438 |
71
- | 3.0774 | 4.7699 | 8500 | 3.1859 | 0.4194 | 24.1889 | 0.1461 |
72
 
73
 
74
  ### Framework versions
 
17
 
18
  This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 3.1861
21
+ - Accuracy: 0.4193
22
+ - Perplexity: 24.1930
23
+ - Bleu: 0.1440
24
 
25
  ## Model description
26
 
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy | Perplexity | Bleu |
54
+ |:-------------:|:------:|:----:|:---------------:|:--------:|:----------:|:------:|
55
+ | 6.0438 | 0.2806 | 500 | 5.9200 | 0.1897 | 372.4009 | 0.0359 |
56
+ | 5.0422 | 0.5612 | 1000 | 4.8934 | 0.2636 | 133.4091 | 0.0610 |
57
+ | 4.3494 | 0.8418 | 1500 | 4.2389 | 0.3183 | 69.3337 | 0.0833 |
58
+ | 3.9486 | 1.1223 | 2000 | 3.8856 | 0.3521 | 48.6953 | 0.1037 |
59
+ | 3.7605 | 1.4029 | 2500 | 3.7143 | 0.3671 | 41.0301 | 0.1206 |
60
+ | 3.6544 | 1.6835 | 3000 | 3.5898 | 0.3781 | 36.2282 | 0.1332 |
61
+ | 3.5527 | 1.9641 | 3500 | 3.5051 | 0.3862 | 33.2836 | 0.1349 |
62
+ | 3.4346 | 2.2447 | 4000 | 3.4410 | 0.3919 | 31.2181 | 0.1335 |
63
+ | 3.374 | 2.5253 | 4500 | 3.3867 | 0.3972 | 29.5672 | 0.1354 |
64
+ | 3.3442 | 2.8058 | 5000 | 3.3410 | 0.4017 | 28.2468 | 0.1405 |
65
+ | 3.2251 | 3.0864 | 5500 | 3.3072 | 0.4055 | 27.3093 | 0.1404 |
66
+ | 3.2187 | 3.3670 | 6000 | 3.2781 | 0.4088 | 26.5242 | 0.1401 |
67
+ | 3.1975 | 3.6476 | 6500 | 3.2494 | 0.4118 | 25.7753 | 0.1433 |
68
+ | 3.172 | 3.9282 | 7000 | 3.2276 | 0.4142 | 25.2178 | 0.1445 |
69
+ | 3.1055 | 4.2088 | 7500 | 3.2109 | 0.4163 | 24.8014 | 0.1447 |
70
+ | 3.0676 | 4.4893 | 8000 | 3.1977 | 0.4178 | 24.4763 | 0.1453 |
71
+ | 3.0779 | 4.7699 | 8500 | 3.1861 | 0.4193 | 24.1930 | 0.1440 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c7a2ac975270295cb9f8b893c0687a523bec8cd92f794b3b282581d8dc36dc5
3
  size 1419322880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9062c5cf6e74adbf118174e57a33cbd4d8758e18adb16a98323b4894d9c43298
3
  size 1419322880