Hugging Face's logo

tyzhu
/
lmind_nq_train600_eval300_v1_recite_qa_gpt2-xl

Text Generation
Transformers
PyTorch
gpt2
Generated from Trainer
Eval Results
text-generation-inference
Model card Files Community
1
tyzhu commited on
Commit
850f96f
·
verified ·
1 Parent(s): d0b7bba

Model save

Browse files
Files changed (2) hide show
  1. README.md +45 -37
  2. pytorch_model.bin +1 -1
README.md CHANGED
@@ -3,23 +3,11 @@ license: mit
3
  base_model: gpt2-xl
4
  tags:
5
  - generated_from_trainer
6
- datasets:
7
- - tyzhu/lmind_nq_train600_eval300_v1_recite_qa
8
  metrics:
9
  - accuracy
10
  model-index:
11
  - name: lmind_nq_train600_eval300_v1_recite_qa_gpt2-xl
12
- results:
13
- - task:
14
- name: Causal Language Modeling
15
- type: text-generation
16
- dataset:
17
- name: tyzhu/lmind_nq_train600_eval300_v1_recite_qa
18
- type: tyzhu/lmind_nq_train600_eval300_v1_recite_qa
19
- metrics:
20
- - name: Accuracy
21
- type: accuracy
22
- value: 0.841281045751634
23
  ---
24
 
25
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -27,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
27
 
28
  # lmind_nq_train600_eval300_v1_recite_qa_gpt2-xl
29
 
30
- This model is a fine-tuned version of [gpt2-xl](https://huggingface.co/gpt2-xl) on the tyzhu/lmind_nq_train600_eval300_v1_recite_qa dataset.
31
  It achieves the following results on the evaluation set:
32
- - Loss: 0.3552
33
  - Accuracy: 0.8413
34
 
35
  ## Model description
@@ -55,31 +43,51 @@ The following hyperparameters were used during training:
55
  - seed: 42
56
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
57
  - lr_scheduler_type: constant
58
- - num_epochs: 10.0
59
 
60
  ### Training results
61
 
62
- | Training Loss | Epoch | Step | Validation Loss | Accuracy |
63
- |:-------------:|:-----:|:----:|:---------------:|:--------:|
64
- | 2.4392 | 0.51 | 47 | 2.1629 | 0.5938 |
65
- | 2.2015 | 1.01 | 94 | 1.8377 | 0.6250 |
66
- | 1.5193 | 1.52 | 141 | 1.8218 | 0.6524 |
67
- | 1.405 | 2.02 | 188 | 1.2418 | 0.6983 |
68
- | 0.8654 | 2.53 | 235 | 1.0606 | 0.7264 |
69
- | 0.7158 | 3.03 | 282 | 0.7902 | 0.7665 |
70
- | 0.4185 | 3.54 | 329 | 0.6745 | 0.7867 |
71
- | 0.4556 | 4.04 | 376 | 0.5201 | 0.8105 |
72
- | 0.253 | 4.55 | 423 | 0.4699 | 0.8198 |
73
- | 0.1895 | 5.05 | 470 | 0.4096 | 0.8301 |
74
- | 0.1649 | 5.56 | 517 | 0.3918 | 0.8323 |
75
- | 0.1468 | 6.06 | 564 | 0.3684 | 0.8367 |
76
- | 0.1179 | 6.57 | 611 | 0.3645 | 0.8377 |
77
- | 0.1171 | 7.08 | 658 | 0.3590 | 0.8394 |
78
- | 0.0953 | 7.58 | 705 | 0.3537 | 0.8402 |
79
- | 0.0831 | 8.09 | 752 | 0.3615 | 0.8400 |
80
- | 0.0824 | 8.59 | 799 | 0.3527 | 0.8408 |
81
- | 0.0764 | 9.1 | 846 | 0.3586 | 0.8410 |
82
- | 0.0731 | 9.6 | 893 | 0.3589 | 0.8408 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
83
 
84
 
85
  ### Framework versions
 
3
  base_model: gpt2-xl
4
  tags:
5
  - generated_from_trainer
 
 
6
  metrics:
7
  - accuracy
8
  model-index:
9
  - name: lmind_nq_train600_eval300_v1_recite_qa_gpt2-xl
10
+ results: []
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
15
 
16
  # lmind_nq_train600_eval300_v1_recite_qa_gpt2-xl
17
 
18
+ This model is a fine-tuned version of [gpt2-xl](https://huggingface.co/gpt2-xl) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.3638
21
  - Accuracy: 0.8413
22
 
23
  ## Model description
 
43
  - seed: 42
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: constant
46
+ - num_epochs: 20.0
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Accuracy | Validation Loss |
51
+ |:-------------:|:-----:|:----:|:--------:|:---------------:|
52
+ | 2.4392 | 0.51 | 47 | 0.5938 | 2.1629 |
53
+ | 2.2015 | 1.01 | 94 | 0.6250 | 1.8377 |
54
+ | 1.5193 | 1.52 | 141 | 0.6524 | 1.8218 |
55
+ | 1.405 | 2.02 | 188 | 0.6983 | 1.2418 |
56
+ | 0.8654 | 2.53 | 235 | 0.7264 | 1.0606 |
57
+ | 0.7158 | 3.03 | 282 | 0.7665 | 0.7902 |
58
+ | 0.4185 | 3.54 | 329 | 0.7867 | 0.6745 |
59
+ | 0.4556 | 4.04 | 376 | 0.8105 | 0.5201 |
60
+ | 0.253 | 4.55 | 423 | 0.8198 | 0.4699 |
61
+ | 0.1895 | 5.05 | 470 | 0.8301 | 0.4096 |
62
+ | 0.1649 | 5.56 | 517 | 0.8323 | 0.3918 |
63
+ | 0.1468 | 6.06 | 564 | 0.8367 | 0.3684 |
64
+ | 0.1179 | 6.57 | 611 | 0.8377 | 0.3645 |
65
+ | 0.1171 | 7.08 | 658 | 0.8394 | 0.3590 |
66
+ | 0.0953 | 7.58 | 705 | 0.8402 | 0.3537 |
67
+ | 0.0831 | 8.09 | 752 | 0.8400 | 0.3615 |
68
+ | 0.0824 | 8.59 | 799 | 0.8408 | 0.3527 |
69
+ | 0.0764 | 9.1 | 846 | 0.8410 | 0.3586 |
70
+ | 0.0731 | 9.6 | 893 | 0.8408 | 0.3589 |
71
+ | 0.0637 | 10.11 | 940 | 0.3618 | 0.8412 |
72
+ | 0.069 | 10.61 | 987 | 0.3563 | 0.8415 |
73
+ | 0.0636 | 11.12 | 1034 | 0.3650 | 0.8409 |
74
+ | 0.0663 | 11.62 | 1081 | 0.3554 | 0.8418 |
75
+ | 0.0636 | 12.13 | 1128 | 0.3675 | 0.8409 |
76
+ | 0.0632 | 12.63 | 1175 | 0.3590 | 0.8418 |
77
+ | 0.0605 | 13.14 | 1222 | 0.3635 | 0.8413 |
78
+ | 0.0621 | 13.65 | 1269 | 0.3558 | 0.8413 |
79
+ | 0.0579 | 14.15 | 1316 | 0.3682 | 0.8410 |
80
+ | 0.0618 | 14.66 | 1363 | 0.3653 | 0.8405 |
81
+ | 0.0552 | 15.16 | 1410 | 0.3661 | 0.8413 |
82
+ | 0.0619 | 15.67 | 1457 | 0.3596 | 0.8416 |
83
+ | 0.0536 | 16.17 | 1504 | 0.3710 | 0.8414 |
84
+ | 0.0602 | 16.68 | 1551 | 0.3609 | 0.8418 |
85
+ | 0.054 | 17.18 | 1598 | 0.3759 | 0.8410 |
86
+ | 0.0635 | 17.69 | 1645 | 0.3597 | 0.8414 |
87
+ | 0.0536 | 18.19 | 1692 | 0.3750 | 0.8410 |
88
+ | 0.0588 | 18.7 | 1739 | 0.3684 | 0.8414 |
89
+ | 0.0713 | 19.2 | 1786 | 0.3691 | 0.8411 |
90
+ | 0.0704 | 19.71 | 1833 | 0.3638 | 0.8413 |
91
 
92
 
93
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83824ec995c6529762b6535e63512aabd5e3f31377ab61e7396e4f94aa5df53a
3
  size 6230637102
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ed51b164e98ba9303881ebaa6a9f1b4939a0edd647a9e5654a453eef41baa5
3
  size 6230637102