Hugging Face's logo

augustocsc
/
Se124M10KInfPrompt_endtoken

PEFT
Safetensors
Generated from Trainer
Model card Files
xet
Community
augustocsc commited on
Commit
716dbb5
·
verified ·
1 Parent(s): d245392

Training in progress, epoch 1

Browse files
Files changed (10) hide show
  1. README.md +36 -50
  2. adapter_model.safetensors +2 -2
  3. added_tokens.json +3 -2
  4. all_results.json +11 -11
  5. eval_results.json +6 -6
  6. special_tokens_map.json +1 -14
  7. tokenizer.json +12 -3
  8. tokenizer_config.json +13 -6
  9. train_results.json +6 -6
  10. training_args.bin +1 -1
README.md CHANGED
@@ -5,18 +5,18 @@ base_model: gpt2
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
- - name: Se124M10KInfPrompt_endtoken
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
- # Se124M10KInfPrompt_endtoken
16
 
17
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.7552
20
 
21
  ## Model description
22
 
@@ -46,53 +46,39 @@ The following hyperparameters were used during training:
46
 
47
  ### Training results
48
 
49
- | Training Loss | Epoch | Step | Validation Loss |
50
- |:-------------:|:-----:|:----:|:---------------:|
51
- | 0.6082 | 1.0 | 153 | 1.4745 |
52
- | 0.3175 | 2.0 | 306 | 1.0258 |
53
- | 0.2798 | 3.0 | 459 | 0.9099 |
54
- | 0.244 | 4.0 | 612 | 0.8688 |
55
- | 0.2373 | 5.0 | 765 | 0.8479 |
56
- | 0.2252 | 6.0 | 918 | 0.8343 |
57
- | 0.2289 | 7.0 | 1071 | 0.8216 |
58
- | 0.2209 | 8.0 | 1224 | 0.8143 |
59
- | 0.2211 | 9.0 | 1377 | 0.8082 |
60
- | 0.2176 | 10.0 | 1530 | 0.8029 |
61
- | 0.2157 | 11.0 | 1683 | 0.7990 |
62
- | 0.2097 | 12.0 | 1836 | 0.7945 |
63
- | 0.2113 | 13.0 | 1989 | 0.7921 |
64
- | 0.2099 | 14.0 | 2142 | 0.7891 |
65
- | 0.2073 | 15.0 | 2295 | 0.7863 |
66
- | 0.2055 | 16.0 | 2448 | 0.7805 |
67
- | 0.2051 | 17.0 | 2601 | 0.7806 |
68
- | 0.2031 | 18.0 | 2754 | 0.7776 |
69
- | 0.2046 | 19.0 | 2907 | 0.7760 |
70
- | 0.206 | 20.0 | 3060 | 0.7720 |
71
- | 0.2043 | 21.0 | 3213 | 0.7725 |
72
- | 0.204 | 22.0 | 3366 | 0.7707 |
73
- | 0.2032 | 23.0 | 3519 | 0.7681 |
74
- | 0.2026 | 24.0 | 3672 | 0.7678 |
75
- | 0.1991 | 25.0 | 3825 | 0.7665 |
76
- | 0.2037 | 26.0 | 3978 | 0.7660 |
77
- | 0.2011 | 27.0 | 4131 | 0.7634 |
78
- | 0.2015 | 28.0 | 4284 | 0.7635 |
79
- | 0.2006 | 29.0 | 4437 | 0.7620 |
80
- | 0.2014 | 30.0 | 4590 | 0.7640 |
81
- | 0.2 | 31.0 | 4743 | 0.7609 |
82
- | 0.202 | 32.0 | 4896 | 0.7606 |
83
- | 0.1989 | 33.0 | 5049 | 0.7599 |
84
- | 0.1983 | 34.0 | 5202 | 0.7594 |
85
- | 0.2 | 35.0 | 5355 | 0.7596 |
86
- | 0.1991 | 36.0 | 5508 | 0.7588 |
87
- | 0.1978 | 37.0 | 5661 | 0.7576 |
88
- | 0.1975 | 38.0 | 5814 | 0.7572 |
89
- | 0.2007 | 39.0 | 5967 | 0.7569 |
90
- | 0.1987 | 40.0 | 6120 | 0.7563 |
91
- | 0.2002 | 41.0 | 6273 | 0.7561 |
92
- | 0.1961 | 42.0 | 6426 | 0.7563 |
93
- | 0.201 | 43.0 | 6579 | 0.7552 |
94
- | 0.1993 | 44.0 | 6732 | 0.7553 |
95
- | 0.1969 | 45.0 | 6885 | 0.7553 |
96
 
97
 
98
  ### Framework versions
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: Se124M500KInfPrompt_endtoken
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
+ # Se124M500KInfPrompt_endtoken
16
 
17
  This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.6716
20
 
21
  ## Model description
22
 
 
46
 
47
  ### Training results
48
 
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:------:|:---------------:|
51
+ | 0.1898 | 1.0 | 5427 | 0.7433 |
52
+ | 0.1857 | 2.0 | 10854 | 0.7238 |
53
+ | 0.1843 | 3.0 | 16281 | 0.7118 |
54
+ | 0.1813 | 4.0 | 21708 | 0.7045 |
55
+ | 0.1802 | 5.0 | 27135 | 0.6990 |
56
+ | 0.1785 | 6.0 | 32562 | 0.6944 |
57
+ | 0.1769 | 7.0 | 37989 | 0.6918 |
58
+ | 0.1743 | 8.0 | 43416 | 0.6875 |
59
+ | 0.1752 | 9.0 | 48843 | 0.6854 |
60
+ | 0.1756 | 10.0 | 54270 | 0.6854 |
61
+ | 0.1736 | 11.0 | 59697 | 0.6837 |
62
+ | 0.1756 | 12.0 | 65124 | 0.6812 |
63
+ | 0.173 | 13.0 | 70551 | 0.6798 |
64
+ | 0.1737 | 14.0 | 75978 | 0.6791 |
65
+ | 0.1741 | 15.0 | 81405 | 0.6783 |
66
+ | 0.177 | 16.0 | 86832 | 0.6771 |
67
+ | 0.1734 | 17.0 | 92259 | 0.6765 |
68
+ | 0.1719 | 18.0 | 97686 | 0.6760 |
69
+ | 0.1737 | 19.0 | 103113 | 0.6763 |
70
+ | 0.1716 | 20.0 | 108540 | 0.6747 |
71
+ | 0.1713 | 21.0 | 113967 | 0.6741 |
72
+ | 0.1739 | 22.0 | 119394 | 0.6738 |
73
+ | 0.1694 | 23.0 | 124821 | 0.6737 |
74
+ | 0.1703 | 24.0 | 130248 | 0.6743 |
75
+ | 0.1697 | 25.0 | 135675 | 0.6730 |
76
+ | 0.172 | 26.0 | 141102 | 0.6731 |
77
+ | 0.1711 | 27.0 | 146529 | 0.6720 |
78
+ | 0.1726 | 28.0 | 151956 | 0.6720 |
79
+ | 0.1703 | 29.0 | 157383 | 0.6716 |
80
+ | 0.1732 | 30.0 | 162810 | 0.6716 |
81
+ | 0.171 | 31.0 | 168237 | 0.6719 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82
 
83
 
84
  ### Framework versions
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:becdfda6ffd9bb761a7db78b383bdc2364d7d7864f0e26a424ad9e0dcbd174e2
3
- size 309974336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97369058fd0481fa20cb01f0f83e4c65dc6f4ae1a380505ea9622d50bc4a9660
3
+ size 309980480
added_tokens.json CHANGED
@@ -1,4 +1,5 @@
1
  {
2
- "<endofex>": 50258,
3
- "<startofex>": 50257
 
4
  }
 
1
  {
2
+ "<endofex>": 50257,
3
+ "<pad>": 50258,
4
+ "<startofex>": 50259
5
  }
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
- "epoch": 45.0,
3
- "eval_loss": 0.7551774382591248,
4
- "eval_runtime": 6.5379,
5
- "eval_samples_per_second": 161.672,
6
- "eval_steps_per_second": 5.2,
7
- "perplexity": 2.127989076535295,
8
- "total_flos": 1.438582110879744e+16,
9
- "train_loss": 0.2186263353822884,
10
- "train_runtime": 769.5598,
11
- "train_samples_per_second": 316.869,
12
- "train_steps_per_second": 9.941
13
  }
 
1
  {
2
+ "epoch": 31.0,
3
+ "eval_loss": 0.6716023087501526,
4
+ "eval_runtime": 232.3059,
5
+ "eval_samples_per_second": 160.323,
6
+ "eval_steps_per_second": 5.011,
7
+ "perplexity": 1.9573711221830141,
8
+ "total_flos": 3.528546650263388e+17,
9
+ "train_loss": 0.17647521918996942,
10
+ "train_runtime": 17128.7716,
11
+ "train_samples_per_second": 506.884,
12
+ "train_steps_per_second": 15.842
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 45.0,
3
- "eval_loss": 0.7551774382591248,
4
- "eval_runtime": 6.5379,
5
- "eval_samples_per_second": 161.672,
6
- "eval_steps_per_second": 5.2,
7
- "perplexity": 2.127989076535295
8
  }
 
1
  {
2
+ "epoch": 31.0,
3
+ "eval_loss": 0.6716023087501526,
4
+ "eval_runtime": 232.3059,
5
+ "eval_samples_per_second": 160.323,
6
+ "eval_steps_per_second": 5.011,
7
+ "perplexity": 1.9573711221830141
8
  }
special_tokens_map.json CHANGED
@@ -6,23 +6,10 @@
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false
9
- },
10
- {
11
- "content": "<endofex>",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
  }
17
  ],
18
  "bos_token": "<|endoftext|>",
19
  "eos_token": "<endofex>",
20
- "pad_token": {
21
- "content": "<|endoftext|>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false
26
- },
27
  "unk_token": "<|endoftext|>"
28
  }
 
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false
 
 
 
 
 
 
 
9
  }
10
  ],
11
  "bos_token": "<|endoftext|>",
12
  "eos_token": "<endofex>",
13
+ "pad_token": "<pad>",
 
 
 
 
 
 
14
  "unk_token": "<|endoftext|>"
15
  }
tokenizer.json CHANGED
@@ -14,12 +14,12 @@
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
- "normalized": false,
18
  "special": true
19
  },
20
  {
21
  "id": 50257,
22
- "content": "<startofex>",
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
@@ -28,7 +28,16 @@
28
  },
29
  {
30
  "id": 50258,
31
- "content": "<endofex>",
 
 
 
 
 
 
 
 
 
32
  "single_word": false,
33
  "lstrip": false,
34
  "rstrip": false,
 
14
  "single_word": false,
15
  "lstrip": false,
16
  "rstrip": false,
17
+ "normalized": true,
18
  "special": true
19
  },
20
  {
21
  "id": 50257,
22
+ "content": "<endofex>",
23
  "single_word": false,
24
  "lstrip": false,
25
  "rstrip": false,
 
28
  },
29
  {
30
  "id": 50258,
31
+ "content": "<pad>",
32
+ "single_word": false,
33
+ "lstrip": false,
34
+ "rstrip": false,
35
+ "normalized": false,
36
+ "special": true
37
+ },
38
+ {
39
+ "id": 50259,
40
+ "content": "<startofex>",
41
  "single_word": false,
42
  "lstrip": false,
43
  "rstrip": false,
tokenizer_config.json CHANGED
@@ -4,13 +4,13 @@
4
  "50256": {
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
7
- "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
  "50257": {
13
- "content": "<startofex>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
@@ -18,7 +18,15 @@
18
  "special": true
19
  },
20
  "50258": {
21
- "content": "<endofex>",
 
 
 
 
 
 
 
 
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
@@ -27,15 +35,14 @@
27
  }
28
  },
29
  "additional_special_tokens": [
30
- "<startofex>",
31
- "<endofex>"
32
  ],
33
  "bos_token": "<|endoftext|>",
34
  "clean_up_tokenization_spaces": false,
35
  "eos_token": "<endofex>",
36
  "extra_special_tokens": {},
37
  "model_max_length": 1024,
38
- "pad_token": "<|endoftext|>",
39
  "tokenizer_class": "GPT2Tokenizer",
40
  "unk_token": "<|endoftext|>"
41
  }
 
4
  "50256": {
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
7
+ "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
  "50257": {
13
+ "content": "<endofex>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
 
18
  "special": true
19
  },
20
  "50258": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<startofex>",
30
  "lstrip": false,
31
  "normalized": false,
32
  "rstrip": false,
 
35
  }
36
  },
37
  "additional_special_tokens": [
38
+ "<startofex>"
 
39
  ],
40
  "bos_token": "<|endoftext|>",
41
  "clean_up_tokenization_spaces": false,
42
  "eos_token": "<endofex>",
43
  "extra_special_tokens": {},
44
  "model_max_length": 1024,
45
+ "pad_token": "<pad>",
46
  "tokenizer_class": "GPT2Tokenizer",
47
  "unk_token": "<|endoftext|>"
48
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 45.0,
3
- "total_flos": 1.438582110879744e+16,
4
- "train_loss": 0.2186263353822884,
5
- "train_runtime": 769.5598,
6
- "train_samples_per_second": 316.869,
7
- "train_steps_per_second": 9.941
8
  }
 
1
  {
2
+ "epoch": 31.0,
3
+ "total_flos": 3.528546650263388e+17,
4
+ "train_loss": 0.17647521918996942,
5
+ "train_runtime": 17128.7716,
6
+ "train_samples_per_second": 506.884,
7
+ "train_steps_per_second": 15.842
8
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cb8d07c46dde0176d6d1431dfbd1cc46896dd403ee33fdaae0d352f111ea564
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a96b81c7f50a7f675785b2ef6fe69a21a57d6c26d5a1dbe61b36bcfb02febcf
3
  size 5432