Hugging Face's logo

gjonesQ02
/
StatementOfWork_Generator_Omega2

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files
xet
Metrics Community
gjonesQ02 commited on
Commit
ffa2260
·
verified ·
1 Parent(s): 8a4031b

End of training

Browse files
Files changed (6) hide show
  1. README.md +53 -23
  2. model.safetensors +1 -1
  3. runs/Jun27_16-49-30_viridian/events.out.tfevents.1719506973.viridian.2678733.12 +3 -0
  4. special_tokens_map.json +22 -3
  5. tokenizer_config.json +1 -0
  6. training_args.bin +1 -1
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
- base_model: distilgpt2
6
  model-index:
7
  - name: StatementOfWork_Generator_Omega2
8
  results: []
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.9660
19
 
20
  ## Model description
21
 
@@ -40,32 +40,62 @@ The following hyperparameters were used during training:
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
- - num_epochs: 20
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
- | No log | 1.0 | 15 | 0.9874 |
50
- | No log | 2.0 | 30 | 0.9890 |
51
- | No log | 3.0 | 45 | 0.9814 |
52
- | No log | 4.0 | 60 | 0.9776 |
53
- | No log | 5.0 | 75 | 0.9778 |
54
- | No log | 6.0 | 90 | 0.9790 |
55
- | No log | 7.0 | 105 | 0.9780 |
56
- | No log | 8.0 | 120 | 0.9726 |
57
- | No log | 9.0 | 135 | 0.9727 |
58
- | No log | 10.0 | 150 | 0.9716 |
59
- | No log | 11.0 | 165 | 0.9711 |
60
- | No log | 12.0 | 180 | 0.9686 |
61
- | No log | 13.0 | 195 | 0.9690 |
62
- | No log | 14.0 | 210 | 0.9693 |
63
- | No log | 15.0 | 225 | 0.9679 |
64
- | No log | 16.0 | 240 | 0.9670 |
65
- | No log | 17.0 | 255 | 0.9660 |
66
- | No log | 18.0 | 270 | 0.9646 |
67
- | No log | 19.0 | 285 | 0.9661 |
68
- | No log | 20.0 | 300 | 0.9660 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
 
1
  ---
2
  license: apache-2.0
3
+ base_model: distilgpt2
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: StatementOfWork_Generator_Omega2
8
  results: []
 
15
 
16
  This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.9436
19
 
20
  ## Model description
21
 
 
40
  - seed: 42
41
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
  - lr_scheduler_type: linear
43
+ - num_epochs: 50
44
 
45
  ### Training results
46
 
47
  | Training Loss | Epoch | Step | Validation Loss |
48
  |:-------------:|:-----:|:----:|:---------------:|
49
+ | No log | 1.0 | 15 | 0.9674 |
50
+ | No log | 2.0 | 30 | 0.9673 |
51
+ | No log | 3.0 | 45 | 0.9633 |
52
+ | No log | 4.0 | 60 | 0.9629 |
53
+ | No log | 5.0 | 75 | 0.9633 |
54
+ | No log | 6.0 | 90 | 0.9634 |
55
+ | No log | 7.0 | 105 | 0.9635 |
56
+ | No log | 8.0 | 120 | 0.9603 |
57
+ | No log | 9.0 | 135 | 0.9550 |
58
+ | No log | 10.0 | 150 | 0.9583 |
59
+ | No log | 11.0 | 165 | 0.9574 |
60
+ | No log | 12.0 | 180 | 0.9544 |
61
+ | No log | 13.0 | 195 | 0.9540 |
62
+ | No log | 14.0 | 210 | 0.9575 |
63
+ | No log | 15.0 | 225 | 0.9530 |
64
+ | No log | 16.0 | 240 | 0.9519 |
65
+ | No log | 17.0 | 255 | 0.9514 |
66
+ | No log | 18.0 | 270 | 0.9534 |
67
+ | No log | 19.0 | 285 | 0.9498 |
68
+ | No log | 20.0 | 300 | 0.9554 |
69
+ | No log | 21.0 | 315 | 0.9474 |
70
+ | No log | 22.0 | 330 | 0.9539 |
71
+ | No log | 23.0 | 345 | 0.9470 |
72
+ | No log | 24.0 | 360 | 0.9491 |
73
+ | No log | 25.0 | 375 | 0.9478 |
74
+ | No log | 26.0 | 390 | 0.9454 |
75
+ | No log | 27.0 | 405 | 0.9472 |
76
+ | No log | 28.0 | 420 | 0.9481 |
77
+ | No log | 29.0 | 435 | 0.9467 |
78
+ | No log | 30.0 | 450 | 0.9473 |
79
+ | No log | 31.0 | 465 | 0.9478 |
80
+ | No log | 32.0 | 480 | 0.9439 |
81
+ | No log | 33.0 | 495 | 0.9453 |
82
+ | 0.2954 | 34.0 | 510 | 0.9446 |
83
+ | 0.2954 | 35.0 | 525 | 0.9453 |
84
+ | 0.2954 | 36.0 | 540 | 0.9452 |
85
+ | 0.2954 | 37.0 | 555 | 0.9442 |
86
+ | 0.2954 | 38.0 | 570 | 0.9459 |
87
+ | 0.2954 | 39.0 | 585 | 0.9442 |
88
+ | 0.2954 | 40.0 | 600 | 0.9443 |
89
+ | 0.2954 | 41.0 | 615 | 0.9445 |
90
+ | 0.2954 | 42.0 | 630 | 0.9442 |
91
+ | 0.2954 | 43.0 | 645 | 0.9441 |
92
+ | 0.2954 | 44.0 | 660 | 0.9453 |
93
+ | 0.2954 | 45.0 | 675 | 0.9447 |
94
+ | 0.2954 | 46.0 | 690 | 0.9441 |
95
+ | 0.2954 | 47.0 | 705 | 0.9438 |
96
+ | 0.2954 | 48.0 | 720 | 0.9438 |
97
+ | 0.2954 | 49.0 | 735 | 0.9437 |
98
+ | 0.2954 | 50.0 | 750 | 0.9436 |
99
 
100
 
101
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be4eb3e438ce5e49d5aa97f0d12ef53e2aba977c3066261382bc6c82e05461af
3
  size 327657928
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30ddad8e4f69252a55ca7da39b4df696ada779576d46960546b9485e12437ae0
3
  size 327657928
runs/Jun27_16-49-30_viridian/events.out.tfevents.1719506973.viridian.2678733.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8809b5f238ff59eb82f27f3e020820c730e318987874cc79e47a847d1c993bc
3
+ size 19117
special_tokens_map.json CHANGED
@@ -1,5 +1,24 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
  }
tokenizer_config.json CHANGED
@@ -14,6 +14,7 @@
14
  "clean_up_tokenization_spaces": true,
15
  "eos_token": "<|endoftext|>",
16
  "model_max_length": 1024,
 
17
  "tokenizer_class": "GPT2Tokenizer",
18
  "unk_token": "<|endoftext|>"
19
  }
 
14
  "clean_up_tokenization_spaces": true,
15
  "eos_token": "<|endoftext|>",
16
  "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
  "tokenizer_class": "GPT2Tokenizer",
19
  "unk_token": "<|endoftext|>"
20
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcd3416513e8eb19b4b21d4a4367a63e9084f048dff92b5274ea23d37827e9bb
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:679b8acb71348fa85d8ca3fef5484876c5c6a4bce535c6ca4af72c44b1688a17
3
  size 5048