Hugging Face's logo

ke-lly
/
47185774_0

Text Generation
Transformers
Safetensors
gpt2
trl
sft
Generated from Trainer
Inference Endpoints
text-generation-inference
Model card Files Community
ke-lly commited on
Commit
4844c56
•
1 Parent(s): d87eef2

Model save

Browse files
Files changed (2) hide show
  1. README.md +146 -0
  2. generation_config.json +6 -0
README.md ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: openai-community/gpt2
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ metrics:
9
+ - accuracy
10
+ model-index:
11
+ - name: '47185774_0'
12
+ results: []
13
+ ---
14
+
15
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
16
+ should probably proofread and complete it, then remove this comment. -->
17
+
18
+ # 47185774_0
19
+
20
+ This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
21
+ It achieves the following results on the evaluation set:
22
+ - Loss: 0.5103
23
+ - Accuracy: 0.0000
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 1.41e-05
43
+ - train_batch_size: 32
44
+ - eval_batch_size: 4
45
+ - seed: 42
46
+ - distributed_type: multi-GPU
47
+ - num_devices: 2
48
+ - gradient_accumulation_steps: 4
49
+ - total_train_batch_size: 256
50
+ - total_eval_batch_size: 8
51
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
52
+ - lr_scheduler_type: linear
53
+ - training_steps: 2000
54
+
55
+ ### Training results
56
+
57
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
58
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
59
+ | 1.0647 | 1.67 | 25 | 0.9608 | 0.0001 |
60
+ | 0.8454 | 3.33 | 50 | 0.7926 | 0.0001 |
61
+ | 0.7865 | 5.0 | 75 | 0.7448 | 0.0001 |
62
+ | 0.757 | 6.67 | 100 | 0.7207 | 0.0001 |
63
+ | 0.7338 | 8.33 | 125 | 0.7058 | 0.0000 |
64
+ | 0.721 | 10.0 | 150 | 0.6932 | 0.0000 |
65
+ | 0.7216 | 11.67 | 175 | 0.6845 | 0.0000 |
66
+ | 0.709 | 13.33 | 200 | 0.6766 | 0.0000 |
67
+ | 0.6942 | 15.0 | 225 | 0.6694 | 0.0000 |
68
+ | 0.6921 | 16.67 | 250 | 0.6633 | 0.0000 |
69
+ | 0.6945 | 18.33 | 275 | 0.6582 | 0.0000 |
70
+ | 0.6826 | 20.0 | 300 | 0.6524 | 0.0000 |
71
+ | 0.6702 | 21.67 | 325 | 0.6475 | 0.0000 |
72
+ | 0.6637 | 23.33 | 350 | 0.6428 | 0.0000 |
73
+ | 0.6695 | 25.0 | 375 | 0.6384 | 0.0000 |
74
+ | 0.6615 | 26.67 | 400 | 0.6334 | 0.0000 |
75
+ | 0.6491 | 28.33 | 425 | 0.6299 | 0.0000 |
76
+ | 0.6553 | 30.0 | 450 | 0.6254 | 0.0000 |
77
+ | 0.6473 | 31.67 | 475 | 0.6216 | 0.0000 |
78
+ | 0.6345 | 33.33 | 500 | 0.6183 | 0.0000 |
79
+ | 0.6486 | 35.0 | 525 | 0.6145 | 0.0000 |
80
+ | 0.6365 | 36.67 | 550 | 0.6109 | 0.0000 |
81
+ | 0.6313 | 38.33 | 575 | 0.6079 | 0.0000 |
82
+ | 0.636 | 40.0 | 600 | 0.6048 | 0.0000 |
83
+ | 0.6268 | 41.67 | 625 | 0.6015 | 0.0000 |
84
+ | 0.6274 | 43.33 | 650 | 0.5981 | 0.0000 |
85
+ | 0.6135 | 45.0 | 675 | 0.5952 | 0.0000 |
86
+ | 0.6219 | 46.67 | 700 | 0.5919 | 0.0000 |
87
+ | 0.6166 | 48.33 | 725 | 0.5890 | 0.0000 |
88
+ | 0.6136 | 50.0 | 750 | 0.5863 | 0.0000 |
89
+ | 0.6053 | 51.67 | 775 | 0.5837 | 0.0000 |
90
+ | 0.5999 | 53.33 | 800 | 0.5806 | 0.0000 |
91
+ | 0.6141 | 55.0 | 825 | 0.5782 | 0.0000 |
92
+ | 0.6058 | 56.67 | 850 | 0.5753 | 0.0000 |
93
+ | 0.6026 | 58.33 | 875 | 0.5728 | 0.0000 |
94
+ | 0.5949 | 60.0 | 900 | 0.5702 | 0.0000 |
95
+ | 0.6007 | 61.67 | 925 | 0.5675 | 0.0000 |
96
+ | 0.5927 | 63.33 | 950 | 0.5647 | 0.0000 |
97
+ | 0.593 | 65.0 | 975 | 0.5625 | 0.0000 |
98
+ | 0.5831 | 66.67 | 1000 | 0.5597 | 0.0000 |
99
+ | 0.6008 | 68.33 | 1025 | 0.5574 | 0.0000 |
100
+ | 0.5877 | 70.0 | 1050 | 0.5551 | 0.0000 |
101
+ | 0.5847 | 71.67 | 1075 | 0.5524 | 0.0000 |
102
+ | 0.5794 | 73.33 | 1100 | 0.5500 | 0.0000 |
103
+ | 0.5952 | 75.0 | 1125 | 0.5474 | 0.0000 |
104
+ | 0.5857 | 76.67 | 1150 | 0.5455 | 0.0000 |
105
+ | 0.5787 | 78.33 | 1175 | 0.5433 | 0.0000 |
106
+ | 0.5963 | 80.0 | 1200 | 0.5416 | 0.0000 |
107
+ | 0.564 | 81.67 | 1225 | 0.5390 | 0.0000 |
108
+ | 0.5691 | 83.33 | 1250 | 0.5368 | 0.0000 |
109
+ | 0.5837 | 85.0 | 1275 | 0.5352 | 0.0000 |
110
+ | 0.5668 | 86.67 | 1300 | 0.5333 | 0.0000 |
111
+ | 0.5716 | 88.33 | 1325 | 0.5319 | 0.0000 |
112
+ | 0.557 | 90.0 | 1350 | 0.5300 | 0.0000 |
113
+ | 0.5539 | 91.67 | 1375 | 0.5286 | 0.0000 |
114
+ | 0.5683 | 93.33 | 1400 | 0.5273 | 0.0000 |
115
+ | 0.5671 | 95.0 | 1425 | 0.5255 | 0.0000 |
116
+ | 0.5723 | 96.67 | 1450 | 0.5244 | 0.0000 |
117
+ | 0.5627 | 98.33 | 1475 | 0.5229 | 0.0000 |
118
+ | 0.5627 | 100.0 | 1500 | 0.5215 | 0.0000 |
119
+ | 0.5606 | 101.67 | 1525 | 0.5205 | 0.0000 |
120
+ | 0.5651 | 103.33 | 1550 | 0.5192 | 0.0000 |
121
+ | 0.5703 | 105.0 | 1575 | 0.5184 | 0.0000 |
122
+ | 0.5533 | 106.67 | 1600 | 0.5176 | 0.0000 |
123
+ | 0.5627 | 108.33 | 1625 | 0.5165 | 0.0000 |
124
+ | 0.5563 | 110.0 | 1650 | 0.5158 | 0.0000 |
125
+ | 0.5526 | 111.67 | 1675 | 0.5151 | 0.0000 |
126
+ | 0.5432 | 113.33 | 1700 | 0.5143 | 0.0000 |
127
+ | 0.5224 | 115.0 | 1725 | 0.5136 | 0.0000 |
128
+ | 0.5622 | 116.67 | 1750 | 0.5130 | 0.0000 |
129
+ | 0.5494 | 118.33 | 1775 | 0.5125 | 0.0000 |
130
+ | 0.554 | 120.0 | 1800 | 0.5121 | 0.0000 |
131
+ | 0.5495 | 121.67 | 1825 | 0.5116 | 0.0000 |
132
+ | 0.5458 | 123.33 | 1850 | 0.5113 | 0.0000 |
133
+ | 0.552 | 125.0 | 1875 | 0.5110 | 0.0000 |
134
+ | 0.5475 | 126.67 | 1900 | 0.5108 | 0.0000 |
135
+ | 0.5493 | 128.33 | 1925 | 0.5105 | 0.0000 |
136
+ | 0.5296 | 130.0 | 1950 | 0.5105 | 0.0000 |
137
+ | 0.5562 | 131.67 | 1975 | 0.5104 | 0.0000 |
138
+ | 0.561 | 133.33 | 2000 | 0.5103 | 0.0000 |
139
+
140
+
141
+ ### Framework versions
142
+
143
+ - Transformers 4.37.0
144
+ - Pytorch 2.0.0+cu118
145
+ - Datasets 2.16.1
146
+ - Tokenizers 0.15.1
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.37.0"
6
+ }