Hugging Face's logo

ke-lly
/
47015772_3

Text Generation
Transformers
Safetensors
gpt2
trl
sft
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
ke-lly commited on
Commit
82177f2
·
verified ·
1 Parent(s): 018721d

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: '47015772_3'
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
+ # 47015772_3
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: 0.6606
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
+ | 1.0942 | 0.0 | 25 | 0.9862 | 0.0001 |
60
+ | 0.8794 | 0.0 | 50 | 0.8269 | 0.0001 |
61
+ | 0.8241 | 0.0 | 75 | 0.7812 | 0.0001 |
62
+ | 0.8085 | 0.0 | 100 | 0.7559 | 0.0001 |
63
+ | 0.78 | 0.0 | 125 | 0.7417 | 0.0001 |
64
+ | 0.7656 | 0.0 | 150 | 0.7316 | 0.0000 |
65
+ | 0.759 | 0.0 | 175 | 0.7247 | 0.0000 |
66
+ | 0.7558 | 0.0 | 200 | 0.7191 | 0.0000 |
67
+ | 0.7434 | 0.0 | 225 | 0.7143 | 0.0000 |
68
+ | 0.7419 | 0.0 | 250 | 0.7114 | 0.0000 |
69
+ | 0.7383 | 0.0 | 275 | 0.7086 | 0.0000 |
70
+ | 0.7395 | 0.0 | 300 | 0.7051 | 0.0000 |
71
+ | 0.7324 | 0.0 | 325 | 0.7031 | 0.0000 |
72
+ | 0.721 | 0.0 | 350 | 0.7008 | 0.0000 |
73
+ | 0.7279 | 0.0 | 375 | 0.6982 | 0.0000 |
74
+ | 0.7303 | 0.01 | 400 | 0.6959 | 0.0000 |
75
+ | 0.7185 | 0.01 | 425 | 0.6932 | 0.0000 |
76
+ | 0.7221 | 0.01 | 450 | 0.6914 | 0.0000 |
77
+ | 0.6984 | 0.01 | 475 | 0.6887 | 0.0000 |
78
+ | 0.7162 | 0.01 | 500 | 0.6875 | 0.0000 |
79
+ | 0.712 | 0.01 | 525 | 0.6859 | 0.0000 |
80
+ | 0.7057 | 0.01 | 550 | 0.6848 | 0.0000 |
81
+ | 0.7058 | 0.01 | 575 | 0.6831 | 0.0000 |
82
+ | 0.705 | 0.01 | 600 | 0.6820 | 0.0000 |
83
+ | 0.6941 | 0.01 | 625 | 0.6810 | 0.0000 |
84
+ | 0.6973 | 0.01 | 650 | 0.6798 | 0.0000 |
85
+ | 0.7044 | 0.01 | 675 | 0.6784 | 0.0000 |
86
+ | 0.6943 | 0.01 | 700 | 0.6775 | 0.0000 |
87
+ | 0.6993 | 0.01 | 725 | 0.6766 | 0.0000 |
88
+ | 0.698 | 0.01 | 750 | 0.6755 | 0.0000 |
89
+ | 0.7054 | 0.01 | 775 | 0.6745 | 0.0000 |
90
+ | 0.693 | 0.01 | 800 | 0.6743 | 0.0000 |
91
+ | 0.6957 | 0.01 | 825 | 0.6732 | 0.0000 |
92
+ | 0.7015 | 0.01 | 850 | 0.6725 | 0.0000 |
93
+ | 0.6878 | 0.01 | 875 | 0.6719 | 0.0000 |
94
+ | 0.6965 | 0.01 | 900 | 0.6715 | 0.0000 |
95
+ | 0.6887 | 0.01 | 925 | 0.6712 | 0.0000 |
96
+ | 0.6945 | 0.01 | 950 | 0.6704 | 0.0000 |
97
+ | 0.6885 | 0.01 | 975 | 0.6695 | 0.0000 |
98
+ | 0.6872 | 0.01 | 1000 | 0.6692 | 0.0000 |
99
+ | 0.6908 | 0.01 | 1025 | 0.6688 | 0.0000 |
100
+ | 0.6912 | 0.01 | 1050 | 0.6684 | 0.0000 |
101
+ | 0.6729 | 0.01 | 1075 | 0.6676 | 0.0000 |
102
+ | 0.6852 | 0.01 | 1100 | 0.6674 | 0.0000 |
103
+ | 0.6869 | 0.01 | 1125 | 0.6669 | 0.0000 |
104
+ | 0.6875 | 0.01 | 1150 | 0.6663 | 0.0000 |
105
+ | 0.6884 | 0.02 | 1175 | 0.6659 | 0.0000 |
106
+ | 0.6905 | 0.02 | 1200 | 0.6658 | 0.0000 |
107
+ | 0.6817 | 0.02 | 1225 | 0.6653 | 0.0000 |
108
+ | 0.6875 | 0.02 | 1250 | 0.6649 | 0.0000 |
109
+ | 0.6897 | 0.02 | 1275 | 0.6644 | 0.0000 |
110
+ | 0.6727 | 0.02 | 1300 | 0.6642 | 0.0000 |
111
+ | 0.6859 | 0.02 | 1325 | 0.6640 | 0.0000 |
112
+ | 0.6836 | 0.02 | 1350 | 0.6637 | 0.0000 |
113
+ | 0.6788 | 0.02 | 1375 | 0.6636 | 0.0000 |
114
+ | 0.6866 | 0.02 | 1400 | 0.6634 | 0.0000 |
115
+ | 0.6847 | 0.02 | 1425 | 0.6632 | 0.0000 |
116
+ | 0.6804 | 0.02 | 1450 | 0.6630 | 0.0000 |
117
+ | 0.6861 | 0.02 | 1475 | 0.6628 | 0.0000 |
118
+ | 0.6803 | 0.02 | 1500 | 0.6625 | 0.0000 |
119
+ | 0.6829 | 0.02 | 1525 | 0.6622 | 0.0000 |
120
+ | 0.6825 | 0.02 | 1550 | 0.6621 | 0.0000 |
121
+ | 0.6892 | 0.02 | 1575 | 0.6620 | 0.0000 |
122
+ | 0.6801 | 0.02 | 1600 | 0.6619 | 0.0000 |
123
+ | 0.6811 | 0.02 | 1625 | 0.6616 | 0.0000 |
124
+ | 0.6764 | 0.02 | 1650 | 0.6616 | 0.0000 |
125
+ | 0.6698 | 0.02 | 1675 | 0.6613 | 0.0000 |
126
+ | 0.6879 | 0.02 | 1700 | 0.6613 | 0.0000 |
127
+ | 0.6704 | 0.02 | 1725 | 0.6612 | 0.0000 |
128
+ | 0.6888 | 0.02 | 1750 | 0.6611 | 0.0000 |
129
+ | 0.6735 | 0.02 | 1775 | 0.6611 | 0.0000 |
130
+ | 0.6859 | 0.02 | 1800 | 0.6609 | 0.0000 |
131
+ | 0.6827 | 0.02 | 1825 | 0.6610 | 0.0000 |
132
+ | 0.6826 | 0.02 | 1850 | 0.6608 | 0.0000 |
133
+ | 0.6779 | 0.02 | 1875 | 0.6608 | 0.0000 |
134
+ | 0.6749 | 0.02 | 1900 | 0.6607 | 0.0000 |
135
+ | 0.6791 | 0.02 | 1925 | 0.6607 | 0.0000 |
136
+ | 0.6801 | 0.03 | 1950 | 0.6607 | 0.0000 |
137
+ | 0.6921 | 0.03 | 1975 | 0.6606 | 0.0000 |
138
+ | 0.6792 | 0.03 | 2000 | 0.6606 | 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
+ }