Model save
Browse files- README.md +146 -0
- 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_1'
|
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_1
|
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: 0.6501
|
23 |
+
- Accuracy: 0.0001
|
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 |
+
| 1.1019 | 0.03 | 25 | 0.9747 | 0.0001 |
|
60 |
+
| 0.8784 | 0.06 | 50 | 0.8178 | 0.0001 |
|
61 |
+
| 0.8308 | 0.09 | 75 | 0.7727 | 0.0002 |
|
62 |
+
| 0.7975 | 0.11 | 100 | 0.7508 | 0.0001 |
|
63 |
+
| 0.787 | 0.14 | 125 | 0.7370 | 0.0001 |
|
64 |
+
| 0.7752 | 0.17 | 150 | 0.7279 | 0.0001 |
|
65 |
+
| 0.7703 | 0.2 | 175 | 0.7210 | 0.0001 |
|
66 |
+
| 0.7584 | 0.23 | 200 | 0.7157 | 0.0001 |
|
67 |
+
| 0.7662 | 0.26 | 225 | 0.7108 | 0.0001 |
|
68 |
+
| 0.7431 | 0.28 | 250 | 0.7073 | 0.0001 |
|
69 |
+
| 0.7437 | 0.31 | 275 | 0.7038 | 0.0001 |
|
70 |
+
| 0.7378 | 0.34 | 300 | 0.7006 | 0.0001 |
|
71 |
+
| 0.7252 | 0.37 | 325 | 0.6974 | 0.0001 |
|
72 |
+
| 0.7242 | 0.4 | 350 | 0.6948 | 0.0001 |
|
73 |
+
| 0.7284 | 0.43 | 375 | 0.6922 | 0.0001 |
|
74 |
+
| 0.7187 | 0.46 | 400 | 0.6898 | 0.0001 |
|
75 |
+
| 0.7169 | 0.48 | 425 | 0.6878 | 0.0001 |
|
76 |
+
| 0.723 | 0.51 | 450 | 0.6858 | 0.0001 |
|
77 |
+
| 0.7189 | 0.54 | 475 | 0.6834 | 0.0001 |
|
78 |
+
| 0.7142 | 0.57 | 500 | 0.6818 | 0.0001 |
|
79 |
+
| 0.7071 | 0.6 | 525 | 0.6798 | 0.0001 |
|
80 |
+
| 0.7131 | 0.63 | 550 | 0.6782 | 0.0001 |
|
81 |
+
| 0.7107 | 0.66 | 575 | 0.6768 | 0.0001 |
|
82 |
+
| 0.702 | 0.68 | 600 | 0.6761 | 0.0001 |
|
83 |
+
| 0.6937 | 0.71 | 625 | 0.6742 | 0.0001 |
|
84 |
+
| 0.6984 | 0.74 | 650 | 0.6732 | 0.0001 |
|
85 |
+
| 0.7023 | 0.77 | 675 | 0.6720 | 0.0001 |
|
86 |
+
| 0.7002 | 0.8 | 700 | 0.6708 | 0.0001 |
|
87 |
+
| 0.7057 | 0.83 | 725 | 0.6697 | 0.0001 |
|
88 |
+
| 0.6991 | 0.85 | 750 | 0.6687 | 0.0001 |
|
89 |
+
| 0.6951 | 0.88 | 775 | 0.6674 | 0.0001 |
|
90 |
+
| 0.7101 | 0.91 | 800 | 0.6668 | 0.0001 |
|
91 |
+
| 0.6931 | 0.94 | 825 | 0.6661 | 0.0001 |
|
92 |
+
| 0.6866 | 0.97 | 850 | 0.6652 | 0.0001 |
|
93 |
+
| 0.702 | 1.0 | 875 | 0.6643 | 0.0001 |
|
94 |
+
| 0.6996 | 1.03 | 900 | 0.6637 | 0.0001 |
|
95 |
+
| 0.7077 | 1.05 | 925 | 0.6629 | 0.0001 |
|
96 |
+
| 0.6955 | 1.08 | 950 | 0.6623 | 0.0001 |
|
97 |
+
| 0.6947 | 1.11 | 975 | 0.6619 | 0.0001 |
|
98 |
+
| 0.6933 | 1.14 | 1000 | 0.6612 | 0.0001 |
|
99 |
+
| 0.6855 | 1.17 | 1025 | 0.6601 | 0.0001 |
|
100 |
+
| 0.7004 | 1.2 | 1050 | 0.6597 | 0.0001 |
|
101 |
+
| 0.6934 | 1.22 | 1075 | 0.6594 | 0.0001 |
|
102 |
+
| 0.6863 | 1.25 | 1100 | 0.6585 | 0.0001 |
|
103 |
+
| 0.6886 | 1.28 | 1125 | 0.6580 | 0.0001 |
|
104 |
+
| 0.6851 | 1.31 | 1150 | 0.6579 | 0.0001 |
|
105 |
+
| 0.683 | 1.34 | 1175 | 0.6574 | 0.0001 |
|
106 |
+
| 0.703 | 1.37 | 1200 | 0.6570 | 0.0001 |
|
107 |
+
| 0.6792 | 1.4 | 1225 | 0.6564 | 0.0001 |
|
108 |
+
| 0.6849 | 1.42 | 1250 | 0.6558 | 0.0001 |
|
109 |
+
| 0.6856 | 1.45 | 1275 | 0.6556 | 0.0001 |
|
110 |
+
| 0.6856 | 1.48 | 1300 | 0.6551 | 0.0001 |
|
111 |
+
| 0.6856 | 1.51 | 1325 | 0.6550 | 0.0001 |
|
112 |
+
| 0.6857 | 1.54 | 1350 | 0.6543 | 0.0001 |
|
113 |
+
| 0.6856 | 1.57 | 1375 | 0.6539 | 0.0001 |
|
114 |
+
| 0.689 | 1.59 | 1400 | 0.6538 | 0.0001 |
|
115 |
+
| 0.6892 | 1.62 | 1425 | 0.6534 | 0.0001 |
|
116 |
+
| 0.6823 | 1.65 | 1450 | 0.6532 | 0.0001 |
|
117 |
+
| 0.6828 | 1.68 | 1475 | 0.6529 | 0.0001 |
|
118 |
+
| 0.6864 | 1.71 | 1500 | 0.6528 | 0.0001 |
|
119 |
+
| 0.6886 | 1.74 | 1525 | 0.6523 | 0.0001 |
|
120 |
+
| 0.6642 | 1.77 | 1550 | 0.6521 | 0.0001 |
|
121 |
+
| 0.6849 | 1.79 | 1575 | 0.6519 | 0.0001 |
|
122 |
+
| 0.6834 | 1.82 | 1600 | 0.6516 | 0.0001 |
|
123 |
+
| 0.6839 | 1.85 | 1625 | 0.6515 | 0.0001 |
|
124 |
+
| 0.6856 | 1.88 | 1650 | 0.6514 | 0.0001 |
|
125 |
+
| 0.6725 | 1.91 | 1675 | 0.6511 | 0.0001 |
|
126 |
+
| 0.6813 | 1.94 | 1700 | 0.6509 | 0.0001 |
|
127 |
+
| 0.6832 | 1.97 | 1725 | 0.6508 | 0.0001 |
|
128 |
+
| 0.6739 | 1.99 | 1750 | 0.6508 | 0.0001 |
|
129 |
+
| 0.6716 | 2.02 | 1775 | 0.6506 | 0.0001 |
|
130 |
+
| 0.6798 | 2.05 | 1800 | 0.6505 | 0.0001 |
|
131 |
+
| 0.6758 | 2.08 | 1825 | 0.6503 | 0.0001 |
|
132 |
+
| 0.6791 | 2.11 | 1850 | 0.6503 | 0.0001 |
|
133 |
+
| 0.6735 | 2.14 | 1875 | 0.6503 | 0.0001 |
|
134 |
+
| 0.6887 | 2.16 | 1900 | 0.6502 | 0.0001 |
|
135 |
+
| 0.686 | 2.19 | 1925 | 0.6502 | 0.0001 |
|
136 |
+
| 0.682 | 2.22 | 1950 | 0.6501 | 0.0001 |
|
137 |
+
| 0.675 | 2.25 | 1975 | 0.6501 | 0.0001 |
|
138 |
+
| 0.6792 | 2.28 | 2000 | 0.6501 | 0.0001 |
|
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 |
+
}
|