Hugging Face's logo

nlp04
/
gpt_trinity_2_4_3e-5_lp5_nb5

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
1
54data commited on
Commit
1cefefa
·
1 Parent(s): 3acf428

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +141 -0
README.md ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: gpt_trinity_2_4_3e-5_lp5_nb5
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # gpt_trinity_2_4_3e-5_lp5_nb5
14
+
15
+ This model is a fine-tuned version of [skt/kogpt2-base-v2](https://huggingface.co/skt/kogpt2-base-v2) on an unknown dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: 4.0291
18
+
19
+ ## Model description
20
+
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
+
31
+ ## Training procedure
32
+
33
+ ### Training hyperparameters
34
+
35
+ The following hyperparameters were used during training:
36
+ - learning_rate: 3e-05
37
+ - train_batch_size: 2
38
+ - eval_batch_size: 2
39
+ - seed: 42
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: linear
42
+ - lr_scheduler_warmup_ratio: 0.1
43
+ - num_epochs: 4.0
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:-----:|:---------------:|
50
+ | 3.5765 | 0.05 | 1000 | 4.1247 |
51
+ | 3.19 | 0.09 | 2000 | 4.0578 |
52
+ | 3.1177 | 0.14 | 3000 | 4.0708 |
53
+ | 3.1116 | 0.19 | 4000 | 4.0654 |
54
+ | 3.0777 | 0.24 | 5000 | 4.0857 |
55
+ | 3.1105 | 0.28 | 6000 | 4.1127 |
56
+ | 3.1018 | 0.33 | 7000 | 4.1410 |
57
+ | 3.0728 | 0.38 | 8000 | 4.1834 |
58
+ | 3.1248 | 0.42 | 9000 | 4.2058 |
59
+ | 3.1035 | 0.47 | 10000 | 4.2048 |
60
+ | 3.0943 | 0.52 | 11000 | 4.1892 |
61
+ | 3.0724 | 0.57 | 12000 | 4.2063 |
62
+ | 3.0517 | 0.61 | 13000 | 4.1923 |
63
+ | 3.0372 | 0.66 | 14000 | 4.2112 |
64
+ | 3.0235 | 0.71 | 15000 | 4.2043 |
65
+ | 3.0329 | 0.76 | 16000 | 4.1630 |
66
+ | 3.0171 | 0.8 | 17000 | 4.1631 |
67
+ | 2.9997 | 0.85 | 18000 | 4.1563 |
68
+ | 2.9913 | 0.9 | 19000 | 4.1616 |
69
+ | 2.9579 | 0.94 | 20000 | 4.1494 |
70
+ | 2.9576 | 0.99 | 21000 | 4.1367 |
71
+ | 2.7461 | 1.04 | 22000 | 4.1593 |
72
+ | 2.7637 | 1.09 | 23000 | 4.1453 |
73
+ | 2.741 | 1.13 | 24000 | 4.1624 |
74
+ | 2.7514 | 1.18 | 25000 | 4.1357 |
75
+ | 2.755 | 1.23 | 26000 | 4.1524 |
76
+ | 2.7365 | 1.27 | 27000 | 4.1399 |
77
+ | 2.7356 | 1.32 | 28000 | 4.1285 |
78
+ | 2.7386 | 1.37 | 29000 | 4.1286 |
79
+ | 2.7489 | 1.42 | 30000 | 4.1231 |
80
+ | 2.7518 | 1.46 | 31000 | 4.1104 |
81
+ | 2.7317 | 1.51 | 32000 | 4.1202 |
82
+ | 2.7378 | 1.56 | 33000 | 4.1132 |
83
+ | 2.7309 | 1.6 | 34000 | 4.1047 |
84
+ | 2.7791 | 1.65 | 35000 | 4.0976 |
85
+ | 2.7427 | 1.7 | 36000 | 4.0874 |
86
+ | 2.7184 | 1.75 | 37000 | 4.0953 |
87
+ | 2.7107 | 1.79 | 38000 | 4.0963 |
88
+ | 2.7122 | 1.84 | 39000 | 4.0841 |
89
+ | 2.7172 | 1.89 | 40000 | 4.0852 |
90
+ | 2.7126 | 1.94 | 41000 | 4.0632 |
91
+ | 2.7063 | 1.98 | 42000 | 4.0643 |
92
+ | 2.5311 | 2.03 | 43000 | 4.0848 |
93
+ | 2.4496 | 2.08 | 44000 | 4.0943 |
94
+ | 2.4597 | 2.12 | 45000 | 4.0799 |
95
+ | 2.4472 | 2.17 | 46000 | 4.0802 |
96
+ | 2.4628 | 2.22 | 47000 | 4.0880 |
97
+ | 2.4508 | 2.27 | 48000 | 4.0791 |
98
+ | 2.4743 | 2.31 | 49000 | 4.0765 |
99
+ | 2.4692 | 2.36 | 50000 | 4.0739 |
100
+ | 2.4651 | 2.41 | 51000 | 4.0690 |
101
+ | 2.4885 | 2.45 | 52000 | 4.0723 |
102
+ | 2.5023 | 2.5 | 53000 | 4.0675 |
103
+ | 2.4651 | 2.55 | 54000 | 4.0649 |
104
+ | 2.4774 | 2.6 | 55000 | 4.0695 |
105
+ | 2.4717 | 2.64 | 56000 | 4.0559 |
106
+ | 2.4856 | 2.69 | 57000 | 4.0512 |
107
+ | 2.4572 | 2.74 | 58000 | 4.0473 |
108
+ | 2.486 | 2.79 | 59000 | 4.0438 |
109
+ | 2.449 | 2.83 | 60000 | 4.0385 |
110
+ | 2.456 | 2.88 | 61000 | 4.0355 |
111
+ | 2.4802 | 2.93 | 62000 | 4.0378 |
112
+ | 2.4635 | 2.97 | 63000 | 4.0308 |
113
+ | 2.3742 | 3.02 | 64000 | 4.0488 |
114
+ | 2.2371 | 3.07 | 65000 | 4.0579 |
115
+ | 2.2496 | 3.12 | 66000 | 4.0630 |
116
+ | 2.2758 | 3.16 | 67000 | 4.0516 |
117
+ | 2.2489 | 3.21 | 68000 | 4.0585 |
118
+ | 2.2374 | 3.26 | 69000 | 4.0715 |
119
+ | 2.2862 | 3.3 | 70000 | 4.0507 |
120
+ | 2.2502 | 3.35 | 71000 | 4.0512 |
121
+ | 2.238 | 3.4 | 72000 | 4.0545 |
122
+ | 2.2407 | 3.45 | 73000 | 4.0459 |
123
+ | 2.2529 | 3.49 | 74000 | 4.0452 |
124
+ | 2.2453 | 3.54 | 75000 | 4.0459 |
125
+ | 2.2314 | 3.59 | 76000 | 4.0416 |
126
+ | 2.2408 | 3.63 | 77000 | 4.0379 |
127
+ | 2.2497 | 3.68 | 78000 | 4.0348 |
128
+ | 2.2475 | 3.73 | 79000 | 4.0374 |
129
+ | 2.2376 | 3.78 | 80000 | 4.0319 |
130
+ | 2.244 | 3.82 | 81000 | 4.0331 |
131
+ | 2.2611 | 3.87 | 82000 | 4.0306 |
132
+ | 2.237 | 3.92 | 83000 | 4.0301 |
133
+ | 2.2337 | 3.97 | 84000 | 4.0291 |
134
+
135
+
136
+ ### Framework versions
137
+
138
+ - Transformers 4.25.1
139
+ - Pytorch 1.9.0+cu102
140
+ - Datasets 2.8.0
141
+ - Tokenizers 0.13.2