DedeProGames commited on
Commit
fa76969
·
verified ·
1 Parent(s): 6bce847

Model save

Browse files
Files changed (1) hide show
  1. README.md +98 -0
README.md ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/DialoGPT-small
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: dialochess-v4
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # dialochess-v4
18
+
19
+ This model is a fine-tuned version of [microsoft/DialoGPT-small](https://huggingface.co/microsoft/DialoGPT-small) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.8124
22
+ - Accuracy: 0.0004
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 5e-05
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
46
+ - lr_scheduler_type: cosine
47
+ - num_epochs: 6
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Accuracy |
53
+ |:-------------:|:------:|:----:|:---------------:|:--------:|
54
+ | 1.3141 | 0.1616 | 200 | 1.1921 | 0.0002 |
55
+ | 1.194 | 0.3231 | 400 | 1.0974 | 0.0003 |
56
+ | 1.118 | 0.4847 | 600 | 1.0425 | 0.0 |
57
+ | 1.0767 | 0.6462 | 800 | 1.0071 | 0.0 |
58
+ | 1.0414 | 0.8078 | 1000 | 0.9825 | 0.0005 |
59
+ | 1.0158 | 0.9693 | 1200 | 0.9601 | 0.0002 |
60
+ | 1.0035 | 1.1309 | 1400 | 0.9427 | 0.0001 |
61
+ | 0.9715 | 1.2924 | 1600 | 0.9300 | 0.0002 |
62
+ | 0.9745 | 1.4540 | 1800 | 0.9193 | 0.0002 |
63
+ | 0.9447 | 1.6155 | 2000 | 0.9063 | 0.0002 |
64
+ | 0.9573 | 1.7771 | 2200 | 0.8980 | 0.0005 |
65
+ | 0.9386 | 1.9386 | 2400 | 0.8893 | 0.0003 |
66
+ | 0.9204 | 2.1002 | 2600 | 0.8786 | 0.0003 |
67
+ | 0.9128 | 2.2617 | 2800 | 0.8732 | 0.0003 |
68
+ | 0.9079 | 2.4233 | 3000 | 0.8670 | 0.0002 |
69
+ | 0.9073 | 2.5848 | 3200 | 0.8603 | 0.0002 |
70
+ | 0.8938 | 2.7464 | 3400 | 0.8532 | 0.0004 |
71
+ | 0.8899 | 2.9079 | 3600 | 0.8501 | 0.0002 |
72
+ | 0.8834 | 3.0695 | 3800 | 0.8426 | 0.0002 |
73
+ | 0.8693 | 3.2310 | 4000 | 0.8416 | 0.0003 |
74
+ | 0.8808 | 3.3926 | 4200 | 0.8335 | 0.0002 |
75
+ | 0.872 | 3.5541 | 4400 | 0.8297 | 0.0003 |
76
+ | 0.8689 | 3.7157 | 4600 | 0.8296 | 0.0003 |
77
+ | 0.8607 | 3.8772 | 4800 | 0.8237 | 0.0002 |
78
+ | 0.8516 | 4.0388 | 5000 | 0.8246 | 0.0004 |
79
+ | 0.8652 | 4.2003 | 5200 | 0.8210 | 0.0004 |
80
+ | 0.8522 | 4.3619 | 5400 | 0.8192 | 0.0003 |
81
+ | 0.8466 | 4.5234 | 5600 | 0.8181 | 0.0002 |
82
+ | 0.8525 | 4.6850 | 5800 | 0.8163 | 0.0004 |
83
+ | 0.8485 | 4.8465 | 6000 | 0.8163 | 0.0004 |
84
+ | 0.8444 | 5.0081 | 6200 | 0.8144 | 0.0003 |
85
+ | 0.8512 | 5.1696 | 6400 | 0.8141 | 0.0004 |
86
+ | 0.8405 | 5.3312 | 6600 | 0.8135 | 0.0004 |
87
+ | 0.8337 | 5.4927 | 6800 | 0.8124 | 0.0004 |
88
+ | 0.8601 | 5.6543 | 7000 | 0.8125 | 0.0004 |
89
+ | 0.8506 | 5.8158 | 7200 | 0.8124 | 0.0004 |
90
+ | 0.8562 | 5.9774 | 7400 | 0.8124 | 0.0004 |
91
+
92
+
93
+ ### Framework versions
94
+
95
+ - Transformers 4.57.2
96
+ - Pytorch 2.9.0+cu126
97
+ - Datasets 4.0.0
98
+ - Tokenizers 0.22.1