Katpeeler commited on
Commit
ee86502
1 Parent(s): 7bb8c96

End of training

Browse files
Files changed (2) hide show
  1. README.md +87 -0
  2. generation_config.json +5 -0
README.md ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: gpt2
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: midi_model_3
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # midi_model_3
15
+
16
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.5542
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.0005
38
+ - train_batch_size: 4
39
+ - eval_batch_size: 2
40
+ - seed: 1
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: cosine
43
+ - lr_scheduler_warmup_ratio: 0.01
44
+ - num_epochs: 10
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:-----:|:----:|:---------------:|
50
+ | 0.8047 | 0.33 | 300 | 0.7969 |
51
+ | 0.7924 | 0.66 | 600 | 0.7735 |
52
+ | 0.7758 | 1.0 | 900 | 0.7528 |
53
+ | 0.75 | 1.33 | 1200 | 0.7436 |
54
+ | 0.7432 | 1.66 | 1500 | 0.7277 |
55
+ | 0.7361 | 1.99 | 1800 | 0.7175 |
56
+ | 0.7121 | 2.32 | 2100 | 0.7025 |
57
+ | 0.708 | 2.65 | 2400 | 0.6861 |
58
+ | 0.6971 | 2.99 | 2700 | 0.6781 |
59
+ | 0.6777 | 3.32 | 3000 | 0.6718 |
60
+ | 0.6733 | 3.65 | 3300 | 0.6578 |
61
+ | 0.6643 | 3.98 | 3600 | 0.6500 |
62
+ | 0.6422 | 4.31 | 3900 | 0.6423 |
63
+ | 0.6401 | 4.65 | 4200 | 0.6330 |
64
+ | 0.6302 | 4.98 | 4500 | 0.6228 |
65
+ | 0.6103 | 5.31 | 4800 | 0.6148 |
66
+ | 0.6066 | 5.64 | 5100 | 0.6069 |
67
+ | 0.5995 | 5.97 | 5400 | 0.5979 |
68
+ | 0.5724 | 6.31 | 5700 | 0.5915 |
69
+ | 0.5772 | 6.64 | 6000 | 0.5870 |
70
+ | 0.5677 | 6.97 | 6300 | 0.5771 |
71
+ | 0.5491 | 7.3 | 6600 | 0.5740 |
72
+ | 0.5433 | 7.63 | 6900 | 0.5675 |
73
+ | 0.5384 | 7.96 | 7200 | 0.5630 |
74
+ | 0.5245 | 8.3 | 7500 | 0.5611 |
75
+ | 0.5206 | 8.63 | 7800 | 0.5578 |
76
+ | 0.5198 | 8.96 | 8100 | 0.5553 |
77
+ | 0.5141 | 9.29 | 8400 | 0.5544 |
78
+ | 0.5091 | 9.62 | 8700 | 0.5543 |
79
+ | 0.5096 | 9.96 | 9000 | 0.5542 |
80
+
81
+
82
+ ### Framework versions
83
+
84
+ - Transformers 4.35.2
85
+ - Pytorch 2.1.0+cu118
86
+ - Datasets 2.15.0
87
+ - Tokenizers 0.15.0
generation_config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "pad_token_id": 3,
4
+ "transformers_version": "4.35.2"
5
+ }