bferrando commited on
Commit
28f9efe
·
verified ·
1 Parent(s): ded0163

End of training

Browse files
Files changed (2) hide show
  1. README.md +112 -0
  2. generation_config.json +7 -0
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: microsoft/git-base
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: git-base-naruto2
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
+ # git-base-naruto2
15
+
16
+ This model is a fine-tuned version of [microsoft/git-base](https://huggingface.co/microsoft/git-base) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.0286
19
+ - Wer Score: 0.3515
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 3
40
+ - eval_batch_size: 1
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 5
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss | Wer Score |
49
+ |:-------------:|:------:|:----:|:---------------:|:---------:|
50
+ | 10.2502 | 0.0909 | 5 | 9.1485 | 62.2485 |
51
+ | 8.8428 | 0.1818 | 10 | 8.3401 | 80.6545 |
52
+ | 8.1981 | 0.2727 | 15 | 7.8041 | 80.8121 |
53
+ | 7.7018 | 0.3636 | 20 | 7.3280 | 80.3636 |
54
+ | 7.2331 | 0.4545 | 25 | 6.8603 | 40.0485 |
55
+ | 6.7819 | 0.5455 | 30 | 6.3932 | 20.9152 |
56
+ | 6.3079 | 0.6364 | 35 | 5.9241 | 22.0424 |
57
+ | 5.8546 | 0.7273 | 40 | 5.4566 | 6.7515 |
58
+ | 5.3926 | 0.8182 | 45 | 4.9938 | 6.9636 |
59
+ | 4.9258 | 0.9091 | 50 | 4.5336 | 6.8909 |
60
+ | 4.4733 | 1.0 | 55 | 4.0808 | 7.4061 |
61
+ | 4.0241 | 1.0909 | 60 | 3.6383 | 6.9273 |
62
+ | 3.5895 | 1.1818 | 65 | 3.2081 | 7.2121 |
63
+ | 3.1657 | 1.2727 | 70 | 2.7929 | 7.2121 |
64
+ | 2.7513 | 1.3636 | 75 | 2.3954 | 7.8303 |
65
+ | 2.3667 | 1.4545 | 80 | 2.0232 | 8.1576 |
66
+ | 1.9959 | 1.5455 | 85 | 1.6770 | 8.8727 |
67
+ | 1.6518 | 1.6364 | 90 | 1.3655 | 9.2242 |
68
+ | 1.349 | 1.7273 | 95 | 1.0882 | 9.3758 |
69
+ | 1.081 | 1.8182 | 100 | 0.8536 | 9.1939 |
70
+ | 0.8455 | 1.9091 | 105 | 0.6599 | 8.8667 |
71
+ | 0.6619 | 2.0 | 110 | 0.5056 | 9.2727 |
72
+ | 0.5017 | 2.0909 | 115 | 0.3868 | 9.3636 |
73
+ | 0.385 | 2.1818 | 120 | 0.2934 | 10.9758 |
74
+ | 0.2916 | 2.2727 | 125 | 0.2254 | 10.6848 |
75
+ | 0.2292 | 2.3636 | 130 | 0.1742 | 9.3758 |
76
+ | 0.1773 | 2.4545 | 135 | 0.1368 | 8.8909 |
77
+ | 0.1397 | 2.5455 | 140 | 0.1088 | 8.4364 |
78
+ | 0.1214 | 2.6364 | 145 | 0.0907 | 0.4121 |
79
+ | 0.0964 | 2.7273 | 150 | 0.0764 | 0.3939 |
80
+ | 0.0812 | 2.8182 | 155 | 0.0649 | 0.3818 |
81
+ | 0.07 | 2.9091 | 160 | 0.0597 | 0.3818 |
82
+ | 0.0613 | 3.0 | 165 | 0.0516 | 0.4121 |
83
+ | 0.0454 | 3.0909 | 170 | 0.0472 | 0.3879 |
84
+ | 0.0492 | 3.1818 | 175 | 0.0422 | 0.4 |
85
+ | 0.0411 | 3.2727 | 180 | 0.0411 | 0.4364 |
86
+ | 0.035 | 3.3636 | 185 | 0.0394 | 0.4303 |
87
+ | 0.0378 | 3.4545 | 190 | 0.0370 | 0.3879 |
88
+ | 0.0389 | 3.5455 | 195 | 0.0348 | 0.3939 |
89
+ | 0.0341 | 3.6364 | 200 | 0.0335 | 0.3636 |
90
+ | 0.0391 | 3.7273 | 205 | 0.0327 | 0.3697 |
91
+ | 0.0266 | 3.8182 | 210 | 0.0314 | 0.5212 |
92
+ | 0.0282 | 3.9091 | 215 | 0.0308 | 2.6364 |
93
+ | 0.0306 | 4.0 | 220 | 0.0300 | 0.4848 |
94
+ | 0.0263 | 4.0909 | 225 | 0.0306 | 0.3758 |
95
+ | 0.0237 | 4.1818 | 230 | 0.0300 | 0.3697 |
96
+ | 0.0255 | 4.2727 | 235 | 0.0292 | 0.3515 |
97
+ | 0.0232 | 4.3636 | 240 | 0.0290 | 0.3576 |
98
+ | 0.024 | 4.4545 | 245 | 0.0291 | 0.3515 |
99
+ | 0.0243 | 4.5455 | 250 | 0.0294 | 0.3636 |
100
+ | 0.0245 | 4.6364 | 255 | 0.0296 | 0.3697 |
101
+ | 0.022 | 4.7273 | 260 | 0.0294 | 0.3576 |
102
+ | 0.0228 | 4.8182 | 265 | 0.0291 | 0.3576 |
103
+ | 0.0255 | 4.9091 | 270 | 0.0287 | 0.3515 |
104
+ | 0.025 | 5.0 | 275 | 0.0286 | 0.3515 |
105
+
106
+
107
+ ### Framework versions
108
+
109
+ - Transformers 4.41.0
110
+ - Pytorch 2.3.0+cu121
111
+ - Datasets 2.19.1
112
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 101,
4
+ "eos_token_id": 102,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.41.0"
7
+ }