End of training
Browse files- README.md +165 -0
- trainer_state.json +0 -0
README.md
ADDED
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- wer
|
8 |
+
model-index:
|
9 |
+
- name: 1-bpe20k-freeze_cnn-drop.1
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# 1-bpe20k-freeze_cnn-drop.1
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.0929
|
21 |
+
- Wer: 1.0076
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 2e-05
|
41 |
+
- train_batch_size: 8
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- distributed_type: multi-GPU
|
45 |
+
- num_devices: 4
|
46 |
+
- total_train_batch_size: 32
|
47 |
+
- total_eval_batch_size: 32
|
48 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: linear
|
50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
51 |
+
- training_steps: 200000
|
52 |
+
- mixed_precision_training: Native AMP
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
57 |
+
|:-------------:|:-----:|:------:|:---------------:|:------:|
|
58 |
+
| 91.1741 | 0.05 | 2000 | 179.2776 | 1.0 |
|
59 |
+
| 56.7966 | 0.09 | 4000 | 111.7828 | 1.0 |
|
60 |
+
| 11.4825 | 0.14 | 6000 | 16.6212 | 1.0 |
|
61 |
+
| 7.5731 | 0.19 | 8000 | 8.3634 | 1.0 |
|
62 |
+
| 7.3291 | 0.23 | 10000 | 8.3149 | 1.0 |
|
63 |
+
| 7.1995 | 0.28 | 12000 | 8.1837 | 1.0 |
|
64 |
+
| 7.1092 | 0.33 | 14000 | 8.1877 | 1.0 |
|
65 |
+
| 6.9362 | 0.38 | 16000 | 7.8934 | 1.0 |
|
66 |
+
| 6.7999 | 0.42 | 18000 | 7.7947 | 1.0 |
|
67 |
+
| 6.7773 | 0.47 | 20000 | 7.8173 | 1.0 |
|
68 |
+
| 6.7489 | 0.52 | 22000 | 7.8197 | 1.0117 |
|
69 |
+
| 6.7139 | 0.56 | 24000 | 7.6664 | 1.0078 |
|
70 |
+
| 6.6024 | 0.61 | 26000 | 7.8397 | 1.0 |
|
71 |
+
| 6.3451 | 0.66 | 28000 | 7.2039 | 1.0044 |
|
72 |
+
| 5.7315 | 0.7 | 30000 | 6.3228 | 1.0039 |
|
73 |
+
| 4.8494 | 0.75 | 32000 | 5.3767 | 1.0058 |
|
74 |
+
| 4.4103 | 0.8 | 34000 | 4.5216 | 1.0073 |
|
75 |
+
| 3.8434 | 0.85 | 36000 | 3.9239 | 1.0125 |
|
76 |
+
| 3.3268 | 0.89 | 38000 | 3.4547 | 1.0074 |
|
77 |
+
| 2.9034 | 0.94 | 40000 | 3.0617 | 1.0079 |
|
78 |
+
| 2.5747 | 0.99 | 42000 | 2.7700 | 1.0108 |
|
79 |
+
| 2.4532 | 1.03 | 44000 | 2.5497 | 1.0113 |
|
80 |
+
| 2.3169 | 1.08 | 46000 | 2.3780 | 1.0105 |
|
81 |
+
| 2.2304 | 1.13 | 48000 | 2.2581 | 1.0075 |
|
82 |
+
| 2.0592 | 1.17 | 50000 | 2.1189 | 1.0051 |
|
83 |
+
| 2.023 | 1.22 | 52000 | 2.0325 | 1.0049 |
|
84 |
+
| 1.8011 | 1.27 | 54000 | 1.9284 | 1.0081 |
|
85 |
+
| 1.817 | 1.31 | 56000 | 1.8635 | 1.0091 |
|
86 |
+
| 1.6902 | 1.36 | 58000 | 1.7967 | 1.0076 |
|
87 |
+
| 1.6398 | 1.41 | 60000 | 1.7413 | 1.0081 |
|
88 |
+
| 1.8097 | 1.46 | 62000 | 1.7066 | 1.0054 |
|
89 |
+
| 1.5504 | 1.5 | 64000 | 1.6525 | 1.0074 |
|
90 |
+
| 1.5759 | 1.55 | 66000 | 1.6402 | 1.0098 |
|
91 |
+
| 1.6652 | 1.6 | 68000 | 1.5884 | 1.0055 |
|
92 |
+
| 1.5074 | 1.64 | 70000 | 1.5423 | 1.0066 |
|
93 |
+
| 1.414 | 1.69 | 72000 | 1.5397 | 1.0095 |
|
94 |
+
| 1.4792 | 1.74 | 74000 | 1.4822 | 1.0062 |
|
95 |
+
| 1.4648 | 1.78 | 76000 | 1.5023 | 1.0083 |
|
96 |
+
| 1.4326 | 1.83 | 78000 | 1.4627 | 1.0070 |
|
97 |
+
| 1.3691 | 1.88 | 80000 | 1.4435 | 1.0073 |
|
98 |
+
| 1.3624 | 1.92 | 82000 | 1.4290 | 1.0066 |
|
99 |
+
| 1.5254 | 1.97 | 84000 | 1.4090 | 1.0104 |
|
100 |
+
| 1.3362 | 2.02 | 86000 | 1.3790 | 1.0065 |
|
101 |
+
| 1.3586 | 2.07 | 88000 | 1.3730 | 1.0061 |
|
102 |
+
| 1.29 | 2.11 | 90000 | 1.3825 | 1.0099 |
|
103 |
+
| 1.387 | 2.16 | 92000 | 1.3499 | 1.0087 |
|
104 |
+
| 1.356 | 2.21 | 94000 | 1.3591 | 1.0102 |
|
105 |
+
| 1.3145 | 2.25 | 96000 | 1.3154 | 1.0084 |
|
106 |
+
| 1.2747 | 2.3 | 98000 | 1.3095 | 1.0080 |
|
107 |
+
| 1.3444 | 2.35 | 100000 | 1.2910 | 1.0087 |
|
108 |
+
| 1.2304 | 2.39 | 102000 | 1.2850 | 1.0074 |
|
109 |
+
| 1.3306 | 2.44 | 104000 | 1.2698 | 1.0085 |
|
110 |
+
| 1.2431 | 2.49 | 106000 | 1.2645 | 1.0087 |
|
111 |
+
| 1.1938 | 2.54 | 108000 | 1.2497 | 1.0061 |
|
112 |
+
| 1.2476 | 2.58 | 110000 | 1.2416 | 1.0077 |
|
113 |
+
| 1.1743 | 2.63 | 112000 | 1.2460 | 1.0064 |
|
114 |
+
| 1.2554 | 2.68 | 114000 | 1.2369 | 1.0076 |
|
115 |
+
| 1.1518 | 2.72 | 116000 | 1.2212 | 1.0076 |
|
116 |
+
| 1.1812 | 2.77 | 118000 | 1.1954 | 1.0054 |
|
117 |
+
| 1.2447 | 2.82 | 120000 | 1.2144 | 1.0082 |
|
118 |
+
| 1.2839 | 2.86 | 122000 | 1.1976 | 1.0076 |
|
119 |
+
| 1.117 | 2.91 | 124000 | 1.1809 | 1.0060 |
|
120 |
+
| 1.1151 | 2.96 | 126000 | 1.1930 | 1.0087 |
|
121 |
+
| 1.182 | 3.0 | 128000 | 1.1750 | 1.0079 |
|
122 |
+
| 1.214 | 3.05 | 130000 | 1.1687 | 1.0047 |
|
123 |
+
| 1.1701 | 3.1 | 132000 | 1.1651 | 1.0071 |
|
124 |
+
| 1.1268 | 3.15 | 134000 | 1.1635 | 1.0068 |
|
125 |
+
| 1.193 | 3.19 | 136000 | 1.1550 | 1.0075 |
|
126 |
+
| 1.1245 | 3.24 | 138000 | 1.1436 | 1.0068 |
|
127 |
+
| 1.136 | 3.29 | 140000 | 1.1378 | 1.0059 |
|
128 |
+
| 1.1318 | 3.33 | 142000 | 1.1526 | 1.0074 |
|
129 |
+
| 1.1129 | 3.38 | 144000 | 1.1452 | 1.0074 |
|
130 |
+
| 1.1175 | 3.43 | 146000 | 1.1491 | 1.0092 |
|
131 |
+
| 1.0812 | 3.47 | 148000 | 1.1300 | 1.0075 |
|
132 |
+
| 1.0735 | 3.52 | 150000 | 1.1442 | 1.0083 |
|
133 |
+
| 1.0626 | 3.57 | 152000 | 1.1298 | 1.0083 |
|
134 |
+
| 1.0952 | 3.61 | 154000 | 1.1326 | 1.0087 |
|
135 |
+
| 1.0756 | 3.66 | 156000 | 1.1341 | 1.0089 |
|
136 |
+
| 1.0695 | 3.71 | 158000 | 1.1287 | 1.0092 |
|
137 |
+
| 1.0672 | 3.76 | 160000 | 1.1379 | 1.0085 |
|
138 |
+
| 1.1802 | 3.8 | 162000 | 1.1235 | 1.0074 |
|
139 |
+
| 1.094 | 3.85 | 164000 | 1.1155 | 1.0068 |
|
140 |
+
| 1.0811 | 3.9 | 166000 | 1.1172 | 1.0078 |
|
141 |
+
| 0.9901 | 3.94 | 168000 | 1.0964 | 1.0064 |
|
142 |
+
| 1.0907 | 3.99 | 170000 | 1.1031 | 1.0084 |
|
143 |
+
| 1.0799 | 4.04 | 172000 | 1.0924 | 1.0071 |
|
144 |
+
| 1.0271 | 4.08 | 174000 | 1.1020 | 1.0086 |
|
145 |
+
| 1.0482 | 4.13 | 176000 | 1.1067 | 1.0084 |
|
146 |
+
| 1.1078 | 4.18 | 178000 | 1.1083 | 1.0088 |
|
147 |
+
| 1.1798 | 4.23 | 180000 | 1.0964 | 1.0064 |
|
148 |
+
| 1.0933 | 4.27 | 182000 | 1.1034 | 1.0080 |
|
149 |
+
| 1.0272 | 4.32 | 184000 | 1.1036 | 1.0075 |
|
150 |
+
| 1.1125 | 4.37 | 186000 | 1.1022 | 1.0084 |
|
151 |
+
| 1.033 | 4.41 | 188000 | 1.0906 | 1.0070 |
|
152 |
+
| 1.1048 | 4.46 | 190000 | 1.0923 | 1.0079 |
|
153 |
+
| 1.1565 | 4.51 | 192000 | 1.0976 | 1.0078 |
|
154 |
+
| 1.0698 | 4.55 | 194000 | 1.0950 | 1.0073 |
|
155 |
+
| 1.0735 | 4.6 | 196000 | 1.0920 | 1.0074 |
|
156 |
+
| 1.0137 | 4.65 | 198000 | 1.0899 | 1.0073 |
|
157 |
+
| 1.0669 | 4.69 | 200000 | 1.0929 | 1.0076 |
|
158 |
+
|
159 |
+
|
160 |
+
### Framework versions
|
161 |
+
|
162 |
+
- Transformers 4.35.0
|
163 |
+
- Pytorch 2.1.0+cu118
|
164 |
+
- Datasets 2.14.6
|
165 |
+
- Tokenizers 0.14.1
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|