End of training
Browse files- README.md +138 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: ft_0124_korean_2
|
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 |
+
# ft_0124_korean_2
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
17 |
+
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.5092
|
19 |
+
- Cer: 0.1001
|
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: 0.0001
|
39 |
+
- train_batch_size: 8
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: linear
|
44 |
+
- lr_scheduler_warmup_steps: 500
|
45 |
+
- num_epochs: 20
|
46 |
+
- mixed_precision_training: Native AMP
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
51 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|
|
52 |
+
| 25.0263 | 0.25 | 500 | 5.1785 | 1.0 |
|
53 |
+
| 4.7178 | 0.5 | 1000 | 4.7781 | 1.0 |
|
54 |
+
| 4.4523 | 0.76 | 1500 | 4.1013 | 0.9077 |
|
55 |
+
| 3.2148 | 1.01 | 2000 | 2.3856 | 0.4777 |
|
56 |
+
| 2.4229 | 1.26 | 2500 | 1.8502 | 0.4047 |
|
57 |
+
| 2.0145 | 1.51 | 3000 | 1.5497 | 0.3475 |
|
58 |
+
| 1.7916 | 1.77 | 3500 | 1.3324 | 0.3076 |
|
59 |
+
| 1.5849 | 2.02 | 4000 | 1.1873 | 0.2773 |
|
60 |
+
| 1.3956 | 2.27 | 4500 | 1.0617 | 0.2578 |
|
61 |
+
| 1.3086 | 2.52 | 5000 | 0.9643 | 0.2368 |
|
62 |
+
| 1.2211 | 2.78 | 5500 | 0.8894 | 0.2246 |
|
63 |
+
| 1.1562 | 3.03 | 6000 | 0.8537 | 0.2189 |
|
64 |
+
| 1.0729 | 3.28 | 6500 | 0.7973 | 0.2101 |
|
65 |
+
| 1.0089 | 3.53 | 7000 | 0.7549 | 0.1959 |
|
66 |
+
| 1.0027 | 3.79 | 7500 | 0.7327 | 0.1945 |
|
67 |
+
| 0.9496 | 4.04 | 8000 | 0.7082 | 0.1849 |
|
68 |
+
| 0.887 | 4.29 | 8500 | 0.6909 | 0.1789 |
|
69 |
+
| 0.8607 | 4.54 | 9000 | 0.6617 | 0.1739 |
|
70 |
+
| 0.853 | 4.8 | 9500 | 0.6518 | 0.1730 |
|
71 |
+
| 0.8305 | 5.05 | 10000 | 0.6402 | 0.1657 |
|
72 |
+
| 0.774 | 5.3 | 10500 | 0.6365 | 0.1650 |
|
73 |
+
| 0.7621 | 5.55 | 11000 | 0.6206 | 0.1600 |
|
74 |
+
| 0.7553 | 5.81 | 11500 | 0.6080 | 0.1594 |
|
75 |
+
| 0.7186 | 6.06 | 12000 | 0.5951 | 0.1543 |
|
76 |
+
| 0.6772 | 6.31 | 12500 | 0.5814 | 0.1490 |
|
77 |
+
| 0.6752 | 6.56 | 13000 | 0.5815 | 0.1501 |
|
78 |
+
| 0.672 | 6.81 | 13500 | 0.5603 | 0.1440 |
|
79 |
+
| 0.6351 | 7.07 | 14000 | 0.5670 | 0.1439 |
|
80 |
+
| 0.6186 | 7.32 | 14500 | 0.5700 | 0.1431 |
|
81 |
+
| 0.6035 | 7.57 | 15000 | 0.5614 | 0.1417 |
|
82 |
+
| 0.5848 | 7.82 | 15500 | 0.5470 | 0.1396 |
|
83 |
+
| 0.5719 | 8.08 | 16000 | 0.5514 | 0.1386 |
|
84 |
+
| 0.556 | 8.33 | 16500 | 0.5515 | 0.1376 |
|
85 |
+
| 0.5596 | 8.58 | 17000 | 0.5407 | 0.1325 |
|
86 |
+
| 0.5472 | 8.83 | 17500 | 0.5405 | 0.1349 |
|
87 |
+
| 0.5309 | 9.09 | 18000 | 0.5279 | 0.1295 |
|
88 |
+
| 0.5072 | 9.34 | 18500 | 0.5275 | 0.1310 |
|
89 |
+
| 0.5072 | 9.59 | 19000 | 0.5330 | 0.1272 |
|
90 |
+
| 0.4905 | 9.84 | 19500 | 0.5238 | 0.1262 |
|
91 |
+
| 0.4842 | 10.1 | 20000 | 0.5234 | 0.1237 |
|
92 |
+
| 0.4513 | 10.35 | 20500 | 0.5210 | 0.1231 |
|
93 |
+
| 0.4513 | 10.6 | 21000 | 0.5165 | 0.1208 |
|
94 |
+
| 0.4541 | 10.85 | 21500 | 0.5189 | 0.1207 |
|
95 |
+
| 0.4417 | 11.11 | 22000 | 0.5209 | 0.1192 |
|
96 |
+
| 0.4337 | 11.36 | 22500 | 0.5246 | 0.1191 |
|
97 |
+
| 0.4339 | 11.61 | 23000 | 0.5210 | 0.1183 |
|
98 |
+
| 0.4357 | 11.86 | 23500 | 0.4990 | 0.1162 |
|
99 |
+
| 0.4066 | 12.12 | 24000 | 0.4956 | 0.1132 |
|
100 |
+
| 0.3932 | 12.37 | 24500 | 0.5064 | 0.1148 |
|
101 |
+
| 0.384 | 12.62 | 25000 | 0.5011 | 0.1134 |
|
102 |
+
| 0.3902 | 12.87 | 25500 | 0.5064 | 0.1130 |
|
103 |
+
| 0.3883 | 13.12 | 26000 | 0.5128 | 0.1121 |
|
104 |
+
| 0.3625 | 13.38 | 26500 | 0.5140 | 0.1119 |
|
105 |
+
| 0.3648 | 13.63 | 27000 | 0.5091 | 0.1108 |
|
106 |
+
| 0.365 | 13.88 | 27500 | 0.4923 | 0.1098 |
|
107 |
+
| 0.3604 | 14.13 | 28000 | 0.5062 | 0.1090 |
|
108 |
+
| 0.3517 | 14.39 | 28500 | 0.5007 | 0.1089 |
|
109 |
+
| 0.3485 | 14.64 | 29000 | 0.4956 | 0.1081 |
|
110 |
+
| 0.3407 | 14.89 | 29500 | 0.5090 | 0.1084 |
|
111 |
+
| 0.333 | 15.14 | 30000 | 0.5018 | 0.1067 |
|
112 |
+
| 0.3211 | 15.4 | 30500 | 0.5114 | 0.1063 |
|
113 |
+
| 0.3204 | 15.65 | 31000 | 0.4976 | 0.1053 |
|
114 |
+
| 0.3265 | 15.9 | 31500 | 0.4947 | 0.1046 |
|
115 |
+
| 0.3169 | 16.15 | 32000 | 0.4988 | 0.1043 |
|
116 |
+
| 0.304 | 16.41 | 32500 | 0.5115 | 0.1041 |
|
117 |
+
| 0.2944 | 16.66 | 33000 | 0.5144 | 0.1042 |
|
118 |
+
| 0.311 | 16.91 | 33500 | 0.5068 | 0.1025 |
|
119 |
+
| 0.2997 | 17.16 | 34000 | 0.5079 | 0.1030 |
|
120 |
+
| 0.288 | 17.42 | 34500 | 0.5065 | 0.1019 |
|
121 |
+
| 0.2897 | 17.67 | 35000 | 0.5077 | 0.1016 |
|
122 |
+
| 0.2939 | 17.92 | 35500 | 0.5003 | 0.1017 |
|
123 |
+
| 0.2766 | 18.17 | 36000 | 0.5116 | 0.1013 |
|
124 |
+
| 0.2841 | 18.43 | 36500 | 0.5019 | 0.1010 |
|
125 |
+
| 0.2882 | 18.68 | 37000 | 0.5046 | 0.1008 |
|
126 |
+
| 0.2678 | 18.93 | 37500 | 0.5086 | 0.1013 |
|
127 |
+
| 0.269 | 19.18 | 38000 | 0.5108 | 0.1001 |
|
128 |
+
| 0.2815 | 19.43 | 38500 | 0.5111 | 0.1001 |
|
129 |
+
| 0.2668 | 19.69 | 39000 | 0.5091 | 0.1000 |
|
130 |
+
| 0.2715 | 19.94 | 39500 | 0.5092 | 0.1001 |
|
131 |
+
|
132 |
+
|
133 |
+
### Framework versions
|
134 |
+
|
135 |
+
- Transformers 4.36.2
|
136 |
+
- Pytorch 2.1.2+cu118
|
137 |
+
- Datasets 2.16.1
|
138 |
+
- Tokenizers 0.15.0
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1267846804
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71cdfdce67108d7d44fa6f642092d3de133301e9538077eeb406dbeabbf85bca
|
3 |
size 1267846804
|