End of training
Browse files- README.md +141 -0
- model.safetensors +1 -1
README.md
ADDED
@@ -0,0 +1,141 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: facebook/wav2vec2-base
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: dfmodel
|
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 |
+
# dfmodel
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.0061
|
22 |
+
- Accuracy: 0.9984
|
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: 0.0001
|
42 |
+
- train_batch_size: 1
|
43 |
+
- eval_batch_size: 1
|
44 |
+
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 32
|
46 |
+
- total_train_batch_size: 32
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 1.0
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:------:|:----:|:---------------:|:--------:|
|
55 |
+
| 0.5468 | 0.0126 | 10 | 0.3332 | 0.9004 |
|
56 |
+
| 0.2523 | 0.0252 | 20 | 0.6204 | 0.8444 |
|
57 |
+
| 0.2843 | 0.0378 | 30 | 0.1581 | 0.9570 |
|
58 |
+
| 0.0499 | 0.0503 | 40 | 0.0812 | 0.9822 |
|
59 |
+
| 0.0571 | 0.0629 | 50 | 0.0928 | 0.9806 |
|
60 |
+
| 0.099 | 0.0755 | 60 | 0.0443 | 0.9923 |
|
61 |
+
| 0.0417 | 0.0881 | 70 | 0.0464 | 0.9893 |
|
62 |
+
| 0.0499 | 0.1007 | 80 | 0.3664 | 0.9331 |
|
63 |
+
| 0.131 | 0.1133 | 90 | 0.1152 | 0.9728 |
|
64 |
+
| 0.0675 | 0.1259 | 100 | 0.0706 | 0.9852 |
|
65 |
+
| 0.0234 | 0.1385 | 110 | 0.0436 | 0.9926 |
|
66 |
+
| 0.0237 | 0.1510 | 120 | 0.0701 | 0.9885 |
|
67 |
+
| 0.0221 | 0.1636 | 130 | 0.0958 | 0.9835 |
|
68 |
+
| 0.0296 | 0.1762 | 140 | 0.0269 | 0.9950 |
|
69 |
+
| 0.0224 | 0.1888 | 150 | 0.0791 | 0.9866 |
|
70 |
+
| 0.1075 | 0.2014 | 160 | 0.0421 | 0.9888 |
|
71 |
+
| 0.05 | 0.2140 | 170 | 0.0361 | 0.9918 |
|
72 |
+
| 0.0097 | 0.2266 | 180 | 0.0372 | 0.9931 |
|
73 |
+
| 0.0394 | 0.2392 | 190 | 0.0415 | 0.9920 |
|
74 |
+
| 0.0678 | 0.2517 | 200 | 0.0396 | 0.9912 |
|
75 |
+
| 0.0689 | 0.2643 | 210 | 0.0196 | 0.9965 |
|
76 |
+
| 0.0291 | 0.2769 | 220 | 0.0416 | 0.9923 |
|
77 |
+
| 0.0527 | 0.2895 | 230 | 0.0297 | 0.9947 |
|
78 |
+
| 0.0552 | 0.3021 | 240 | 0.0191 | 0.9964 |
|
79 |
+
| 0.0678 | 0.3147 | 250 | 0.0202 | 0.9967 |
|
80 |
+
| 0.0252 | 0.3273 | 260 | 0.0253 | 0.9945 |
|
81 |
+
| 0.077 | 0.3398 | 270 | 0.0221 | 0.9961 |
|
82 |
+
| 0.0202 | 0.3524 | 280 | 0.0306 | 0.9942 |
|
83 |
+
| 0.0559 | 0.3650 | 290 | 0.0178 | 0.9969 |
|
84 |
+
| 0.018 | 0.3776 | 300 | 0.0186 | 0.9964 |
|
85 |
+
| 0.0157 | 0.3902 | 310 | 0.0175 | 0.9962 |
|
86 |
+
| 0.0144 | 0.4028 | 320 | 0.0201 | 0.9959 |
|
87 |
+
| 0.0274 | 0.4154 | 330 | 0.0276 | 0.9937 |
|
88 |
+
| 0.0226 | 0.4280 | 340 | 0.0222 | 0.9958 |
|
89 |
+
| 0.0022 | 0.4405 | 350 | 0.0199 | 0.9962 |
|
90 |
+
| 0.0043 | 0.4531 | 360 | 0.0494 | 0.9912 |
|
91 |
+
| 0.0306 | 0.4657 | 370 | 0.0198 | 0.9959 |
|
92 |
+
| 0.0177 | 0.4783 | 380 | 0.0179 | 0.9964 |
|
93 |
+
| 0.0014 | 0.4909 | 390 | 0.0242 | 0.9959 |
|
94 |
+
| 0.0012 | 0.5035 | 400 | 0.0259 | 0.9959 |
|
95 |
+
| 0.0136 | 0.5161 | 410 | 0.0286 | 0.9956 |
|
96 |
+
| 0.0562 | 0.5287 | 420 | 0.0214 | 0.9962 |
|
97 |
+
| 0.0019 | 0.5412 | 430 | 0.0225 | 0.9958 |
|
98 |
+
| 0.0028 | 0.5538 | 440 | 0.0190 | 0.9964 |
|
99 |
+
| 0.0124 | 0.5664 | 450 | 0.0197 | 0.9965 |
|
100 |
+
| 0.0243 | 0.5790 | 460 | 0.0152 | 0.9972 |
|
101 |
+
| 0.0156 | 0.5916 | 470 | 0.0196 | 0.9951 |
|
102 |
+
| 0.0189 | 0.6042 | 480 | 0.0150 | 0.9964 |
|
103 |
+
| 0.0205 | 0.6168 | 490 | 0.0181 | 0.9956 |
|
104 |
+
| 0.0249 | 0.6294 | 500 | 0.0142 | 0.9961 |
|
105 |
+
| 0.0253 | 0.6419 | 510 | 0.0099 | 0.9975 |
|
106 |
+
| 0.0034 | 0.6545 | 520 | 0.0198 | 0.9959 |
|
107 |
+
| 0.0111 | 0.6671 | 530 | 0.0363 | 0.9935 |
|
108 |
+
| 0.0214 | 0.6797 | 540 | 0.0142 | 0.9964 |
|
109 |
+
| 0.0015 | 0.6923 | 550 | 0.0107 | 0.9975 |
|
110 |
+
| 0.0075 | 0.7049 | 560 | 0.0117 | 0.9972 |
|
111 |
+
| 0.0088 | 0.7175 | 570 | 0.0077 | 0.9981 |
|
112 |
+
| 0.015 | 0.7300 | 580 | 0.0094 | 0.9980 |
|
113 |
+
| 0.0141 | 0.7426 | 590 | 0.0076 | 0.9983 |
|
114 |
+
| 0.0097 | 0.7552 | 600 | 0.0084 | 0.9980 |
|
115 |
+
| 0.0132 | 0.7678 | 610 | 0.0072 | 0.9981 |
|
116 |
+
| 0.0009 | 0.7804 | 620 | 0.0096 | 0.9980 |
|
117 |
+
| 0.0003 | 0.7930 | 630 | 0.0122 | 0.9978 |
|
118 |
+
| 0.0003 | 0.8056 | 640 | 0.0131 | 0.9976 |
|
119 |
+
| 0.0267 | 0.8182 | 650 | 0.0112 | 0.9978 |
|
120 |
+
| 0.0006 | 0.8307 | 660 | 0.0120 | 0.9975 |
|
121 |
+
| 0.0207 | 0.8433 | 670 | 0.0075 | 0.9981 |
|
122 |
+
| 0.0183 | 0.8559 | 680 | 0.0051 | 0.9984 |
|
123 |
+
| 0.002 | 0.8685 | 690 | 0.0047 | 0.9987 |
|
124 |
+
| 0.0022 | 0.8811 | 700 | 0.0050 | 0.9991 |
|
125 |
+
| 0.0184 | 0.8937 | 710 | 0.0050 | 0.9987 |
|
126 |
+
| 0.0009 | 0.9063 | 720 | 0.0047 | 0.9989 |
|
127 |
+
| 0.003 | 0.9189 | 730 | 0.0047 | 0.9989 |
|
128 |
+
| 0.0005 | 0.9314 | 740 | 0.0062 | 0.9981 |
|
129 |
+
| 0.0102 | 0.9440 | 750 | 0.0076 | 0.9980 |
|
130 |
+
| 0.0063 | 0.9566 | 760 | 0.0079 | 0.9978 |
|
131 |
+
| 0.0148 | 0.9692 | 770 | 0.0069 | 0.9981 |
|
132 |
+
| 0.0173 | 0.9818 | 780 | 0.0065 | 0.9984 |
|
133 |
+
| 0.0099 | 0.9944 | 790 | 0.0061 | 0.9984 |
|
134 |
+
|
135 |
+
|
136 |
+
### Framework versions
|
137 |
+
|
138 |
+
- Transformers 4.45.0.dev0
|
139 |
+
- Pytorch 2.1.2
|
140 |
+
- Datasets 2.21.1.dev0
|
141 |
+
- Tokenizers 0.19.1
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 379881432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df6e71aaed2c95b708cd1ce8e2f8f65f95ba353d86106b9eef0bb3006e96583f
|
3 |
size 379881432
|