HF中国镜像站's logo

ekunish
/
wav2vec2-pretraining-demo

Transformers
TensorBoard
Safetensors
wav2vec2
pretraining
Generated from Trainer
Model card Files Metrics Community
ekunish commited on
Commit
bf2c0f7
·
verified ·
1 Parent(s): 8806c4e

End of training

Browse files
Files changed (3) hide show
  1. README.md +91 -0
  2. model.safetensors +1 -1
  3. runs/Feb05_12-16-03_6be9d2e23d10/events.out.tfevents.1738757950.6be9d2e23d10.69380.3 +2 -2
README.md ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: facebook/wav2vec2-base-960h
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: wav2vec2-pretraining-demo
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # wav2vec2-pretraining-demo
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 451.3242
20
+ - Constrast Loss: 443.2349
21
+ - Div Loss: 80.8922
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: 0.0001
41
+ - train_batch_size: 8
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_ratio: 0.1
47
+ - num_epochs: 10
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss | Constrast Loss | Div Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:--------:|
54
+ | 478.7255 | 0.5 | 100 | 420.3063 | 412.4319 | 78.7440 |
55
+ | 555.9113 | 1.0 | 200 | 407.1626 | 399.2634 | 78.9919 |
56
+ | 555.9113 | 1.0 | 200 | 433.5689 | 425.1757 | 83.9328 |
57
+ | 445.2046 | 1.5 | 300 | 390.8622 | 383.1959 | 76.6634 |
58
+ | 480.6411 | 2.0 | 400 | 439.1803 | 430.9575 | 82.2276 |
59
+ | 480.6411 | 2.0 | 400 | 403.2052 | 395.3518 | 78.5338 |
60
+ | 484.0212 | 2.5 | 500 | 418.4225 | 410.3823 | 80.4012 |
61
+ | 442.1686 | 3.0 | 600 | 410.6022 | 402.7102 | 78.9197 |
62
+ | 442.1686 | 3.0 | 600 | 454.8314 | 446.3063 | 85.2508 |
63
+ | 404.1281 | 3.5 | 700 | 423.5104 | 415.3885 | 81.2197 |
64
+ | 479.2968 | 4.0 | 800 | 422.7674 | 414.8620 | 79.0535 |
65
+ | 479.2968 | 4.0 | 800 | 433.8821 | 425.6849 | 81.9722 |
66
+ | 482.9329 | 4.5 | 900 | 465.1997 | 456.7795 | 84.2019 |
67
+ | 480.0253 | 5.0 | 1000 | 475.0238 | 466.5422 | 84.8163 |
68
+ | 480.0253 | 5.0 | 1000 | 427.2379 | 419.3205 | 79.1747 |
69
+ | 408.0809 | 5.5 | 1100 | 453.6945 | 445.3407 | 83.5376 |
70
+ | 484.2443 | 6.0 | 1200 | 414.2449 | 406.5308 | 77.1410 |
71
+ | 484.2443 | 6.0 | 1200 | 448.2039 | 439.9778 | 82.2607 |
72
+ | 518.4024 | 6.5 | 1300 | 451.1086 | 442.8609 | 82.4774 |
73
+ | 449.2522 | 7.0 | 1400 | 382.4106 | 375.1262 | 72.8438 |
74
+ | 449.2522 | 7.0 | 1400 | 431.2335 | 423.1804 | 80.5309 |
75
+ | 448.0326 | 7.5 | 1500 | 416.1967 | 408.4327 | 77.6399 |
76
+ | 441.6883 | 8.0 | 1600 | 434.1829 | 426.2272 | 79.5572 |
77
+ | 441.6883 | 8.0 | 1600 | 440.8153 | 432.5998 | 82.1544 |
78
+ | 408.1424 | 8.5 | 1700 | 403.8840 | 396.4740 | 74.1004 |
79
+ | 442.7975 | 9.0 | 1800 | 392.1655 | 384.8187 | 73.4681 |
80
+ | 442.7975 | 9.0 | 1800 | 443.3363 | 435.3478 | 79.8843 |
81
+ | 512.9667 | 9.5 | 1900 | 389.8308 | 382.4903 | 73.4044 |
82
+ | 485.8844 | 10.0 | 2000 | 446.7708 | 438.7427 | 80.2811 |
83
+ | 485.8844 | 10.0 | 2000 | 451.3242 | 443.2349 | 80.8922 |
84
+
85
+
86
+ ### Framework versions
87
+
88
+ - Transformers 4.49.0.dev0
89
+ - Pytorch 2.6.0+cu124
90
+ - Datasets 3.2.0
91
+ - Tokenizers 0.21.0
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32333cf1281c89e446a97750c618948d24233257f6da7e66d084e89c90213ffb
3
  size 380204744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdc60fa3ec3cc2eb5c923b02e99b8c8690810c1fcc5ff01aa90b042ebbbe0d0f
3
  size 380204744
runs/Feb05_12-16-03_6be9d2e23d10/events.out.tfevents.1738757950.6be9d2e23d10.69380.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79ca427cc6c3d16b7d7f576c70b0908c07385461744241d4fabb13467affcc83
3
- size 52372
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f1d33d41f97eb73519ba72fd73b0a74fc5b0327f97f95a668e75110ae1f4a33
3
+ size 55252