End of training
Browse files
README.md
ADDED
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-base
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- accuracy
|
8 |
+
model-index:
|
9 |
+
- name: wav2vec2-base-finetuned-ic-slurp
|
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 |
+
# wav2vec2-base-finetuned-ic-slurp
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.1101
|
21 |
+
- Accuracy: 0.7393
|
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: 5e-05
|
41 |
+
- train_batch_size: 24
|
42 |
+
- eval_batch_size: 24
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 4
|
45 |
+
- total_train_batch_size: 96
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: linear
|
48 |
+
- lr_scheduler_warmup_ratio: 0.1
|
49 |
+
- num_epochs: 50
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
54 |
+
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
55 |
+
| 4.0345 | 1.0 | 527 | 3.9813 | 0.0673 |
|
56 |
+
| 3.5622 | 2.0 | 1055 | 3.4634 | 0.1867 |
|
57 |
+
| 2.7737 | 3.0 | 1582 | 2.7252 | 0.3638 |
|
58 |
+
| 2.1285 | 4.0 | 2110 | 2.1754 | 0.4827 |
|
59 |
+
| 1.6216 | 5.0 | 2637 | 1.8169 | 0.5701 |
|
60 |
+
| 1.1786 | 6.0 | 3165 | 1.5773 | 0.6347 |
|
61 |
+
| 0.8747 | 7.0 | 3692 | 1.5024 | 0.6568 |
|
62 |
+
| 0.7565 | 8.0 | 4220 | 1.5020 | 0.6694 |
|
63 |
+
| 0.5236 | 9.0 | 4747 | 1.5287 | 0.6799 |
|
64 |
+
| 0.4517 | 10.0 | 5275 | 1.5165 | 0.6879 |
|
65 |
+
| 0.364 | 11.0 | 5802 | 1.5159 | 0.6949 |
|
66 |
+
| 0.3221 | 12.0 | 6330 | 1.5217 | 0.6996 |
|
67 |
+
| 0.227 | 13.0 | 6857 | 1.5718 | 0.7075 |
|
68 |
+
| 0.1828 | 14.0 | 7385 | 1.6979 | 0.6901 |
|
69 |
+
| 0.1691 | 15.0 | 7912 | 1.6162 | 0.7093 |
|
70 |
+
| 0.1642 | 16.0 | 8440 | 1.6973 | 0.7048 |
|
71 |
+
| 0.1254 | 17.0 | 8967 | 1.7060 | 0.7100 |
|
72 |
+
| 0.1578 | 18.0 | 9495 | 1.7328 | 0.7063 |
|
73 |
+
| 0.1509 | 19.0 | 10022 | 1.7658 | 0.7073 |
|
74 |
+
| 0.1409 | 20.0 | 10550 | 1.7770 | 0.7052 |
|
75 |
+
| 0.1085 | 21.0 | 11077 | 1.8033 | 0.7074 |
|
76 |
+
| 0.106 | 22.0 | 11605 | 1.7000 | 0.7149 |
|
77 |
+
| 0.0764 | 23.0 | 12132 | 1.7943 | 0.7104 |
|
78 |
+
| 0.0671 | 24.0 | 12660 | 1.8323 | 0.7155 |
|
79 |
+
| 0.0768 | 25.0 | 13187 | 1.8486 | 0.7146 |
|
80 |
+
| 0.0741 | 26.0 | 13715 | 1.8227 | 0.7187 |
|
81 |
+
| 0.0731 | 27.0 | 14242 | 1.7824 | 0.7230 |
|
82 |
+
| 0.0935 | 28.0 | 14770 | 1.8987 | 0.7164 |
|
83 |
+
| 0.0829 | 29.0 | 15297 | 1.8774 | 0.7202 |
|
84 |
+
| 0.0588 | 30.0 | 15825 | 1.8820 | 0.7211 |
|
85 |
+
| 0.059 | 31.0 | 16352 | 1.9535 | 0.7246 |
|
86 |
+
| 0.0431 | 32.0 | 16880 | 1.9621 | 0.7237 |
|
87 |
+
| 0.0324 | 33.0 | 17407 | 2.0160 | 0.7256 |
|
88 |
+
| 0.0447 | 34.0 | 17935 | 1.9392 | 0.7262 |
|
89 |
+
| 0.025 | 35.0 | 18462 | 2.0095 | 0.7284 |
|
90 |
+
| 0.0522 | 36.0 | 18990 | 1.9994 | 0.7244 |
|
91 |
+
| 0.0482 | 37.0 | 19517 | 2.0566 | 0.7262 |
|
92 |
+
| 0.0203 | 38.0 | 20045 | 2.0287 | 0.7295 |
|
93 |
+
| 0.0221 | 39.0 | 20572 | 2.0634 | 0.7300 |
|
94 |
+
| 0.0444 | 40.0 | 21100 | 2.0593 | 0.7302 |
|
95 |
+
| 0.0348 | 41.0 | 21627 | 2.0712 | 0.7298 |
|
96 |
+
| 0.0154 | 42.0 | 22155 | 2.0429 | 0.7351 |
|
97 |
+
| 0.024 | 43.0 | 22682 | 2.0708 | 0.7352 |
|
98 |
+
| 0.0157 | 44.0 | 23210 | 2.0701 | 0.7368 |
|
99 |
+
| 0.0222 | 45.0 | 23737 | 2.0963 | 0.7338 |
|
100 |
+
| 0.0126 | 46.0 | 24265 | 2.1329 | 0.7340 |
|
101 |
+
| 0.0211 | 47.0 | 24792 | 2.1230 | 0.7370 |
|
102 |
+
| 0.0288 | 48.0 | 25320 | 2.1101 | 0.7393 |
|
103 |
+
| 0.0347 | 49.0 | 25847 | 2.1201 | 0.7375 |
|
104 |
+
| 0.0162 | 49.95 | 26350 | 2.1197 | 0.7381 |
|
105 |
+
|
106 |
+
|
107 |
+
### Framework versions
|
108 |
+
|
109 |
+
- Transformers 4.37.2
|
110 |
+
- Pytorch 2.2.0+cu121
|
111 |
+
- Datasets 2.17.1
|
112 |
+
- Tokenizers 0.15.2
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 378394896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a5bc2f4854e5d4a06a85a18b52049ec8f22cf72f3476a4d7afaa9d3ed3571a1
|
3 |
size 378394896
|
runs/Mar05_13-18-30_ki-g0009/events.out.tfevents.1709644713.ki-g0009
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:975c7414185edba0924a9b04f2f20cb8b4311506cdfd8d60f4c94e4994063568
|
3 |
+
size 444097
|
runs/Mar05_13-18-30_ki-g0009/events.out.tfevents.1709706851.ki-g0009
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:425ddbbe733d54e62045466c42f5600b5ee2169f3a6aadf8df6a1f230001010d
|
3 |
+
size 40
|