gokuls commited on
Commit
d44a5db
1 Parent(s): 282275f

End of training

Browse files
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/hubert-base-ls960
4
+ tags:
5
+ - generated_from_trainer
6
+ metrics:
7
+ - accuracy
8
+ model-index:
9
+ - name: hubert-base-ls960-finetuned-ic-slurp-wt_init
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
+ # hubert-base-ls960-finetuned-ic-slurp-wt_init
17
+
18
+ This model is a fine-tuned version of [facebook/hubert-base-ls960](https://huggingface.co/facebook/hubert-base-ls960) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 3.1377
21
+ - Accuracy: 0.4604
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
+ | 3.9613 | 1.0 | 527 | 3.8944 | 0.0803 |
56
+ | 3.7817 | 2.0 | 1055 | 3.7275 | 0.0910 |
57
+ | 3.6357 | 3.0 | 1582 | 3.5410 | 0.1308 |
58
+ | 3.4527 | 4.0 | 2110 | 3.3426 | 0.1676 |
59
+ | 3.0715 | 5.0 | 2637 | 3.0751 | 0.2331 |
60
+ | 2.9153 | 6.0 | 3165 | 2.8168 | 0.2969 |
61
+ | 2.5333 | 7.0 | 3692 | 2.6229 | 0.3375 |
62
+ | 2.3807 | 8.0 | 4220 | 2.5673 | 0.3620 |
63
+ | 2.181 | 9.0 | 4747 | 2.4933 | 0.3835 |
64
+ | 1.9118 | 10.0 | 5275 | 2.4411 | 0.4046 |
65
+ | 1.9015 | 11.0 | 5802 | 2.4254 | 0.4126 |
66
+ | 1.5811 | 12.0 | 6330 | 2.4216 | 0.4275 |
67
+ | 1.491 | 13.0 | 6857 | 2.4833 | 0.4284 |
68
+ | 1.3697 | 14.0 | 7385 | 2.5243 | 0.4368 |
69
+ | 1.1232 | 15.0 | 7912 | 2.5944 | 0.4309 |
70
+ | 1.1071 | 16.0 | 8440 | 2.6475 | 0.4317 |
71
+ | 0.9439 | 17.0 | 8967 | 2.6379 | 0.4449 |
72
+ | 0.917 | 18.0 | 9495 | 2.7438 | 0.4468 |
73
+ | 0.7628 | 19.0 | 10022 | 2.7671 | 0.4513 |
74
+ | 0.7642 | 20.0 | 10550 | 2.8993 | 0.4418 |
75
+ | 0.6716 | 21.0 | 11077 | 2.9354 | 0.4472 |
76
+ | 0.6166 | 22.0 | 11605 | 2.9961 | 0.4510 |
77
+ | 0.4819 | 23.0 | 12132 | 3.0959 | 0.4451 |
78
+ | 0.5903 | 24.0 | 12660 | 3.0542 | 0.4557 |
79
+ | 0.515 | 25.0 | 13187 | 3.0723 | 0.4589 |
80
+ | 0.518 | 26.0 | 13715 | 3.1377 | 0.4604 |
81
+ | 0.3902 | 27.0 | 14242 | 3.2230 | 0.4524 |
82
+ | 0.4825 | 28.0 | 14770 | 3.2925 | 0.4583 |
83
+ | 0.29 | 29.0 | 15297 | 3.4027 | 0.4498 |
84
+ | 0.2789 | 30.0 | 15825 | 3.3573 | 0.4598 |
85
+ | 0.3202 | 31.0 | 16352 | 3.4381 | 0.4542 |
86
+
87
+
88
+ ### Framework versions
89
+
90
+ - Transformers 4.37.2
91
+ - Pytorch 2.2.0+cu121
92
+ - Datasets 2.17.1
93
+ - Tokenizers 0.15.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59a83cc5ad9512a9e5790da382ef5435554363a33c5a02d811a9d556e2e905db
3
  size 378394560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:740c76cf37b172469f0ef1f296b92bef0550495f789f84eaaeaa363242f60b9d
3
  size 378394560
runs/Mar05_14-58-12_ki-g0009/events.out.tfevents.1709650695.ki-g0009 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4b179f60832e9c7d15422ba4807a3d8ad8d2a19c002185c046d0899826e009a
3
- size 267767
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:872c914ec4458c5da2cd43a4a874c941065a5c2a3ae3c9e229807147c94d94a7
3
+ size 277088
runs/Mar05_14-58-12_ki-g0009/events.out.tfevents.1709684716.ki-g0009 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59fbd5fe1a4144974b26c1f3c3cedab8c45bc911206b5ab51eeb07814ace6497
3
+ size 40