AlexN commited on
Commit
1f92738
β€’
1 Parent(s): 90fe400

update model card README.md

Browse files
README.md ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice
7
+ model-index:
8
+ - name: ''
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
+ #
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2290
20
+ - Wer: 0.2382
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0002
40
+ - train_batch_size: 32
41
+ - eval_batch_size: 32
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 1500
46
+ - num_epochs: 15.0
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
53
+ | 3.0952 | 0.64 | 500 | 3.0982 | 1.0 |
54
+ | 1.7975 | 1.29 | 1000 | 0.7887 | 0.5651 |
55
+ | 1.4138 | 1.93 | 1500 | 0.5238 | 0.4389 |
56
+ | 1.344 | 2.57 | 2000 | 0.4775 | 0.4318 |
57
+ | 1.2737 | 3.21 | 2500 | 0.4648 | 0.4075 |
58
+ | 1.2554 | 3.86 | 3000 | 0.4069 | 0.3678 |
59
+ | 1.1996 | 4.5 | 3500 | 0.3914 | 0.3668 |
60
+ | 1.1427 | 5.14 | 4000 | 0.3694 | 0.3572 |
61
+ | 1.1372 | 5.78 | 4500 | 0.3568 | 0.3501 |
62
+ | 1.0831 | 6.43 | 5000 | 0.3331 | 0.3253 |
63
+ | 1.1074 | 7.07 | 5500 | 0.3332 | 0.3352 |
64
+ | 1.0536 | 7.71 | 6000 | 0.3131 | 0.3152 |
65
+ | 1.0248 | 8.35 | 6500 | 0.3024 | 0.3023 |
66
+ | 1.0075 | 9.0 | 7000 | 0.2948 | 0.3028 |
67
+ | 0.979 | 9.64 | 7500 | 0.2796 | 0.2853 |
68
+ | 0.9594 | 10.28 | 8000 | 0.2719 | 0.2789 |
69
+ | 0.9172 | 10.93 | 8500 | 0.2620 | 0.2695 |
70
+ | 0.9047 | 11.57 | 9000 | 0.2537 | 0.2596 |
71
+ | 0.8777 | 12.21 | 9500 | 0.2438 | 0.2525 |
72
+ | 0.8629 | 12.85 | 10000 | 0.2409 | 0.2493 |
73
+ | 0.8575 | 13.5 | 10500 | 0.2366 | 0.2440 |
74
+ | 0.8361 | 14.14 | 11000 | 0.2317 | 0.2385 |
75
+ | 0.8126 | 14.78 | 11500 | 0.2290 | 0.2382 |
76
+
77
+
78
+ ### Framework versions
79
+
80
+ - Transformers 4.17.0.dev0
81
+ - Pytorch 1.10.2+cu102
82
+ - Datasets 1.18.2.dev0
83
+ - Tokenizers 0.11.0
wandb/run-20220201_223624-2b1hcyq3/files/output.log CHANGED
@@ -10070,3 +10070,9 @@ Deleting older checkpoint [checkpoint-4500] due to args.save_total_limit
10070
  {'train_runtime': 23640.5221, 'train_samples_per_second': 15.785, 'train_steps_per_second': 0.494, 'train_loss': 1.3307904394651542, 'epoch': 15.0}
10071
  13%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 33/260 [00:40<04:42, 1.24s/it]
10072
  13%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 33/260 [00:40<04:42, 1.24s/it]
 
 
 
 
 
 
 
10070
  {'train_runtime': 23640.5221, 'train_samples_per_second': 15.785, 'train_steps_per_second': 0.494, 'train_loss': 1.3307904394651542, 'epoch': 15.0}
10071
  13%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 33/260 [00:40<04:42, 1.24s/it]
10072
  13%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 33/260 [00:40<04:42, 1.24s/it]
10073
+ 13%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 33/260 [00:40<04:42, 1.24s/it]
10074
+ 13%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 33/260 [00:40<04:42, 1.24s/it]
10075
+ 13%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 33/260 [00:40<04:42, 1.24s/it]
10076
+ 02/02/2022 05:10:57 - WARNING - huggingface_hub.repository - To https://huggingface.co/AlexN/xls-r-300m-pt
10077
+ 1f31f7e..90fe400 main -> main
10078
+ 13%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 33/260 [00:40<04:42, 1.24s/it]
wandb/run-20220201_223624-2b1hcyq3/logs/debug-internal.log CHANGED
@@ -15647,3 +15647,10 @@
15647
  2022-02-02 05:10:30,912 INFO Thread-8 :38198 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-pt/wandb/run-20220201_223624-2b1hcyq3/files/output.log
15648
  2022-02-02 05:10:35,640 DEBUG HandlerThread:38198 [handler.py:handle_request():130] handle_request: stop_status
15649
  2022-02-02 05:10:35,641 DEBUG SenderThread:38198 [sender.py:send_request():248] send_request: stop_status
 
 
 
 
 
 
 
 
15647
  2022-02-02 05:10:30,912 INFO Thread-8 :38198 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-pt/wandb/run-20220201_223624-2b1hcyq3/files/output.log
15648
  2022-02-02 05:10:35,640 DEBUG HandlerThread:38198 [handler.py:handle_request():130] handle_request: stop_status
15649
  2022-02-02 05:10:35,641 DEBUG SenderThread:38198 [sender.py:send_request():248] send_request: stop_status
15650
+ 2022-02-02 05:10:50,814 DEBUG HandlerThread:38198 [handler.py:handle_request():130] handle_request: stop_status
15651
+ 2022-02-02 05:10:50,815 DEBUG SenderThread:38198 [sender.py:send_request():248] send_request: stop_status
15652
+ 2022-02-02 05:10:54,926 INFO Thread-8 :38198 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-pt/wandb/run-20220201_223624-2b1hcyq3/files/output.log
15653
+ 2022-02-02 05:10:56,927 INFO Thread-8 :38198 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-pt/wandb/run-20220201_223624-2b1hcyq3/files/output.log
15654
+ 2022-02-02 05:10:58,718 DEBUG SenderThread:38198 [sender.py:send():234] send: stats
15655
+ 2022-02-02 05:10:58,928 INFO Thread-8 :38198 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-pt/wandb/run-20220201_223624-2b1hcyq3/files/output.log
15656
+ 2022-02-02 05:11:00,929 INFO Thread-8 :38198 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-pt/wandb/run-20220201_223624-2b1hcyq3/files/output.log
wandb/run-20220201_223624-2b1hcyq3/run-2b1hcyq3.wandb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6367f0baa24526ed1632d9505d6533d44ba8b3128ed9c0a9aa64f288312aad00
3
- size 77229875
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b136da7b148d309b90b6ed41c2a300508201c94dc0ac980afd1bf4ef6ba2dfec
3
+ size 77234252