Hugging Face's logo

Plim
/
xls-r-300m-cv_8-fr

Automatic Speech Recognition
Transformers
PyTorch
French
wav2vec2
mozilla-foundation/common_voice_8_0
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Community
Plim commited on
Commit
e0e93b5
·
1 Parent(s): d6f309b

update model card README.md

Browse files
Files changed (4) hide show
  1. README.md +77 -0
  2. wandb/run-20220203_135844-2tzexn1o/files/output.log +7 -0
  3. wandb/run-20220203_135844-2tzexn1o/logs/debug-internal.log +8 -0
  4. wandb/run-20220203_135844-2tzexn1o/run-2tzexn1o.wandb +2 -2
README.md ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: ''
7
+ results: []
8
+ ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ #
14
+
15
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
16
+ It achieves the following results on the evaluation set:
17
+ - Loss: inf
18
+ - Wer: 0.2172
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 7.5e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 128
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 2000
46
+ - num_epochs: 5.0
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
52
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
53
+ | 2.9114 | 0.29 | 1000 | inf | 0.9997 |
54
+ | 1.2436 | 0.57 | 2000 | inf | 0.4310 |
55
+ | 1.0552 | 0.86 | 3000 | inf | 0.3144 |
56
+ | 1.0044 | 1.15 | 4000 | inf | 0.2814 |
57
+ | 0.9718 | 1.43 | 5000 | inf | 0.2658 |
58
+ | 0.9502 | 1.72 | 6000 | inf | 0.2566 |
59
+ | 0.9418 | 2.01 | 7000 | inf | 0.2476 |
60
+ | 0.9215 | 2.29 | 8000 | inf | 0.2420 |
61
+ | 0.9236 | 2.58 | 9000 | inf | 0.2388 |
62
+ | 0.9014 | 2.87 | 10000 | inf | 0.2354 |
63
+ | 0.8814 | 3.15 | 11000 | inf | 0.2312 |
64
+ | 0.8809 | 3.44 | 12000 | inf | 0.2285 |
65
+ | 0.8717 | 3.73 | 13000 | inf | 0.2263 |
66
+ | 0.8787 | 4.01 | 14000 | inf | 0.2218 |
67
+ | 0.8567 | 4.3 | 15000 | inf | 0.2193 |
68
+ | 0.8488 | 4.59 | 16000 | inf | 0.2187 |
69
+ | 0.8359 | 4.87 | 17000 | inf | 0.2172 |
70
+
71
+
72
+ ### Framework versions
73
+
74
+ - Transformers 4.17.0.dev0
75
+ - Pytorch 1.10.2+cu102
76
+ - Datasets 1.18.3.dev0
77
+ - Tokenizers 0.11.0
wandb/run-20220203_135844-2tzexn1o/files/output.log CHANGED
@@ -23531,3 +23531,10 @@ Saving model checkpoint to ./
23531
  Saving model checkpoint to ./ | 81/1002 [00:50<10:06, 1.52it/s]
23532
  {'train_runtime': 143109.8834, 'train_samples_per_second': 15.599, 'train_steps_per_second': 0.122, 'train_loss': 1.187884036554109, 'epoch': 5.0}
23533
  Saving model checkpoint to ./ | 81/1002 [00:50<10:06, 1.52it/s]
 
 
 
 
 
 
 
 
23531
  Saving model checkpoint to ./ | 81/1002 [00:50<10:06, 1.52it/s]
23532
  {'train_runtime': 143109.8834, 'train_samples_per_second': 15.599, 'train_steps_per_second': 0.122, 'train_loss': 1.187884036554109, 'epoch': 5.0}
23533
  Saving model checkpoint to ./ | 81/1002 [00:50<10:06, 1.52it/s]
23534
+ Saving model checkpoint to ./ | 81/1002 [00:50<10:06, 1.52it/s]
23535
+ Saving model checkpoint to ./ | 81/1002 [00:50<10:06, 1.52it/s]
23536
+ Saving model checkpoint to ./ | 81/1002 [00:50<10:06, 1.52it/s]
23537
+ Saving model checkpoint to ./ | 81/1002 [00:50<10:06, 1.52it/s]
23538
+ 02/05/2022 05:45:28 - WARNING - huggingface_hub.repository - To https://huggingface.co/Plim/xls-r-300m-cv_8-fr
23539
+ Upload file wandb/run-20220203_135844-2tzexn1o/run-2tzexn1o.wandb: 100%|███████████████████████████████████████████████████████████████████████████████████████| 125M/125M [00:06<00:00, 21.3MB/s]
23540
+ Upload file wandb/run-20220203_135844-2tzexn1o/run-2tzexn1o.wandb: 100%|███████████████████████████████████████████████████████████████████████████████████████| 125M/125M [00:06<00:00, 21.3MB/s]
wandb/run-20220203_135844-2tzexn1o/logs/debug-internal.log CHANGED
@@ -48942,3 +48942,11 @@
48942
  2022-02-05 05:44:59,230 DEBUG SenderThread:3742 [sender.py:send_request():249] send_request: stop_status
48943
  2022-02-05 05:45:14,392 DEBUG HandlerThread:3742 [handler.py:handle_request():131] handle_request: stop_status
48944
  2022-02-05 05:45:14,392 DEBUG SenderThread:3742 [sender.py:send_request():249] send_request: stop_status
 
 
 
 
 
 
 
 
 
48942
  2022-02-05 05:44:59,230 DEBUG SenderThread:3742 [sender.py:send_request():249] send_request: stop_status
48943
  2022-02-05 05:45:14,392 DEBUG HandlerThread:3742 [handler.py:handle_request():131] handle_request: stop_status
48944
  2022-02-05 05:45:14,392 DEBUG SenderThread:3742 [sender.py:send_request():249] send_request: stop_status
48945
+ 2022-02-05 05:45:24,973 INFO Thread-8 :3742 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-cv_8-fr/wandb/run-20220203_135844-2tzexn1o/files/output.log
48946
+ 2022-02-05 05:45:26,974 INFO Thread-8 :3742 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-cv_8-fr/wandb/run-20220203_135844-2tzexn1o/files/output.log
48947
+ 2022-02-05 05:45:28,192 DEBUG SenderThread:3742 [sender.py:send():235] send: stats
48948
+ 2022-02-05 05:45:28,976 INFO Thread-8 :3742 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-cv_8-fr/wandb/run-20220203_135844-2tzexn1o/files/output.log
48949
+ 2022-02-05 05:45:29,771 DEBUG HandlerThread:3742 [handler.py:handle_request():131] handle_request: stop_status
48950
+ 2022-02-05 05:45:29,771 DEBUG SenderThread:3742 [sender.py:send_request():249] send_request: stop_status
48951
+ 2022-02-05 05:45:30,977 INFO Thread-8 :3742 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-cv_8-fr/wandb/run-20220203_135844-2tzexn1o/files/output.log
48952
+ 2022-02-05 05:45:34,980 INFO Thread-8 :3742 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-cv_8-fr/wandb/run-20220203_135844-2tzexn1o/files/output.log
wandb/run-20220203_135844-2tzexn1o/run-2tzexn1o.wandb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16778d7647e5649a67b93699fa64a7d5752d469690253f71dd4aecd2ab1af7de
3
- size 131078471
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ccd05a52613cf7428d8f8839c3c3aebb2cd3cdd63d287214b797522ecbd7077
3
+ size 131081989