update model card README.md
Browse files
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%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 125M/125M [00:06<00:00, 21.3MB/s]
|
23540 |
+
Upload file wandb/run-20220203_135844-2tzexn1o/run-2tzexn1o.wandb: 100%|βββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββββ| 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:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ccd05a52613cf7428d8f8839c3c3aebb2cd3cdd63d287214b797522ecbd7077
|
3 |
+
size 131081989
|