lucio commited on
Commit
8527826
1 Parent(s): c84e394

Training in progress, step 500

Browse files
.ipynb_checkpoints/run-checkpoint.sh CHANGED
@@ -3,11 +3,11 @@ python ~/xls-r-uzbek-cv8/run_speech_recognition_ctc.py \
3
  --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
4
  --dataset_config_name="uz" \
5
  --output_dir="~/xls-r-uzbek-cv8" \
6
- --train_split_name="train[:30%]" \
7
  --eval_split_name="validation[50%:]" \
8
  --overwrite_output_dir \
9
- --num_train_epochs="50" \
10
- --per_device_train_batch_size="64" \
11
  --per_device_eval_batch_size="8" \
12
  --gradient_accumulation_steps="4" \
13
  --learning_rate="3e-5" \
@@ -16,11 +16,11 @@ python ~/xls-r-uzbek-cv8/run_speech_recognition_ctc.py \
16
  --evaluation_strategy="steps" \
17
  --text_column_name="sentence" \
18
  --eval_metrics wer cer \
19
- --save_steps="200" \
20
- --eval_steps="200" \
21
  --logging_steps="100" \
22
  --min_duration_in_seconds="0.2" \
23
- --layerdrop="0.05" \
24
  --activation_dropout="0.1" \
25
  --save_total_limit="3" \
26
  --freeze_feature_encoder \
 
3
  --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
4
  --dataset_config_name="uz" \
5
  --output_dir="~/xls-r-uzbek-cv8" \
6
+ --train_split_name="train[:50%]" \
7
  --eval_split_name="validation[50%:]" \
8
  --overwrite_output_dir \
9
+ --num_train_epochs="100" \
10
+ --per_device_train_batch_size="32" \
11
  --per_device_eval_batch_size="8" \
12
  --gradient_accumulation_steps="4" \
13
  --learning_rate="3e-5" \
 
16
  --evaluation_strategy="steps" \
17
  --text_column_name="sentence" \
18
  --eval_metrics wer cer \
19
+ --save_steps="500" \
20
+ --eval_steps="500" \
21
  --logging_steps="100" \
22
  --min_duration_in_seconds="0.2" \
23
+ --layerdrop="0.01" \
24
  --activation_dropout="0.1" \
25
  --save_total_limit="3" \
26
  --freeze_feature_encoder \
config.json CHANGED
@@ -58,7 +58,7 @@
58
  "initializer_range": 0.02,
59
  "intermediate_size": 4096,
60
  "layer_norm_eps": 1e-05,
61
- "layerdrop": 0.05,
62
  "mask_feature_length": 64,
63
  "mask_feature_min_masks": 0,
64
  "mask_feature_prob": 0.15,
 
58
  "initializer_range": 0.02,
59
  "intermediate_size": 4096,
60
  "layer_norm_eps": 1e-05,
61
+ "layerdrop": 0.01,
62
  "mask_feature_length": 64,
63
  "mask_feature_min_masks": 0,
64
  "mask_feature_prob": 0.15,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:70f4a970f9f9c4f36b9d61bfda0396db6279464573cdefd4e6d769ffaf533ee7
3
  size 1262058993
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:540a30bdf0d799b51b9686bbace361acca12e4c2cba8d6ca437c79984797c17d
3
  size 1262058993
run.sh CHANGED
@@ -3,11 +3,11 @@ python ~/xls-r-uzbek-cv8/run_speech_recognition_ctc.py \
3
  --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
4
  --dataset_config_name="uz" \
5
  --output_dir="~/xls-r-uzbek-cv8" \
6
- --train_split_name="train[:30%]" \
7
  --eval_split_name="validation[50%:]" \
8
  --overwrite_output_dir \
9
- --num_train_epochs="50" \
10
- --per_device_train_batch_size="64" \
11
  --per_device_eval_batch_size="8" \
12
  --gradient_accumulation_steps="4" \
13
  --learning_rate="3e-5" \
@@ -16,11 +16,11 @@ python ~/xls-r-uzbek-cv8/run_speech_recognition_ctc.py \
16
  --evaluation_strategy="steps" \
17
  --text_column_name="sentence" \
18
  --eval_metrics wer cer \
19
- --save_steps="200" \
20
- --eval_steps="200" \
21
  --logging_steps="100" \
22
  --min_duration_in_seconds="0.2" \
23
- --layerdrop="0.05" \
24
  --activation_dropout="0.1" \
25
  --save_total_limit="3" \
26
  --freeze_feature_encoder \
 
3
  --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
4
  --dataset_config_name="uz" \
5
  --output_dir="~/xls-r-uzbek-cv8" \
6
+ --train_split_name="train[:50%]" \
7
  --eval_split_name="validation[50%:]" \
8
  --overwrite_output_dir \
9
+ --num_train_epochs="100" \
10
+ --per_device_train_batch_size="32" \
11
  --per_device_eval_batch_size="8" \
12
  --gradient_accumulation_steps="4" \
13
  --learning_rate="3e-5" \
 
16
  --evaluation_strategy="steps" \
17
  --text_column_name="sentence" \
18
  --eval_metrics wer cer \
19
+ --save_steps="500" \
20
+ --eval_steps="500" \
21
  --logging_steps="100" \
22
  --min_duration_in_seconds="0.2" \
23
+ --layerdrop="0.01" \
24
  --activation_dropout="0.1" \
25
  --save_total_limit="3" \
26
  --freeze_feature_encoder \
runs/Feb06_16-03-20_job-0a778896-a7e2-46e9-bcf5-016f91f242cf/events.out.tfevents.1644163569.job-0a778896-a7e2-46e9-bcf5-016f91f242cf.775427.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa8be02dec06a438b7a508baf3d039576eabab8d69a4dedad47bd5cace55328b
3
- size 6782
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4512c39d63475890a03f93668698098db6441e4f7f39bc64a504ed2e9d6fc4
3
+ size 6939
runs/Feb06_18-52-28_job-0a778896-a7e2-46e9-bcf5-016f91f242cf/1644173767.9556613/events.out.tfevents.1644173767.job-0a778896-a7e2-46e9-bcf5-016f91f242cf.841782.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fede87fcb3a28444a73f79e8f40572a8fcd3a443d2e7d1adea22516c5efad02f
3
+ size 4826
runs/Feb06_18-52-28_job-0a778896-a7e2-46e9-bcf5-016f91f242cf/events.out.tfevents.1644173767.job-0a778896-a7e2-46e9-bcf5-016f91f242cf.841782.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d30f9f6ede585f4c855be571cd4b2713c2384739356d788b2d07ceb4f8d6ff6
3
+ size 5896
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8038e4755ffed0897ea06919cec764a4e3039a214a6e022867aaec6e399aba3
3
  size 3055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07ae4abc8c48013db20dc56c875f2a1b7115ee1ed5e58dc64886f0b18aec42a
3
  size 3055