lucio commited on
Commit
98fed8a
1 Parent(s): 3685205

Training in progress, step 500

Browse files
.ipynb_checkpoints/run-checkpoint.sh CHANGED
@@ -2,10 +2,12 @@ python xls-r-uyghur-cv8/run_speech_recognition_ctc.py \
2
  --dataset_name="mozilla-foundation/common_voice_8_0" \
3
  --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
4
  --dataset_config_name="ug" \
 
 
5
  --output_dir="./xls-r-uyghur-cv8" \
6
  --overwrite_output_dir \
7
  --num_train_epochs="100" \
8
- --per_device_train_batch_size="8" \
9
  --per_device_eval_batch_size="8" \
10
  --gradient_accumulation_steps="4" \
11
  --learning_rate="1e-4" \
@@ -18,7 +20,7 @@ python xls-r-uyghur-cv8/run_speech_recognition_ctc.py \
18
  --save_steps="500" \
19
  --eval_steps="500" \
20
  --logging_steps="100" \
21
- --min_duration_in_seconds="0.5" \
22
  --layerdrop="0.0" \
23
  --activation_dropout="0.1" \
24
  --save_total_limit="3" \
 
2
  --dataset_name="mozilla-foundation/common_voice_8_0" \
3
  --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
4
  --dataset_config_name="ug" \
5
+ --train_split_name="train+validation" \
6
+ --eval_split_name="test" \
7
  --output_dir="./xls-r-uyghur-cv8" \
8
  --overwrite_output_dir \
9
  --num_train_epochs="100" \
10
+ --per_device_train_batch_size="16" \
11
  --per_device_eval_batch_size="8" \
12
  --gradient_accumulation_steps="4" \
13
  --learning_rate="1e-4" \
 
20
  --save_steps="500" \
21
  --eval_steps="500" \
22
  --logging_steps="100" \
23
+ --min_duration_in_seconds="0.2" \
24
  --layerdrop="0.0" \
25
  --activation_dropout="0.1" \
26
  --save_total_limit="3" \
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db0e471c34569c02c147a064f69a5a4ea5a610cdf294ff0d6c62761469d546e1
3
  size 1262079473
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8337059e36c0188c01346e7a922b15dd72cd05615fd8219f336c3132c0cb79c
3
  size 1262079473
run.sh CHANGED
@@ -2,10 +2,12 @@ python xls-r-uyghur-cv8/run_speech_recognition_ctc.py \
2
  --dataset_name="mozilla-foundation/common_voice_8_0" \
3
  --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
4
  --dataset_config_name="ug" \
 
 
5
  --output_dir="./xls-r-uyghur-cv8" \
6
  --overwrite_output_dir \
7
  --num_train_epochs="100" \
8
- --per_device_train_batch_size="8" \
9
  --per_device_eval_batch_size="8" \
10
  --gradient_accumulation_steps="4" \
11
  --learning_rate="1e-4" \
@@ -18,7 +20,7 @@ python xls-r-uyghur-cv8/run_speech_recognition_ctc.py \
18
  --save_steps="500" \
19
  --eval_steps="500" \
20
  --logging_steps="100" \
21
- --min_duration_in_seconds="0.5" \
22
  --layerdrop="0.0" \
23
  --activation_dropout="0.1" \
24
  --save_total_limit="3" \
 
2
  --dataset_name="mozilla-foundation/common_voice_8_0" \
3
  --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
4
  --dataset_config_name="ug" \
5
+ --train_split_name="train+validation" \
6
+ --eval_split_name="test" \
7
  --output_dir="./xls-r-uyghur-cv8" \
8
  --overwrite_output_dir \
9
  --num_train_epochs="100" \
10
+ --per_device_train_batch_size="16" \
11
  --per_device_eval_batch_size="8" \
12
  --gradient_accumulation_steps="4" \
13
  --learning_rate="1e-4" \
 
20
  --save_steps="500" \
21
  --eval_steps="500" \
22
  --logging_steps="100" \
23
+ --min_duration_in_seconds="0.2" \
24
  --layerdrop="0.0" \
25
  --activation_dropout="0.1" \
26
  --save_total_limit="3" \
runs/Feb03_17-57-48_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/1643911172.6488388/events.out.tfevents.1643911172.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.861419.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e232c37a49cc4d14da1202f55c1a5f1db21f9badc20be80a27deda0d28c68336
3
+ size 4802
runs/Feb03_17-57-48_job-699ba53c-fea9-4eb2-81af-a97f440eaa45/events.out.tfevents.1643911172.job-699ba53c-fea9-4eb2-81af-a97f440eaa45.861419.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1081188443b186492cc0262b65512e09c46f044695b76698dfeeea8ce9c9b0c1
3
+ size 5857
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}]}
 
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}]}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0256db558b20d490bb5b401bebdb5dcf15a383e11f8ce6baad32f012d07bfa3c
3
  size 3055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c98159182d3687ae1dcd2b4a1e004306270d526e84b15b24da056e0aa5b420d
3
  size 3055