Training in progress, step 13500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./checkpoint-10500",
+  "_name_or_path": "./checkpoint-13000",
   "activation_dropout": 0.0,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:327c9db2b5e6c9aef1248be48a750901c4dccfeb294915d43c6c4708adb224c7
+oid sha256:d8494513a916de6316ce29fe8066c179abd7ba4861406897eb0bb23188ff0297
 size 3850522801

run.sh

@@ -1,15 +1,16 @@
 python run_speech_recognition_ctc.py \
 	--dataset_name="common_voice" \
-	--model_name_or_path="./checkpoint-10500" \
+	--model_name_or_path="./checkpoint-13000" \
 	--dataset_config_name="tr" \
 	--output_dir="./" \
 	--overwrite_output_dir \
-	--num_train_epochs="120" \
+	--num_train_epochs="200" \
 	--per_device_train_batch_size="32" \
 	--gradient_accumulation_steps="1" \
 	--learning_rate="2e-4" \
-	--adam_beta1="0.999" \
-	--adam_beta2="0.9999" \
+	--adam_beta1="0.99999" \
+	--adam_beta2="0.999999" \
+	--lr_scheduler_type="linear" \
 	--warmup_steps="0" \
 	--evaluation_strategy="steps" \
 	--text_column_name="sentence" \

run02.sh

@@ -0,0 +1,33 @@
+python run_speech_recognition_ctc.py \
+	--dataset_name="common_voice" \
+	--model_name_or_path="./checkpoint-10500" \
+	--dataset_config_name="tr" \
+	--output_dir="./" \
+	--overwrite_output_dir \
+	--num_train_epochs="120" \
+	--per_device_train_batch_size="32" \
+	--gradient_accumulation_steps="1" \
+	--learning_rate="2e-4" \
+	--adam_beta1="0.999" \
+	--adam_beta2="0.9999" \
+	--warmup_steps="0" \
+	--evaluation_strategy="steps" \
+	--text_column_name="sentence" \
+	--save_steps="500" \
+	--eval_steps="500" \
+	--logging_steps="1" \
+	--layerdrop="0.0" \
+	--eval_metrics wer cer \
+	--save_total_limit="1" \
+	--mask_time_prob="0.3" \
+	--mask_time_length="10" \
+	--mask_feature_prob="0.1" \
+	--mask_feature_length="64" \
+	--chars_to_ignore , ? . ! - \; \: \" “ % ‘ ” � \
+	--fp16 \
+	--group_by_length \
+	--push_to_hub \
+	--do_train --do_eval \
+	--gradient_checkpointing \
+	--report_to tensorboard \
+	--use_auth_token

runs/Feb02_12-45-07_job-98a7eb1d-c6a6-4e4b-936b-3898557b5e73/1643806051.3083758/events.out.tfevents.1643806051.job-98a7eb1d-c6a6-4e4b-936b-3898557b5e73.638515.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a144812eaa6678d243a37fac170e48ebd620d7118712f44fb4871bcf1d47aabf
+size 4747

runs/Feb02_12-45-07_job-98a7eb1d-c6a6-4e4b-936b-3898557b5e73/events.out.tfevents.1643806051.job-98a7eb1d-c6a6-4e4b-936b-3898557b5e73.638515.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:679f1272c542a0602c14cbf1defbb0d71ee5138c8f52cd088807becb974f3071
+size 83526

special_tokens_map.json

@@ -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}]}
+{"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}]}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ba0581b197496a36b1ca40ab46e8cdb3ee1716ff0ee4e432891cbfdc210d0c
+oid sha256:aa75907883469fd5c7d8aec7402766a5d85324c2315ffc7be87c9fc5cf96d12a
 size 2991