Training in progress, step 200

.ipynb_checkpoints/run-checkpoint.sh

@@ -4,16 +4,18 @@ python run_speech_recognition_ctc.py \
 	--dataset_config_name="ur" \
 	--output_dir="./" \
 	--overwrite_output_dir \
-	--max_steps="2000" \
-	--per_device_train_batch_size="16" \
+	--max_steps="3000" \
+	--gradient_accumulation_steps="2" \
+	--lr_scheduler_type="linear" \
+	--per_device_train_batch_size="64" \
 	--learning_rate="4e-4" \
-	--save_total_limit="10" \
+	--save_total_limit="5" \
 	--evaluation_strategy="steps" \
 	--text_column_name="sentence" \
 	--length_column_name="input_length" \
 	--chars_to_ignore ,\?\.\!\-\;\:\"\“\%\‘\”\�\ّ\ٔ\َِ,ً\
-	--save_steps="100" \
-	--layerdrop="0.0" \
+	--save_steps="200" \
+	--num_train_epochs="1000.0" \
 	--freeze_feature_encoder \
 	--gradient_checkpointing \
 	--fp16 \

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca81fa302fdac82c18aacc7d81dca2f92642f3e328ae0dc8551439ff57046bf6
+oid sha256:ab3ab630c986b23e9b31761e48867b23d33b4838a573ee4407440d45bf8bcdcc
 size 1262149169

run.sh

@@ -4,16 +4,18 @@ python run_speech_recognition_ctc.py \
 	--dataset_config_name="ur" \
 	--output_dir="./" \
 	--overwrite_output_dir \
-	--max_steps="2000" \
-	--per_device_train_batch_size="16" \
+	--max_steps="3000" \
+	--gradient_accumulation_steps="2" \
+	--lr_scheduler_type="linear" \
+	--per_device_train_batch_size="64" \
 	--learning_rate="4e-4" \
-	--save_total_limit="10" \
+	--save_total_limit="5" \
 	--evaluation_strategy="steps" \
 	--text_column_name="sentence" \
 	--length_column_name="input_length" \
 	--chars_to_ignore ,\?\.\!\-\;\:\"\“\%\‘\”\�\ّ\ٔ\َِ,ً\
-	--save_steps="100" \
-	--layerdrop="0.0" \
+	--save_steps="200" \
+	--num_train_epochs="1000.0" \
 	--freeze_feature_encoder \
 	--gradient_checkpointing \
 	--fp16 \

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 sha256:5d235b3aedc73da590fbd6bd2aee14f73a79349ea575c7ae01be2c9d6e21778e
+oid sha256:ff8e9fbda78cdc66136dc476d2cef558c305ffcb23a4b3428f386f79718fa61f
 size 2991