Training in progress, step 400

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b178aa0b6684d82db6f349cab5c9566073e483893ad43b642a1c3cced25ee119
+oid sha256:545d2582b3602bce6ded5dafdfa979c06ac65a0c1ee2cef69c3607b8db1a98ce
 size 1262165553

run.sh

@@ -4,12 +4,12 @@ python run_speech_recognition_ctc.py \
 --dataset_config_name="ur" \
 --output_dir="./" \
 --overwrite_output_dir \
---num_train_epochs="500" \
+--num_train_epochs="200" \
 --per_device_train_batch_size="8" \
 --per_device_eval_batch_size="8" \
 --gradient_accumulation_steps="2" \
 --learning_rate="7.5e-5" \
---warmup_steps="1000" \
+--warmup_steps="100" \
 --length_column_name="input_length" \
 --evaluation_strategy="steps" \
 --text_column_name="sentence" \

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}]}
+{"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}]}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c79f076369387aa87f93f189c1c8a52b39db467cd7200d2b78abce1dc59bcdd
+oid sha256:f059f8ce3ad95651e9becb81ea331644ce6b3ab545b66ec5027889b6f8712221
 size 2991