Training in progress, step 500

.ipynb_checkpoints/run-checkpoint.sh

@@ -7,8 +7,8 @@ python run_speech_recognition_ctc.py \
         --num_train_epochs="100" \
         --per_device_train_batch_size="16" \
         --per_device_eval_batch_size="8" \
-        --learning_rate="3.3e-4" \
-        --warmup_steps="1100" \
+        --learning_rate="3e-4" \
+        --warmup_steps="1500" \
         --length_column_name="input_length" \
         --evaluation_strategy="steps" \
         --text_column_name="sentence" \
@@ -23,7 +23,7 @@ python run_speech_recognition_ctc.py \
         --mask_time_prob="0.05" \
         --mask_time_length="10" \
         --mask_feature_prob="0.01" \
-        --mask_feature_length="64" \
+        --mask_feature_length="10" \
         --chars_to_ignore , ? . ! \- \; \: \" “ % ‘ ” � — ’ … – « » „ \` _ \
         --gradient_checkpointing \
         --use_auth_token \

config.json

@@ -59,7 +59,7 @@
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.0,
-  "mask_feature_length": 64,
+  "mask_feature_length": 10,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.01,
   "mask_time_length": 10,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f77ebef20da3f82867d603eaae210bcf34ee0a8e499d7da8455350f3b1b687b
+oid sha256:e81ca840485f8fd7f340e8e68fd7e5b1e0266e9261e27eaeeb51cb5f2ec38331
 size 1262194289

run.sh

@@ -23,7 +23,7 @@ python run_speech_recognition_ctc.py \
         --mask_time_prob="0.05" \
         --mask_time_length="10" \
         --mask_feature_prob="0.01" \
-        --mask_feature_length="64" \
+        --mask_feature_length="10" \
         --chars_to_ignore , ? . ! \- \; \: \" “ % ‘ ” � — ’ … – « » „ \` _ \
         --gradient_checkpointing \
         --use_auth_token \

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 sha256:6088759a29d83fbb29e58135193b16ec759fe8fe9e6fa848ab8014dbe5baa933
+oid sha256:bcb5b35057bb1070af6c79d3fb64bcd25c758fdb8d4b1eeffde5133937c34b7c
 size 2991