Training in progress, step 500

.ipynb_checkpoints/eval_results-checkpoint.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 20.0,
+    "eval_loss": 1.3742073774337769,
+    "eval_runtime": 417.2357,
+    "eval_samples": 10388,
+    "eval_samples_per_second": 24.897,
+    "eval_steps_per_second": 3.113,
+    "eval_wer": 0.9387498381338217
+}

.ipynb_checkpoints/run-checkpoint.sh

@@ -3,12 +3,13 @@ python run_speech_recognition_ctc_bnb.py \
 	--model_name_or_path="facebook/wav2vec2-xls-r-1b" \
 	--dataset_config_name="ar" \
 	--output_dir="./" \
-	--num_train_epochs="20" \
-	--per_device_train_batch_size="32" \
+	--num_train_epochs="10" \
+    --overwrite_output_dir \
+	--per_device_train_batch_size="16" \
 	--per_device_eval_batch_size="8" \
-	--gradient_accumulation_steps="2" \
+	--gradient_accumulation_steps="4" \
 	--learning_rate="6.5e-5" \
-	--warmup_steps="500" \
+	--warmup_steps="2000" \
 	--length_column_name="input_length" \
 	--evaluation_strategy="steps" \
 	--text_column_name="sentence" \

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76f2e1b8cdc880d5260ac915d590f3d31a09b4c1ce56ed0fabed9db38933d0d8
+oid sha256:3fa9786fb327713b6ab5e28e856abc149b51204e04dcab0a7fff6962cb610fd6
 size 3850799473

run.sh

@@ -3,12 +3,13 @@ python run_speech_recognition_ctc_bnb.py \
 	--model_name_or_path="facebook/wav2vec2-xls-r-1b" \
 	--dataset_config_name="ar" \
 	--output_dir="./" \
-	--num_train_epochs="20" \
-	--per_device_train_batch_size="32" \
+	--num_train_epochs="10" \
+    --overwrite_output_dir \
+	--per_device_train_batch_size="16" \
 	--per_device_eval_batch_size="8" \
-	--gradient_accumulation_steps="2" \
+	--gradient_accumulation_steps="4" \
 	--learning_rate="6.5e-5" \
-	--warmup_steps="500" \
+	--warmup_steps="2000" \
 	--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}, {"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}, {"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}, {"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:c1e03ec2a5f851e6b65ac7d116c597fbb9739426525fe4b26c6e931c0c329292
+oid sha256:6570138dc794c741bb82b5ade234724de8ea9ddd378ee3cfd1ab1c36ee79d131
 size 2991