Training in progress, step 250

config.json

@@ -58,7 +58,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
+  "layerdrop": 0.1,
   "mask_feature_length": 64,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.25,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab8442f42242eba6dceb2c933b909df204091bb41fcf99f2d109e6fce18f88f0
-size 1262063089
+oid sha256:bf860c4269abebda916456f37102b6c3e8e56e5f696e8c8ab73f439cba34b915
+size 569727136

run.sh

@@ -2,6 +2,7 @@ python run_speech_recognition_ctc.py \
         --dataset_name="NbAiLab/NPSC" \
         --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
         --dataset_config_name="16K_mp3" \
+        --data_cache_dir="/mnt/lv_ai_1_ficino/rolvb/cache" \
         --output_dir="./" \
         --overwrite_output_dir \
         --num_train_epochs="20" \

run_ex1.sh

@@ -2,6 +2,7 @@ python run_speech_recognition_ctc.py \
         --dataset_name="NbAiLab/NPSC" \
         --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
         --dataset_config_name="16K_mp3" \
+        --data_cache_dir="/mnt/lv_ai_1_ficino/rolvb/cache" \
         --output_dir="./" \
         --overwrite_output_dir \
         --num_train_epochs="20" \

run_ex3.sh

@@ -2,7 +2,8 @@ python run_speech_recognition_ctc.py \
         --dataset_name="NbAiLab/NPSC" \
         --model_name_or_path="facebook/wav2vec2-xls-r-300m" \
         --dataset_config_name="16K_mp3" \
-        --output_dir="./ex3" \
+        --data_cache_dir="/mnt/lv_ai_1_ficino/rolvb/cache" \
+        --output_dir="./" \
         --overwrite_output_dir \
         --num_train_epochs="20" \
         --per_device_train_batch_size="16" \

run_speech_recognition_ctc.py

@@ -237,6 +237,10 @@ class DataTrainingArguments:
             " this is only relevant if the model classifies the"
             " input audio to a sequence of phoneme sequences."
         },
+    ),
+    data_cache_dir: Optional[str] = field(
+        default=None,
+        metadata={"help": "Cache directory for dataset."}
     )
 
 
@@ -415,7 +419,7 @@ def main():
         if "<" in batch["text"]:
             raise ValueError(batch["text"])
         return batch
-
+    assert data_args.data_cache_dir.startswith("/mnt")
     # 1. First, let's load the dataset
     raw_datasets = DatasetDict()
 
@@ -425,6 +429,7 @@ def main():
             data_args.dataset_config_name,
             split=data_args.train_split_name,
             use_auth_token=data_args.use_auth_token,
+            cache_dir=data_args.data_cache_dir
         )
         raw_datasets["train"] = raw_datasets["train"].filter(filter_dataset)
         raw_datasets["train"] = raw_datasets["train"].map(map_dataset)
@@ -452,6 +457,7 @@ def main():
             data_args.dataset_config_name,
             split=data_args.eval_split_name,
             use_auth_token=data_args.use_auth_token,
+            cache_dir=data_args.data_cache_dir
         )
         raw_datasets["eval"] = raw_datasets["eval"].filter(filter_dataset)
         raw_datasets["eval"] = raw_datasets["eval"].map(map_dataset)

runs/Jan31_11-10-54_ficino/events.out.tfevents.1643623929.ficino.269307.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b0758fcf5543564a25c3b99bc7543d4f10e275ff91404551d7c5ea2b36e4cf
-size 12361
+oid sha256:5e158a3b9ebaaebddc919c8d8108e90dd1edddd3c91466e5aafde4abe9054037
+size 13146

runs/Jan31_15-12-29_ficino/1643638974.374903/events.out.tfevents.1643638974.ficino.274851.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90da1e9403bc415312a147da7992baa0d63d67df4e5f38ccefe70208b63de90f
+size 4719

runs/Jan31_15-12-29_ficino/events.out.tfevents.1643638974.ficino.274851.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e4f2ca8390f2c1035d8a2d0991da63d85ca0b8c13ed1994b0f914c2346cfddb
+size 5745

runs/Jan31_15-14-01_ficino/1643638993.9934366/events.out.tfevents.1643638993.ficino.275087.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f0849ee2681cec8dc1acc83de8ba27458f7b861b504892463652e8c54b3260
+size 4719

runs/Jan31_15-14-01_ficino/events.out.tfevents.1643638993.ficino.275087.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002e37168a9da5b8b0a35fef88b252c405be26248cae2b71357cea32785d8df0
+size 5743

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}]}
+{"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}]}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc6cbb10c3c21f7e4c00ecbefa42f06369abcd99e39d4879ec6f4e6804ee755e
+oid sha256:8a47239e05c536ae72f6dfb5b0171a4189827226ec67e1a549e250529ffefac8
 size 2991