Synced cluster code

3 files changed, 12 insertions, 12 deletions

diff --git a/config.cluster.yaml b/config.cluster.yaml
index a3def0e..7af0aca 100644
--- a/config.cluster.yaml
+++ b/config.cluster.yaml
@@ -4,18 +4,18 @@ model:
   rnn_dim: 512
   n_feats: 128 # number of mel features
   stride: 2
-  dropout: 0.25 # recommended to be around 0.4-0.6 for smaller datasets, 0.1 for really large datasets
+  dropout: 0.2 # recommended to be around 0.4-0.6 for smaller datasets, 0.1 for really large datasets
 
 training:
   learning_rate: 0.0005
-  batch_size: 64 # recommended to maximum number that fits on the GPU (batch size of 32 fits on a 12GB GPU)
+  batch_size: 400 # recommended to maximum number that fits on the GPU (batch size of 32 fits on a 12GB GPU)
   epochs: 150 
   eval_every_n: 5 # evaluate every n epochs
-  num_workers: 8 # number of workers for dataloader
+  num_workers: 12 # number of workers for dataloader
   device: "cuda" # device to run inference on if gpu is available, else "cpu" will be set automatically
 
 dataset:
-  download: True
+  download: False
   dataset_root_path: "/mnt/lustre/mladm/mfa252/data" # files will be downloaded into this dir
   language_name: "mls_german_opus"
   limited_supervision: False # set to True if you want to use limited supervision
@@ -26,9 +26,9 @@ tokenizer:
   tokenizer_path: "data/tokenizers/char_tokenizer_german.json"
 
 checkpoints:
-  model_load_path: "data/runs/epoch31" # path to load model from
+  model_load_path: "data/runs/epoch50" # path to load model from
   model_save_path: "data/runs/epoch" # path to save model to
 
 inference:
   model_load_path: ~ # path to load model from
-  device: "cuda" # device to run inference on if gpu is available, else "cpu" will be set automatically
\ No newline at end of file
+  device: "cuda" # device to run inference on if gpu is available, else "cpu" will be set automatically
diff --git a/hpc.sh b/hpc.sh
index ba0c5eb..718b6d2 100755
--- a/hpc.sh
+++ b/hpc.sh
@@ -2,15 +2,15 @@
 
 #SBATCH --job-name=swr-teamprojekt
 #SBATCH --partition=a100
-#SBATCH --time=00:30:00
+#SBATCH --time=24:00:00
 
 ### Note: --gres=gpu:x should equal to ntasks-per-node
 #SBATCH --nodes=1
 #SBATCH --ntasks-per-node=1
-#SBATCH --gres=gpu:a100:1
-#SBATCH --cpus-per-task=8
-#SBATCH --mem=64gb
-#SBATCH --chdir=/mnt/lustre/mladm/mfa252/SWR2-cool-projekt-main/
+#SBATCH --gres=gpu:a100:4
+#SBATCH --cpus-per-task=16
+#SBATCH --mem=32gb
+#SBATCH --chdir=/mnt/lustre/mladm/mfa252/ref/
 #SBATCH --output=/mnt/lustre/mladm/mfa252/%x-%j.out
 
 source venv/bin/activate
diff --git a/hpc_train.sh b/hpc_train.sh
index 2280087..9b21a53 100755
--- a/hpc_train.sh
+++ b/hpc_train.sh
@@ -1,3 +1,3 @@
 #!/bin/sh
 
-yes no | python -m swr2_asr.train --config_path config.cluster.yaml  
+python -m swr2_asr.train --config_path config.cluster.yaml