c_bl_arafix_slurm.out

This job can be monitored from: https://job.c3se.chalmers.se/alvis/4059592
Using c_bl_comb91k_10_arafix config...
Loading new model openai/whisper-base (in 8bit for PEFT)...
trainable params: 786,432 || all params: 73,380,352 || trainable%: 1.0717
Loading ['ara'] (limit: [1000]) from asc-train.
Resampling audio...
Samples asc train: 1000
Loading ['ja', 'pl', 'mt', 'hu', 'fi', 'el', 'ta'] (limit: [1000, 1000, 1000, 1000, 1000, 1000, 1000]) from multipa-train.
Resampling audio...
Samples multipa train: 7000
Loading ['cmn'] (limit: [1000]) from thchs-train.
Resampling audio...
Samples thchs train: 1000
Creating input values and labels...
Loading ['ara'] (limit: [50]) from asc-dev.
Resampling audio...
Samples asc dev: 50
Loading ['ja', 'pl', 'mt', 'hu', 'fi', 'el', 'ta'] (limit: [50, 50, 50, 50, 50, 50, 50]) from multipa-dev.
Resampling audio...
Samples multipa validation: 350
Loading ['cmn'] (limit: [50]) from thchs-dev.
Resampling audio...
Samples thchs dev: 50
Creating input values and labels...
--------------------------------------------------------------------------------
Start fine-tuning...
{'loss': 4.8407, 'grad_norm': 26.586772918701172, 'learning_rate': 1e-05, 'epoch': 0.0}
{'loss': 1.5428, 'grad_norm': 0.9762190580368042, 'learning_rate': 0.0008610687022900763, 'epoch': 1.1}
{'eval_loss': 1.2981462478637695, 'eval_runtime': 49.4189, 'eval_samples_per_second': 9.086, 'eval_steps_per_second': 1.153, 'epoch': 1.1}
{'loss': 0.7498, 'grad_norm': 1.0431804656982422, 'learning_rate': 0.0006458015267175574, 'epoch': 3.1}
{'eval_loss': 0.8457677960395813, 'eval_runtime': 49.1336, 'eval_samples_per_second': 9.138, 'eval_steps_per_second': 1.16, 'epoch': 3.1}
{'loss': 0.5968, 'grad_norm': 0.7923967242240906, 'learning_rate': 0.00043053435114503817, 'epoch': 5.1}
{'eval_loss': 0.759925901889801, 'eval_runtime': 49.3582, 'eval_samples_per_second': 9.097, 'eval_steps_per_second': 1.155, 'epoch': 5.1}
{'loss': 0.5156, 'grad_norm': 0.7825987935066223, 'learning_rate': 0.00021526717557251909, 'epoch': 7.1}
{'eval_loss': 0.7213243246078491, 'eval_runtime': 50.5179, 'eval_samples_per_second': 8.888, 'eval_steps_per_second': 1.128, 'epoch': 7.1}
{'loss': 0.4603, 'grad_norm': 1.3247737884521484, 'learning_rate': 0.0, 'epoch': 9.1}
{'eval_loss': 0.7064764499664307, 'eval_runtime': 49.4904, 'eval_samples_per_second': 9.072, 'eval_steps_per_second': 1.152, 'epoch': 9.1}
{'train_runtime': 10168.0361, 'train_samples_per_second': 8.875, 'train_steps_per_second': 0.139, 'train_loss': 0.7754128374951951, 'epoch': 9.1}
----------------------------------- COMPLETE 10168.212074518204 -----------------------------------