learning_rate: 0.0001
train_batch_size: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 2
gradient_accumulation_steps: 4
total_train_batch_size: 32
total_eval_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.03
num_epochs: 3
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
0.2195	0.1795	200	0.2569
0.2411	0.3590	400	0.2332
0.2527	0.5385	600	0.2226
0.1987	0.7180	800	0.2163
0.1872	0.8975	1000	0.2107
0.1624	1.0770	1200	0.2117
0.1873	1.2565	1400	0.2109
0.1585	1.4359	1600	0.2051
0.1597	1.6154	1800	0.2044
0.1674	1.7949	2000	0.1997
0.169	1.9744	2200	0.1962
0.1053	2.1539	2400	0.2097
0.1151	2.3334	2600	0.2081
0.1071	2.5129	2800	0.2073
0.1077	2.6924	3000	0.2072
0.1113	2.8719	3200	0.2069

marcuschill1823/incar-nlu-qwen1.5b-v3

incar-nlu-qwen1.5b-v3