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
0.2358	0.1584	200	0.2502
0.2186	0.3169	400	0.2291
0.2148	0.4753	600	0.2118
0.1912	0.6338	800	0.2052
0.1944	0.7922	1000	0.2026
0.2061	0.9507	1200	0.1971
0.1589	1.1091	1400	0.1950
0.1771	1.2676	1600	0.1934
0.1592	1.4260	1800	0.1897
0.1418	1.5845	2000	0.1891
0.1494	1.7429	2200	0.1862
0.1389	1.9014	2400	0.1843
0.1005	2.0600	2600	0.1877
0.0992	2.2187	2800	0.1912
0.0977	2.3771	3000	0.1917
0.1093	2.5356	3200	0.1910
0.1042	2.6940	3400	0.1899
0.1035	2.8524	3600	0.1901

marcuschill1823/incar-nlu-qwen1.5b-v31

incar-nlu-qwen1.5b-v31