learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 8
total_train_batch_size: 8
total_eval_batch_size: 8
optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 2.0

Training Loss	Epoch	Step	Validation Loss
0.2938	0.1408	10	0.3067
0.2167	0.2817	20	0.2746
0.2339	0.4225	30	0.2653
0.3247	0.5634	40	0.2608
0.2055	0.7042	50	0.2564
0.2555	0.8451	60	0.2536
0.2486	0.9859	70	0.2510
0.254	1.1268	80	0.2533
0.188	1.2676	90	0.2525
0.2137	1.4085	100	0.2502
0.2181	1.5493	110	0.2500
0.2752	1.6901	120	0.2501
0.1925	1.8310	130	0.2497
0.1969	1.9718	140	0.2495

merty/7b-claude-32k-20250419_153234-2ep

7b-claude-32k-20250419_153234-2ep