learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 50
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss
0.3153	0.2667	100	0.3164
0.3042	0.5333	200	0.3090
0.3044	0.8	300	0.3044
0.2739	1.0667	400	0.3051
0.2482	1.3333	500	0.3048
0.2443	1.6	600	0.3050
0.2406	1.8667	700	0.3051
0.1865	2.1333	800	0.3300
0.1773	2.4	900	0.3310
0.177	2.6667	1000	0.3320
0.1839	2.9333	1100	0.3318

EshAhm/Mistral-7B-v0.1-LoRA-MathReasoning1

Mistral-7B-v0.1-LoRA-MathReasoning1