learning_rate: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 16
total_train_batch_size: 64
total_eval_batch_size: 4
optimizer: Use 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: 0.1
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss
0.8425	0.1290	32	0.7648
0.7261	0.2580	64	0.6592
0.6559	0.3870	96	0.5983
0.6316	0.5160	128	0.5707
0.6236	0.6450	160	0.5557
0.6061	0.7740	192	0.5463
0.593	0.9030	224	0.5396
0.5771	1.0282	256	0.5375
0.5953	1.1572	288	0.5316
0.5735	1.2862	320	0.5289
0.5752	1.4152	352	0.5264
0.5903	1.5442	384	0.5242
0.5662	1.6732	416	0.5225
0.5656	1.8022	448	0.5209
0.574	1.9312	480	0.5199
0.5692	2.0564	512	0.5193
0.5656	2.1854	544	0.5183
0.5654	2.3144	576	0.5177
0.5664	2.4434	608	0.5173
0.5714	2.5724	640	0.5170
0.5656	2.7014	672	0.5168
0.5681	2.8304	704	0.5168
0.5541	2.9594	736	0.5167

effcot/Bespoke_17k_lora_checkpoint-225

Bespoke_17k_lora