learning_rate: 0.0002
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
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: 100
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss
4.5433	0.1333	100	4.4747
4.4162	0.2667	200	4.4774
4.2759	0.4	300	4.4755
4.4021	0.5333	400	4.4764
4.3925	0.6667	500	4.4775
4.6016	0.8	600	4.5976
4.2527	0.9333	700	4.5484
4.5823	1.0667	800	4.5037
4.5826	1.2	900	4.5032
4.0654	1.3333	1000	4.5073
4.5386	1.4667	1100	4.4961
4.1046	1.6	1200	4.4957
4.1705	1.7333	1300	4.4943
4.4922	1.8667	1400	4.4918
4.7333	2.0	1500	4.4901
3.997	2.1333	1600	4.4889
4.5407	2.2667	1700	4.4880
3.8457	2.4	1800	4.4877
4.6653	2.5333	1900	4.4873
4.4524	2.6667	2000	4.4865
4.3138	2.8	2100	4.4870
4.3203	2.9333	2200	4.4865

EshAhm/phi-2-LoRa-Python

phi-2-LoRa-Python