learning_rate: 0.0002
train_batch_size: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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: 1
training_steps: 1000

Training Loss	Epoch	Step	Validation Loss
1.8756	0.0665	25	0.8069
0.5969	0.1331	50	0.6492
0.7373	0.1996	75	0.5183
0.4293	0.2661	100	0.5101
0.611	0.3327	125	0.4577
0.3935	0.3992	150	0.4664
0.5535	0.4657	175	0.4308
0.3765	0.5323	200	0.4349
0.487	0.5988	225	0.4017
0.3464	0.6653	250	0.4049
0.4799	0.7319	275	0.3849
0.3313	0.7984	300	0.3953
0.4697	0.8649	325	0.3686
0.354	0.9315	350	0.3699
0.3705	0.9980	375	0.3521
0.3968	1.0639	400	0.3441
0.2887	1.1304	425	0.3566
0.3884	1.1969	450	0.3338
0.2879	1.2635	475	0.3366
0.3961	1.3300	500	0.3237
0.3062	1.3965	525	0.3233
0.3572	1.4631	550	0.3145
0.2787	1.5296	575	0.3168
0.3594	1.5961	600	0.3096
0.2788	1.6627	625	0.3116
0.3406	1.7292	650	0.3015
0.2848	1.7957	675	0.3008
0.3488	1.8623	700	0.2946
0.2774	1.9288	725	0.2960
0.3092	1.9953	750	0.2888
0.3158	2.0612	775	0.2855
0.2678	2.1277	800	0.2856
0.2927	2.1943	825	0.2854
0.276	2.2608	850	0.2819
0.3042	2.3273	875	0.2790
0.2351	2.3939	900	0.2770
0.305	2.4604	925	0.2759
0.2599	2.5269	950	0.2753
0.3014	2.5935	975	0.2747
0.2236	2.6600	1000	0.2741

predator3769/peft-dialogue-summary-training-1767960897

peft-dialogue-summary-training-1767960897