learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss
3.3021	0.0568	500	2.9186
3.372	0.1136	1000	2.9741
3.2939	0.1703	1500	2.9741
3.3757	0.2271	2000	2.9197
3.2192	0.2839	2500	2.9396
3.2966	0.3407	3000	2.9476
3.2634	0.3975	3500	2.8903
3.1503	0.4542	4000	2.8886
3.2281	0.5110	4500	nan
3.2165	0.5678	5000	nan
3.1273	0.6246	5500	2.8244
3.1743	0.6814	6000	2.8228
3.054	0.7381	6500	nan
3.0531	0.7949	7000	2.8213
3.0738	0.8517	7500	2.7571
3.0572	0.9085	8000	2.7764
3.0247	0.9653	8500	2.8006
2.9202	1.0220	9000	2.7288
2.8448	1.0788	9500	2.7300
2.866	1.1356	10000	2.6930
2.7476	1.1924	10500	2.6738
2.7801	1.2491	11000	2.6572
2.8685	1.3059	11500	2.6302
2.7265	1.3627	12000	2.6264
2.8173	1.4195	12500	2.6205
2.7561	1.4763	13000	2.6139
2.717	1.5330	13500	2.5742
2.5455	1.5898	14000	2.5571
2.7207	1.6466	14500	2.5352
2.7243	1.7034	15000	2.5022
2.5593	1.7602	15500	2.4617
2.5833	1.8169	16000	2.4913
2.5604	1.8737	16500	nan
2.6395	1.9305	17000	2.4648
2.5545	1.9873	17500	2.4603
2.5088	2.0441	18000	2.4281
2.4837	2.1008	18500	2.4210
2.3461	2.1576	19000	2.4174
2.3152	2.2144	19500	2.3661
2.4186	2.2712	20000	2.3611
2.416	2.3280	20500	2.3640
2.3894	2.3847	21000	2.3449
2.3077	2.4415	21500	2.3038
2.3199	2.4983	22000	2.3256
2.2644	2.5551	22500	2.2911
2.2888	2.6119	23000	2.2873
2.3648	2.6686	23500	2.2728
2.3545	2.7254	24000	2.2645
2.2642	2.7822	24500	2.2473
2.2299	2.8390	25000	nan
2.2673	2.8958	25500	2.2445
2.2081	2.9525	26000	2.2321

martijn75/berel_finetuned_on_shuffled_HB_3_epochs_general

berel_finetuned_on_shuffled_HB_3_epochs_general