Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 1e-07
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 100
training_steps: 1000

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.5498	0.2667	50	0.4912	0.1121	-0.3443	1.0	0.4564	-40.5745	-22.3430	-1.0192	-0.9446
0.0327	0.5333	100	0.0171	1.0812	-3.0693	1.0	4.1505	-49.6580	-19.1129	-1.0134	-0.9308
0.0003	0.8	150	0.0003	1.5742	-6.5919	1.0	8.1661	-61.3998	-17.4696	-1.0139	-0.9245
0.0002	1.0667	200	0.0001	1.6592	-7.2290	1.0	8.8882	-63.5234	-17.1860	-1.0140	-0.9239
0.0001	1.3333	250	0.0001	1.6951	-7.6290	1.0	9.3240	-64.8568	-17.0666	-1.0158	-0.9262
0.0001	1.6	300	0.0001	1.7233	-7.9318	1.0	9.6551	-65.8661	-16.9725	-1.0138	-0.9236
0.0001	1.8667	350	0.0001	1.7438	-8.1604	1.0	9.9041	-66.6280	-16.9042	-1.0149	-0.9250
0.0	2.1333	400	0.0000	1.7606	-8.3497	1.0	10.1103	-67.2590	-16.8480	-1.0148	-0.9248
0.0	2.4	450	0.0000	1.7718	-8.5043	1.0	10.2761	-67.7745	-16.8110	-1.0156	-0.9253
0.0	2.6667	500	0.0000	1.7869	-8.6044	1.0	10.3914	-68.1083	-16.7604	-1.0155	-0.9255
0.0	2.9333	550	0.0000	1.7898	-8.6872	1.0	10.4771	-68.3843	-16.7507	-1.0156	-0.9257
0.0	3.2	600	0.0000	1.7933	-8.7495	1.0	10.5428	-68.5918	-16.7392	-1.0156	-0.9255
0.0	3.4667	650	0.0000	1.7958	-8.7981	1.0	10.5938	-68.7538	-16.7309	-1.0161	-0.9257
0.0	3.7333	700	0.0000	1.7940	-8.7816	1.0	10.5756	-68.6987	-16.7368	-1.0159	-0.9258
0.0	4.0	750	0.0000	1.7960	-8.7901	1.0	10.5861	-68.7271	-16.7300	-1.0154	-0.9252
0.0	4.2667	800	0.0000	1.7949	-8.7990	1.0	10.5939	-68.7570	-16.7339	-1.0142	-0.9238
0.0	4.5333	850	0.0000	1.7942	-8.7985	1.0	10.5927	-68.7553	-16.7363	-1.0155	-0.9251
0.0	4.8	900	0.0000	1.7932	-8.7964	1.0	10.5896	-68.7483	-16.7396	-1.0156	-0.9252
0.0	5.0667	950	0.0000	1.7947	-8.7966	1.0	10.5913	-68.7488	-16.7345	-1.0156	-0.9252
0.0	5.3333	1000	0.0000	1.7947	-8.7966	1.0	10.5913	-68.7488	-16.7345	-1.0156	-0.9252

Framework versions

Transformers 4.42.3
Pytorch 2.0.0+cu117
Datasets 2.20.0
Tokenizers 0.19.1

tsavage68/Hyponatremia_L3_1000steps_1e7rate_05beta_DPO

Hyponatremia_L3_1000steps_1e7rate_05beta_DPO

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

tsavage68/
Hyponatremia_L3_1000steps_1e7rate_05beta_DPO