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-08
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
0.6962	0.2667	50	0.6922	0.0018	-0.0003	0.5600	0.0021	-39.4298	-22.6992	-1.0181	-0.9449
0.6954	0.5333	100	0.6954	0.0009	0.0052	0.4000	-0.0043	-39.3750	-22.7083	-1.0190	-0.9459
0.6894	0.8	150	0.6934	0.0007	0.0011	0.4900	-0.0004	-39.4157	-22.7094	-1.0191	-0.9457
0.69	1.0667	200	0.6926	0.0030	0.0019	0.5500	0.0011	-39.4083	-22.6871	-1.0185	-0.9454
0.6908	1.3333	250	0.6907	0.0045	-0.0004	0.6000	0.0049	-39.4311	-22.6717	-1.0186	-0.9455
0.6903	1.6	300	0.6915	0.0025	-0.0009	0.5500	0.0034	-39.4359	-22.6917	-1.0199	-0.9466
0.6908	1.8667	350	0.6913	0.0011	-0.0027	0.5400	0.0038	-39.4535	-22.7055	-1.0186	-0.9454
0.688	2.1333	400	0.6915	0.0038	0.0005	0.5600	0.0033	-39.4222	-22.6792	-1.0189	-0.9458
0.6899	2.4	450	0.6915	0.0038	0.0003	0.5300	0.0035	-39.4237	-22.6788	-1.0189	-0.9457
0.6926	2.6667	500	0.6912	0.0029	-0.0011	0.6200	0.0040	-39.4378	-22.6879	-1.0192	-0.9461
0.6887	2.9333	550	0.6904	0.0040	-0.0015	0.6000	0.0056	-39.4422	-22.6765	-1.0195	-0.9464
0.6881	3.2	600	0.6908	0.0031	-0.0017	0.6200	0.0048	-39.4443	-22.6863	-1.0190	-0.9459
0.688	3.4667	650	0.6901	0.0043	-0.0019	0.6200	0.0062	-39.4461	-22.6735	-1.0186	-0.9454
0.6903	3.7333	700	0.6904	0.0041	-0.0014	0.6400	0.0055	-39.4404	-22.6756	-1.0186	-0.9457
0.6908	4.0	750	0.6905	0.0034	-0.0019	0.6400	0.0053	-39.4462	-22.6833	-1.0190	-0.9460
0.6897	4.2667	800	0.6905	0.0036	-0.0018	0.6400	0.0054	-39.4451	-22.6809	-1.0190	-0.9460
0.6906	4.5333	850	0.6905	0.0037	-0.0018	0.6400	0.0054	-39.4444	-22.6801	-1.0190	-0.9460
0.6895	4.8	900	0.6905	0.0037	-0.0018	0.6400	0.0054	-39.4444	-22.6801	-1.0190	-0.9460
0.6889	5.0667	950	0.6905	0.0037	-0.0018	0.6400	0.0054	-39.4444	-22.6801	-1.0190	-0.9460
0.6872	5.3333	1000	0.6905	0.0037	-0.0018	0.6400	0.0054	-39.4444	-22.6801	-1.0190	-0.9460

Framework versions

Transformers 4.42.3
Pytorch 2.0.0+cu117
Datasets 2.20.0
Tokenizers 0.19.1

tsavage68/Hyponatremia_L3_1000steps_1e8rate_01beta_DPO

Hyponatremia_L3_1000steps_1e8rate_01beta_DPO

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

tsavage68/
Hyponatremia_L3_1000steps_1e8rate_01beta_DPO