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
0.6917	0.2667	50	0.7006	0.0051	0.0168	0.4500	-0.0118	-70.8478	-36.7169	-2.2476	-2.2422
0.6801	0.5333	100	0.6899	0.0048	-0.0060	0.5900	0.0108	-70.8935	-36.7174	-2.2467	-2.2416
0.6127	0.8	150	0.6124	0.0486	-0.1257	0.9200	0.1743	-71.1328	-36.6299	-2.2467	-2.2416
0.5328	1.0667	200	0.5441	0.0725	-0.2574	1.0	0.3299	-71.3964	-36.5821	-2.2465	-2.2415
0.499	1.3333	250	0.4977	0.1004	-0.3476	1.0	0.4480	-71.5766	-36.5262	-2.2466	-2.2417
0.4707	1.6	300	0.4636	0.1150	-0.4251	1.0	0.5400	-71.7316	-36.4971	-2.2465	-2.2417
0.435	1.8667	350	0.4538	0.1116	-0.4529	1.0	0.5645	-71.7873	-36.5038	-2.2457	-2.2410
0.4546	2.1333	400	0.4395	0.1351	-0.4706	1.0	0.6057	-71.8227	-36.4569	-2.2455	-2.2407
0.439	2.4	450	0.4377	0.1195	-0.4924	1.0	0.6118	-71.8662	-36.4881	-2.2464	-2.2416
0.4441	2.6667	500	0.4346	0.1256	-0.4956	1.0	0.6212	-71.8726	-36.4758	-2.2455	-2.2407
0.4388	2.9333	550	0.4402	0.1265	-0.4767	1.0	0.6032	-71.8349	-36.4741	-2.2467	-2.2419
0.4333	3.2	600	0.4371	0.1322	-0.4815	1.0	0.6137	-71.8444	-36.4626	-2.2461	-2.2413
0.4355	3.4667	650	0.4366	0.1316	-0.4856	1.0	0.6173	-71.8527	-36.4638	-2.2459	-2.2411
0.4432	3.7333	700	0.4356	0.1448	-0.4757	1.0	0.6205	-71.8329	-36.4375	-2.2463	-2.2415
0.4461	4.0	750	0.4380	0.1391	-0.4731	1.0	0.6122	-71.8277	-36.4489	-2.2464	-2.2415
0.4312	4.2667	800	0.4380	0.1396	-0.4723	1.0	0.6119	-71.8261	-36.4478	-2.2464	-2.2415
0.4428	4.5333	850	0.4381	0.1397	-0.4720	1.0	0.6116	-71.8254	-36.4477	-2.2464	-2.2415
0.4366	4.8	900	0.4382	0.1403	-0.4711	1.0	0.6114	-71.8237	-36.4464	-2.2464	-2.2415
0.4357	5.0667	950	0.4382	0.1403	-0.4711	1.0	0.6114	-71.8237	-36.4464	-2.2464	-2.2415
0.4454	5.3333	1000	0.4382	0.1403	-0.4711	1.0	0.6114	-71.8237	-36.4464	-2.2464	-2.2415

Framework versions

Transformers 4.42.4
Pytorch 2.0.0+cu117
Datasets 2.20.0
Tokenizers 0.19.1

tsavage68/Hyponatremia_M2_1000steps_1e8rate_05beta_DPO

Hyponatremia_M2_1000steps_1e8rate_05beta_DPO

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

tsavage68/
Hyponatremia_M2_1000steps_1e8rate_05beta_DPO