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	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.0009	0.2667	50	0.8288	-9.6992	1.0	10.5280	-90.2799	-35.0694	-2.2283	-2.2332
0.0	0.5333	100	0.7731	-11.4586	1.0	12.2317	-93.7986	-35.1808	-2.2236	-2.2301
0.0	0.8	150	0.7528	-12.1438	1.0	12.8966	-95.1690	-35.2215	-2.2211	-2.2282
0.0	1.0667	200	0.7382	-12.5986	1.0	13.3368	-96.0787	-35.2507	-2.2202	-2.2278
0.0	1.3333	250	0.7142	-13.0630	1.0	13.7772	-97.0075	-35.2987	-2.2180	-2.2262
0.0	1.6	300	0.6864	-13.3376	1.0	14.0240	-97.5566	-35.3542	-2.2171	-2.2257
0.0	1.8667	350	0.6758	-13.5516	1.0	14.2274	-97.9847	-35.3755	-2.2162	-2.2251
0.0	2.1333	400	0.6502	-13.7675	1.0	14.4177	-98.4164	-35.4266	-2.2153	-2.2243
0.0	2.4	450	0.6422	-13.9291	1.0	14.5712	-98.7396	-35.4427	-2.2146	-2.2239
0.0	2.6667	500	0.6435	-14.0130	1.0	14.6564	-98.9074	-35.4401	-2.2144	-2.2239
0.0	2.9333	550	0.6341	-14.0963	1.0	14.7304	-99.0741	-35.4589	-2.2145	-2.2241
0.0	3.2	600	0.6375	-14.1392	1.0	14.7767	-99.1599	-35.4521	-2.2144	-2.2239
0.0	3.4667	650	0.6270	-14.1769	1.0	14.8039	-99.2353	-35.4731	-2.2140	-2.2237
0.0	3.7333	700	0.6401	-14.1999	1.0	14.8400	-99.2813	-35.4469	-2.2141	-2.2238
0.0	4.0	750	0.6332	-14.1728	1.0	14.8060	-99.2270	-35.4606	-2.2135	-2.2232
0.0	4.2667	800	0.6216	-14.2039	1.0	14.8255	-99.2892	-35.4838	-2.2142	-2.2239
0.0	4.5333	850	0.6349	-14.1877	1.0	14.8226	-99.2568	-35.4572	-2.2140	-2.2237
0.0	4.8	900	0.6394	-14.1952	1.0	14.8346	-99.2718	-35.4482	-2.2139	-2.2236
0.0	5.0667	950	0.6394	-14.1952	1.0	14.8346	-99.2718	-35.4482	-2.2139	-2.2236
0.0	5.3333	1000	0.6394	-14.1952	1.0	14.8346	-99.2718	-35.4482	-2.2139	-2.2236

Framework versions

Transformers 4.42.4
Pytorch 2.0.0+cu117
Datasets 2.20.0
Tokenizers 0.19.1

tsavage68/Hyponatremia_M2_1000steps_1e7rate_05beta_DPO

Hyponatremia_M2_1000steps_1e7rate_05beta_DPO

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

tsavage68/
Hyponatremia_M2_1000steps_1e7rate_05beta_DPO