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-05
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: 475

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
1.3908	0.2	25	1.2815	-0.1831	-0.0153	0.4600	-0.1678	-18.6058	-19.1447	-0.7380	-0.7444
0.7696	0.4	50	0.6447	-2.0796	-3.1294	0.4800	1.0498	-28.9860	-25.4662	-0.6995	-0.6959
1.4448	0.6	75	1.1250	2.3681	1.6567	0.5400	0.7115	-13.0325	-10.6404	-1.2011	-1.1986
5.4772	0.8	100	0.9871	-6.9709	-6.8051	0.4600	-0.1658	-41.2385	-41.7705	0.9489	0.9489
2.2944	1.0	125	0.8798	-10.1674	-10.2198	0.5400	0.0523	-52.6206	-52.4257	0.6962	0.6962
0.8336	1.2	150	0.8186	-9.6977	-9.5821	0.4600	-0.1156	-50.4949	-50.8599	0.4903	0.4903
0.7825	1.4	175	0.7237	-9.6813	-9.6518	0.5400	-0.0295	-50.7273	-50.8051	0.4625	0.4626
0.7932	1.6	200	0.7522	-9.9879	-9.9031	0.4600	-0.0848	-51.5651	-51.8274	0.4098	0.4098
0.7731	1.8	225	0.8182	-9.7026	-9.5887	0.4600	-0.1139	-50.5170	-50.8761	0.3866	0.3866
0.7804	2.0	250	0.7488	-9.8729	-9.7896	0.4500	-0.0833	-51.1867	-51.4438	0.3206	0.3206
0.7516	2.2	275	0.7189	-9.4725	-9.4301	0.4400	-0.0424	-49.9884	-50.1092	0.2071	0.2071
0.7694	2.4	300	0.7305	-9.5857	-9.5207	0.4300	-0.0651	-50.2902	-50.4867	0.2008	0.2008
0.7501	2.6	325	0.7492	-9.6520	-9.5783	0.4600	-0.0737	-50.4823	-50.7074	0.2615	0.2615
0.7308	2.8	350	0.6952	-9.5047	-9.5153	0.4800	0.0106	-50.2725	-50.2166	0.2711	0.2711
0.7173	3.0	375	0.6857	-9.3866	-9.5399	0.5400	0.1533	-50.3543	-49.8229	0.2067	0.2067
0.6094	3.2	400	0.5305	-8.8179	-10.0709	0.75	1.2530	-52.1245	-47.9272	0.1834	0.1832
0.3894	3.4	425	0.7364	-9.0047	-11.3681	0.7700	2.3633	-56.4483	-48.5501	0.3452	0.3450
0.4838	3.6	450	0.7539	-8.9636	-11.1930	0.75	2.2294	-55.8647	-48.4129	0.3187	0.3184
0.2744	3.8	475	0.7574	-8.9677	-11.1818	0.75	2.2141	-55.8273	-48.4265	0.3180	0.3178

Framework versions

Transformers 4.40.2
Pytorch 2.0.0+cu117
Datasets 2.19.1
Tokenizers 0.19.1

tsavage68/Transaminitis_L3_475steps_1e5rate_03beta_CSFTDPO

Transaminitis_L3_475steps_1e5rate_03beta_CSFTDPO

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

tsavage68/
Transaminitis_L3_475steps_1e5rate_03beta_CSFTDPO