Hyponatremia_L3_450steps_1e8rate_03beta_DPO – AI Model by tsavage68 | AlphaNeural AI

You can deploy this model and start earning money today!

tsavage68/
Hyponatremia_L3_450steps_1e8rate_03beta_DPO

like

0

text-generation

generated_from_trainer

tsavage68/Hyponatremia_L3_450steps_1e7rate_SFT

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

Hyponatremia_L3_450steps_1e8rate_03beta_DPO

This model is a fine-tuned version of tsavage68/Hyponatremia_L3_450steps_1e7rate_SFT on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.6867
Rewards/chosen: 0.0084
Rewards/rejected: -0.0055
Rewards/accuracies: 0.5500
Rewards/margins: 0.0139
Logps/rejected: -39.4453
Logps/chosen: -22.6888
Logits/rejected: -1.0194
Logits/chosen: -0.9460

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: 450

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.7031	0.2667	50	0.6911	0.0069	0.0019	0.5400	0.0049	-39.4204	-22.6940	-1.0181	-0.9449
0.6932	0.5333	100	0.6947	0.0031	0.0056	0.4900	-0.0025	-39.4082	-22.7065	-1.0186	-0.9454
0.6863	0.8	150	0.6952	0.0085	0.0116	0.5	-0.0031	-39.3880	-22.6884	-1.0196	-0.9465
0.6835	1.0667	200	0.6904	0.0071	0.0005	0.5600	0.0066	-39.4251	-22.6932	-1.0195	-0.9461
0.6893	1.3333	250	0.6949	0.0036	0.0063	0.4700	-0.0027	-39.4057	-22.7047	-1.0186	-0.9454
0.6794	1.6	300	0.6881	0.0143	0.0036	0.5800	0.0107	-39.4150	-22.6692	-1.0187	-0.9455
0.6843	1.8667	350	0.6877	0.0079	-0.0040	0.5400	0.0119	-39.4403	-22.6906	-1.0194	-0.9460
0.6885	2.1333	400	0.6867	0.0084	-0.0055	0.5500	0.0139	-39.4453	-22.6888	-1.0194	-0.9460
0.6843	2.4	450	0.6867	0.0084	-0.0055	0.5500	0.0139	-39.4453	-22.6888	-1.0194	-0.9460

Framework versions

Transformers 4.42.3
Pytorch 2.0.0+cu117
Datasets 2.20.0
Tokenizers 0.19.1