Hyponatremia_L3_100steps_1e6rate_05beta_DPO – AI Model by tsavage68 | AlphaNeural AI

You can deploy this model and start earning money today!

tsavage68/
Hyponatremia_L3_100steps_1e6rate_05beta_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_100steps_1e6rate_05beta_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: 0.0000
Rewards/chosen: 2.5502
Rewards/rejected: -9.9725
Rewards/accuracies: 1.0
Rewards/margins: 12.5227
Logps/rejected: -59.3719
Logps/chosen: -17.6164
Logits/rejected: -1.0131
Logits/chosen: -0.9245

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-06
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: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Rewards/rejected	Rewards/accuracies	Rewards/margins	Logps/rejected	Logps/chosen	Logits/rejected	Logits/chosen
0.0	0.2667	50	0.0000	2.3120	-8.2717	1.0	10.5837	-55.9703	-18.0928	-1.0142	-0.9271
0.0	0.5333	100	0.0000	2.5502	-9.9725	1.0	12.5227	-59.3719	-17.6164	-1.0131	-0.9245

Framework versions

Transformers 4.42.3
Pytorch 2.0.0+cu117
Datasets 2.20.0
Tokenizers 0.19.1