Hyponatremia_M2_100steps_1e7rate_01beta_DPO – AI Model by tsavage68 | AlphaNeural AI

You can deploy this model and start earning money today!

tsavage68/
Hyponatremia_M2_100steps_1e7rate_01beta_DPO

like

0

text-generation

generated_from_trainer

tsavage68/Hyponatremia_M2_150steps_1e6rate_SFT

autotrain_compatible

text-generation-inference

endpoints_compatible

Views

No views yet

Hyponatremia_M2_100steps_1e7rate_01beta_DPO

This model is a fine-tuned version of tsavage68/Hyponatremia_M2_150steps_1e6rate_SFT on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.0001
Rewards/chosen: 0.5624
Rewards/rejected: -9.1803
Rewards/accuracies: 1.0
Rewards/margins: 9.7427
Logps/rejected: -162.6846
Logps/chosen: -31.1030
Logits/rejected: -2.0967
Logits/chosen: -2.1493

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: 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
0.1809	0.2667	50	0.0764	0.2775	-2.3601	1.0	2.6376	-94.4829	-33.9523	-2.2243	-2.2318
0.0001	0.5333	100	0.0001	0.5624	-9.1803	1.0	9.7427	-162.6846	-31.1030	-2.0967	-2.1493

Framework versions

Transformers 4.42.4
Pytorch 2.0.0+cu117
Datasets 2.20.0
Tokenizers 0.19.1