MN-12B-Mag-Mell-R1-KTO – AI Model by taozi555 | AlphaNeural AI

You can deploy this model and start earning money today!

taozi555/
MN-12B-Mag-Mell-R1-KTO

like

0

text-generation

generated_from_trainer

inflatebot/MN-12B-Mag-Mell-R1

text-generation-inference

endpoints_compatible

Views

No views yet

sft

This model is a fine-tuned version of inflatebot/MN-12B-Mag-Mell-R1 on the kto_rp dataset. It achieves the following results on the evaluation set:

Loss: 0.3763
Rewards/chosen: 0.6433
Logps/chosen: -219.3819
Logits/chosen: -923703389.9450
Rewards/rejected: -1.3013
Logps/rejected: -231.1543
Logits/rejected: -831308124.5957
Rewards/margins: 1.9446
Kl: 0.0

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: 5e-07
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 8
total_train_batch_size: 32
total_eval_batch_size: 4
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rewards/chosen	Logps/chosen	Logits/chosen	Rewards/rejected	Logps/rejected	Logits/rejected	Rewards/margins
0.3079	0.8421	500	0.3781	0.8047	-217.7675	-922359676.4771	-1.0247	-228.3881	-826945158.3546	1.8294	0.0

Framework versions

Transformers 4.55.0
Pytorch 2.5.1+cu124
Datasets 3.6.0
Tokenizers 0.21.1