This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.5
Eval/rewards/chosen: -924.2795
Eval/logps/chosen: -9280.1759
Eval/rewards/rejected: -892.2998
Eval/logps/rejected: -8997.4511
Eval/rewards/margins: -31.9797
Eval/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: 0.15
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 128
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
lr_scheduler_warmup_steps: 200
num_epochs: 3
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5008	1.1552	100	0.5	0.0
0.4977	2.3105	200	0.5	0.0

Framework versions

Transformers 4.45.0
Pytorch 2.5.1+cu124
Datasets 2.19.2
Tokenizers 0.20.3

stojchet/kto7

kto7

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

stojchet/
kto7