This model is a fine-tuned version of /workspace/checkpoints/knk_vf_lab_38b on the kurotama_pretrain_text dataset. It achieves the following results on the evaluation set:

Loss: 5.6999

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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
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_steps: 0.05
training_steps: 60

Training results

Training Loss	Epoch	Step	Validation Loss
51.4560	1.2	30	6.2616
45.2052	2.4	60	5.6999

Framework versions

PEFT 0.18.1
Transformers 5.6.0
Pytorch 2.4.1+cu124
Datasets 4.0.0
Tokenizers 0.22.2

MagistrTheOne/KUROTAMA-KNK-VF-Lab38B-PT-LoRA

kurotama-knk-vf-lab38b-pt-lora

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

MagistrTheOne/
KUROTAMA-KNK-VF-Lab38B-PT-LoRA