RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

ruadaptqwen2.53Bextu48fulllr5e4peftmlp3232_bs256

This model is a fine-tuned version of RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 2.3370
• —Accuracy: 0.5155

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: 0.0005
• —trainbatchsize: 2
• —evalbatchsize: 2
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 64
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 256
• —totalevalbatch_size: 128
• —optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 100
• —num_epochs: 1.0

Training results

Framework versions

• —PEFT 0.9.0
• —Transformers 4.45.2
• —Pytorch 2.3.0a0+6ddf5cf85e.nv24.04
• —Datasets 2.18.0
• —Tokenizers 0.20.1