haqishen/v1_phi4_mini_bs1x2x2_lr1e4_dora64_128do80_4ep_final_lora

<!-- 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. -->

v1phi4minibs1x2x2lr1e4dora64128do804epfinal

This model is a fine-tuned version of microsoft/Phi-4-mini-instruct on the flock-task17-train and the flock-task17-valid datasets. It achieves the following results on the evaluation set:

• —Loss: 1.2161

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
• —trainbatchsize: 1
• —evalbatchsize: 1
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 2
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 4
• —totalevalbatch_size: 2
• —optimizer: Use pagedadamw32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 20
• —num_epochs: 4

Training results

Framework versions

• —PEFT 0.15.1
• —Transformers 4.52.4
• —Pytorch 2.9.1+cu128
• —Datasets 3.5.0
• —Tokenizers 0.21.4