oliverdk/pythia-14m-measurement_pred

<!-- 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. -->

pythia-14m-measurement_pred

This model is a fine-tuned version of EleutherAI/pythia-14m on an unknown dataset. It achieves the following results on the evaluation set:

• —Loss: 3.4923
• —Accuracy: 0.25
• —Accuracy Sensor 0: 1.0
• —Auroc Sensor 0: 0.0
• —Accuracy Sensor 1: 0.0
• —Auroc Sensor 1: 0.0
• —Accuracy Sensor 2: 0.0
• —Auroc Sensor 2: 0.0
• —Accuracy Aggregated: 0.0
• —Auroc Aggregated: 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: 2e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 32
• —totaltrainbatch_size: 256
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 64
• —num_epochs: 5

Training results

Framework versions

• —Transformers 4.41.0
• —Pytorch 2.3.0+cu121
• —Datasets 2.19.1
• —Tokenizers 0.19.1