AmritJain/A-soldier-Memory

<!-- 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. -->

train_2025-12-23-16-11-58

This model is a fine-tuned version of baidu/ERNIE-4.5-0.3B-PT on the synthetic_memories dataset. It achieves the following results on the evaluation set:

• —Loss: 1.8149
• —Num Input Tokens Seen: 3234144

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: 0.0003
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 64
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: cosine
• —num_epochs: 3.0

Training results

Framework versions

• —PEFT 0.17.1
• —Transformers 4.54.0
• —Pytorch 2.5.1+cu121
• —Datasets 3.5.1
• —Tokenizers 0.21.4