Kenito21/experiments

<!-- 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. -->

experiments

This model is a fine-tuned version of 4i-ai/Llama-2-7b-alpaca-es on an unknown dataset. It achieves the following results on the evaluation set:

• —eval_loss: 0.3489
• —eval_runtime: 9.7593
• —evalsamplesper_second: 20.493
• —evalstepsper_second: 2.562
• —epoch: 7.7859
• —step: 100

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: 4
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 32
• —totaltrainbatch_size: 128
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 100
• —training_steps: 100
• —mixedprecisiontraining: Native AMP

Framework versions

• —PEFT 0.10.1.dev0
• —Transformers 4.40.0.dev0
• —Pytorch 2.0.0+cu117
• —Datasets 2.10.1
• —Tokenizers 0.15.2