metadata
license: mit
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: microsoft/Phi-3-mini-4k-instruct
model-index:
- name: realDataFineTune
results: []
realDataFineTune
This model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 12.1175
- eval_runtime: 379.7612
- eval_samples_per_second: 15.407
- eval_steps_per_second: 3.852
- step: 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: 0.0001
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- lr_scheduler_warmup_steps: 20
- training_steps: 1000
Framework versions
- Transformers 4.40.1
- Pytorch 2.1.0+cpu
- Datasets 2.19.0
- Tokenizers 0.19.1
Training procedure
Framework versions
- PEFT 0.6.2