metadata

base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
  - >-
    barc0/induction_20k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3
library_name: peft
license: llama3.1
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: >-
      induction-run4-gpt4omini-20k-100seeds-barc-llama3.1-8b-instruct-lora64_lr2e-4_epoch3
    results: []

induction-run4-gpt4omini-20k-100seeds-barc-llama3.1-8b-instruct-lora64_lr2e-4_epoch3

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the barc0/induction_20k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3 dataset. It achieves the following results on the evaluation set:

Loss: 0.3360

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: 0.0002
train_batch_size: 8
eval_batch_size: 4
seed: 4
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 128
total_eval_batch_size: 32
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.3484	0.9966	145	0.3561
0.3202	2.0	291	0.3388
0.3107	2.9897	435	0.3360

Framework versions

PEFT 0.13.0
Transformers 4.45.0.dev0
Pytorch 2.4.0+cu121
Datasets 3.0.1
Tokenizers 0.19.1