metadata

base_model: meta-llama/Llama-2-7b-chat-hf
tags:
  - generated_from_trainer
model-index:
  - name: llama-2-7b-reward-oasst1
    results: []
library_name: peft

llama-2-7b-reward-oasst1

This model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on the None dataset. It achieves the following results on the evaluation set:

eval_loss: 0.5062
eval_accuracy: 0.7593
eval_runtime: 431.9996
eval_samples_per_second: 2.058
eval_steps_per_second: 2.058
epoch: 0.72
step: 3000

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

The following bitsandbytes quantization config was used during training:

load_in_8bit: False
load_in_4bit: True
llm_int8_threshold: 6.0
llm_int8_skip_modules: None
llm_int8_enable_fp32_cpu_offload: False
llm_int8_has_fp16_weight: False
bnb_4bit_quant_type: nf4
bnb_4bit_use_double_quant: False
bnb_4bit_compute_dtype: float16

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 4
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 1

Framework versions

PEFT 0.5.0.dev0
Transformers 4.32.0.dev0
Pytorch 2.0.1+cu118
Datasets 2.14.0
Tokenizers 0.13.3