metadata
library_name: transformers
license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- >-
barc0/transduction_100k-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3
model-index:
- name: >-
gpt4-description-barc-llama3.1-8b-instruct-fft-transduction-gpt4omini100k_lr1e-5_epoch2
results: []
gpt4-description-barc-llama3.1-8b-instruct-fft-transduction-gpt4omini100k_lr1e-5_epoch2
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the barc0/transduction_100k-gpt4-description-gpt4omini-code_generated_problems_messages_format_0.3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0460
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 4
- seed: 42
- 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: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0655 | 1.0 | 760 | 0.0572 |
| 0.0329 | 2.0 | 1520 | 0.0460 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1