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/cot_transduction_100k-gpt4omini-description
- barc0/cot_transduction_100k-gpt4-description
- barc0/cot_transduction_200k_HEAVY_gpt4o-description
model-index:
- name: cot-400k-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3
results: []
cot-400k-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the barc0/cot_transduction_100k-gpt4omini-description, the barc0/cot_transduction_100k-gpt4-description and the barc0/cot_transduction_200k_HEAVY_gpt4o-description datasets. It achieves the following results on the evaluation set:
- Loss: 0.2160
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: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- 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 |
|---|---|---|---|
| 0.2231 | 0.9998 | 2994 | 0.2183 |
| 0.1861 | 2.0 | 5989 | 0.2049 |
| 0.1483 | 2.9995 | 8982 | 0.2160 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1