metadata
library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
- trl
- sft
- generated_from_trainer
datasets:
- >-
barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems
- barc0/transduction_angmented_100k_gpt4o-mini_generated_problems
- barc0/transduction_rearc_dataset_400k
model-index:
- name: llama3.2-1b-instruct-fft-transduction-engineer_lr1e-5_epoch4
results: []
llama3.2-1b-instruct-fft-transduction-engineer_lr1e-5_epoch4
This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems, the barc0/transduction_angmented_100k_gpt4o-mini_generated_problems and the barc0/transduction_rearc_dataset_400k datasets. It achieves the following results on the evaluation set:
- Loss: 0.0363
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: 16
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- 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: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0584 | 0.9998 | 2251 | 0.0631 |
| 0.0502 | 2.0 | 4503 | 0.0447 |
| 0.0421 | 2.9998 | 6754 | 0.0367 |
| 0.0269 | 3.9991 | 9004 | 0.0363 |
Framework versions
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1