metadata
base_model: barc0/llama3.2-1b-instruct-fft-transduction-engineer_lr1e-5_epoch4
datasets:
- >-
barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems
- barc0/transduction_augmented_test_timearc_all_evaluation_new_seperate
- barc0/transduction_rearc_dataset_400k
library_name: peft
license: llama3.2
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: barc-llama3.2-1b-instruct-lora64-testtime-finetuning
results: []
barc-llama3.2-1b-instruct-lora64-testtime-finetuning
This model is a fine-tuned version of barc0/llama3.2-1b-instruct-fft-transduction-engineer_lr1e-5_epoch4 on the barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems, the barc0/transduction_augmented_test_timearc_all_evaluation_new_seperate and the barc0/transduction_rearc_dataset_400k datasets. It achieves the following results on the evaluation set:
- Loss: 0.0591
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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_batch_size: 8
- 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 |
---|---|---|---|
0.074 | 1.0 | 1355 | 0.0688 |
0.045 | 2.0 | 2710 | 0.0575 |
0.0207 | 3.0 | 4065 | 0.0591 |
Framework versions
- PEFT 0.12.0
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1