llama3.2-1b-instruct-fft-transduction-engineer_lr1e-5_epoch4

This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct 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: 0.0409

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: 8
gradient_accumulation_steps: 2
total_train_batch_size: 256
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: 4

Training results

Training Loss	Epoch	Step	Validation Loss
0.0618	1.0	1126	0.0657
0.0504	2.0	2252	0.0494
0.0363	3.0	3378	0.0418
0.0238	4.0	4504	0.0409

Framework versions

Transformers 4.45.0.dev0
Pytorch 2.4.0+cu121
Datasets 3.0.1
Tokenizers 0.19.1

barc0/llama3.2-1b-instruct-fft-transduction-engineer_lr1e-5_epoch4

llama3.2-1b-instruct-fft-transduction-engineer_lr1e-5_epoch4

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

barc0/
llama3.2-1b-instruct-fft-transduction-engineer_lr1e-5_epoch4