engineer-heavy-500k-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/transduction_heavy_100k_jsonl, the barc0/transduction_heavy_suggestfunction_100k_jsonl, the barc0/transduction_formatted_rearc_dataset_100k, the barc0/transduction_angmented_100k-gpt4-description-gpt4omini-code_generated_problems and the barc0/transduction_angmented_100k_gpt4o-mini_generated_problems datasets. It achieves the following results on the evaluation set:

Loss: 0.0210

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
total_train_batch_size: 64
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
0.0444	1.0	7458	0.0327
0.0229	2.0	14916	0.0218
0.0055	3.0	22374	0.0210

Framework versions

Transformers 4.45.0.dev0
Pytorch 2.4.0a0+3bcc3cddb5.nv24.07
Datasets 3.4.0
Tokenizers 0.19.1

apolo-mind/engineer-heavy-500k-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3

engineer-heavy-500k-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

apolo-mind/
engineer-heavy-500k-barc-llama3.1-8b-ins-fft-transduction_lr1e-5_epoch3