This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the 2and3_apps_30k_v6 dataset. It achieves the following results on the evaluation set:

Loss: 0.1840

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: 5e-06
train_batch_size: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 2
total_train_batch_size: 8
total_eval_batch_size: 4
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.2225	0.1052	100	0.2175
0.2026	0.2103	200	0.2027
0.2014	0.3155	300	0.1976
0.2157	0.4206	400	0.1964
0.2025	0.5258	500	0.1910
0.1898	0.6309	600	0.1874
0.1948	0.7361	700	0.1863
0.1901	0.8412	800	0.1849
0.1869	0.9464	900	0.1839

Framework versions

Transformers 4.46.1
Pytorch 2.6.0+cu124
Datasets 3.1.0
Tokenizers 0.20.3

lemonhat/Llama-3.2-3B-Instruct-2and3_apps_30k_v6-976

2and3_apps_30k_v6

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

lemonhat/
Llama-3.2-3B-Instruct-2and3_apps_30k_v6-976