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

Loss: 1.2968

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: 4
eval_batch_size: 4
seed: 42
distributed_type: multi-GPU
num_devices: 8
gradient_accumulation_steps: 2
total_train_batch_size: 64
total_eval_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1.0

Training results

Training Loss	Epoch	Step	Validation Loss
2.6993	0.3285	3000	1.2968
2.3312	0.6570	6000	1.3082
2.2325	0.9855	9000	1.3405

Framework versions

Transformers 4.56.2
Pytorch 2.9.1+rocm6.3
Datasets 4.0.0
Tokenizers 0.22.2

sathiiiii/polyalign-llama3.2-3b-en-dist-sft

polyalign

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

sathiiiii/
polyalign-llama3.2-3b-en-dist-sft