This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the gobrowse_plan dataset. It achieves the following results on the evaluation set:

Loss: 0.1908

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: 1
eval_batch_size: 1
seed: 42
distributed_type: multi-GPU
num_devices: 4
gradient_accumulation_steps: 4
total_train_batch_size: 16
total_eval_batch_size: 4
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: 3

Training results

Training Loss	Epoch	Step	Validation Loss
0.339	0.2232	100	0.3283
0.3298	0.4464	200	0.3053
0.2866	0.6696	300	0.2722
0.2627	0.8929	400	0.2445
0.1743	1.1161	500	0.2278
0.149	1.3393	600	0.2221
0.1469	1.5625	700	0.2064
0.1255	1.7857	800	0.1907
0.1055	2.0089	900	0.1777
0.0576	2.2321	1000	0.1938
0.054	2.4554	1100	0.1919
0.0492	2.6786	1200	0.1904
0.0431	2.9018	1300	0.1907

Framework versions

Transformers 4.57.1
Pytorch 2.9.1+cu128
Datasets 4.0.0
Tokenizers 0.22.2

Rain-air/llama3-8B-gobrowse-plan-sft_0122

sft

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

Rain-air/
llama3-8B-gobrowse-plan-sft_0122