This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 6.0472

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: 0.0003
train_batch_size: 32
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-07 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 1

Training results

Training Loss	Epoch	Step	Validation Loss
0.2384	0.0605	1000	4.3588
0.1456	0.1211	2000	4.8782
0.1349	0.1816	3000	4.9783
0.1238	0.2422	4000	5.1408
0.1234	0.3027	5000	5.2627
0.115	0.3632	6000	5.1261
0.1145	0.4238	7000	5.3884
0.1089	0.4843	8000	5.3399
0.1018	0.5448	9000	5.4000
0.1019	0.6054	10000	5.4818
0.0982	0.6659	11000	5.7525
0.0935	0.7265	12000	5.7180
0.092	0.7870	13000	5.7179
0.0892	0.8475	14000	5.8992
0.0918	0.9081	15000	6.0000
0.0944	0.9686	16000	6.0472

Framework versions

Transformers 4.51.0
Pytorch 2.8.0+cu128
Datasets 3.6.0
Tokenizers 0.21.0

ferrazzipietro/Llama-3.2-1B-Instruct-unsup-crf-full-weight

Llama-3.2-1B-Instruct-unsup-crf-full-weight

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

ferrazzipietro/
Llama-3.2-1B-Instruct-unsup-crf-full-weight