tlocvsdyspneaTask-unsup-Llama-3.1-8B-Instruct-datav2-all

ferrazzipietro/tlocvsdyspneaTask-unsup-Llama-3.1-8B-Instruct-datav2-all

tlocvsdyspneaTask-unsup-Llama-3.1-8B-Instruct-datav2-all is a text generation model from ferrazzipietro. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as llama3.1.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

8% of all-time downloads

All-time downloads

Public

Repo size

358 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors168 MB · 86%

At a glance

Task: Text Generation
Library: peft
License: llama3.1
Access: Public
Created: Apr 8, 2026
Updated: Apr 8, 2026
SHA: efacb5ef

Try a prompt

Base models

ferrazzipietro/unsup-Llama-3.1-8B-Instruct-datav2

Model card

From the Hugging Face model README

tlocvsdyspneaTask-unsup-Llama-3.1-8B-Instruct-datav2-all

This model is a fine-tuned version of ferrazzipietro/unsup-Llama-3.1-8B-Instruct-datav2 on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 1.1430
F1 Micro: 0.6498
F1 Macro: 0.3689
F1 Weighted: 0.7696

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: 8
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
gradient_accumulation_steps: 8
total_train_batch_size: 64
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: 3

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Micro	F1 Macro	F1 Weighted
1.643	0.1067	2	1.6754	0.0	0.0	0.0
1.643	0.2133	4	1.6177	0.0	0.0	0.0
1.6418	0.32	6	1.4832	0.0	0.0	0.0
1.6418	0.4267	8	1.3355	0.0	0.0	0.0
1.368	0.5333	10	1.2723	0.3949	0.1672	0.4026
1.368	0.64	12	1.2291	0.5019	0.2256	0.6666
1.368	0.7467	14	1.2055	0.6148	0.2684	0.6302
1.2324	0.8533	16	1.1988	0.6459	0.2810	0.7482
1.2324	0.96	18	1.1885	0.6712	0.2729	0.7421
1.2031	1.0533	20	1.1830	0.5992	0.2496	0.6002
1.2031	1.16	22	1.1744	0.4319	0.2340	0.5129
1.2031	1.2667	24	1.1683	0.6693	0.2605	0.7212
1.1448	1.3733	26	1.1637	0.6829	0.3363	0.7385
1.1448	1.48	28	1.1605	0.5661	0.3659	0.7207
1.1146	1.5867	30	1.1573	0.6809	0.3346	0.7358
1.1146	1.6933	32	1.1534	0.6984	0.3504	0.7606
1.1146	1.8	34	1.1502	0.5778	0.3661	0.7324
1.1051	1.9067	36	1.1477	0.5914	0.3716	0.7433
1.1051	2.0	38	1.1457	0.6965	0.3488	0.7581
1.1165	2.1067	40	1.1447	0.6751	0.3295	0.7277
1.1165	2.2133	42	1.1442	0.6946	0.3472	0.7556
1.1165	2.32	44	1.1439	0.6401	0.3706	0.7677
1.0882	2.4267	46	1.1437	0.5545	0.3630	0.7059
1.0882	2.5333	48	1.1434	0.5720	0.3687	0.7246
1.148	2.64	50	1.1432	0.6109	0.3696	0.7543
1.148	2.7467	52	1.1432	0.6362	0.3682	0.7639
1.148	2.8533	54	1.1430	0.6498	0.3689	0.7696

Framework versions

PEFT 0.18.1
Transformers 4.51.0
Pytorch 2.8.0+cu128
Datasets 3.6.0
Tokenizers 0.21.0

Task: Text Generation
Library: peft
License: llama3.1
Created: Apr 8, 2026
Updated: Apr 8, 2026