Saltar al contenido
ModelPublicadoExterno
Descargar

Iris Llama 3.2 3b Iris Only K10

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the None dataset. It achieves the following results on the evaluation set: Loss: 0.5994 Model Preparation Time: 0.0211 Soft Mae: 0.0445 Soft...

Fuentehuggingface.co/daryaZare/iris-llama-3.2-3b-iris-only-k10/tree/8cc6298f96e42d57b66b2193363ba559a0b1800d
TipoOtherModelo basemeta-llama/Llama-3.2-3B-InstructVersiónRevision 8cc6298Bcalidad

Fuente del modelo

Tipo
Other
Tamaño del archivo
92,8 MB
Modelo base
meta-llama/Llama-3.2-3B-Instruct
Versión
vRevision 8cc6298
Actualizado
20 oct 2026
Descargas
27
Fuente
Hugging Face

Descripción de la fuente

iris-llama-3.2-3b-iris-only-k10

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5994
  • Model Preparation Time: 0.0211
  • Soft Mae: 0.0445
  • Soft Brier: 0.0070
  • Student Prelevantmean: 0.2169
  • Teacher Prelevantmean: 0.2340
  • Bin F1: 0.8689
  • Cal Ece: 0.1030
  • Cal Brier: 0.0609
  • Cal Auroc: 0.9877
  • Info Ndcg@p8: 0.9592
  • Info Pairwiseacc: 0.9264
  • Num Questions: 30
  • Num Pairs: 240

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-05
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 16
  • optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: constant
  • lr_scheduler_warmup_steps: 0.03
  • num_epochs: 6.0

Training results

Training LossEpochStepValidation LossModel Preparation TimeSoft MaeSoft BrierStudent PrelevantmeanTeacher PrelevantmeanBin F1Cal EceCal BrierCal AurocInfo Ndcg@p8Info PairwiseaccNum QuestionsNum Pairs
0.79790.2519340.64950.02110.06890.01530.21460.23400.82640.08760.07990.97100.95340.927130240
0.71590.5037680.54560.02110.05200.00930.23940.23400.90230.08300.05700.98170.96170.931430240
0.79740.75561020.67470.02110.08120.01370.23540.23400.81740.14930.07540.98750.96320.942930240
0.62661.00741360.44940.02110.04330.00630.23900.23400.91600.09360.05050.99040.95970.929930240
0.61001.25931700.50280.02110.05340.01000.25690.23400.94030.12670.06260.98880.96130.929830240
0.45041.51112040.48510.02110.04790.00740.25220.23400.91730.09580.05510.98770.96250.933030240
0.50751.76302380.56210.02110.04840.00870.21000.23400.8960.09540.05530.99080.95960.928930240
0.40042.01482720.69110.02110.05430.00960.20370.23400.88520.09420.06530.99040.96220.937930240
0.49902.26673060.63540.02110.05100.00890.24850.23400.93430.12600.06450.99250.96240.940030240
0.33522.51853400.51590.02110.04060.00730.24450.23400.93940.09050.04890.98840.96190.923630240
0.38432.77043740.50690.02110.04270.00690.22140.23400.90480.09360.05690.98910.96170.930930240
0.33803.02224080.52250.02110.04520.00730.23610.23400.89230.10830.05950.99260.96150.932630240
0.29213.27414420.53400.02110.04310.00740.24370.23400.92310.10020.05830.98600.96080.929430240
0.36173.52594760.59010.02110.04700.00790.21400.23400.89080.09600.06170.98980.96070.919630240
0.31463.77785100.65940.02110.04730.00860.25430.23400.92750.09980.05490.99020.96360.942530240
0.43984.02965440.60770.02110.05060.00740.24210.23400.93330.12140.06020.99240.96150.931830240
0.42974.28155780.71190.02110.05360.00930.21120.23400.87390.11160.06890.99140.96180.933130240
0.27714.53336120.71990.02110.04690.00720.21870.23400.89260.11410.06200.99300.96110.932230240
0.29164.78526460.55410.02110.04310.00700.22400.23400.90320.09290.05510.99090.96200.933730240
0.20445.03706800.67370.02110.04580.00740.22410.23400.87800.09500.05990.98890.96090.931530240
0.25045.28897140.82730.02110.05850.00930.23070.23400.89430.13790.06490.99370.96210.933130240
0.28245.54077480.69570.02110.05090.00790.23250.23400.93020.12710.06240.99240.96110.929530240
0.30545.79267820.52870.02110.04340.00720.24650.23400.92650.09900.05520.98950.96260.921330240
0.25706.08100.59940.02110.04450.00700.21690.23400.86890.10300.06090.98770.95920.926430240

Framework versions

  • PEFT 0.19.1
  • Transformers 5.14.1
  • Pytorch 2.5.1+cu124
  • Datasets 5.0.0
  • Tokenizers 0.22.2

Fuentes

1 fuente
Hugging FacePrincipalVersión 8cc6298f96e42d57b66b2193363ba559a0b1800d
huggingface.co/daryaZare/iris-llama-3.2-3b-iris-only-k10/tree/8cc6298f96e42d57b66b2193363ba559a0b1800d

Verificado 20 oct

Artefactos del modelo

13 artefactos

adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 f04e829f4bf8…8704 · Hugging Face

Descargar

checkpoint-136/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 68a9974305cd…9f4c · Hugging Face

Descargar

checkpoint-204/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 5665703ef38d…24fa · Hugging Face

Descargar

checkpoint-272/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 17c55ffb432e…d2d7 · Hugging Face

Descargar

checkpoint-340/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 7078866f63cf…d852 · Hugging Face

Descargar

checkpoint-408/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 c45fa0b0288b…0fd1 · Hugging Face

Descargar

checkpoint-476/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 b315aa10c6ac…ef0b · Hugging Face

Descargar

checkpoint-544/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 3aec9c89879e…3b34 · Hugging Face

Descargar

checkpoint-612/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 71560b54000f…a5c5 · Hugging Face

Descargar

checkpoint-68/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 e649e3b2e0e5…f914 · Hugging Face

Descargar

checkpoint-680/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 40d0f065f2c2…46a9 · Hugging Face

Descargar

checkpoint-748/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 b4b06b737cf4…5258 · Hugging Face

Descargar

checkpoint-810/adapter_model.safetensors

safetensors · 92,8 MB · SHA-256 f04e829f4bf8…8704 · Hugging Face

Descargar

Extractos de fuentes

3 extractos
Readme3 agohuggingface.co/daryaZare/iris-llama-3.2-3b-iris-only-k10

--- library_name: peft license: llama3.2 base_model: meta-llama/Llama-3.2-3B-Instruct tags: - base_model:adapter:meta-llama/Llama-3.2-3B-Instruct - lora - transformers pipeline_tag: text-generation model-index: - name: iris-llama-3.2-3b-iris-only-k10 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # iris-llama-3.2-3b-iris-only-k10 This model is a fine-tuned version of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5994 - Model Preparation Time: 0.0211 - Soft Mae: 0.0445 - Soft Brier: 0.0070 - Student Prelevantmean: 0.2169 - Teacher Prelevantmean: 0.2340 - Bin F1: 0.8689 - Cal Ece: 0.1030 - Cal Brier: 0.0609 - Cal Auroc: 0.9877 - Info Ndcg@p8: 0.9592 - Info Pairwiseacc: 0.9264 - Num Questions: 30 - Num Pairs: 240 ## 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-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 16 - optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: constant - lr_scheduler_warmup_steps: 0.03 - num_epochs: 6.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Soft Mae | Soft Brier | Student Prelevantmean | Teacher Prelevantmean | Bin F1 | Cal Ece | Cal Brier | Cal Auroc | Info Ndcg@p8 | Info Pairwiseacc | Num Questions | Num Pairs | |:-------------:|:------:|:----:|:---------------:|:----------------------:|:--------:|:----------:|:---------------------:|:---------------------:|:------:|:-------:|:---------:|:---------:|:------------:|:----------------:|:-------------:|:---------:| | 0.7979 | 0.2519 | 34 | 0.6495 | 0.0211 | 0.0689 | 0.0153 | 0.2146 | 0.2340 | 0.8264 | 0.0876 | 0.0799 | 0.9710 | 0.9534 | 0.9271 | 30 | 240 | | 0.7159 | 0.5037 | 68 | 0.5456 | 0.0211 | 0.0520 | 0.0093 | 0.2394 | 0.2340 | 0.9023...

Note20 octhuggingface.co/daryaZare/iris-llama-3.2-3b-iris-only-k10

Source context: 27 downloads · 0 likes · Pipeline text-generation · Library peft · Repo daryaZare/iris-llama-3.2-3b-iris-only-k10

Note3 agohuggingface.co/daryaZare/iris-llama-3.2-3b-iris-only-k10

Source context: 257 downloads · 0 likes · Pipeline text-generation · Library peft · Repo daryaZare/iris-llama-3.2-3b-iris-only-k10