Edit model card

Modelo_Resumen

Éste modelo fue creado para la clase del Dr. Gendry

  • Loss: 2.2007
  • Rouge1: 0.1957
  • Rouge2: 0.095
  • Rougel: 0.1645
  • Rougelsum: 0.1645
  • Gen Len: 19.0

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: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Rouge1 Rouge2 Rougel Rougelsum Gen Len
No log 1.0 62 2.3594 0.1957 0.0921 0.1645 0.1645 19.0
No log 2.0 124 2.3268 0.194 0.0898 0.1631 0.1631 19.0
No log 3.0 186 2.3013 0.194 0.0923 0.1649 0.1648 19.0
No log 4.0 248 2.2776 0.195 0.0932 0.166 0.1659 19.0
No log 5.0 310 2.2620 0.1944 0.0925 0.165 0.1649 19.0
No log 6.0 372 2.2474 0.1935 0.0917 0.1648 0.1646 19.0
No log 7.0 434 2.2362 0.1931 0.0929 0.1642 0.1642 19.0
No log 8.0 496 2.2276 0.1937 0.0935 0.1642 0.1644 19.0
2.4678 9.0 558 2.2203 0.1941 0.0938 0.164 0.164 19.0
2.4678 10.0 620 2.2141 0.195 0.0954 0.1648 0.1648 19.0
2.4678 11.0 682 2.2095 0.1956 0.096 0.1649 0.1649 19.0
2.4678 12.0 744 2.2055 0.1952 0.0955 0.1645 0.1645 19.0
2.4678 13.0 806 2.2030 0.1945 0.0947 0.1639 0.1638 19.0
2.4678 14.0 868 2.2014 0.1956 0.095 0.1644 0.1644 19.0
2.4678 15.0 930 2.2007 0.1957 0.095 0.1645 0.1645 19.0

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.1.0+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
6
Safetensors
Model size
60.5M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for RodMed0709/Modelo_Resumen

Finetuned
(2)
this model