How to use from the
Use from the
Transformers library
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("deepanshu120/summarization_model")
model = AutoModelForSeq2SeqLM.from_pretrained("deepanshu120/summarization_model", device_map="auto")
Quick Links

summarization_model

This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 2.3409
  • Rouge1: 0.2
  • Rouge2: 0.0979
  • Rougel: 0.1665
  • Rougelsum: 0.166
  • Gen Len: 20.0

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • 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 2.8547 0.1315 0.0399 0.1076 0.1077 20.0
No log 2.0 124 2.6254 0.1439 0.0482 0.115 0.1149 20.0
No log 3.0 186 2.5276 0.1621 0.065 0.1323 0.1321 20.0
No log 4.0 248 2.4783 0.1942 0.0908 0.16 0.1595 20.0
No log 5.0 310 2.4379 0.2017 0.0981 0.167 0.1666 20.0
No log 6.0 372 2.4160 0.2018 0.099 0.1682 0.1678 20.0
No log 7.0 434 2.3963 0.2017 0.0992 0.1681 0.1677 20.0
No log 8.0 496 2.3818 0.201 0.0986 0.1678 0.1675 20.0
2.7128 9.0 558 2.3687 0.2001 0.0985 0.1667 0.1664 20.0
2.7128 10.0 620 2.3606 0.2005 0.0988 0.1674 0.1671 20.0
2.7128 11.0 682 2.3533 0.1998 0.0977 0.1664 0.166 20.0
2.7128 12.0 744 2.3482 0.2001 0.0982 0.1667 0.1662 20.0
2.7128 13.0 806 2.3432 0.2 0.0988 0.167 0.1665 20.0
2.7128 14.0 868 2.3413 0.1997 0.0976 0.1662 0.1658 20.0
2.7128 15.0 930 2.3409 0.2 0.0979 0.1665 0.166 20.0

Framework versions

  • Transformers 4.53.2
  • Pytorch 2.11.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.21.4
Downloads last month
11
Safetensors
Model size
60.5M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for deepanshu120/summarization_model

Finetuned
(2,345)
this model