metadata
library_name: transformers
license: apache-2.0
base_model: allenai/led-base-16384
tags:
- generated_from_trainer
metrics:
- rouge
- bleu
- precision
- recall
- f1
model-index:
- name: LED_sum_outcome
results: []
LED_sum_outcome
This model is a fine-tuned version of allenai/led-base-16384 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4730
- Rouge1: 0.3601
- Rouge2: 0.1515
- Rougel: 0.3017
- Rougelsum: 0.301
- Gen Len: 20.36
- Bleu: 0.0595
- Precisions: 0.1544
- Brevity Penalty: 0.6108
- Length Ratio: 0.6698
- Translation Length: 785.0
- Reference Length: 1172.0
- Precision: 0.8997
- Recall: 0.8766
- F1: 0.8879
- Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0)
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bleu | Precisions | Brevity Penalty | Length Ratio | Translation Length | Reference Length | Precision | Recall | F1 | Hashcode |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 7 | 7.7628 | 0.2668 | 0.0617 | 0.2177 | 0.2179 | 21.0 | 0.0211 | 0.0856 | 0.6935 | 0.7321 | 858.0 | 1172.0 | 0.8742 | 0.86 | 0.8669 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) |
| No log | 2.0 | 14 | 6.5648 | 0.3427 | 0.124 | 0.2806 | 0.2804 | 20.16 | 0.0514 | 0.1396 | 0.6085 | 0.6681 | 783.0 | 1172.0 | 0.8991 | 0.8717 | 0.8851 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) |
| No log | 3.0 | 21 | 5.1851 | 0.3468 | 0.1383 | 0.282 | 0.2807 | 19.7 | 0.0722 | 0.1711 | 0.578 | 0.6459 | 757.0 | 1172.0 | 0.9029 | 0.8772 | 0.8898 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) |
| No log | 4.0 | 28 | 4.4398 | 0.3475 | 0.1299 | 0.2825 | 0.2821 | 20.18 | 0.0455 | 0.1417 | 0.598 | 0.6604 | 774.0 | 1172.0 | 0.8979 | 0.8766 | 0.887 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) |
| No log | 5.0 | 35 | 4.0655 | 0.3506 | 0.1412 | 0.2913 | 0.2901 | 19.94 | 0.054 | 0.1556 | 0.5685 | 0.6391 | 749.0 | 1172.0 | 0.8987 | 0.8772 | 0.8877 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) |
| No log | 6.0 | 42 | 3.8299 | 0.356 | 0.148 | 0.295 | 0.294 | 20.38 | 0.0616 | 0.1566 | 0.6073 | 0.6672 | 782.0 | 1172.0 | 0.9002 | 0.8781 | 0.8889 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) |
| No log | 7.0 | 49 | 3.6727 | 0.3645 | 0.144 | 0.2966 | 0.296 | 20.38 | 0.0637 | 0.1593 | 0.6108 | 0.6698 | 785.0 | 1172.0 | 0.8987 | 0.8774 | 0.8878 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) |
| No log | 8.0 | 56 | 3.5737 | 0.3586 | 0.146 | 0.2948 | 0.2941 | 20.44 | 0.0632 | 0.1563 | 0.6201 | 0.6766 | 793.0 | 1172.0 | 0.8965 | 0.8762 | 0.8862 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) |
| No log | 9.0 | 63 | 3.5072 | 0.3568 | 0.1486 | 0.2976 | 0.2963 | 20.36 | 0.0598 | 0.1536 | 0.6189 | 0.6758 | 792.0 | 1172.0 | 0.8986 | 0.8769 | 0.8875 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) |
| No log | 10.0 | 70 | 3.4730 | 0.3601 | 0.1515 | 0.3017 | 0.301 | 20.36 | 0.0595 | 0.1544 | 0.6108 | 0.6698 | 785.0 | 1172.0 | 0.8997 | 0.8766 | 0.8879 | roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.0) |
Framework versions
- Transformers 4.53.0
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1