metadata

library_name: transformers
license: apache-2.0
base_model: google/long-t5-tglobal-base
tags:
  - generated_from_trainer
metrics:
  - rouge
  - bleu
  - precision
  - recall
  - f1
model-index:
  - name: long_T5_sum_challenge
    results: []

long_T5_sum_challenge

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

Loss: 7.6212
Rouge1: 0.1351
Rouge2: 0.0198
Rougel: 0.1098
Rougelsum: 0.1097
Gen Len: 20.0
Bleu: 0.0
Precisions: 0.0382
Brevity Penalty: 0.516
Length Ratio: 0.6018
Translation Length: 727.0
Reference Length: 1208.0
Precision: 0.8374
Recall: 0.8398
F1: 0.8385
Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)

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: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
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: 12

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	28.1900	0.1279	0.0207	0.1007	0.1007	20.0	0.0	0.0385	0.5476	0.6242	754.0	1208.0	0.8406	0.8397	0.8401	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
No log	2.0	14	25.4058	0.1405	0.0253	0.1073	0.1077	20.0	0.0	0.0427	0.5395	0.6184	747.0	1208.0	0.8426	0.8415	0.842	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
No log	3.0	21	23.2077	0.145	0.0273	0.1108	0.1107	20.0	0.0078	0.045	0.5453	0.6225	752.0	1208.0	0.8434	0.8418	0.8425	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
No log	4.0	28	21.4668	0.1471	0.0265	0.115	0.114	20.0	0.007	0.0437	0.543	0.6209	750.0	1208.0	0.8438	0.8422	0.8429	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
No log	5.0	35	19.9034	0.1508	0.0275	0.1178	0.117	20.0	0.0072	0.0442	0.5453	0.6225	752.0	1208.0	0.8444	0.8425	0.8434	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
No log	6.0	42	18.3550	0.1519	0.0288	0.1197	0.1189	20.0	0.0071	0.0437	0.536	0.6159	744.0	1208.0	0.8446	0.8428	0.8436	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
No log	7.0	49	16.6792	0.1515	0.0289	0.1195	0.1194	20.0	0.0072	0.0442	0.5407	0.6192	748.0	1208.0	0.8453	0.8427	0.8439	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
No log	8.0	56	14.7162	0.1445	0.0228	0.116	0.1157	20.0	0.0	0.0391	0.5348	0.6151	743.0	1208.0	0.8427	0.8409	0.8417	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
No log	9.0	63	12.4721	0.1556	0.0205	0.1205	0.1208	20.0	0.0	0.0391	0.5325	0.6134	741.0	1208.0	0.8449	0.8421	0.8435	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
No log	10.0	70	10.1636	0.1562	0.0263	0.1245	0.1238	20.0	0.0	0.0418	0.5407	0.6192	748.0	1208.0	0.845	0.8433	0.8441	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
No log	11.0	77	8.3358	0.142	0.0231	0.1155	0.1153	20.0	0.0	0.0401	0.5125	0.5993	724.0	1208.0	0.8395	0.8411	0.8402	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
No log	12.0	84	7.6212	0.1351	0.0198	0.1098	0.1097	20.0	0.0	0.0382	0.516	0.6018	727.0	1208.0	0.8374	0.8398	0.8385	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)

Framework versions

Transformers 4.53.1
Pytorch 2.7.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1