usakha/Prophetnet_GovReport_model

1---2datasets:3- ccdv/govreport-summarization4metrics:5- bleu6- rouge7pipeline_tag: summarization8---9# Hyperparameters10    learning_rate=2e-511    per_device_train_batch_size=1412    per_device_eval_batch_size=1413    weight_decay=0.0114    save_total_limit=315    num_train_epochs=316    predict_with_generate=True17    fp16=True18 19# Training Output20    global_step=3003,21    training_loss=2.5178213735600132,22    metrics={'train_runtime': 8703.174,23    'train_samples_per_second': 4.83,24    'train_steps_per_second': 0.345,25    'total_flos': 9.272950245870797e+16,26    'train_loss': 2.5178213735600132,27    'epoch': 3.0}28 29# Training Results30 31| Epoch	| Training Loss | Validation Loss |  Rouge1  |  Rouge2	|  Rougel  | Rougelsum |   Bleu	  |  Gen Len  |32|:----- |:------------  |:--------------- |:-------- | :------- |:-------- |:--------- |:-------- |:--------- |331|	2.661100|	2.469111|	0.451300|	0.185200|	0.279000|	0.278900|	0.553300|	141.720300|342|	2.434100|	2.403647|	0.456900|	0.192800|	0.284500|	0.284500|	0.556800|	141.763100|353|	2.313700|	2.393932|	0.459500|	0.194400|	0.286300|	0.286200|	0.559200|	141.571600|