flan-t5-base-finetuned-xsum

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

• Loss: nan

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	7	nan
No log	2.0	14	nan
No log	3.0	21	nan
No log	4.0	28	nan
No log	5.0	35	nan
No log	6.0	42	nan
No log	7.0	49	nan
No log	8.0	56	nan
No log	9.0	63	nan
No log	10.0	70	nan
No log	11.0	77	nan
No log	12.0	84	nan
No log	13.0	91	nan
No log	14.0	98	nan
No log	15.0	105	nan
No log	16.0	112	nan
No log	17.0	119	nan
No log	18.0	126	nan
No log	19.0	133	nan
No log	20.0	140	nan
No log	21.0	147	nan
No log	22.0	154	nan
No log	23.0	161	nan
No log	24.0	168	nan
No log	25.0	175	nan
No log	26.0	182	nan
No log	27.0	189	nan
No log	28.0	196	nan
No log	29.0	203	nan
No log	30.0	210	nan
No log	31.0	217	nan
No log	32.0	224	nan
No log	33.0	231	nan
No log	34.0	238	nan
No log	35.0	245	nan
No log	36.0	252	nan
No log	37.0	259	nan
No log	38.0	266	nan
No log	39.0	273	nan
No log	40.0	280	nan
No log	41.0	287	nan
No log	42.0	294	nan
No log	43.0	301	nan
No log	44.0	308	nan
No log	45.0	315	nan
No log	46.0	322	nan
No log	47.0	329	nan
No log	48.0	336	nan
No log	49.0	343	nan
No log	50.0	350	nan

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.0
• Tokenizers 0.13.3