expected_model_nov1

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: 0.1943
• Rouge1: 72.751
• Rouge2: 64.531
• Rougel: 71.7809
• Rougelsum: 72.5858
• Gen Len: 16.4797

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: 5e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
11.5118	0.68	200	0.4990	52.9797	43.7182	52.2591	52.9986	9.6068
0.4597	1.36	400	0.2770	71.5492	62.6473	70.6589	71.4471	16.4237
0.3259	2.03	600	0.2486	72.1475	63.0992	71.3032	72.0859	16.3983
0.273	2.71	800	0.2273	71.9258	63.3664	71.1095	71.7798	16.5339
0.2545	3.39	1000	0.2161	72.3257	63.5931	71.5259	72.3231	16.4322
0.2374	4.07	1200	0.2091	72.3551	63.9109	71.5349	72.2473	16.4746
0.2143	4.75	1400	0.2116	72.3027	63.8027	71.6227	72.221	16.439
0.2161	5.42	1600	0.1991	72.3081	63.7819	71.4337	72.2038	16.4712
0.1987	6.1	1800	0.2039	72.4605	64.0889	71.6023	72.3601	16.4864
0.1942	6.78	2000	0.2020	72.458	63.8879	71.4977	72.3096	16.4424
0.1826	7.46	2200	0.2000	72.2467	63.7052	71.3826	72.0909	16.4288
0.1867	8.14	2400	0.1965	72.417	64.0356	71.5254	72.3042	16.4983
0.1773	8.81	2600	0.1930	72.5715	64.1819	71.6728	72.501	16.4797
0.1875	9.49	2800	0.1943	72.751	64.531	71.7809	72.5858	16.4797

Framework versions

• Transformers 4.33.2
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3