flan-t5-base-finetuned-FOMC

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: 2.2508
• Rouge1: 33.4635
• Rouge2: 20.2223
• Rougel: 30.0686
• Rougelsum: 30.5667
• Gen Len: 19.0

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	10	2.6211	30.3857	18.7991	27.6215	28.1883	19.0
No log	2.0	20	2.5670	30.484	18.1632	27.4386	28.171	19.0
No log	3.0	30	2.5087	29.9232	17.615	26.8812	27.6851	19.0
No log	4.0	40	2.4691	29.9232	17.615	26.8812	27.6851	19.0
No log	5.0	50	2.4427	30.3286	17.7647	27.3411	28.085	19.0
No log	6.0	60	2.4165	30.7106	18.153	27.7262	28.3967	19.0
No log	7.0	70	2.3916	31.0342	18.6915	28.0288	28.757	19.0
No log	8.0	80	2.3753	31.0342	18.6915	28.0288	28.757	19.0
No log	9.0	90	2.3556	31.0342	18.6915	28.0288	28.757	19.0
No log	10.0	100	2.3410	32.0795	19.3562	29.0882	29.5601	19.0
No log	11.0	110	2.3272	32.0795	19.3562	29.0882	29.5601	19.0
No log	12.0	120	2.3180	32.5188	19.5364	29.4727	29.6928	19.0
No log	13.0	130	2.3097	32.5188	19.5364	29.4727	29.4824	19.0
No log	14.0	140	2.3008	32.5188	19.5364	29.4727	29.4824	19.0
No log	15.0	150	2.2947	32.5188	19.5364	29.4727	29.4824	19.0
No log	16.0	160	2.2861	32.5188	19.5364	29.4727	29.4824	19.0
No log	17.0	170	2.2791	33.4635	20.2223	30.0686	30.5667	19.0
No log	18.0	180	2.2755	33.4635	20.2223	30.0686	30.5667	19.0
No log	19.0	190	2.2712	33.4635	20.2223	30.0686	30.5667	19.0
No log	20.0	200	2.2661	33.4635	20.2223	30.0686	30.5667	19.0
No log	21.0	210	2.2623	33.4635	20.2223	30.0686	30.5667	19.0
No log	22.0	220	2.2602	33.4635	20.2223	30.0686	30.5667	19.0
No log	23.0	230	2.2588	33.4635	20.2223	30.0686	30.5667	19.0
No log	24.0	240	2.2561	33.4635	20.2223	30.0686	30.5667	19.0
No log	25.0	250	2.2545	33.4635	20.2223	30.0686	30.5667	19.0
No log	26.0	260	2.2532	33.4635	20.2223	30.0686	30.5667	19.0
No log	27.0	270	2.2526	33.4635	20.2223	30.0686	30.5667	19.0
No log	28.0	280	2.2518	33.4635	20.2223	30.0686	30.5667	19.0
No log	29.0	290	2.2509	33.4635	20.2223	30.0686	30.5667	19.0
No log	30.0	300	2.2508	33.4635	20.2223	30.0686	30.5667	19.0

Framework versions

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