oop-de-qg-flan-t5-base-v6

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: 0.7965
• Rouge1: 65.2469
• Rouge2: 52.5016
• Rougel: 63.4057
• Rougelsum: 63.531
• Gen Len: 15.1903
• Bleu: 0.4231
• Precisions: [0.7077429983525535, 0.5410502958579881, 0.4610198061525495, 0.3966699314397649]
• Brevity Penalty: 0.8225
• Length Ratio: 0.8365
• Translation Length: 3035
• Reference Length: 3628

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

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len	Bleu	Precisions	Brevity Penalty	Length Ratio	Translation Length	Reference Length
No log	1.0	233	0.9298	59.4999	45.9581	57.5532	57.7586	14.9094	0.3448	[0.6374833555259654, 0.4552936775158997, 0.3672075149444919, 0.3043262058677275]	0.8124	0.8280	3004	3628
No log	2.0	466	0.8616	58.9163	46.1813	57.3535	57.5989	14.1631	0.3488	[0.6636553161917998, 0.48095798979191207, 0.39620938628158847, 0.3320954907161804]	0.7706	0.7933	2878	3628
1.0446	3.0	699	0.8276	62.7765	50.2006	61.0262	61.1999	14.5952	0.3837	[0.6885413124787487, 0.5160919540229885, 0.42957437472575694, 0.3613963039014374]	0.7917	0.8106	2941	3628
1.0446	4.0	932	0.8107	63.8174	51.0448	61.7972	62.0925	14.9305	0.3969	[0.6949949613705072, 0.5249433106575964, 0.43844492440604754, 0.3719758064516129]	0.8036	0.8206	2977	3628
0.7689	5.0	1165	0.7966	64.5126	51.7002	62.5	62.6287	15.1239	0.4088	[0.6974900924702774, 0.5272525027808677, 0.4437869822485207, 0.3778869778869779]	0.8202	0.8346	3028	3628
0.7689	6.0	1398	0.7986	64.2531	50.9604	62.2618	62.4906	15.3263	0.4077	[0.6919570172582221, 0.5182481751824818, 0.43295973432959733, 0.36766121270452357]	0.8341	0.8465	3071	3628
0.6741	7.0	1631	0.7974	64.9736	52.3108	63.2436	63.3625	15.2175	0.4205	[0.7034233048057933, 0.5386036202438124, 0.45707070707070707, 0.3926650366748166]	0.8235	0.8374	3038	3628
0.6741	8.0	1864	0.7965	65.2469	52.5016	63.4057	63.531	15.1903	0.4231	[0.7077429983525535, 0.5410502958579881, 0.4610198061525495, 0.3966699314397649]	0.8225	0.8365	3035	3628

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1