my_custom_ABB_KUKA_model

This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1896
• Bleu: 0.1819
• Gen Len: 20.0

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: 8e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 50
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	1	5.1270	0.1819	20.0
No log	2.0	2	4.6990	0.1819	20.0
No log	3.0	3	4.3339	0.1819	20.0
No log	4.0	4	4.1635	0.1819	20.0
No log	5.0	5	4.0522	0.1819	20.0
No log	6.0	6	3.9550	0.1819	20.0
No log	7.0	7	3.8757	0.1819	20.0
No log	8.0	8	3.7976	0.1819	20.0
No log	9.0	9	3.7234	0.1819	20.0
No log	10.0	10	3.6516	0.1819	20.0
No log	11.0	11	3.5770	0.1819	20.0
No log	12.0	12	3.5103	0.1819	20.0
No log	13.0	13	3.4245	0.1819	20.0
No log	14.0	14	3.3503	0.1819	20.0
No log	15.0	15	3.2882	0.1819	20.0
No log	16.0	16	3.2301	0.1819	20.0
No log	17.0	17	3.1717	0.1819	20.0
No log	18.0	18	3.1134	0.1819	20.0
No log	19.0	19	3.0558	0.1819	20.0
No log	20.0	20	2.9999	0.1819	20.0
No log	21.0	21	2.9451	0.1819	20.0
No log	22.0	22	2.8918	0.1819	20.0
No log	23.0	23	2.8393	0.1819	20.0
No log	24.0	24	2.7904	0.1819	20.0
No log	25.0	25	2.7435	0.1819	20.0
No log	26.0	26	2.6998	0.1819	20.0
No log	27.0	27	2.6575	0.1819	20.0
No log	28.0	28	2.6198	0.1819	20.0
No log	29.0	29	2.5815	0.1819	20.0
No log	30.0	30	2.5459	0.1819	20.0
No log	31.0	31	2.5119	0.1819	20.0
No log	32.0	32	2.4795	0.1819	20.0
No log	33.0	33	2.4505	0.1819	20.0
No log	34.0	34	2.4232	0.1819	20.0
No log	35.0	35	2.3957	0.1819	20.0
No log	36.0	36	2.3701	0.1819	20.0
No log	37.0	37	2.3466	0.1819	20.0
No log	38.0	38	2.3253	0.1819	20.0
No log	39.0	39	2.3055	0.1819	20.0
No log	40.0	40	2.2875	0.1819	20.0
No log	41.0	41	2.2707	0.1819	20.0
No log	42.0	42	2.2556	0.1819	20.0
No log	43.0	43	2.2417	0.1819	20.0
No log	44.0	44	2.2293	0.1819	20.0
No log	45.0	45	2.2182	0.1819	20.0
No log	46.0	46	2.2090	0.1819	20.0
No log	47.0	47	2.2013	0.1819	20.0
No log	48.0	48	2.1955	0.1819	20.0
No log	49.0	49	2.1915	0.1819	20.0
No log	50.0	50	2.1896	0.1819	20.0

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0