opt-125m-synthetic-finetuned3

This model is a fine-tuned version of facebook/opt-125m on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.3087

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: 1
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	1	8.7103
No log	2.0	2	5.6817
No log	3.0	3	4.5453
No log	4.0	4	4.2713
No log	5.0	5	4.1090
No log	6.0	6	3.9754
No log	7.0	7	3.8689
No log	8.0	8	3.7827
No log	9.0	9	3.7025
No log	10.0	10	3.6302
No log	11.0	11	3.5675
No log	12.0	12	3.5126
No log	13.0	13	3.4654
No log	14.0	14	3.4253
No log	15.0	15	3.3916
No log	16.0	16	3.3640
No log	17.0	17	3.3420
No log	18.0	18	3.3255
No log	19.0	19	3.3143
No log	20.0	20	3.3087

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0