bert_C_2

This model is a fine-tuned version of bert-base-cased on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 6722.5049
• Mae: 52.1614

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: 2.5e-05
• train_batch_size: 72
• eval_batch_size: 72
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Mae
No log	1.0	51	8283.7012	62.4105
No log	2.0	102	7761.8237	58.8175
No log	3.0	153	7552.2861	57.4051
No log	4.0	204	7422.1416	56.5480
No log	5.0	255	7319.2437	55.8786
No log	6.0	306	7231.1514	55.3173
No log	7.0	357	7153.9229	54.8313
No log	8.0	408	7085.3296	54.4032
No log	9.0	459	7023.9609	54.0201
8468.761	10.0	510	6969.4009	53.6830
8468.761	11.0	561	6920.9131	53.3808
8468.761	12.0	612	6878.1675	53.1132
8468.761	13.0	663	6841.0210	52.8787
8468.761	14.0	714	6809.2080	52.6846
8468.761	15.0	765	6782.4966	52.5224
8468.761	16.0	816	6760.8091	52.3901
8468.761	17.0	867	6744.0356	52.2873
8468.761	18.0	918	6732.0830	52.2164
8468.761	19.0	969	6724.9185	52.1753
7734.004	20.0	1020	6722.5049	52.1614

Framework versions

• Transformers 4.37.1
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1