Tallerfn_tun_mod_eval

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: 0.9860
• Accuracy: 0.6033

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: 8
• eval_batch_size: 8
• seed: 42
• distributed_type: multi-GPU
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
1.6114	0.0667	10	1.6586	0.17
1.6304	0.1333	20	1.6123	0.21
1.624	0.2	30	1.5743	0.3333
1.5797	0.2667	40	1.5025	0.3033
1.4557	0.3333	50	1.4998	0.3167
1.4248	0.4	60	1.3585	0.3733
1.4437	0.4667	70	1.3261	0.3667
1.3708	0.5333	80	1.2190	0.4867
1.3241	0.6	90	1.1851	0.5033
1.2215	0.6667	100	1.1758	0.4367
1.2402	0.7333	110	1.1531	0.5
1.2988	0.8	120	1.2693	0.45
1.2319	0.8667	130	1.1528	0.4967
1.2858	0.9333	140	1.2220	0.4533
1.29	1.0	150	1.1693	0.46
1.15	1.0667	160	1.0932	0.4867
1.0675	1.1333	170	1.0833	0.5233
0.9944	1.2	180	1.1199	0.4867
1.0786	1.2667	190	1.0345	0.5567
0.9587	1.3333	200	1.0319	0.5333
0.9182	1.4	210	1.1022	0.52
0.9735	1.4667	220	0.9948	0.5867
0.9342	1.5333	230	0.9837	0.5633
0.9638	1.6	240	1.0709	0.5567
0.9899	1.6667	250	1.0192	0.5967
0.9613	1.7333	260	0.9636	0.57
0.8724	1.8	270	0.9762	0.56
1.0048	1.8667	280	0.9594	0.59
0.9724	1.9333	290	0.9786	0.6033
0.8906	2.0	300	0.9860	0.6033

Framework versions

• Transformers 4.40.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1