gitlab-mr-analysis-default-model_07112024T123200

This model is a fine-tuned version of crest-data-systems/gitlab-mr-analysis-default-model on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.1618
• F1: 0.6102
• Learning Rate: 0.0

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Rate
No log	0.9943	87	3.4729	0.1512	0.0000
No log	2.0	175	1.5854	0.2612	7e-06
No log	2.9943	262	1.3071	0.5194	0.0000
No log	4.0	350	1.1987	0.5696	0.0000
No log	4.9943	437	1.1969	0.5988	0.0000
1.988	6.0	525	1.2367	0.6025	0.0000
1.988	6.9943	612	1.2985	0.6065	0.0000
1.988	8.0	700	1.3981	0.6012	0.0000
1.988	8.9943	787	1.4878	0.6025	0.0000
1.988	10.0	875	1.6375	0.6039	0.0000
1.988	10.9943	962	1.6594	0.6116	0.0000
0.3297	12.0	1050	1.7861	0.6165	0.0000
0.3297	12.9943	1137	1.8770	0.6306	0.0000
0.3297	14.0	1225	1.9764	0.6021	0.0000
0.3297	14.9943	1312	2.0507	0.6134	0.0000
0.3297	16.0	1400	2.1181	0.6007	0.0000
0.3297	16.9943	1487	2.1135	0.6063	0.0000
0.0529	18.0	1575	2.1483	0.6024	0.0000
0.0529	18.9943	1662	2.1560	0.6138	0.0000
0.0529	19.8857	1740	2.1618	0.6102	0.0

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.1+cu124
• Datasets 3.1.0
• Tokenizers 0.19.1