gitlab-mr-analysis-default-model_07112024T112848

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: 1.4370
• F1: 0.6019
• Learning Rate: 1e-07

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: 10
• 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	1.2343	0.6066	0.0000
1.988	6.9943	612	1.2930	0.6052	0.0000
1.988	8.0	700	1.3840	0.6037	0.0000
1.988	8.9943	787	1.4193	0.5945	0.0000
1.988	9.9429	870	1.4370	0.6019	1e-07

Framework versions

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