gitlab-mr-analysis-default-model_07112024T124024

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: 1.5698
• F1: 0.5908
• 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: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Rate
No log	0.9968	157	1.3933	0.4233	0.0000
No log	2.0	315	1.1736	0.4818	0.0000
No log	2.9968	472	1.0885	0.5673	0.0000
1.4241	4.0	630	1.1164	0.6118	0.0000
1.4241	4.9968	787	1.1692	0.6285	0.0000
1.4241	6.0	945	1.3032	0.6036	0.0000
0.6247	6.9968	1102	1.4004	0.6043	0.0000
0.6247	8.0	1260	1.4752	0.5980	0.0000
0.6247	8.9968	1417	1.5317	0.5985	0.0000
0.2719	9.9683	1570	1.5698	0.5908	0.0

Framework versions

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