robust-camel

This model is a fine-tuned version of Anwaarma/Improved-CAMEL-attempt2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3197
• Accuracy: 0.93

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	0.0546	50	0.3280	0.88
No log	0.1092	100	0.3441	0.87
No log	0.1638	150	0.2609	0.9
No log	0.2183	200	0.2643	0.91
No log	0.2729	250	0.3780	0.93
No log	0.3275	300	0.1840	0.93
No log	0.3821	350	0.2006	0.94
No log	0.4367	400	0.2439	0.92
No log	0.4913	450	0.3146	0.93
0.2322	0.5459	500	0.3726	0.88
0.2322	0.6004	550	0.2331	0.93
0.2322	0.6550	600	0.2121	0.93
0.2322	0.7096	650	0.3261	0.92
0.2322	0.7642	700	0.2385	0.91
0.2322	0.8188	750	0.2052	0.93
0.2322	0.8734	800	0.2409	0.94
0.2322	0.9279	850	0.2545	0.92
0.2322	0.9825	900	0.2751	0.92
0.2322	1.0371	950	0.3859	0.91
0.2005	1.0917	1000	0.2718	0.94
0.2005	1.1463	1050	0.2568	0.92
0.2005	1.2009	1100	0.2847	0.93
0.2005	1.2555	1150	0.3298	0.92
0.2005	1.3100	1200	0.3540	0.91
0.2005	1.3646	1250	0.3197	0.93

Framework versions

• Transformers 4.42.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1