f0a4179751521b3655365f909c9bbc47

This model is a fine-tuned version of FacebookAI/xlm-roberta-large on the contemmcm/trec dataset. It achieves the following results on the evaluation set:

• Loss: 1.6690
• Data Size: 1.0
• Epoch Runtime: 32.2184
• Accuracy: 0.2771
• F1 Macro: 0.0723

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
• num_devices: 4
• total_train_batch_size: 32
• total_eval_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Data Size	Epoch Runtime	Accuracy	F1 Macro
No log	0	0	1.8516	0	1.3496	0.2271	0.0617
No log	1	170	1.7200	0.0078	1.9180	0.2	0.0706
No log	2	340	1.7027	0.0156	2.7576	0.2604	0.1449
No log	3	510	1.7166	0.0312	4.2365	0.1792	0.0852
No log	4	680	1.6588	0.0625	5.7020	0.2771	0.0723
0.1026	5	850	1.7545	0.125	8.3275	0.1333	0.0392
0.1026	6	1020	1.7429	0.25	11.7692	0.1792	0.0506
1.6479	7	1190	1.8262	0.5	18.6640	0.2521	0.1393
1.6713	8.0	1360	1.6690	1.0	32.2184	0.2771	0.0723

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu128
• Datasets 4.3.0
• Tokenizers 0.22.1