This model is a fine-tuned version of Qwen/Qwen2.5-0.5B-Instruct on the gloss_finetune_train dataset. It achieves the following results on the evaluation set:

Loss: 0.3241

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: 0.0001
train_batch_size: 2
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.5830	0.0889	100	0.6260
0.4804	0.1778	200	0.5447
0.5416	0.2667	300	0.5175
0.5262	0.3556	400	0.4651
0.4754	0.4444	500	0.4591
0.4172	0.5333	600	0.4256
0.4155	0.6222	700	0.4044
0.4361	0.7111	800	0.3769
0.3298	0.8	900	0.3677
0.4278	0.8889	1000	0.3614
0.3231	0.9778	1100	0.3458
0.3277	1.0667	1200	0.3407
0.2685	1.1556	1300	0.3311
0.2161	1.2444	1400	0.3358
0.2306	1.3333	1500	0.3352
0.2123	2.8427	1600	0.3250

Framework versions

PEFT 0.18.1
Transformers 5.2.0
Pytorch 2.11.0+cu130
Datasets 3.2.0
Tokenizers 0.22.2

24-mohamedyehia/gloss2text-Qwen2.5-0.5B-ArSL-LoRA

models

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

24-mohamedyehia/
gloss2text-Qwen2.5-0.5B-ArSL-LoRA