You can deploy this model and start earning money today!

mohammedkhas/
customized-ar-translator_1.5B_d1

Name: customized-ar-translator_1.5B_d1
Availability: InStock

Qwen/Qwen2.5-1.5B-Instruct

apache-2.0

Views

No views yet

customized-ar-translator_1.5B_d1

This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the trans_finetune_train dataset. It achieves the following results on the evaluation set:

Loss: 0.6304

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: 3
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 3
total_train_batch_size: 9
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_ratio: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.951	0.2	10	0.8807
0.8366	0.4	20	0.8009
0.7447	0.6	30	0.7536
0.7792	0.8	40	0.7192
0.7695	1.0	50	0.6943
0.6191	1.2	60	0.6769
0.589	1.4	70	0.6586
0.5886	1.6	80	0.6539
0.5715	1.8	90	0.6405
0.5954	2.0	100	0.6322
0.4942	2.2	110	0.6348
0.4583	2.4	120	0.6358
0.4807	2.6	130	0.6314
0.5074	2.8	140	0.6306
0.4912	3.0	150	0.6304

Framework versions

PEFT 0.17.1
Transformers 4.57.1
Pytorch 2.9.0+cu126
Datasets 4.0.0
Tokenizers 0.22.1

mohammedkhas/customized-ar-translator_1.5B_d1

customized-ar-translator_1.5B_d1

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

mohammedkhas/
customized-ar-translator_1.5B_d1