qwen3-1.7b-arabic-standard-kd-500k-run1/README.md

library_name, license, base_model, tags, model-index

library_name	license	base_model	tags	model-index
transformers	apache-2.0	Qwen/Qwen3-1.7B-Base	generated_from_trainer	name results qwen3-1.7b-arabic-standard-kd-500k-run1

qwen3-1.7b-arabic-standard-kd-500k-run1

This model is a fine-tuned version of Qwen/Qwen3-1.7B-Base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2204

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: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH 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: 0.05
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss
14.6668	0.08	500	1.8397
12.1563	0.16	1000	1.4620
11.3135	0.24	1500	1.3525
9.9210	0.32	2000	1.3104
10.3060	0.4	2500	1.2888
10.0837	0.48	3000	1.2734
9.9288	0.56	3500	1.2624
9.7258	0.64	4000	1.2535
10.5379	0.72	4500	1.2467
9.6359	0.8	5000	1.2411
9.7599	0.88	5500	1.2378
9.5537	0.96	6000	1.2341
8.9824	1.04	6500	1.2330
9.1426	1.12	7000	1.2301
9.1812	1.2	7500	1.2278
9.5528	1.28	8000	1.2263
9.5329	1.3600	8500	1.2253
9.7780	1.44	9000	1.2244
9.0461	1.52	9500	1.2233
9.1856	1.6	10000	1.2225
9.5591	1.6800	10500	1.2218
9.4817	1.76	11000	1.2216
9.1887	1.8400	11500	1.2214
9.2712	1.92	12000	1.2209
9.4848	2.0	12500	1.2207
9.4791	2.08	13000	1.2208
9.0451	2.16	13500	1.2207
9.2963	2.24	14000	1.2206
9.2480	2.32	14500	1.2205
9.5312	2.4	15000	1.2204
9.6915	2.48	15500	1.2205
9.7962	2.56	16000	1.2204
9.4335	2.64	16500	1.2205
9.7608	2.7200	17000	1.2203
9.4249	2.8	17500	1.2204
9.5159	2.88	18000	1.2204
8.9972	2.96	18500	1.2205
9.3566	3.0	18750	1.2204

Framework versions

• Transformers 5.4.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.4
• Tokenizers 0.22.2