初始化项目，由ModelHub XC社区提供模型

Model: raalr/qwen3-1.7b-arabic-standard-kd-500k-run1 Source: Original Platform
2026-06-13 10:38:16 +08:00
commit 6f6b4b5b96
16 changed files with 525 additions and 0 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,98 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen3-1.7B-Base
+tags:
+- generated_from_trainer
+model-index:
+- name: qwen3-1.7b-arabic-standard-kd-500k-run1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen3-1.7b-arabic-standard-kd-500k-run1
+
+This model is a fine-tuned version of [Qwen/Qwen3-1.7B-Base](https://huggingface.co/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