This model is a fine-tuned version of Qwen/Qwen2.5-1.5B-Instruct on the masri_mt_train dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4435 | 0.1902 | 250 | 1.4625 |
| 1.4275 | 0.3804 | 500 | 1.3892 |
| 1.4364 | 0.5707 | 750 | 1.2964 |
| 1.3305 | 0.7609 | 1000 | 1.3135 |
| 1.2944 | 0.9511 | 1250 | 1.2123 |
| 1.1027 | 1.1408 | 1500 | 1.1593 |
| 1.0091 | 1.3310 | 1750 | 1.0794 |
| 0.9850 | 1.5212 | 2000 | 1.0165 |
| 0.9172 | 1.7114 | 2250 | 0.9542 |
| 0.8544 | 1.9017 | 2500 | 0.8973 |
| 0.5629 | 2.0913 | 2750 | 0.8865 |
| 0.5548 | 2.2815 | 3000 | 0.8515 |
| 0.5164 | 2.4718 | 3250 | 0.8300 |
| 0.4951 | 2.6620 | 3500 | 0.8165 |
| 0.5091 | 2.8522 | 3750 | 0.8102 |
| 0.4613 | 3.0 | 3945 | 0.8088 |
adapter_model.safetensors 295 MBtraining_args.bin 6 kBQwen/Qwen2.5-1.5B-Instruct