🔒 Permission Denied — Role Viewer has limited access. Some actions are disabled.
Fine-Tuning Hub
Browse and launch fine-tuning jobs on pre-trained models.
🔧
5,968
Total Jobs
▶️
2,282
Running
✅
3,205
Completed
❌
3,550
Failed
| Name | Status | Base Model | Method | Dataset | GPU Type | Epoch | Loss | |
|---|---|---|---|---|---|---|---|---|
| full-llama-31 | Completed | bert-large | QLoRA | dolly-5 | H100-80G | 6/16 | 1.0291 | |
| adapter-bert-17 | Failed | codellama-34b | Full Fine-Tune | custom-14 | A100-80G | 5/11 | 0.5218 | |
| adapter-mistral-82 | Running | mistral-7b | Full Fine-Tune | alpaca-20 | H100-80G | 10/10 | 1.1245 | |
| qlora-gpt-12 | Running | bert-large | LoRA | squad-18 | A100-80G | 5/20 | 0.5266 | |
| lora-llama-93 | Running | bert-large | QLoRA | squad-14 | A100-80G | 6/5 | 1.0686 | |
| adapter-gpt-48 | Running | mistral-7b | Adapter | custom-8 | A100-80G | 1/6 | 0.1763 | |
| qlora-bert-40 | Failed | bert-large | LoRA | alpaca-18 | H100-80G | 10/11 | 1.1759 | |
| adapter-gpt-40 | Running | llama-3.1-70b | Adapter | alpaca-9 | A100-80G | 3/8 | 1.5107 | |
| lora-bert-24 | Completed | codellama-34b | QLoRA | custom-1 | H100-80G | 7/14 | 0.5285 | |
| lora-gpt-45 | Running | codellama-34b | Adapter | dolly-7 | H100-80G | 9/8 | 0.2211 |