Download artifacts/tiny/training-report.json from devildasdf/NEXORA: direct link, hf CLI and curl.
- Browser
- Download file 2.18 kB
-
https://huggingface.co/devildasdf/NEXORA/resolve/main/artifacts/tiny/training-report.json
- Command line
-
hf download hf://devildasdf/NEXORA/artifacts/tiny/training-report.json
-
curl -L -o training-report.json https://huggingface.co/devildasdf/NEXORA/resolve/main/artifacts/tiny/training-report.json
2.18 kB
| { | |
| "status": "VALIDATED_SMALL_TRAINING_ONLY", | |
| "parameters": 820736, | |
| "device": "cpu", | |
| "elapsed_seconds": 15.017452800064348, | |
| "tokens_per_second_including_eval_and_checkpoints": 8182.479521392168, | |
| "peak_vram_bytes": null, | |
| "steps_completed": 120, | |
| "metadata": { | |
| "data_manifest_sha256": "999e69022adc29c9d1ccb4c787900aa0c2bd79dd30259d0b2eeafeb1f98b1b1a", | |
| "training": { | |
| "steps": 120, | |
| "batch_size": 8, | |
| "sequence_length": 128, | |
| "learning_rate": 0.0005, | |
| "seed": 42, | |
| "eval_every": 20, | |
| "checkpoint_every": 40, | |
| "device": "auto", | |
| "threads": 4 | |
| }, | |
| "experiment_id": "391ba7962b714390ad4eaedf35d13ee5" | |
| }, | |
| "metrics": [ | |
| { | |
| "step": 1, | |
| "train_loss": 5.5218987464904785, | |
| "validation_loss": 5.294267177581787, | |
| "grad_norm": 6.178246974945068, | |
| "lr": 0.0005 | |
| }, | |
| { | |
| "step": 20, | |
| "train_loss": 3.742738723754883, | |
| "validation_loss": 4.077296733856201, | |
| "grad_norm": 2.3472182750701904, | |
| "lr": 0.00047273385034894217 | |
| }, | |
| { | |
| "step": 40, | |
| "train_loss": 2.6784613132476807, | |
| "validation_loss": 3.4821360111236572, | |
| "grad_norm": 1.4373022317886353, | |
| "lr": 0.0003925621770610885 | |
| }, | |
| { | |
| "step": 60, | |
| "train_loss": 2.0638818740844727, | |
| "validation_loss": 3.3395001888275146, | |
| "grad_norm": 2.702136278152466, | |
| "lr": 0.00028088981336927144 | |
| }, | |
| { | |
| "step": 80, | |
| "train_loss": 1.5123050212860107, | |
| "validation_loss": 3.2726292610168457, | |
| "grad_norm": 2.4991934299468994, | |
| "lr": 0.0001676392789415881 | |
| }, | |
| { | |
| "step": 100, | |
| "train_loss": 1.6528286933898926, | |
| "validation_loss": 3.239670515060425, | |
| "grad_norm": 1.6973609924316406, | |
| "lr": 8.315596302032927e-05 | |
| }, | |
| { | |
| "step": 120, | |
| "train_loss": 1.0740044116973877, | |
| "validation_loss": 3.209406614303589, | |
| "grad_norm": 1.9410029649734497, | |
| "lr": 5.007710188049962e-05 | |
| } | |
| ], | |
| "limitations": "Tiny educational corpus; no general assistant, reasoning or coding capability claim" | |
| } |