Upload sft_metrics.jsonl with huggingface_hub
Browse files- sft_metrics.jsonl +3 -0
sft_metrics.jsonl
CHANGED
|
@@ -504,3 +504,6 @@
|
|
| 504 |
{"timestamp": 1787701439.6274204, "elapsed_hours": 1.0903774145576688, "event": "train_step", "step": 12760, "epoch": 1, "loss": 1.48983842253685, "perplexity": 4.43637864228307, "muon_lr": 0.0007267258031833763, "adamw_lr": 1.8168145079584406e-05, "tokens_per_sec": 429742.9809477809, "vram_gb": 2.363706111907959, "tokens_processed": 1672478720}
|
| 505 |
{"timestamp": 1787701447.0443091, "elapsed_hours": 1.092437661488851, "event": "train_step", "step": 12770, "epoch": 1, "loss": 1.4620972335338593, "perplexity": 4.314999607328407, "muon_lr": 0.0007256918165746067, "adamw_lr": 1.814229541436517e-05, "tokens_per_sec": 429261.70020533097, "vram_gb": 2.785654067993164, "tokens_processed": 1673789440}
|
| 506 |
{"timestamp": 1787701454.4717758, "elapsed_hours": 1.0945008465316561, "event": "train_step", "step": 12780, "epoch": 1, "loss": 1.4974453413486482, "perplexity": 4.470254496517094, "muon_lr": 0.0007246584270050152, "adamw_lr": 1.8116460675125384e-05, "tokens_per_sec": 428781.0815400905, "vram_gb": 2.785654067993164, "tokens_processed": 1675100160}
|
|
|
|
|
|
|
|
|
|
|
|
| 504 |
{"timestamp": 1787701439.6274204, "elapsed_hours": 1.0903774145576688, "event": "train_step", "step": 12760, "epoch": 1, "loss": 1.48983842253685, "perplexity": 4.43637864228307, "muon_lr": 0.0007267258031833763, "adamw_lr": 1.8168145079584406e-05, "tokens_per_sec": 429742.9809477809, "vram_gb": 2.363706111907959, "tokens_processed": 1672478720}
|
| 505 |
{"timestamp": 1787701447.0443091, "elapsed_hours": 1.092437661488851, "event": "train_step", "step": 12770, "epoch": 1, "loss": 1.4620972335338593, "perplexity": 4.314999607328407, "muon_lr": 0.0007256918165746067, "adamw_lr": 1.814229541436517e-05, "tokens_per_sec": 429261.70020533097, "vram_gb": 2.785654067993164, "tokens_processed": 1673789440}
|
| 506 |
{"timestamp": 1787701454.4717758, "elapsed_hours": 1.0945008465316561, "event": "train_step", "step": 12780, "epoch": 1, "loss": 1.4974453413486482, "perplexity": 4.470254496517094, "muon_lr": 0.0007246584270050152, "adamw_lr": 1.8116460675125384e-05, "tokens_per_sec": 428781.0815400905, "vram_gb": 2.785654067993164, "tokens_processed": 1675100160}
|
| 507 |
+
{"timestamp": 1787701462.537499, "elapsed_hours": 1.0967413251929814, "event": "train_step", "step": 12790, "epoch": 1, "loss": 1.5109550070762634, "perplexity": 4.531055919188869, "muon_lr": 0.0007236256361229075, "adamw_lr": 1.8090640903072686e-05, "tokens_per_sec": 428232.45731437503, "vram_gb": 2.785654067993164, "tokens_processed": 1676410880}
|
| 508 |
+
{"timestamp": 1787701470.0494027, "elapsed_hours": 1.0988279651933246, "event": "train_step", "step": 12800, "epoch": 1, "loss": 1.4830675089359284, "perplexity": 4.406441770154444, "muon_lr": 0.0007215618570095847, "adamw_lr": 1.803904642523962e-05, "tokens_per_sec": 427746.4768063933, "vram_gb": 2.363706111907959, "tokens_processed": 1677721600}
|
| 509 |
+
{"timestamp": 1787701482.8748226, "elapsed_hours": 1.1023905818329918, "event": "validation", "step": 12800, "val_loss": 1.469779477119446, "val_perplexity": 4.348276140945847, "best_loss": 1.469779477119446}
|