Upload sft_metrics.jsonl with huggingface_hub
Browse files- sft_metrics.jsonl +7 -0
sft_metrics.jsonl
CHANGED
|
@@ -613,3 +613,10 @@
|
|
| 613 |
{"timestamp": 1787702282.6746333, "elapsed_hours": 1.3245571959018707, "event": "train_step", "step": 13790, "epoch": 1, "loss": 1.567523717880249, "perplexity": 4.794760301758906, "muon_lr": 0.0005997800697361917, "adamw_lr": 1.4994501743404791e-05, "tokens_per_sec": 381739.5550407514, "vram_gb": 2.785654067993164, "tokens_processed": 1807482880}
|
| 614 |
{"timestamp": 1787702290.2037318, "elapsed_hours": 1.326648612221082, "event": "train_step", "step": 13800, "epoch": 1, "loss": 1.5369046354293823, "perplexity": 4.6501739868649565, "muon_lr": 0.0005978918255827352, "adamw_lr": 1.4947295639568383e-05, "tokens_per_sec": 381409.89003128005, "vram_gb": 2.363706111907959, "tokens_processed": 1808793600}
|
| 615 |
{"timestamp": 1787702303.0311015, "elapsed_hours": 1.3302117705345153, "event": "validation", "step": 13800, "val_loss": 1.469243314266205, "val_perplexity": 4.345945381692539, "best_loss": 1.469243314266205}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 613 |
{"timestamp": 1787702282.6746333, "elapsed_hours": 1.3245571959018707, "event": "train_step", "step": 13790, "epoch": 1, "loss": 1.567523717880249, "perplexity": 4.794760301758906, "muon_lr": 0.0005997800697361917, "adamw_lr": 1.4994501743404791e-05, "tokens_per_sec": 381739.5550407514, "vram_gb": 2.785654067993164, "tokens_processed": 1807482880}
|
| 614 |
{"timestamp": 1787702290.2037318, "elapsed_hours": 1.326648612221082, "event": "train_step", "step": 13800, "epoch": 1, "loss": 1.5369046354293823, "perplexity": 4.6501739868649565, "muon_lr": 0.0005978918255827352, "adamw_lr": 1.4947295639568383e-05, "tokens_per_sec": 381409.89003128005, "vram_gb": 2.363706111907959, "tokens_processed": 1808793600}
|
| 615 |
{"timestamp": 1787702303.0311015, "elapsed_hours": 1.3302117705345153, "event": "validation", "step": 13800, "val_loss": 1.469243314266205, "val_perplexity": 4.345945381692539, "best_loss": 1.469243314266205}
|
| 616 |
+
{"timestamp": 1787702311.0076363, "elapsed_hours": 1.3324274745252398, "event": "train_step", "step": 13810, "epoch": 1, "loss": 1.523507319688797, "perplexity": 4.588289605634553, "muon_lr": 0.000596948904082639, "adamw_lr": 1.4923722602065975e-05, "tokens_per_sec": 380019.1959247719, "vram_gb": 2.785654067993164, "tokens_processed": 1810104320}
|
| 617 |
+
{"timestamp": 1787702318.4299395, "elapsed_hours": 1.3344892254140641, "event": "train_step", "step": 13820, "epoch": 1, "loss": 1.503324989080429, "perplexity": 4.49661543881331, "muon_lr": 0.0005960067849727289, "adamw_lr": 1.4900169624318223e-05, "tokens_per_sec": 379702.69667365693, "vram_gb": 2.785654067993164, "tokens_processed": 1811415040}
|
| 618 |
+
{"timestamp": 1787702325.870532, "elapsed_hours": 1.3365560567378998, "event": "train_step", "step": 13830, "epoch": 1, "loss": 1.5302890419960022, "perplexity": 4.619511862278405, "muon_lr": 0.0005950654697557295, "adamw_lr": 1.487663674389324e-05, "tokens_per_sec": 379385.7383507945, "vram_gb": 2.785654067993164, "tokens_processed": 1812725760}
|
| 619 |
+
{"timestamp": 1787702333.4057932, "elapsed_hours": 1.3386491848362816, "event": "train_step", "step": 13840, "epoch": 1, "loss": 1.52026202917099, "perplexity": 4.573423408496192, "muon_lr": 0.0005931852570049456, "adamw_lr": 1.482963142512364e-05, "tokens_per_sec": 379062.2438900804, "vram_gb": 2.363706111907959, "tokens_processed": 1814036480}
|
| 620 |
+
{"timestamp": 1787702340.8364062, "elapsed_hours": 1.3407132438818614, "event": "train_step", "step": 13850, "epoch": 1, "loss": 1.5673408222198486, "perplexity": 4.793883441096503, "muon_lr": 0.0005922463624701893, "adamw_lr": 1.4806159061754735e-05, "tokens_per_sec": 378748.0534810674, "vram_gb": 2.785654067993164, "tokens_processed": 1815347200}
|
| 621 |
+
{"timestamp": 1787702348.2645802, "elapsed_hours": 1.3427766256862217, "event": "train_step", "step": 13860, "epoch": 1, "loss": 1.5790202796459198, "perplexity": 4.850201641469723, "muon_lr": 0.0005913082778263945, "adamw_lr": 1.4782706945659864e-05, "tokens_per_sec": 378435.0246078503, "vram_gb": 2.785654067993164, "tokens_processed": 1816657920}
|
| 622 |
+
{"timestamp": 1787702355.6916049, "elapsed_hours": 1.344839688009686, "event": "train_step", "step": 13870, "epoch": 1, "loss": 1.5832368564605712, "perplexity": 4.870696067052321, "muon_lr": 0.0005903710045698503, "adamw_lr": 1.4759275114246257e-05, "tokens_per_sec": 378123.0500330998, "vram_gb": 2.785654067993164, "tokens_processed": 1817968640}
|