Upload sft_metrics.jsonl with huggingface_hub
Browse files- sft_metrics.jsonl +21 -0
sft_metrics.jsonl
CHANGED
|
@@ -592,3 +592,24 @@
|
|
| 592 |
{"timestamp": 1787702120.375381, "elapsed_hours": 1.2794740702708562, "event": "train_step", "step": 13590, "epoch": 1, "loss": 1.480308976173401, "perplexity": 4.394303206175885, "muon_lr": 0.000623648483889721, "adamw_lr": 1.5591212097243025e-05, "tokens_per_sec": 389556.1060916778, "vram_gb": 2.785654067993164, "tokens_processed": 1781268480}
|
| 593 |
{"timestamp": 1787702127.892107, "elapsed_hours": 1.281562049653795, "event": "train_step", "step": 13600, "epoch": 1, "loss": 1.452657709121704, "perplexity": 4.2744597029291675, "muon_lr": 0.0006217212184585353, "adamw_lr": 1.5543030461463386e-05, "tokens_per_sec": 389202.9482366352, "vram_gb": 2.363706111907959, "tokens_processed": 1782579200}
|
| 594 |
{"timestamp": 1787702140.7189462, "elapsed_hours": 1.2851250607437557, "event": "validation", "step": 13600, "val_loss": 1.469328236579895, "val_perplexity": 4.34631446510101, "best_loss": 1.469328236579895}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 592 |
{"timestamp": 1787702120.375381, "elapsed_hours": 1.2794740702708562, "event": "train_step", "step": 13590, "epoch": 1, "loss": 1.480308976173401, "perplexity": 4.394303206175885, "muon_lr": 0.000623648483889721, "adamw_lr": 1.5591212097243025e-05, "tokens_per_sec": 389556.1060916778, "vram_gb": 2.785654067993164, "tokens_processed": 1781268480}
|
| 593 |
{"timestamp": 1787702127.892107, "elapsed_hours": 1.281562049653795, "event": "train_step", "step": 13600, "epoch": 1, "loss": 1.452657709121704, "perplexity": 4.2744597029291675, "muon_lr": 0.0006217212184585353, "adamw_lr": 1.5543030461463386e-05, "tokens_per_sec": 389202.9482366352, "vram_gb": 2.363706111907959, "tokens_processed": 1782579200}
|
| 594 |
{"timestamp": 1787702140.7189462, "elapsed_hours": 1.2851250607437557, "event": "validation", "step": 13600, "val_loss": 1.469328236579895, "val_perplexity": 4.34631446510101, "best_loss": 1.469328236579895}
|
| 595 |
+
{"timestamp": 1787702148.6125274, "elapsed_hours": 1.2873177220424017, "event": "train_step", "step": 13610, "epoch": 1, "loss": 1.4649865460395812, "perplexity": 4.327485018096969, "muon_lr": 0.0006207587292904938, "adamw_lr": 1.5518968232262344e-05, "tokens_per_sec": 387735.0065035273, "vram_gb": 2.785654067993164, "tokens_processed": 1783889920}
|
| 596 |
+
{"timestamp": 1787702156.0394292, "elapsed_hours": 1.2893807502587635, "event": "train_step", "step": 13620, "epoch": 1, "loss": 1.4629065608978271, "perplexity": 4.318493268153083, "muon_lr": 0.0006197970045348454, "adamw_lr": 1.5494925113371136e-05, "tokens_per_sec": 387394.5385570256, "vram_gb": 2.785654067993164, "tokens_processed": 1785200640}
|
| 597 |
+
{"timestamp": 1787702163.4665365, "elapsed_hours": 1.2914438356955846, "event": "train_step", "step": 13630, "epoch": 1, "loss": 1.4441556203365327, "perplexity": 4.238271920881618, "muon_lr": 0.0006188360457255877, "adamw_lr": 1.5470901143139692e-05, "tokens_per_sec": 387055.15019015915, "vram_gb": 2.785654067993164, "tokens_processed": 1786511360}
|
| 598 |
+
{"timestamp": 1787702170.9798992, "elapsed_hours": 1.2935308808750576, "event": "train_step", "step": 13640, "epoch": 1, "loss": 1.4989068078994752, "perplexity": 4.476792400237554, "muon_lr": 0.0006169164320761162, "adamw_lr": 1.5422910801902905e-05, "tokens_per_sec": 386709.6310792772, "vram_gb": 2.363706111907959, "tokens_processed": 1787822080}
|
| 599 |
+
{"timestamp": 1787702178.405085, "elapsed_hours": 1.2955934324529437, "event": "train_step", "step": 13650, "epoch": 1, "loss": 1.5169632530212402, "perplexity": 4.558361564917207, "muon_lr": 0.0006159577802977762, "adamw_lr": 1.5398944507444408e-05, "tokens_per_sec": 386372.6003619629, "vram_gb": 2.785654067993164, "tokens_processed": 1789132800}
|
| 600 |
+
{"timestamp": 1787702185.8306427, "elapsed_hours": 1.2976560874117746, "event": "train_step", "step": 13660, "epoch": 1, "loss": 1.511555073261261, "perplexity": 4.533775668561512, "muon_lr": 0.0006149999005895702, "adamw_lr": 1.537499751473926e-05, "tokens_per_sec": 386036.61420064676, "vram_gb": 2.785654067993164, "tokens_processed": 1790443520}
|
| 601 |
+
{"timestamp": 1787702193.2593272, "elapsed_hours": 1.2997196108102798, "event": "train_step", "step": 13670, "epoch": 1, "loss": 1.4824480640888213, "perplexity": 4.403713067733425, "muon_lr": 0.0006140427944793605, "adamw_lr": 1.5351069861984015e-05, "tokens_per_sec": 385701.44052410993, "vram_gb": 2.785654067993164, "tokens_processed": 1791754240}
|
| 602 |
+
{"timestamp": 1787702200.7793767, "elapsed_hours": 1.301808513601621, "event": "train_step", "step": 13680, "epoch": 1, "loss": 1.459892097711563, "perplexity": 4.305494930524215, "muon_lr": 0.000612130909158213, "adamw_lr": 1.5303272728955328e-05, "tokens_per_sec": 385359.77399080986, "vram_gb": 2.363706111907959, "tokens_processed": 1793064960}
|
| 603 |
+
{"timestamp": 1787702208.2024744, "elapsed_hours": 1.303870485027631, "event": "train_step", "step": 13690, "epoch": 1, "loss": 1.438989781141281, "perplexity": 4.21643414345923, "muon_lr": 0.000611176132996822, "adamw_lr": 1.5279403324920547e-05, "tokens_per_sec": 385027.2192268999, "vram_gb": 2.785654067993164, "tokens_processed": 1794375680}
|
| 604 |
+
{"timestamp": 1787702215.631259, "elapsed_hours": 1.305934036374092, "event": "train_step", "step": 13700, "epoch": 1, "loss": 1.4208887588977814, "perplexity": 4.140798977277979, "muon_lr": 0.0006102221365325165, "adamw_lr": 1.5255553413312913e-05, "tokens_per_sec": 384695.24791416794, "vram_gb": 2.785654067993164, "tokens_processed": 1795686400}
|
| 605 |
+
{"timestamp": 1787702223.0526838, "elapsed_hours": 1.3079955432150099, "event": "train_step", "step": 13710, "epoch": 1, "loss": 1.4001616978645324, "perplexity": 4.055855737036456, "muon_lr": 0.0006092689212869669, "adamw_lr": 1.5231723032174172e-05, "tokens_per_sec": 384364.93788700603, "vram_gb": 2.785654067993164, "tokens_processed": 1796997120}
|
| 606 |
+
{"timestamp": 1787702230.5747216, "elapsed_hours": 1.3100849980778164, "event": "train_step", "step": 13720, "epoch": 1, "loss": 1.4196108210086822, "perplexity": 4.135510673155581, "muon_lr": 0.0006073648405325779, "adamw_lr": 1.518412101331445e-05, "tokens_per_sec": 384027.42319318425, "vram_gb": 2.363706111907959, "tokens_processed": 1798307840}
|
| 607 |
+
{"timestamp": 1787702238.0014791, "elapsed_hours": 1.3121479863590664, "event": "train_step", "step": 13730, "epoch": 1, "loss": 1.4684210336208343, "perplexity": 4.342373263762327, "muon_lr": 0.0006064139780608368, "adamw_lr": 1.5160349451520923e-05, "tokens_per_sec": 383698.7936253437, "vram_gb": 2.785654067993164, "tokens_processed": 1799618560}
|
| 608 |
+
{"timestamp": 1787702245.4315813, "elapsed_hours": 1.3142119036780464, "event": "train_step", "step": 13740, "epoch": 1, "loss": 1.4416601264476776, "perplexity": 4.227708525130476, "muon_lr": 0.0006054639028820435, "adamw_lr": 1.5136597572051089e-05, "tokens_per_sec": 383370.9244261761, "vram_gb": 2.785654067993164, "tokens_processed": 1800929280}
|
| 609 |
+
{"timestamp": 1787702252.8668363, "elapsed_hours": 1.316277252237002, "event": "train_step", "step": 13750, "epoch": 1, "loss": 1.492201830148697, "perplexity": 4.446876013232221, "muon_lr": 0.0006045146165116124, "adamw_lr": 1.5112865412790309e-05, "tokens_per_sec": 383043.6714612604, "vram_gb": 2.785654067993164, "tokens_processed": 1802240000}
|
| 610 |
+
{"timestamp": 1787702260.3848083, "elapsed_hours": 1.3183655777904721, "event": "train_step", "step": 13760, "epoch": 1, "loss": 1.5297790050506592, "perplexity": 4.617156341311615, "muon_lr": 0.0006026184162512011, "adamw_lr": 1.5065460406280031e-05, "tokens_per_sec": 382710.73021772143, "vram_gb": 2.363706111907959, "tokens_processed": 1803550720}
|
| 611 |
+
{"timestamp": 1787702267.8154674, "elapsed_hours": 1.3204296497503916, "event": "train_step", "step": 13770, "epoch": 1, "loss": 1.543414089679718, "perplexity": 4.680542816708026, "muon_lr": 0.0006016715053857502, "adamw_lr": 1.5041787634643756e-05, "tokens_per_sec": 382385.9337292264, "vram_gb": 2.785654067993164, "tokens_processed": 1804861440}
|
| 612 |
+
{"timestamp": 1787702275.2505755, "elapsed_hours": 1.322494957645734, "event": "train_step", "step": 13780, "epoch": 1, "loss": 1.5230266308784486, "perplexity": 4.586084596166634, "muon_lr": 0.0006007253893777136, "adamw_lr": 1.5018134734442842e-05, "tokens_per_sec": 382061.7887386112, "vram_gb": 2.785654067993164, "tokens_processed": 1806172160}
|
| 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}
|