Upload sft_metrics.jsonl with huggingface_hub
Browse files- sft_metrics.jsonl +21 -0
sft_metrics.jsonl
CHANGED
|
@@ -465,3 +465,24 @@
|
|
| 465 |
{"timestamp": 1787701137.0828109, "elapsed_hours": 1.0063372451729244, "event": "train_step", "step": 12390, "epoch": 1, "loss": 1.4357111597061156, "perplexity": 4.202632689331254, "muon_lr": 0.0007759660518983305, "adamw_lr": 1.9399151297458264e-05, "tokens_per_sec": 452455.0824185136, "vram_gb": 2.785654067993164, "tokens_processed": 1623982080}
|
| 466 |
{"timestamp": 1787701144.616603, "elapsed_hours": 1.0084299651781718, "event": "train_step", "step": 12400, "epoch": 1, "loss": 1.4547013711929322, "perplexity": 4.283204186440194, "muon_lr": 0.0007738462280847476, "adamw_lr": 1.9346155702118693e-05, "tokens_per_sec": 451871.7852755369, "vram_gb": 2.363706111907959, "tokens_processed": 1625292800}
|
| 467 |
{"timestamp": 1787701157.4437795, "elapsed_hours": 1.0119930699136521, "event": "validation", "step": 12400, "val_loss": 1.4700533843040466, "val_perplexity": 4.3494673281514, "best_loss": 1.4700533843040466}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 465 |
{"timestamp": 1787701137.0828109, "elapsed_hours": 1.0063372451729244, "event": "train_step", "step": 12390, "epoch": 1, "loss": 1.4357111597061156, "perplexity": 4.202632689331254, "muon_lr": 0.0007759660518983305, "adamw_lr": 1.9399151297458264e-05, "tokens_per_sec": 452455.0824185136, "vram_gb": 2.785654067993164, "tokens_processed": 1623982080}
|
| 466 |
{"timestamp": 1787701144.616603, "elapsed_hours": 1.0084299651781718, "event": "train_step", "step": 12400, "epoch": 1, "loss": 1.4547013711929322, "perplexity": 4.283204186440194, "muon_lr": 0.0007738462280847476, "adamw_lr": 1.9346155702118693e-05, "tokens_per_sec": 451871.7852755369, "vram_gb": 2.363706111907959, "tokens_processed": 1625292800}
|
| 467 |
{"timestamp": 1787701157.4437795, "elapsed_hours": 1.0119930699136521, "event": "validation", "step": 12400, "val_loss": 1.4700533843040466, "val_perplexity": 4.3494673281514, "best_loss": 1.4700533843040466}
|
| 468 |
+
{"timestamp": 1787701165.638289, "elapsed_hours": 1.0142693224218156, "event": "train_step", "step": 12410, "epoch": 1, "loss": 1.4862916493415832, "perplexity": 4.420671684404758, "muon_lr": 0.0007727870956787949, "adamw_lr": 1.9319677391969874e-05, "tokens_per_sec": 449608.4414167814, "vram_gb": 2.785654067993164, "tokens_processed": 1626603520}
|
| 469 |
+
{"timestamp": 1787701173.0709548, "elapsed_hours": 1.016333951883846, "event": "train_step", "step": 12420, "epoch": 1, "loss": 1.4495433402061462, "perplexity": 4.2611681666165335, "muon_lr": 0.0007717284851928328, "adamw_lr": 1.9293212129820823e-05, "tokens_per_sec": 449048.1895020845, "vram_gb": 2.785654067993164, "tokens_processed": 1627914240}
|
| 470 |
+
{"timestamp": 1787701180.4962592, "elapsed_hours": 1.018396536509196, "event": "train_step", "step": 12430, "epoch": 1, "loss": 1.4738389444351196, "perplexity": 4.365963702568849, "muon_lr": 0.0007706703983153945, "adamw_lr": 1.926675995788487e-05, "tokens_per_sec": 448491.1346398662, "vram_gb": 2.785654067993164, "tokens_processed": 1629224960}
|
| 471 |
+
{"timestamp": 1787701188.0146296, "elapsed_hours": 1.0204849725961684, "event": "train_step", "step": 12440, "epoch": 1, "loss": 1.4694536519050598, "perplexity": 4.346859593725946, "muon_lr": 0.0007685558021360463, "adamw_lr": 1.9213895053401157e-05, "tokens_per_sec": 447924.89748114307, "vram_gb": 2.363706111907959, "tokens_processed": 1630535680}
|
| 472 |
+
{"timestamp": 1787701195.439371, "elapsed_hours": 1.0225474008586672, "event": "train_step", "step": 12450, "epoch": 1, "loss": 1.4637502884864808, "perplexity": 4.322138437613616, "muon_lr": 0.0007674992962070169, "adamw_lr": 1.9187482405175425e-05, "tokens_per_sec": 447372.48449168133, "vram_gb": 2.785654067993164, "tokens_processed": 1631846400}
|
| 473 |
+
{"timestamp": 1787701202.866805, "elapsed_hours": 1.0246105769607756, "event": "train_step", "step": 12460, "epoch": 1, "loss": 1.4294869899749756, "perplexity": 4.176556027125744, "muon_lr": 0.0007664433206322666, "adamw_lr": 1.9161083015806667e-05, "tokens_per_sec": 446821.98321335163, "vram_gb": 2.785654067993164, "tokens_processed": 1633157120}
|
| 474 |
+
{"timestamp": 1787701210.3024938, "elapsed_hours": 1.026676046119796, "event": "train_step", "step": 12470, "epoch": 1, "loss": 1.4524687123298645, "perplexity": 4.273651920095053, "muon_lr": 0.0007653878770961272, "adamw_lr": 1.913469692740318e-05, "tokens_per_sec": 446272.711228369, "vram_gb": 2.785654067993164, "tokens_processed": 1634467840}
|
| 475 |
+
{"timestamp": 1787701217.8113143, "elapsed_hours": 1.028761829667621, "event": "train_step", "step": 12480, "epoch": 1, "loss": 1.4556262326240539, "perplexity": 4.287167389218048, "muon_lr": 0.0007632785928727568, "adamw_lr": 1.908196482181892e-05, "tokens_per_sec": 445716.77620214364, "vram_gb": 2.363706111907959, "tokens_processed": 1635778560}
|
| 476 |
+
{"timestamp": 1787701225.2375402, "elapsed_hours": 1.0308246701293522, "event": "train_step", "step": 12490, "epoch": 1, "loss": 1.4789011335372926, "perplexity": 4.388121071523709, "muon_lr": 0.0007622247555499334, "adamw_lr": 1.9055618888748338e-05, "tokens_per_sec": 445173.1362014021, "vram_gb": 2.785654067993164, "tokens_processed": 1637089280}
|
| 477 |
+
{"timestamp": 1787701232.6570258, "elapsed_hours": 1.0328856383429634, "event": "train_step", "step": 12500, "epoch": 1, "loss": 1.4890864324569701, "perplexity": 4.433043783600958, "muon_lr": 0.0007611714569945306, "adamw_lr": 1.9029286424863265e-05, "tokens_per_sec": 444632.46069340664, "vram_gb": 2.785654067993164, "tokens_processed": 1638400000}
|
| 478 |
+
{"timestamp": 1787701240.0837665, "elapsed_hours": 1.0349486217896144, "event": "train_step", "step": 12510, "epoch": 1, "loss": 1.509119621515274, "perplexity": 4.522747311660291, "muon_lr": 0.0007601186988866087, "adamw_lr": 1.9002967472165222e-05, "tokens_per_sec": 444093.1018142096, "vram_gb": 2.785654067993164, "tokens_processed": 1639710720}
|
| 479 |
+
{"timestamp": 1787701247.6037548, "elapsed_hours": 1.0370375073618359, "event": "train_step", "step": 12520, "epoch": 1, "loss": 1.5135452663898468, "perplexity": 4.542807742548187, "muon_lr": 0.0007580148107291392, "adamw_lr": 1.8950370268228482e-05, "tokens_per_sec": 443544.7282686797, "vram_gb": 2.363706111907959, "tokens_processed": 1641021440}
|
| 480 |
+
{"timestamp": 1787701255.021215, "elapsed_hours": 1.0390979130400553, "event": "train_step", "step": 12530, "epoch": 1, "loss": 1.5079632496833801, "perplexity": 4.517520356800452, "muon_lr": 0.0007569636840353921, "adamw_lr": 1.8924092100884804e-05, "tokens_per_sec": 443010.8410462008, "vram_gb": 2.785654067993164, "tokens_processed": 1642332160}
|
| 481 |
+
{"timestamp": 1787701262.4500904, "elapsed_hours": 1.041161489619149, "event": "train_step", "step": 12540, "epoch": 1, "loss": 1.4776013207435608, "perplexity": 4.382421040903384, "muon_lr": 0.0007559131045007221, "adamw_lr": 1.8897827612518053e-05, "tokens_per_sec": 442477.7230854446, "vram_gb": 2.785654067993164, "tokens_processed": 1643642880}
|
| 482 |
+
{"timestamp": 1787701269.8767045, "elapsed_hours": 1.0432244378990596, "event": "train_step", "step": 12550, "epoch": 1, "loss": 1.4950697207450867, "perplexity": 4.459647471953512, "muon_lr": 0.0007548630738008532, "adamw_lr": 1.887157684502133e-05, "tokens_per_sec": 441946.9918225492, "vram_gb": 2.785654067993164, "tokens_processed": 1644953600}
|
| 483 |
+
{"timestamp": 1787701277.3882306, "elapsed_hours": 1.0453109728627734, "event": "train_step", "step": 12560, "epoch": 1, "loss": 1.5219838845729827, "perplexity": 4.581304965801461, "muon_lr": 0.000752764665604034, "adamw_lr": 1.881911664010085e-05, "tokens_per_sec": 441408.3257100037, "vram_gb": 2.363706111907959, "tokens_processed": 1646264320}
|
| 484 |
+
{"timestamp": 1787701284.8145158, "elapsed_hours": 1.0473738299475777, "event": "train_step", "step": 12570, "epoch": 1, "loss": 1.488971425294876, "perplexity": 4.432533981131996, "muon_lr": 0.0007517162914541433, "adamw_lr": 1.8792907286353583e-05, "tokens_per_sec": 440881.8925970514, "vram_gb": 2.785654067993164, "tokens_processed": 1647575040}
|
| 485 |
+
{"timestamp": 1787701292.239834, "elapsed_hours": 1.0494364184141158, "event": "train_step", "step": 12580, "epoch": 1, "loss": 1.4692997932434082, "perplexity": 4.34619084317432, "muon_lr": 0.0007506684728331685, "adamw_lr": 1.8766711820829215e-05, "tokens_per_sec": 440357.66545640735, "vram_gb": 2.785654067993164, "tokens_processed": 1648885760}
|
| 486 |
+
{"timestamp": 1787701299.6716278, "elapsed_hours": 1.051500805483924, "event": "train_step", "step": 12590, "epoch": 1, "loss": 1.5155469322204589, "perplexity": 4.551910032413635, "muon_lr": 0.0007496212114124287, "adamw_lr": 1.874053028531072e-05, "tokens_per_sec": 439834.7350516762, "vram_gb": 2.785654067993164, "tokens_processed": 1650196480}
|
| 487 |
+
{"timestamp": 1787701307.186544, "elapsed_hours": 1.053588282134798, "event": "train_step", "step": 12600, "epoch": 1, "loss": 1.4958340477943421, "perplexity": 4.463057404132164, "muon_lr": 0.00074752836685249, "adamw_lr": 1.868820917131225e-05, "tokens_per_sec": 439304.16239359253, "vram_gb": 2.363706111907959, "tokens_processed": 1651507200}
|
| 488 |
+
{"timestamp": 1787701320.0169647, "elapsed_hours": 1.0571522879600526, "event": "validation", "step": 12600, "val_loss": 1.4698258113861085, "val_perplexity": 4.348477619799736, "best_loss": 1.4698258113861085}
|