Bc-AI commited on
Commit
8fb876b
·
verified ·
1 Parent(s): 665a073

Upload sft_metrics.jsonl with huggingface_hub

Browse files
Files changed (1) hide show
  1. sft_metrics.jsonl +21 -0
sft_metrics.jsonl CHANGED
@@ -550,3 +550,24 @@
550
  {"timestamp": 1787701794.604521, "elapsed_hours": 1.1889821646610896, "event": "train_step", "step": 13190, "epoch": 1, "loss": 1.5149031257629395, "perplexity": 4.548980426491515, "muon_lr": 0.0006727855589664301, "adamw_lr": 1.6819638974160752e-05, "tokens_per_sec": 407093.4079012492, "vram_gb": 2.785654067993164, "tokens_processed": 1728839680}
551
  {"timestamp": 1787701802.1167324, "elapsed_hours": 1.1910688900285298, "event": "train_step", "step": 13200, "epoch": 1, "loss": 1.5492931890487671, "perplexity": 4.708141240474241, "muon_lr": 0.0006707860513822959, "adamw_lr": 1.6769651284557397e-05, "tokens_per_sec": 406682.65638820984, "vram_gb": 2.363706111907959, "tokens_processed": 1730150400}
552
  {"timestamp": 1787701814.9425266, "elapsed_hours": 1.1946316106451882, "event": "validation", "step": 13200, "val_loss": 1.46947806596756, "val_perplexity": 4.346965719523222, "best_loss": 1.46947806596756}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
550
  {"timestamp": 1787701794.604521, "elapsed_hours": 1.1889821646610896, "event": "train_step", "step": 13190, "epoch": 1, "loss": 1.5149031257629395, "perplexity": 4.548980426491515, "muon_lr": 0.0006727855589664301, "adamw_lr": 1.6819638974160752e-05, "tokens_per_sec": 407093.4079012492, "vram_gb": 2.785654067993164, "tokens_processed": 1728839680}
551
  {"timestamp": 1787701802.1167324, "elapsed_hours": 1.1910688900285298, "event": "train_step", "step": 13200, "epoch": 1, "loss": 1.5492931890487671, "perplexity": 4.708141240474241, "muon_lr": 0.0006707860513822959, "adamw_lr": 1.6769651284557397e-05, "tokens_per_sec": 406682.65638820984, "vram_gb": 2.363706111907959, "tokens_processed": 1730150400}
552
  {"timestamp": 1787701814.9425266, "elapsed_hours": 1.1946316106451882, "event": "validation", "step": 13200, "val_loss": 1.46947806596756, "val_perplexity": 4.346965719523222, "best_loss": 1.46947806596756}
553
+ {"timestamp": 1787701823.0257995, "elapsed_hours": 1.1968769643041823, "event": "train_step", "step": 13210, "epoch": 1, "loss": 1.565266489982605, "perplexity": 4.7839496406962265, "muon_lr": 0.0006697873237178631, "adamw_lr": 1.6744683092946578e-05, "tokens_per_sec": 405000.2553583233, "vram_gb": 2.785654067993164, "tokens_processed": 1731461120}
554
+ {"timestamp": 1787701830.467249, "elapsed_hours": 1.1989440335167778, "event": "train_step", "step": 13220, "epoch": 1, "loss": 1.54177241563797, "perplexity": 4.672865194865112, "muon_lr": 0.0006687892822629067, "adamw_lr": 1.6719732056572666e-05, "tokens_per_sec": 404602.58768980746, "vram_gb": 2.785654067993164, "tokens_processed": 1732771840}
555
+ {"timestamp": 1787701837.8964224, "elapsed_hours": 1.2010076928801006, "event": "train_step", "step": 13230, "epoch": 1, "loss": 1.5034008359909057, "perplexity": 4.496956506136234, "muon_lr": 0.0006677919286093508, "adamw_lr": 1.669479821523377e-05, "tokens_per_sec": 404207.45836482785, "vram_gb": 2.785654067993164, "tokens_processed": 1734082560}
556
+ {"timestamp": 1787701845.406328, "elapsed_hours": 1.2030937778287463, "event": "train_step", "step": 13240, "epoch": 1, "loss": 1.4952646851539613, "perplexity": 4.460517029250278, "muon_lr": 0.0006657992910686438, "adamw_lr": 1.6644982276716094e-05, "tokens_per_sec": 403806.10408924415, "vram_gb": 2.363706111907959, "tokens_processed": 1735393280}
557
+ {"timestamp": 1787701852.8332076, "elapsed_hours": 1.2051567998859618, "event": "train_step", "step": 13250, "epoch": 1, "loss": 1.4392117953300476, "perplexity": 4.217370355587421, "muon_lr": 0.0006648040103598428, "adamw_lr": 1.6620100258996072e-05, "tokens_per_sec": 403413.93536444736, "vram_gb": 2.785654067993164, "tokens_processed": 1736704000}
558
+ {"timestamp": 1787701860.259306, "elapsed_hours": 1.20721960498227, "event": "train_step", "step": 13260, "epoch": 1, "loss": 1.466341553926468, "perplexity": 4.3333527689534295, "muon_lr": 0.000663809423809139, "adamw_lr": 1.6595235595228476e-05, "tokens_per_sec": 403023.18999189686, "vram_gb": 2.785654067993164, "tokens_processed": 1738014720}
559
+ {"timestamp": 1787701867.6865542, "elapsed_hours": 1.209282729493247, "event": "train_step", "step": 13270, "epoch": 1, "loss": 1.4760970866680145, "perplexity": 4.375833809451361, "muon_lr": 0.0006628155330029436, "adamw_lr": 1.657038832507359e-05, "tokens_per_sec": 402633.67946812906, "vram_gb": 2.785654067993164, "tokens_processed": 1739325440}
560
+ {"timestamp": 1787701875.2070482, "elapsed_hours": 1.2113717555337482, "event": "train_step", "step": 13280, "epoch": 1, "loss": 1.4556068909168243, "perplexity": 4.287084468883474, "muon_lr": 0.0006608298449641774, "adamw_lr": 1.6520746124104437e-05, "tokens_per_sec": 402236.83513927757, "vram_gb": 2.363706111907959, "tokens_processed": 1740636160}
561
+ {"timestamp": 1787701882.6270087, "elapsed_hours": 1.2134328558047613, "event": "train_step", "step": 13290, "epoch": 1, "loss": 1.4615897691249848, "perplexity": 4.312810454109033, "muon_lr": 0.0006598380508988728, "adamw_lr": 1.6495951272471822e-05, "tokens_per_sec": 401850.6977936871, "vram_gb": 2.785654067993164, "tokens_processed": 1741946880}
562
+ {"timestamp": 1787701890.0543995, "elapsed_hours": 1.2154960198534859, "event": "train_step", "step": 13300, "epoch": 1, "loss": 1.5296158182621002, "perplexity": 4.616402943869929, "muon_lr": 0.0006588469589126034, "adamw_lr": 1.6471173972815085e-05, "tokens_per_sec": 401465.1855085789, "vram_gb": 2.785654067993164, "tokens_processed": 1743257600}
563
+ {"timestamp": 1787701897.4784462, "elapsed_hours": 1.2175582549969355, "event": "train_step", "step": 13310, "epoch": 1, "loss": 1.5347206282615662, "perplexity": 4.640029055879561, "muon_lr": 0.0006578565705862087, "adamw_lr": 1.6446414264655218e-05, "tokens_per_sec": 401081.29891141906, "vram_gb": 2.785654067993164, "tokens_processed": 1744568320}
564
+ {"timestamp": 1787701904.9941401, "elapsed_hours": 1.2196459477477604, "event": "train_step", "step": 13320, "epoch": 1, "loss": 1.5355285024642944, "perplexity": 4.6437791302439235, "muon_lr": 0.0006558779112307793, "adamw_lr": 1.6396947780769486e-05, "tokens_per_sec": 400690.2874326077, "vram_gb": 2.363706111907959, "tokens_processed": 1745879040}
565
+ {"timestamp": 1787701912.4180868, "elapsed_hours": 1.221708155208164, "event": "train_step", "step": 13330, "epoch": 1, "loss": 1.5805455231666565, "perplexity": 4.857605024643501, "muon_lr": 0.0006548896433577998, "adamw_lr": 1.6372241083944998e-05, "tokens_per_sec": 400309.0505602711, "vram_gb": 2.785654067993164, "tokens_processed": 1747189760}
566
+ {"timestamp": 1787701919.8406222, "elapsed_hours": 1.223769970536232, "event": "train_step", "step": 13340, "epoch": 1, "loss": 1.5579882621765138, "perplexity": 4.749257367676303, "muon_lr": 0.0006539020854567994, "adamw_lr": 1.6347552136419987e-05, "tokens_per_sec": 399929.22470431397, "vram_gb": 2.785654067993164, "tokens_processed": 1748500480}
567
+ {"timestamp": 1787701927.2698364, "elapsed_hours": 1.2258336412244373, "event": "train_step", "step": 13350, "epoch": 1, "loss": 1.5107902336120604, "perplexity": 4.53030938291494, "muon_lr": 0.0006529152391029791, "adamw_lr": 1.6322880977574478e-05, "tokens_per_sec": 399550.0804005569, "vram_gb": 2.785654067993164, "tokens_processed": 1749811200}
568
+ {"timestamp": 1787701934.7840955, "elapsed_hours": 1.2279209353526432, "event": "train_step", "step": 13360, "epoch": 1, "loss": 1.4671256780624389, "perplexity": 4.336751987979916, "muon_lr": 0.0006509436873320058, "adamw_lr": 1.627359218330015e-05, "tokens_per_sec": 399164.4815614573, "vram_gb": 2.363706111907959, "tokens_processed": 1751121920}
569
+ {"timestamp": 1787701942.208563, "elapsed_hours": 1.229983287586106, "event": "train_step", "step": 13370, "epoch": 1, "loss": 1.4582443404197694, "perplexity": 4.298406361582095, "muon_lr": 0.0006499589850595714, "adamw_lr": 1.6248974626489287e-05, "tokens_per_sec": 398788.3563339165, "vram_gb": 2.785654067993164, "tokens_processed": 1752432640}
570
+ {"timestamp": 1787701949.6436784, "elapsed_hours": 1.2320485973358155, "event": "train_step", "step": 13380, "epoch": 1, "loss": 1.4642634630203246, "perplexity": 4.324357018202388, "muon_lr": 0.0006489750006237479, "adamw_lr": 1.62243750155937e-05, "tokens_per_sec": 398412.5300146841, "vram_gb": 2.785654067993164, "tokens_processed": 1753743360}
571
+ {"timestamp": 1787701957.064365, "elapsed_hours": 1.2341098991367552, "event": "train_step", "step": 13390, "epoch": 1, "loss": 1.4714792776107788, "perplexity": 4.355673628211779, "muon_lr": 0.0006479917355940366, "adamw_lr": 1.6199793389850917e-05, "tokens_per_sec": 398039.27502623794, "vram_gb": 2.785654067993164, "tokens_processed": 1755054080}
572
+ {"timestamp": 1787701964.5944848, "elapsed_hours": 1.2362015990416209, "event": "train_step", "step": 13400, "epoch": 1, "loss": 1.4962068963050843, "perplexity": 4.464721758695431, "muon_lr": 0.0006460273700252167, "adamw_lr": 1.615068425063042e-05, "tokens_per_sec": 397657.4169657655, "vram_gb": 2.363706111907959, "tokens_processed": 1756364800}
573
+ {"timestamp": 1787701977.4215224, "elapsed_hours": 1.2397646651003096, "event": "validation", "step": 13400, "val_loss": 1.4693743681907654, "val_perplexity": 4.346514972213456, "best_loss": 1.4693743681907654}