Upload hybrid40k/metrics.jsonl with huggingface_hub
Browse files- hybrid40k/metrics.jsonl +85 -0
hybrid40k/metrics.jsonl
CHANGED
|
@@ -1210,3 +1210,88 @@
|
|
| 1210 |
{"event": "train", "epoch": 0, "step": 24180, "loss": 2.0748617947101593, "perplexity": 7.963445792643662, "learning_rate": 0.00024961355865572133, "grad_norm": 0.48031148314476013, "tokens_per_sec": 134199.38042845705, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1211 |
{"event": "train", "epoch": 0, "step": 24200, "loss": 2.5524754524230957, "perplexity": 12.838846431253295, "learning_rate": 0.0002495351960024733, "grad_norm": 0.5238137245178223, "tokens_per_sec": 133917.19897339758, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1212 |
{"event": "train", "epoch": 0, "step": 24220, "loss": 2.323126196861267, "perplexity": 10.207535242982381, "learning_rate": 0.00024945678478195243, "grad_norm": 0.5430716276168823, "tokens_per_sec": 133773.0371616229, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1210 |
{"event": "train", "epoch": 0, "step": 24180, "loss": 2.0748617947101593, "perplexity": 7.963445792643662, "learning_rate": 0.00024961355865572133, "grad_norm": 0.48031148314476013, "tokens_per_sec": 134199.38042845705, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1211 |
{"event": "train", "epoch": 0, "step": 24200, "loss": 2.5524754524230957, "perplexity": 12.838846431253295, "learning_rate": 0.0002495351960024733, "grad_norm": 0.5238137245178223, "tokens_per_sec": 133917.19897339758, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1212 |
{"event": "train", "epoch": 0, "step": 24220, "loss": 2.323126196861267, "perplexity": 10.207535242982381, "learning_rate": 0.00024945678478195243, "grad_norm": 0.5430716276168823, "tokens_per_sec": 133773.0371616229, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1213 |
+
{"event": "train", "epoch": 0, "step": 24240, "loss": 2.4481483101844788, "perplexity": 11.566908550169844, "learning_rate": 0.00024937832503241913, "grad_norm": 0.4707043170928955, "tokens_per_sec": 134035.39274405033, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1214 |
+
{"event": "train", "epoch": 0, "step": 24260, "loss": 2.5710069239139557, "perplexity": 13.078987357935484, "learning_rate": 0.00024929981679215667, "grad_norm": 0.5772544741630554, "tokens_per_sec": 134351.42341060098, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1215 |
+
{"event": "train", "epoch": 0, "step": 24280, "loss": 2.211273819208145, "perplexity": 9.127335566469792, "learning_rate": 0.00024922126009947255, "grad_norm": 0.5414873361587524, "tokens_per_sec": 134277.3922709798, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1216 |
+
{"event": "train", "epoch": 0, "step": 24300, "loss": 3.0331650972366333, "perplexity": 20.762845123314396, "learning_rate": 0.0002491426549926981, "grad_norm": 0.5990711450576782, "tokens_per_sec": 134620.93347163819, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1217 |
+
{"event": "train", "epoch": 0, "step": 24320, "loss": 2.055159091949463, "perplexity": 7.80807997649394, "learning_rate": 0.00024906400151018744, "grad_norm": 0.4551694989204407, "tokens_per_sec": 132556.62775840252, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1218 |
+
{"event": "train", "epoch": 0, "step": 24340, "loss": 2.4536007046699524, "perplexity": 11.63014814550453, "learning_rate": 0.0002489852996903191, "grad_norm": 0.48938512802124023, "tokens_per_sec": 134525.53398254013, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1219 |
+
{"event": "train", "epoch": 0, "step": 24360, "loss": 2.34479296207428, "perplexity": 10.431112867999065, "learning_rate": 0.000248906549571495, "grad_norm": 0.4872884452342987, "tokens_per_sec": 134411.73243411878, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1220 |
+
{"event": "train", "epoch": 0, "step": 24380, "loss": 2.379540264606476, "perplexity": 10.799936609330096, "learning_rate": 0.0002488277511921405, "grad_norm": 0.51906818151474, "tokens_per_sec": 135101.8269672928, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1221 |
+
{"event": "train", "epoch": 0, "step": 24400, "loss": 2.694804310798645, "perplexity": 14.802621756611977, "learning_rate": 0.00024874890459070423, "grad_norm": 0.5010719299316406, "tokens_per_sec": 134119.75770823658, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1222 |
+
{"event": "train", "epoch": 0, "step": 24420, "loss": 2.1302270889282227, "perplexity": 8.416777951516638, "learning_rate": 0.00024867000980565904, "grad_norm": 0.4988638460636139, "tokens_per_sec": 134724.91995941754, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1223 |
+
{"event": "train", "epoch": 0, "step": 24440, "loss": 2.1966023445129395, "perplexity": 8.994401646510758, "learning_rate": 0.0002485910668755007, "grad_norm": 0.46056899428367615, "tokens_per_sec": 134202.1322443974, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1224 |
+
{"event": "train", "epoch": 0, "step": 24460, "loss": 2.8252792358398438, "perplexity": 16.865653823630286, "learning_rate": 0.00024851207583874863, "grad_norm": 0.49265119433403015, "tokens_per_sec": 134681.22079500154, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1225 |
+
{"event": "train", "epoch": 0, "step": 24480, "loss": 2.4958239793777466, "perplexity": 12.131725693138842, "learning_rate": 0.0002484330367339457, "grad_norm": 0.539284348487854, "tokens_per_sec": 135174.24418492574, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1226 |
+
{"event": "train", "epoch": 0, "step": 24500, "loss": 1.7361120283603668, "perplexity": 5.675235318713421, "learning_rate": 0.00024835394959965866, "grad_norm": 0.40019527077674866, "tokens_per_sec": 134642.4301968122, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1227 |
+
{"event": "train", "epoch": 0, "step": 24520, "loss": 2.6377124786376953, "perplexity": 13.981184741009647, "learning_rate": 0.00024827481447447705, "grad_norm": 0.535968005657196, "tokens_per_sec": 135359.15997892382, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1228 |
+
{"event": "train", "epoch": 0, "step": 24540, "loss": 1.8959027528762817, "perplexity": 6.6585567234452565, "learning_rate": 0.00024819563139701436, "grad_norm": 0.426654189825058, "tokens_per_sec": 134894.83684902734, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1229 |
+
{"event": "train", "epoch": 0, "step": 24560, "loss": 3.1666600108146667, "perplexity": 23.728100260956, "learning_rate": 0.000248116400405907, "grad_norm": 0.5923141241073608, "tokens_per_sec": 134045.19717004872, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1230 |
+
{"event": "train", "epoch": 0, "step": 24580, "loss": 2.9499083757400513, "perplexity": 19.104203239555524, "learning_rate": 0.00024803712153981516, "grad_norm": 0.796188235282898, "tokens_per_sec": 135293.60281220684, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1231 |
+
{"event": "train", "epoch": 0, "step": 24600, "loss": 2.3498458862304688, "perplexity": 10.483953878566883, "learning_rate": 0.00024795779483742205, "grad_norm": 0.4919901490211487, "tokens_per_sec": 123331.88272972578, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1232 |
+
{"event": "train", "epoch": 0, "step": 24620, "loss": 2.334188222885132, "perplexity": 10.321078112733675, "learning_rate": 0.00024787842033743455, "grad_norm": 0.4433281421661377, "tokens_per_sec": 134429.8751467159, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1233 |
+
{"event": "train", "epoch": 0, "step": 24640, "loss": 1.9032865464687347, "perplexity": 6.707904093107753, "learning_rate": 0.00024779899807858265, "grad_norm": 0.4193906784057617, "tokens_per_sec": 134425.14179300092, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1234 |
+
{"event": "train", "epoch": 0, "step": 24660, "loss": 2.222422033548355, "perplexity": 9.229658358183045, "learning_rate": 0.0002477195280996197, "grad_norm": 0.44793325662612915, "tokens_per_sec": 134127.48011543014, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1235 |
+
{"event": "train", "epoch": 0, "step": 24680, "loss": 2.008591055870056, "perplexity": 7.452809354478501, "learning_rate": 0.00024764001043932224, "grad_norm": 0.486950159072876, "tokens_per_sec": 134067.9489632676, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1236 |
+
{"event": "train", "epoch": 0, "step": 24700, "loss": 2.212620884180069, "perplexity": 9.139638965376767, "learning_rate": 0.0002475604451364903, "grad_norm": 0.4728984534740448, "tokens_per_sec": 134019.31658989232, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1237 |
+
{"event": "train", "epoch": 0, "step": 24720, "loss": 2.2416937351226807, "perplexity": 9.409254583679704, "learning_rate": 0.0002474808322299468, "grad_norm": 0.45428764820098877, "tokens_per_sec": 134046.3737975576, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1238 |
+
{"event": "train", "epoch": 0, "step": 24740, "loss": 1.7907634973526, "perplexity": 5.9940271436394825, "learning_rate": 0.00024740117175853834, "grad_norm": 0.4435093402862549, "tokens_per_sec": 134020.62345027723, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1239 |
+
{"event": "train", "epoch": 0, "step": 24760, "loss": 2.269582122564316, "perplexity": 9.675356855879983, "learning_rate": 0.00024732146376113453, "grad_norm": 0.4653971493244171, "tokens_per_sec": 134968.3576845837, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1240 |
+
{"event": "train", "epoch": 0, "step": 24780, "loss": 2.009789377450943, "perplexity": 7.461745569926771, "learning_rate": 0.00024724170827662814, "grad_norm": 0.4730072617530823, "tokens_per_sec": 134718.58116258396, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1241 |
+
{"event": "train", "epoch": 0, "step": 24800, "loss": 2.097556620836258, "perplexity": 8.146241219746797, "learning_rate": 0.00024716190534393516, "grad_norm": 0.4205792248249054, "tokens_per_sec": 134833.56450506856, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1242 |
+
{"event": "train", "epoch": 0, "step": 24820, "loss": 2.468265652656555, "perplexity": 11.801960392809125, "learning_rate": 0.0002470820550019944, "grad_norm": 0.46348053216934204, "tokens_per_sec": 134946.88926788987, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1243 |
+
{"event": "train", "epoch": 0, "step": 24840, "loss": 2.379006326198578, "perplexity": 10.794171647575723, "learning_rate": 0.00024700215728976847, "grad_norm": 0.47299328446388245, "tokens_per_sec": 134745.6572743993, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1244 |
+
{"event": "train", "epoch": 0, "step": 24860, "loss": 2.1464490592479706, "perplexity": 8.554428133651427, "learning_rate": 0.0002469222122462424, "grad_norm": 0.462116003036499, "tokens_per_sec": 134092.2783879925, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1245 |
+
{"event": "train", "epoch": 0, "step": 24880, "loss": 2.1690495312213898, "perplexity": 8.74996352002988, "learning_rate": 0.00024684221991042493, "grad_norm": 0.43772467970848083, "tokens_per_sec": 135342.36489737476, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1246 |
+
{"event": "train", "epoch": 0, "step": 24900, "loss": 2.305902659893036, "perplexity": 10.033230761147674, "learning_rate": 0.0002467621803213473, "grad_norm": 0.5038034319877625, "tokens_per_sec": 134719.2414260901, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1247 |
+
{"event": "train", "epoch": 0, "step": 24920, "loss": 1.8501542806625366, "perplexity": 6.36080079546516, "learning_rate": 0.00024668209351806424, "grad_norm": 0.4797751009464264, "tokens_per_sec": 134346.82690397804, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1248 |
+
{"event": "train", "epoch": 0, "step": 24940, "loss": 3.034942537546158, "perplexity": 20.799782658584338, "learning_rate": 0.0002466019595396533, "grad_norm": 0.9484381675720215, "tokens_per_sec": 134186.4091017819, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1249 |
+
{"event": "train", "epoch": 0, "step": 24960, "loss": 1.9552544951438904, "perplexity": 7.065716985566155, "learning_rate": 0.000246521778425215, "grad_norm": 0.43878552317619324, "tokens_per_sec": 133705.49493687757, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1250 |
+
{"event": "train", "epoch": 0, "step": 24980, "loss": 2.1040433645248413, "perplexity": 8.199255557882365, "learning_rate": 0.00024644155021387324, "grad_norm": 0.4547240734100342, "tokens_per_sec": 133149.67000253825, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1251 |
+
{"event": "train", "epoch": 0, "step": 25000, "loss": 2.190276265144348, "perplexity": 8.937681943649654, "learning_rate": 0.0002463612749447744, "grad_norm": 0.48724326491355896, "tokens_per_sec": 134375.85583816894, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1252 |
+
{"event": "train", "epoch": 0, "step": 25020, "loss": 2.2687266767024994, "perplexity": 9.667083651039965, "learning_rate": 0.0002462809526570883, "grad_norm": 0.5001009702682495, "tokens_per_sec": 135352.89465950767, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1253 |
+
{"event": "train", "epoch": 0, "step": 25040, "loss": 2.149941086769104, "perplexity": 8.584352650330668, "learning_rate": 0.00024620058339000695, "grad_norm": 0.42795518040657043, "tokens_per_sec": 135024.97693436738, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1254 |
+
{"event": "train", "epoch": 0, "step": 25060, "loss": 2.1304031014442444, "perplexity": 8.418259540165929, "learning_rate": 0.0002461201671827463, "grad_norm": 0.46164679527282715, "tokens_per_sec": 134687.82005946536, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1255 |
+
{"event": "train", "epoch": 0, "step": 25080, "loss": 2.195079267024994, "perplexity": 8.980712903000178, "learning_rate": 0.0002460397040745444, "grad_norm": 0.46585211157798767, "tokens_per_sec": 134242.63630165753, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1256 |
+
{"event": "train", "epoch": 0, "step": 25100, "loss": 2.340654045343399, "perplexity": 10.388028583066939, "learning_rate": 0.0002459591941046627, "grad_norm": 0.4807687997817993, "tokens_per_sec": 134164.6648268995, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1257 |
+
{"event": "train", "epoch": 0, "step": 25120, "loss": 1.821676880121231, "perplexity": 6.182216598889099, "learning_rate": 0.0002458786373123852, "grad_norm": 0.40519586205482483, "tokens_per_sec": 133794.52442128852, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1258 |
+
{"event": "train", "epoch": 0, "step": 25140, "loss": 1.9397816956043243, "perplexity": 6.957232010515837, "learning_rate": 0.00024579803373701875, "grad_norm": 0.458769828081131, "tokens_per_sec": 134600.10270583132, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1259 |
+
{"event": "train", "epoch": 0, "step": 25160, "loss": 3.082396149635315, "perplexity": 21.810601297377634, "learning_rate": 0.00024571738341789314, "grad_norm": 2.7864694595336914, "tokens_per_sec": 134613.15414028708, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1260 |
+
{"event": "train", "epoch": 0, "step": 25180, "loss": 2.5422577261924744, "perplexity": 12.708330536648957, "learning_rate": 0.0002456366863943611, "grad_norm": 0.5918420553207397, "tokens_per_sec": 133902.06434440683, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1261 |
+
{"event": "train", "epoch": 0, "step": 25200, "loss": 2.668511241674423, "perplexity": 14.418487562891372, "learning_rate": 0.0002455559427057978, "grad_norm": 0.6043678522109985, "tokens_per_sec": 135030.4159428278, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1262 |
+
{"event": "train", "epoch": 0, "step": 25220, "loss": 2.3658504486083984, "perplexity": 10.653094875820367, "learning_rate": 0.00024547515239160144, "grad_norm": 0.4521401822566986, "tokens_per_sec": 134894.572053919, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1263 |
+
{"event": "train", "epoch": 0, "step": 25240, "loss": 2.1294380128383636, "perplexity": 8.410139092908208, "learning_rate": 0.0002453943154911928, "grad_norm": 0.512994110584259, "tokens_per_sec": 134174.48817470932, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1264 |
+
{"event": "train", "epoch": 0, "step": 25260, "loss": 2.1576197743415833, "perplexity": 8.65052293769745, "learning_rate": 0.0002453134320440158, "grad_norm": 0.6571003198623657, "tokens_per_sec": 134337.10961108017, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1265 |
+
{"event": "train", "epoch": 0, "step": 25280, "loss": 1.929662674665451, "perplexity": 6.887186627163212, "learning_rate": 0.00024523250208953657, "grad_norm": 0.4649432301521301, "tokens_per_sec": 134713.03520463422, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1266 |
+
{"event": "train", "epoch": 0, "step": 25300, "loss": 2.015523135662079, "perplexity": 7.504652305732085, "learning_rate": 0.00024515152566724415, "grad_norm": 0.41793590784072876, "tokens_per_sec": 122539.17063602452, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1267 |
+
{"event": "train", "epoch": 0, "step": 25320, "loss": 2.7065827548503876, "perplexity": 14.978004448814334, "learning_rate": 0.00024507050281665003, "grad_norm": 0.6158767342567444, "tokens_per_sec": 134890.20308471433, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1268 |
+
{"event": "train", "epoch": 0, "step": 25340, "loss": 1.963532269001007, "perplexity": 7.124448139152897, "learning_rate": 0.0002449894335772888, "grad_norm": 0.43088772892951965, "tokens_per_sec": 133750.38534495677, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1269 |
+
{"event": "train", "epoch": 0, "step": 25360, "loss": 2.937289595603943, "perplexity": 18.864646137189233, "learning_rate": 0.0002449083179887174, "grad_norm": 0.7314449548721313, "tokens_per_sec": 134792.8353217978, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1270 |
+
{"event": "train", "epoch": 0, "step": 25380, "loss": 2.365346372127533, "perplexity": 10.647726254456597, "learning_rate": 0.0002448271560905153, "grad_norm": 0.5140199065208435, "tokens_per_sec": 134010.4306151422, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1271 |
+
{"event": "train", "epoch": 0, "step": 25400, "loss": 2.0999812483787537, "perplexity": 8.166016785078115, "learning_rate": 0.00024474594792228476, "grad_norm": 0.473860502243042, "tokens_per_sec": 133932.33702403668, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1272 |
+
{"event": "train", "epoch": 0, "step": 25420, "loss": 2.7356303334236145, "perplexity": 15.41945977421099, "learning_rate": 0.0002446646935236507, "grad_norm": 0.5535570383071899, "tokens_per_sec": 134103.792160957, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1273 |
+
{"event": "train", "epoch": 0, "step": 25440, "loss": 2.425923228263855, "perplexity": 11.312668775136727, "learning_rate": 0.0002445833929342603, "grad_norm": 0.42968615889549255, "tokens_per_sec": 134403.58295455435, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1274 |
+
{"event": "train", "epoch": 0, "step": 25460, "loss": 2.032055824995041, "perplexity": 7.629755689012369, "learning_rate": 0.0002445020461937834, "grad_norm": 0.43817001581192017, "tokens_per_sec": 134779.0881670238, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1275 |
+
{"event": "train", "epoch": 0, "step": 25480, "loss": 1.7826462984085083, "perplexity": 5.945569369603296, "learning_rate": 0.00024442065334191244, "grad_norm": 0.507817268371582, "tokens_per_sec": 134438.42232414737, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1276 |
+
{"event": "train", "epoch": 0, "step": 25500, "loss": 2.6532928347587585, "perplexity": 14.200722374525412, "learning_rate": 0.00024433921441836245, "grad_norm": 0.5434606671333313, "tokens_per_sec": 132991.45329104102, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1277 |
+
{"event": "train", "epoch": 0, "step": 25520, "loss": 1.9404296875, "perplexity": 6.961741701438773, "learning_rate": 0.00024425772946287054, "grad_norm": 0.4420452117919922, "tokens_per_sec": 130794.96179756889, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1278 |
+
{"event": "train", "epoch": 0, "step": 25540, "loss": 2.0235218703746796, "perplexity": 7.56492074292662, "learning_rate": 0.0002441761985151968, "grad_norm": 0.3946819305419922, "tokens_per_sec": 134191.38769831313, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1279 |
+
{"event": "train", "epoch": 0, "step": 25560, "loss": 1.9455762207508087, "perplexity": 6.997662892103424, "learning_rate": 0.00024409462161512324, "grad_norm": 0.4450206160545349, "tokens_per_sec": 132273.03027462453, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1280 |
+
{"event": "train", "epoch": 0, "step": 25580, "loss": 3.081941246986389, "perplexity": 21.800681853434515, "learning_rate": 0.0002440129988024547, "grad_norm": 0.6943750381469727, "tokens_per_sec": 135260.84803607507, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1281 |
+
{"event": "train", "epoch": 0, "step": 25600, "loss": 2.163808673620224, "perplexity": 8.704226163380016, "learning_rate": 0.00024393133011701802, "grad_norm": 0.6452540159225464, "tokens_per_sec": 135142.61023882194, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1282 |
+
{"event": "train", "epoch": 0, "step": 25620, "loss": 2.6289674639701843, "perplexity": 13.859452127917507, "learning_rate": 0.000243849615598663, "grad_norm": 0.48410874605178833, "tokens_per_sec": 133291.97358967795, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1283 |
+
{"event": "train", "epoch": 0, "step": 25640, "loss": 2.280469059944153, "perplexity": 9.781267334383056, "learning_rate": 0.00024376785528726125, "grad_norm": 0.46701765060424805, "tokens_per_sec": 132928.29755119528, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1284 |
+
{"event": "train", "epoch": 0, "step": 25660, "loss": 2.174539238214493, "perplexity": 8.798130345869067, "learning_rate": 0.00024368604922270717, "grad_norm": 0.45185941457748413, "tokens_per_sec": 134408.97201584675, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1285 |
+
{"event": "train", "epoch": 0, "step": 25680, "loss": 2.531203418970108, "perplexity": 12.568622357843827, "learning_rate": 0.00024360419744491718, "grad_norm": 0.590377688407898, "tokens_per_sec": 134170.55866297006, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1286 |
+
{"event": "train", "epoch": 0, "step": 25700, "loss": 2.5838537216186523, "perplexity": 13.248094378766892, "learning_rate": 0.0002435222999938301, "grad_norm": 0.48540425300598145, "tokens_per_sec": 133849.1200716776, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1287 |
+
{"event": "train", "epoch": 0, "step": 25720, "loss": 2.2130010426044464, "perplexity": 9.143114136641188, "learning_rate": 0.00024344035690940688, "grad_norm": 0.5592446327209473, "tokens_per_sec": 134561.75404696775, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1288 |
+
{"event": "train", "epoch": 0, "step": 25740, "loss": 2.1189127266407013, "perplexity": 8.322084186443176, "learning_rate": 0.000243358368231631, "grad_norm": 0.4253940284252167, "tokens_per_sec": 134297.2046660426, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1289 |
+
{"event": "train", "epoch": 0, "step": 25760, "loss": 2.4455305337905884, "perplexity": 11.536668568041529, "learning_rate": 0.0002432763340005082, "grad_norm": 0.5387234687805176, "tokens_per_sec": 134117.53277287964, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1290 |
+
{"event": "train", "epoch": 0, "step": 25780, "loss": 2.5448670387268066, "perplexity": 12.741533842871469, "learning_rate": 0.00024319425425606614, "grad_norm": 0.7019080519676208, "tokens_per_sec": 135322.50942459927, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1291 |
+
{"event": "train", "epoch": 0, "step": 25800, "loss": 2.664503186941147, "perplexity": 14.3608131339115, "learning_rate": 0.00024311212903835487, "grad_norm": 0.7120727300643921, "tokens_per_sec": 134744.3362359534, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1292 |
+
{"event": "train", "epoch": 0, "step": 25820, "loss": 2.2229780554771423, "perplexity": 9.234791677612243, "learning_rate": 0.00024302995838744674, "grad_norm": 0.7407183647155762, "tokens_per_sec": 132813.58747460926, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1293 |
+
{"event": "train", "epoch": 0, "step": 25840, "loss": 3.041264057159424, "perplexity": 20.93168536613524, "learning_rate": 0.00024294774234343597, "grad_norm": 0.575259268283844, "tokens_per_sec": 134598.78451984673, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1294 |
+
{"event": "train", "epoch": 0, "step": 25860, "loss": 2.70905601978302, "perplexity": 15.015094870290824, "learning_rate": 0.00024286548094643934, "grad_norm": 0.51579749584198, "tokens_per_sec": 134099.4742643938, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1295 |
+
{"event": "train", "epoch": 0, "step": 25880, "loss": 3.3680469393730164, "perplexity": 29.021790354655238, "learning_rate": 0.0002427831742365955, "grad_norm": 1.2121423482894897, "tokens_per_sec": 133929.85728137082, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1296 |
+
{"event": "train", "epoch": 0, "step": 25900, "loss": 2.1486863493919373, "perplexity": 8.573588296832108, "learning_rate": 0.00024270082225406515, "grad_norm": 0.4957280457019806, "tokens_per_sec": 134159.5572544717, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1297 |
+
{"event": "train", "epoch": 0, "step": 25920, "loss": 2.462051272392273, "perplexity": 11.728845938871531, "learning_rate": 0.00024261842503903107, "grad_norm": 0.534748911857605, "tokens_per_sec": 133789.5752284924, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|