Upload hybrid40k/metrics.jsonl with huggingface_hub
Browse files- hybrid40k/metrics.jsonl +86 -0
hybrid40k/metrics.jsonl
CHANGED
|
@@ -2400,3 +2400,89 @@
|
|
| 2400 |
{"event": "train", "epoch": 1, "step": 47960, "loss": 1.927464485168457, "perplexity": 6.872063913240459, "learning_rate": 0.0001343874233633741, "grad_norm": 0.5847577452659607, "tokens_per_sec": 134407.39468488249, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2401 |
{"event": "train", "epoch": 1, "step": 47980, "loss": 2.451600283384323, "perplexity": 11.606906204186883, "learning_rate": 0.0001342832171559906, "grad_norm": 0.7066119909286499, "tokens_per_sec": 134934.4354162392, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2402 |
{"event": "train", "epoch": 1, "step": 48000, "loss": 1.9689961075782776, "perplexity": 7.163481512656382, "learning_rate": 0.00013417901861746505, "grad_norm": 0.5736967921257019, "tokens_per_sec": 134502.88988862128, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2400 |
{"event": "train", "epoch": 1, "step": 47960, "loss": 1.927464485168457, "perplexity": 6.872063913240459, "learning_rate": 0.0001343874233633741, "grad_norm": 0.5847577452659607, "tokens_per_sec": 134407.39468488249, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2401 |
{"event": "train", "epoch": 1, "step": 47980, "loss": 2.451600283384323, "perplexity": 11.606906204186883, "learning_rate": 0.0001342832171559906, "grad_norm": 0.7066119909286499, "tokens_per_sec": 134934.4354162392, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2402 |
{"event": "train", "epoch": 1, "step": 48000, "loss": 1.9689961075782776, "perplexity": 7.163481512656382, "learning_rate": 0.00013417901861746505, "grad_norm": 0.5736967921257019, "tokens_per_sec": 134502.88988862128, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2403 |
+
{"event": "train", "epoch": 1, "step": 48020, "loss": 2.083765894174576, "perplexity": 8.034669727993242, "learning_rate": 0.00013407482779864008, "grad_norm": 0.9411811828613281, "tokens_per_sec": 134874.05359478793, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2404 |
+
{"event": "train", "epoch": 1, "step": 48040, "loss": 1.4852561950683594, "perplexity": 4.416096650046826, "learning_rate": 0.00013397064475035485, "grad_norm": 0.5115069150924683, "tokens_per_sec": 134333.30186615634, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2405 |
+
{"event": "train", "epoch": 1, "step": 48060, "loss": 2.0085160434246063, "perplexity": 7.452250321990809, "learning_rate": 0.00013386646952344422, "grad_norm": 0.6457865834236145, "tokens_per_sec": 134053.5647478576, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2406 |
+
{"event": "train", "epoch": 1, "step": 48080, "loss": 2.3261775374412537, "perplexity": 10.238729477404323, "learning_rate": 0.00013376230216873965, "grad_norm": 0.6484886407852173, "tokens_per_sec": 134652.1917123218, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2407 |
+
{"event": "train", "epoch": 1, "step": 48100, "loss": 2.680650770664215, "perplexity": 14.594587935814074, "learning_rate": 0.00013365814273706862, "grad_norm": 0.7607699036598206, "tokens_per_sec": 133155.99102081548, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2408 |
+
{"event": "train", "epoch": 1, "step": 48120, "loss": 2.0951037108898163, "perplexity": 8.12628371062572, "learning_rate": 0.00013355399127925482, "grad_norm": 0.6695239543914795, "tokens_per_sec": 132959.41772928272, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2409 |
+
{"event": "train", "epoch": 1, "step": 48140, "loss": 2.267450273036957, "perplexity": 9.654752421520127, "learning_rate": 0.00013344984784611794, "grad_norm": 0.6387630701065063, "tokens_per_sec": 134140.0472890211, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2410 |
+
{"event": "train", "epoch": 1, "step": 48160, "loss": 1.7604011595249176, "perplexity": 5.814769576783652, "learning_rate": 0.0001333457124884739, "grad_norm": 0.5288535356521606, "tokens_per_sec": 134481.3061067933, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2411 |
+
{"event": "train", "epoch": 1, "step": 48180, "loss": 2.149297297000885, "perplexity": 8.578827910503906, "learning_rate": 0.0001332415852571344, "grad_norm": 0.6360021233558655, "tokens_per_sec": 134268.60321293614, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2412 |
+
{"event": "train", "epoch": 1, "step": 48200, "loss": 2.095777839422226, "perplexity": 8.131763717244388, "learning_rate": 0.0001331374662029074, "grad_norm": 0.6199296116828918, "tokens_per_sec": 134819.54454111075, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2413 |
+
{"event": "train", "epoch": 1, "step": 48220, "loss": 1.9626923203468323, "perplexity": 7.118466481021206, "learning_rate": 0.00013303335537659681, "grad_norm": 0.5178159475326538, "tokens_per_sec": 133316.53943945322, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2414 |
+
{"event": "train", "epoch": 1, "step": 48240, "loss": 1.8551340699195862, "perplexity": 6.392555242538514, "learning_rate": 0.00013292925282900266, "grad_norm": 0.5679906606674194, "tokens_per_sec": 134307.70366866866, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2415 |
+
{"event": "train", "epoch": 1, "step": 48260, "loss": 1.896976888179779, "perplexity": 6.665712756878287, "learning_rate": 0.00013282515861092064, "grad_norm": 0.5591392517089844, "tokens_per_sec": 134467.75398005667, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2416 |
+
{"event": "train", "epoch": 1, "step": 48280, "loss": 2.792474687099457, "perplexity": 16.321360125710246, "learning_rate": 0.00013272107277314285, "grad_norm": 0.827536404132843, "tokens_per_sec": 134289.33149120526, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2417 |
+
{"event": "train", "epoch": 1, "step": 48300, "loss": 2.041556179523468, "perplexity": 7.702586484423433, "learning_rate": 0.00013261699536645666, "grad_norm": 0.5747297406196594, "tokens_per_sec": 135069.5631944431, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2418 |
+
{"event": "train", "epoch": 1, "step": 48320, "loss": 2.649047702550888, "perplexity": 14.140566206381969, "learning_rate": 0.00013251292644164594, "grad_norm": 0.8607286214828491, "tokens_per_sec": 134580.33262667677, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2419 |
+
{"event": "train", "epoch": 1, "step": 48340, "loss": 2.7422688603401184, "perplexity": 15.522162794164318, "learning_rate": 0.00013240886604948992, "grad_norm": 0.7832328081130981, "tokens_per_sec": 134126.56385113244, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2420 |
+
{"event": "train", "epoch": 1, "step": 48360, "loss": 2.4998270869255066, "perplexity": 12.18038763032901, "learning_rate": 0.00013230481424076417, "grad_norm": 0.6293100714683533, "tokens_per_sec": 133824.09696478717, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2421 |
+
{"event": "train", "epoch": 1, "step": 48380, "loss": 2.2726642191410065, "perplexity": 9.705223242024474, "learning_rate": 0.00013220077106623944, "grad_norm": 0.5915820002555847, "tokens_per_sec": 135240.7503163579, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2422 |
+
{"event": "train", "epoch": 1, "step": 48400, "loss": 2.016705870628357, "perplexity": 7.513533571480301, "learning_rate": 0.000132096736576683, "grad_norm": 0.5655009150505066, "tokens_per_sec": 134432.7679158654, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2423 |
+
{"event": "train", "epoch": 1, "step": 48420, "loss": 1.9317362010478973, "perplexity": 6.901482206343758, "learning_rate": 0.0001319927108228573, "grad_norm": 0.6528939008712769, "tokens_per_sec": 134689.5359741595, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2424 |
+
{"event": "train", "epoch": 1, "step": 48440, "loss": 2.1821991205215454, "perplexity": 8.865781758991629, "learning_rate": 0.00013188869385552074, "grad_norm": 0.7190245389938354, "tokens_per_sec": 134616.8459142536, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2425 |
+
{"event": "train", "epoch": 1, "step": 48460, "loss": 2.8732175827026367, "perplexity": 17.693858159120207, "learning_rate": 0.0001317846857254275, "grad_norm": 0.8511238098144531, "tokens_per_sec": 134983.7343283025, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2426 |
+
{"event": "train", "epoch": 1, "step": 48480, "loss": 2.054572731256485, "perplexity": 7.803502967328368, "learning_rate": 0.0001316806864833274, "grad_norm": 2.066438674926758, "tokens_per_sec": 134214.3202145258, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2427 |
+
{"event": "train", "epoch": 1, "step": 48500, "loss": 2.4127584099769592, "perplexity": 11.164715571729182, "learning_rate": 0.00013157669617996584, "grad_norm": 0.6643975973129272, "tokens_per_sec": 135094.65590802798, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2428 |
+
{"event": "train", "epoch": 1, "step": 48520, "loss": 1.9211341440677643, "perplexity": 6.828698807374734, "learning_rate": 0.00013147271486608402, "grad_norm": 0.5950134992599487, "tokens_per_sec": 135156.69747838008, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2429 |
+
{"event": "train", "epoch": 1, "step": 48540, "loss": 2.682410418987274, "perplexity": 14.62029188632538, "learning_rate": 0.00013136874259241853, "grad_norm": 1.4056832790374756, "tokens_per_sec": 133870.76217693594, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2430 |
+
{"event": "train", "epoch": 1, "step": 48560, "loss": 2.2107249200344086, "perplexity": 9.122326954256247, "learning_rate": 0.00013126477940970173, "grad_norm": 0.6447938680648804, "tokens_per_sec": 134205.8015078738, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2431 |
+
{"event": "train", "epoch": 1, "step": 48580, "loss": 3.2183476090431213, "perplexity": 24.98679809140849, "learning_rate": 0.00013116082536866145, "grad_norm": 0.9326633810997009, "tokens_per_sec": 134877.36260147282, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2432 |
+
{"event": "train", "epoch": 1, "step": 48600, "loss": 1.8300661146640778, "perplexity": 6.234298823471968, "learning_rate": 0.00013105688052002105, "grad_norm": 0.5543508529663086, "tokens_per_sec": 134245.91439804254, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2433 |
+
{"event": "train", "epoch": 1, "step": 48620, "loss": 2.0830634236335754, "perplexity": 8.029027591152134, "learning_rate": 0.00013095294491449963, "grad_norm": 0.5607770681381226, "tokens_per_sec": 133383.55972220606, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2434 |
+
{"event": "train", "epoch": 1, "step": 48640, "loss": 2.2616555094718933, "perplexity": 9.598967201141681, "learning_rate": 0.00013084901860281153, "grad_norm": 0.6949803829193115, "tokens_per_sec": 134451.04783594186, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2435 |
+
{"event": "train", "epoch": 1, "step": 48660, "loss": 2.400211453437805, "perplexity": 11.02550751563739, "learning_rate": 0.00013074510163566653, "grad_norm": 0.7282930612564087, "tokens_per_sec": 134930.99113968664, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2436 |
+
{"event": "train", "epoch": 1, "step": 48680, "loss": 2.3064476251602173, "perplexity": 10.038700013571061, "learning_rate": 0.00013064119406377, "grad_norm": 0.6764334440231323, "tokens_per_sec": 133132.1290957524, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2437 |
+
{"event": "train", "epoch": 1, "step": 48700, "loss": 1.9619047343730927, "perplexity": 7.112862283849447, "learning_rate": 0.00013053729593782274, "grad_norm": 0.5753436088562012, "tokens_per_sec": 134384.0019555446, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2438 |
+
{"event": "train", "epoch": 1, "step": 48720, "loss": 1.8976698219776154, "perplexity": 6.670333255199041, "learning_rate": 0.00013043340730852082, "grad_norm": 0.5902947187423706, "tokens_per_sec": 133769.1311286175, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2439 |
+
{"event": "train", "epoch": 1, "step": 48740, "loss": 2.1776700615882874, "perplexity": 8.825718902915856, "learning_rate": 0.00013032952822655578, "grad_norm": 0.6850220561027527, "tokens_per_sec": 118036.97913725166, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2440 |
+
{"event": "train", "epoch": 1, "step": 48760, "loss": 2.98962065577507, "perplexity": 19.87814040336701, "learning_rate": 0.0001302256587426143, "grad_norm": 0.7987924218177795, "tokens_per_sec": 133773.81839559742, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2441 |
+
{"event": "train", "epoch": 1, "step": 48780, "loss": 3.4818418622016907, "perplexity": 32.5195635039475, "learning_rate": 0.00013012179890737875, "grad_norm": 1.3184401988983154, "tokens_per_sec": 133963.14569382794, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2442 |
+
{"event": "train", "epoch": 1, "step": 48800, "loss": 2.6357601284980774, "perplexity": 13.95391520153499, "learning_rate": 0.0001300179487715263, "grad_norm": 1.7699520587921143, "tokens_per_sec": 134721.88254483574, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2443 |
+
{"event": "train", "epoch": 1, "step": 48820, "loss": 2.01647886633873, "perplexity": 7.511828160704422, "learning_rate": 0.00012991410838572988, "grad_norm": 0.7021124958992004, "tokens_per_sec": 128724.07607366101, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2444 |
+
{"event": "train", "epoch": 1, "step": 48840, "loss": 2.9074178338050842, "perplexity": 18.30945940740326, "learning_rate": 0.0001298102778006574, "grad_norm": 0.8068447113037109, "tokens_per_sec": 132545.76159133276, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2445 |
+
{"event": "train", "epoch": 1, "step": 48860, "loss": 3.2901748716831207, "perplexity": 26.84755812309858, "learning_rate": 0.00012970645706697197, "grad_norm": 1.6577335596084595, "tokens_per_sec": 133674.67463429816, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2446 |
+
{"event": "train", "epoch": 1, "step": 48880, "loss": 2.143647789955139, "perplexity": 8.530498409252232, "learning_rate": 0.0001296026462353319, "grad_norm": 0.6890670657157898, "tokens_per_sec": 135123.74325506767, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2447 |
+
{"event": "train", "epoch": 1, "step": 48900, "loss": 3.3059422969818115, "perplexity": 27.274229908411233, "learning_rate": 0.00012949884535639076, "grad_norm": 0.9417529106140137, "tokens_per_sec": 134494.3345121901, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2448 |
+
{"event": "train", "epoch": 1, "step": 48920, "loss": 2.9828786849975586, "perplexity": 19.744573320273123, "learning_rate": 0.00012939505448079743, "grad_norm": 0.8716278076171875, "tokens_per_sec": 134077.49655584834, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2449 |
+
{"event": "train", "epoch": 1, "step": 48940, "loss": 3.5076669454574585, "perplexity": 33.37032211195927, "learning_rate": 0.00012929127365919545, "grad_norm": 1.0482896566390991, "tokens_per_sec": 134534.35671061775, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2450 |
+
{"event": "train", "epoch": 1, "step": 48960, "loss": 2.3836467266082764, "perplexity": 10.844377323239257, "learning_rate": 0.00012918750294222377, "grad_norm": 0.7474749088287354, "tokens_per_sec": 132302.06133648817, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2451 |
+
{"event": "train", "epoch": 1, "step": 48980, "loss": 3.289719343185425, "perplexity": 26.835331080374594, "learning_rate": 0.0001290837423805164, "grad_norm": 1.0047634840011597, "tokens_per_sec": 132818.3363680905, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2452 |
+
{"event": "train", "epoch": 1, "step": 49000, "loss": 2.804593324661255, "perplexity": 16.520356118348676, "learning_rate": 0.00012897999202470228, "grad_norm": 0.7531801462173462, "tokens_per_sec": 134273.71909184786, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2453 |
+
{"event": "train", "epoch": 1, "step": 49020, "loss": 2.299430251121521, "perplexity": 9.968501294118495, "learning_rate": 0.00012887625192540539, "grad_norm": 0.699373185634613, "tokens_per_sec": 133949.82834331336, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2454 |
+
{"event": "train", "epoch": 1, "step": 49040, "loss": 2.898818612098694, "perplexity": 18.152687331615866, "learning_rate": 0.0001287725221332449, "grad_norm": 1.0982335805892944, "tokens_per_sec": 134037.61495490433, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2455 |
+
{"event": "train", "epoch": 1, "step": 49060, "loss": 3.10688316822052, "perplexity": 22.351270570160867, "learning_rate": 0.00012866880269883464, "grad_norm": 1.0087556838989258, "tokens_per_sec": 134324.11164701733, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2456 |
+
{"event": "train", "epoch": 1, "step": 49080, "loss": 2.01825350522995, "perplexity": 7.525170778765324, "learning_rate": 0.00012856509367278361, "grad_norm": 1.1484754085540771, "tokens_per_sec": 133104.53731875215, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2457 |
+
{"event": "train", "epoch": 1, "step": 49100, "loss": 2.9473535418510437, "perplexity": 19.055457468884395, "learning_rate": 0.0001284613951056956, "grad_norm": 0.9875789284706116, "tokens_per_sec": 128146.29662587785, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2458 |
+
{"event": "train", "epoch": 1, "step": 49120, "loss": 3.661612808704376, "perplexity": 38.924069352689905, "learning_rate": 0.00012835770704816947, "grad_norm": 2.270785093307495, "tokens_per_sec": 133970.58889606965, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2459 |
+
{"event": "train", "epoch": 1, "step": 49140, "loss": 2.5146971940994263, "perplexity": 12.362864663902487, "learning_rate": 0.00012825402955079886, "grad_norm": 0.7552295327186584, "tokens_per_sec": 133625.80743114484, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2460 |
+
{"event": "train", "epoch": 1, "step": 49160, "loss": 2.132028818130493, "perplexity": 8.431956375739944, "learning_rate": 0.00012815036266417216, "grad_norm": 1.3091762065887451, "tokens_per_sec": 135271.36511735944, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2461 |
+
{"event": "train", "epoch": 1, "step": 49180, "loss": 3.01803857088089, "perplexity": 20.451138859328346, "learning_rate": 0.00012804670643887264, "grad_norm": 0.9052701592445374, "tokens_per_sec": 132694.46294924957, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2462 |
+
{"event": "train", "epoch": 1, "step": 49200, "loss": 2.363260954618454, "perplexity": 10.62554443690802, "learning_rate": 0.00012794306092547844, "grad_norm": 0.7167115807533264, "tokens_per_sec": 133293.1370309271, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2463 |
+
{"event": "train", "epoch": 1, "step": 49220, "loss": 2.499081015586853, "perplexity": 12.171303581319998, "learning_rate": 0.00012783942617456236, "grad_norm": 0.9309031367301941, "tokens_per_sec": 133109.30704184977, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2464 |
+
{"event": "train", "epoch": 1, "step": 49240, "loss": 2.2870749831199646, "perplexity": 9.846095524228206, "learning_rate": 0.00012773580223669217, "grad_norm": 0.7425404787063599, "tokens_per_sec": 133343.31359493168, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2465 |
+
{"event": "train", "epoch": 1, "step": 49260, "loss": 2.4703084528446198, "perplexity": 11.826094081478407, "learning_rate": 0.00012763218916243008, "grad_norm": 0.8211333155632019, "tokens_per_sec": 134883.98110196655, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2466 |
+
{"event": "train", "epoch": 1, "step": 49280, "loss": 2.9031612277030945, "perplexity": 18.231688887425516, "learning_rate": 0.00012752858700233312, "grad_norm": 1.3942464590072632, "tokens_per_sec": 134708.413921805, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2467 |
+
{"event": "train", "epoch": 1, "step": 49300, "loss": 2.185802400112152, "perplexity": 8.897785273637359, "learning_rate": 0.000127424995806953, "grad_norm": 0.692470371723175, "tokens_per_sec": 135002.2970132086, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2468 |
+
{"event": "train", "epoch": 1, "step": 49320, "loss": 2.3004080951213837, "perplexity": 9.978253700685608, "learning_rate": 0.00012732141562683615, "grad_norm": 0.7530258893966675, "tokens_per_sec": 133716.42199994356, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2469 |
+
{"event": "train", "epoch": 1, "step": 49340, "loss": 2.5201855301856995, "perplexity": 12.430902757342908, "learning_rate": 0.00012721784651252357, "grad_norm": 0.8048357963562012, "tokens_per_sec": 130824.59288055217, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2470 |
+
{"event": "train", "epoch": 1, "step": 49360, "loss": 3.256350338459015, "perplexity": 25.9546384280808, "learning_rate": 0.0001271142885145507, "grad_norm": 1.4898343086242676, "tokens_per_sec": 134237.65390175104, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2471 |
+
{"event": "train", "epoch": 1, "step": 49380, "loss": 2.62956041097641, "perplexity": 13.867672485442027, "learning_rate": 0.00012701074168344786, "grad_norm": 0.7907664775848389, "tokens_per_sec": 133108.01789378977, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2472 |
+
{"event": "train", "epoch": 1, "step": 49400, "loss": 2.894414007663727, "perplexity": 18.072907752213627, "learning_rate": 0.00012690720606973956, "grad_norm": 1.197261095046997, "tokens_per_sec": 133302.83316456972, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2473 |
+
{"event": "train", "epoch": 1, "step": 49420, "loss": 2.5718961358070374, "perplexity": 13.090622521339805, "learning_rate": 0.0001268036817239453, "grad_norm": 0.7409248948097229, "tokens_per_sec": 133941.21264498876, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2474 |
+
{"event": "train", "epoch": 1, "step": 49440, "loss": 2.4842342138290405, "perplexity": 11.991933480905187, "learning_rate": 0.00012670016869657853, "grad_norm": 0.8082995414733887, "tokens_per_sec": 133491.3473482185, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2475 |
+
{"event": "train", "epoch": 1, "step": 49460, "loss": 2.66200590133667, "perplexity": 14.324994824892224, "learning_rate": 0.00012659666703814784, "grad_norm": 0.8045006394386292, "tokens_per_sec": 134492.62356750664, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2476 |
+
{"event": "train", "epoch": 1, "step": 49480, "loss": 2.2570010125637054, "perplexity": 9.55439265450009, "learning_rate": 0.00012649317679915554, "grad_norm": 0.8310077786445618, "tokens_per_sec": 134132.71615157972, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2477 |
+
{"event": "train", "epoch": 1, "step": 49500, "loss": 2.8220348954200745, "perplexity": 16.81102456709478, "learning_rate": 0.00012638969803009897, "grad_norm": 1.0778435468673706, "tokens_per_sec": 134393.98886625722, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2478 |
+
{"event": "train", "epoch": 1, "step": 49520, "loss": 2.6145734190940857, "perplexity": 13.66138744769353, "learning_rate": 0.00012628623078146949, "grad_norm": 0.6739001870155334, "tokens_per_sec": 133721.62599107414, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2479 |
+
{"event": "train", "epoch": 1, "step": 49540, "loss": 2.7663381695747375, "perplexity": 15.9003030624302, "learning_rate": 0.00012618277510375298, "grad_norm": 1.0075337886810303, "tokens_per_sec": 134230.7053826493, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2480 |
+
{"event": "train", "epoch": 1, "step": 49560, "loss": 2.698096990585327, "perplexity": 14.851442381293536, "learning_rate": 0.00012607933104742973, "grad_norm": 1.0127063989639282, "tokens_per_sec": 134216.67943219194, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2481 |
+
{"event": "train", "epoch": 1, "step": 49580, "loss": 2.700808048248291, "perplexity": 14.891760125137552, "learning_rate": 0.00012597589866297437, "grad_norm": 0.763148307800293, "tokens_per_sec": 133145.6713009024, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2482 |
+
{"event": "train", "epoch": 1, "step": 49600, "loss": 2.4156635403633118, "perplexity": 11.19719768573464, "learning_rate": 0.00012587247800085563, "grad_norm": 0.7403770685195923, "tokens_per_sec": 134343.67519549577, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2483 |
+
{"event": "train", "epoch": 1, "step": 49620, "loss": 3.1349651217460632, "perplexity": 22.98783405253884, "learning_rate": 0.00012576906911153683, "grad_norm": 0.8325147032737732, "tokens_per_sec": 133561.1393520525, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2484 |
+
{"event": "train", "epoch": 1, "step": 49640, "loss": 2.365789771080017, "perplexity": 10.652448491964376, "learning_rate": 0.0001256656720454753, "grad_norm": 0.8711017966270447, "tokens_per_sec": 134565.70650666958, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2485 |
+
{"event": "train", "epoch": 1, "step": 49660, "loss": 2.6352365016937256, "perplexity": 13.946610470153292, "learning_rate": 0.00012556228685312254, "grad_norm": 0.6844046711921692, "tokens_per_sec": 134042.1903269254, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2486 |
+
{"event": "train", "epoch": 1, "step": 49680, "loss": 2.3214847445487976, "perplexity": 10.190793804548553, "learning_rate": 0.0001254589135849245, "grad_norm": 0.7029236555099487, "tokens_per_sec": 134165.31967200313, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2487 |
+
{"event": "train", "epoch": 1, "step": 49700, "loss": 2.971184551715851, "perplexity": 19.515022463402993, "learning_rate": 0.00012535555229132125, "grad_norm": 0.8495267033576965, "tokens_per_sec": 134477.49018318587, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 2488 |
+
{"event": "train", "epoch": 1, "step": 49720, "loss": 2.629664361476898, "perplexity": 13.869114111865093, "learning_rate": 0.000125252203022747, "grad_norm": 0.9313228130340576, "tokens_per_sec": 133949.95889272128, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|