Upload hybrid40k/metrics.jsonl with huggingface_hub
Browse files- hybrid40k/metrics.jsonl +84 -0
hybrid40k/metrics.jsonl
CHANGED
|
@@ -1723,3 +1723,87 @@
|
|
| 1723 |
{"event": "train", "epoch": 1, "step": 34420, "loss": 2.256019711494446, "perplexity": 9.545021517477489, "learning_rate": 0.0002040507325817669, "grad_norm": 0.6409354209899902, "tokens_per_sec": 134198.07007957817, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1724 |
{"event": "train", "epoch": 1, "step": 34440, "loss": 2.671065866947174, "perplexity": 14.45536848402357, "learning_rate": 0.00020395297915426578, "grad_norm": 1.067868709564209, "tokens_per_sec": 134453.8099827627, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1725 |
{"event": "train", "epoch": 1, "step": 34460, "loss": 2.3294509053230286, "perplexity": 10.272299519199073, "learning_rate": 0.0002038551994009104, "grad_norm": 0.5544965863227844, "tokens_per_sec": 134750.67745673808, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1723 |
{"event": "train", "epoch": 1, "step": 34420, "loss": 2.256019711494446, "perplexity": 9.545021517477489, "learning_rate": 0.0002040507325817669, "grad_norm": 0.6409354209899902, "tokens_per_sec": 134198.07007957817, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1724 |
{"event": "train", "epoch": 1, "step": 34440, "loss": 2.671065866947174, "perplexity": 14.45536848402357, "learning_rate": 0.00020395297915426578, "grad_norm": 1.067868709564209, "tokens_per_sec": 134453.8099827627, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1725 |
{"event": "train", "epoch": 1, "step": 34460, "loss": 2.3294509053230286, "perplexity": 10.272299519199073, "learning_rate": 0.0002038551994009104, "grad_norm": 0.5544965863227844, "tokens_per_sec": 134750.67745673808, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1726 |
+
{"event": "train", "epoch": 1, "step": 34480, "loss": 5.749482750892639, "perplexity": 314.0281874702021, "learning_rate": 0.00020375739336941166, "grad_norm": 1.444145917892456, "tokens_per_sec": 126236.36016213192, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1727 |
+
{"event": "train", "epoch": 1, "step": 34500, "loss": 2.0551145672798157, "perplexity": 7.807732332051842, "learning_rate": 0.00020365956110749304, "grad_norm": 0.5248690843582153, "tokens_per_sec": 133930.50983632758, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1728 |
+
{"event": "train", "epoch": 1, "step": 34520, "loss": 2.01384899020195, "perplexity": 7.492098937159111, "learning_rate": 0.00020356170266289092, "grad_norm": 0.5066630244255066, "tokens_per_sec": 131597.22122461797, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1729 |
+
{"event": "train", "epoch": 1, "step": 34540, "loss": 2.13909649848938, "perplexity": 8.491761842213585, "learning_rate": 0.00020346381808335437, "grad_norm": 0.6079972982406616, "tokens_per_sec": 133495.23717536536, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1730 |
+
{"event": "train", "epoch": 1, "step": 34560, "loss": 2.262898772954941, "perplexity": 9.610908668194627, "learning_rate": 0.00020336590741664535, "grad_norm": 0.8205399513244629, "tokens_per_sec": 134395.82872224227, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1731 |
+
{"event": "train", "epoch": 1, "step": 34580, "loss": 2.139455944299698, "perplexity": 8.494814719069014, "learning_rate": 0.00020326797071053832, "grad_norm": 0.5373108386993408, "tokens_per_sec": 134860.28986940708, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1732 |
+
{"event": "train", "epoch": 1, "step": 34600, "loss": 2.117051839828491, "perplexity": 8.306612130068203, "learning_rate": 0.00020317000801282073, "grad_norm": 0.6197054982185364, "tokens_per_sec": 134190.47056066737, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1733 |
+
{"event": "train", "epoch": 1, "step": 34620, "loss": 2.6921022534370422, "perplexity": 14.762678212699635, "learning_rate": 0.00020307201937129252, "grad_norm": 0.7444853186607361, "tokens_per_sec": 135378.2261140913, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1734 |
+
{"event": "train", "epoch": 1, "step": 34640, "loss": 2.048178017139435, "perplexity": 7.753761009047589, "learning_rate": 0.00020297400483376628, "grad_norm": 0.5374367833137512, "tokens_per_sec": 125174.82483405831, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1735 |
+
{"event": "train", "epoch": 1, "step": 34660, "loss": 2.1785719096660614, "perplexity": 8.833681950733393, "learning_rate": 0.00020287596444806732, "grad_norm": 0.5391154885292053, "tokens_per_sec": 134428.56029280298, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1736 |
+
{"event": "train", "epoch": 1, "step": 34680, "loss": 2.439733177423477, "perplexity": 11.469979884874448, "learning_rate": 0.00020277789826203354, "grad_norm": 0.6794152855873108, "tokens_per_sec": 134508.55019739945, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1737 |
+
{"event": "train", "epoch": 1, "step": 34700, "loss": 2.057367205619812, "perplexity": 7.825340153832935, "learning_rate": 0.00020267980632351546, "grad_norm": 0.5152167081832886, "tokens_per_sec": 135229.8388249555, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1738 |
+
{"event": "train", "epoch": 1, "step": 34720, "loss": 2.7385159134864807, "perplexity": 15.464018117330706, "learning_rate": 0.0002025816886803761, "grad_norm": 0.7817720770835876, "tokens_per_sec": 133615.02506953498, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1739 |
+
{"event": "train", "epoch": 1, "step": 34740, "loss": 2.167048066854477, "perplexity": 8.732468293709072, "learning_rate": 0.000202483545380491, "grad_norm": 0.7789532542228699, "tokens_per_sec": 132122.60412713245, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1740 |
+
{"event": "train", "epoch": 1, "step": 34760, "loss": 2.064698874950409, "perplexity": 7.882923794403348, "learning_rate": 0.0002023853764717483, "grad_norm": 0.5619624853134155, "tokens_per_sec": 133873.3701319068, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1741 |
+
{"event": "train", "epoch": 1, "step": 34780, "loss": 5.0771644115448, "perplexity": 160.31881261809252, "learning_rate": 0.00020228718200204857, "grad_norm": 2.334294080734253, "tokens_per_sec": 134297.5983490181, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1742 |
+
{"event": "train", "epoch": 1, "step": 34800, "loss": 2.091657370328903, "perplexity": 8.098325973078534, "learning_rate": 0.00020218896201930507, "grad_norm": 0.6283835768699646, "tokens_per_sec": 134081.4206182972, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1743 |
+
{"event": "train", "epoch": 1, "step": 34820, "loss": 2.2034245133399963, "perplexity": 9.05597275849873, "learning_rate": 0.00020209071657144317, "grad_norm": 0.5198476314544678, "tokens_per_sec": 133805.72657822154, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1744 |
+
{"event": "train", "epoch": 1, "step": 34840, "loss": 2.7355422377586365, "perplexity": 15.418101446480849, "learning_rate": 0.00020199244570640084, "grad_norm": 0.6501437425613403, "tokens_per_sec": 132777.6609081582, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1745 |
+
{"event": "train", "epoch": 1, "step": 34860, "loss": 2.1936598122119904, "perplexity": 8.967974229970062, "learning_rate": 0.0002018941494721284, "grad_norm": 0.9712774157524109, "tokens_per_sec": 133959.3591188869, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1746 |
+
{"event": "train", "epoch": 1, "step": 34880, "loss": 1.9904428124427795, "perplexity": 7.318773889016358, "learning_rate": 0.00020179582791658859, "grad_norm": 0.4935857355594635, "tokens_per_sec": 133891.49822648917, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1747 |
+
{"event": "train", "epoch": 1, "step": 34900, "loss": 2.418568938970566, "perplexity": 11.22977731378092, "learning_rate": 0.00020169748108775655, "grad_norm": 0.5817787051200867, "tokens_per_sec": 134170.6896429865, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1748 |
+
{"event": "train", "epoch": 1, "step": 34920, "loss": 2.3762620091438293, "perplexity": 10.764589628017653, "learning_rate": 0.00020159910903361965, "grad_norm": 0.6307847499847412, "tokens_per_sec": 133500.55363909312, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1749 |
+
{"event": "train", "epoch": 1, "step": 34940, "loss": 2.246529072523117, "perplexity": 9.45486167826384, "learning_rate": 0.00020150071180217766, "grad_norm": 0.7445127367973328, "tokens_per_sec": 135081.64370765767, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1750 |
+
{"event": "train", "epoch": 1, "step": 34960, "loss": 1.765368491411209, "perplexity": 5.843725323978264, "learning_rate": 0.00020140228944144262, "grad_norm": 0.4840727150440216, "tokens_per_sec": 133478.90142453683, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1751 |
+
{"event": "train", "epoch": 1, "step": 34980, "loss": 2.2531924843788147, "perplexity": 9.518073685594475, "learning_rate": 0.00020130384199943874, "grad_norm": 0.5552508234977722, "tokens_per_sec": 133943.69280817077, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1752 |
+
{"event": "train", "epoch": 1, "step": 35000, "loss": 1.97954723238945, "perplexity": 7.239464447989522, "learning_rate": 0.0002012053695242026, "grad_norm": 0.4910478889942169, "tokens_per_sec": 134832.90312048723, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1753 |
+
{"event": "train", "epoch": 1, "step": 35020, "loss": 2.192440986633301, "perplexity": 8.957050492007468, "learning_rate": 0.00020110687206378286, "grad_norm": 0.5632908940315247, "tokens_per_sec": 134789.5304612536, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1754 |
+
{"event": "train", "epoch": 1, "step": 35040, "loss": 2.073599874973297, "perplexity": 7.953402901218672, "learning_rate": 0.00020100834966624043, "grad_norm": 0.5108877420425415, "tokens_per_sec": 134508.68183815578, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1755 |
+
{"event": "train", "epoch": 1, "step": 35060, "loss": 2.1374931037425995, "perplexity": 8.478157105681086, "learning_rate": 0.00020090980237964844, "grad_norm": 0.8131739497184753, "tokens_per_sec": 134505.12762817426, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1756 |
+
{"event": "train", "epoch": 1, "step": 35080, "loss": 2.2224020957946777, "perplexity": 9.22947434136262, "learning_rate": 0.00020081123025209204, "grad_norm": 0.5804567337036133, "tokens_per_sec": 134555.16713006838, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1757 |
+
{"event": "train", "epoch": 1, "step": 35100, "loss": 2.094294995069504, "perplexity": 8.119714513093609, "learning_rate": 0.00020071263333166882, "grad_norm": 0.5792332887649536, "tokens_per_sec": 133773.0371616229, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1758 |
+
{"event": "train", "epoch": 1, "step": 35120, "loss": 2.25205996632576, "perplexity": 9.507300396938662, "learning_rate": 0.00020061401166648798, "grad_norm": 0.5829582214355469, "tokens_per_sec": 134708.54595405722, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1759 |
+
{"event": "train", "epoch": 1, "step": 35140, "loss": 2.4549891650676727, "perplexity": 11.64630736124373, "learning_rate": 0.0002005153653046711, "grad_norm": 0.6371768712997437, "tokens_per_sec": 134433.6883685217, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1760 |
+
{"event": "train", "epoch": 1, "step": 35160, "loss": 2.0653070509433746, "perplexity": 7.887719457565268, "learning_rate": 0.00020041669429435183, "grad_norm": 0.6575947999954224, "tokens_per_sec": 134947.28676909543, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1761 |
+
{"event": "train", "epoch": 1, "step": 35180, "loss": 2.0657059848308563, "perplexity": 7.890866763893673, "learning_rate": 0.0002003179986836758, "grad_norm": 0.575517475605011, "tokens_per_sec": 133848.5986615038, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1762 |
+
{"event": "train", "epoch": 1, "step": 35200, "loss": 2.1154821515083313, "perplexity": 8.293583566094998, "learning_rate": 0.00020021927852080046, "grad_norm": 0.5576425194740295, "tokens_per_sec": 134553.5863659682, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1763 |
+
{"event": "train", "epoch": 1, "step": 35220, "loss": 2.6905109882354736, "perplexity": 14.739205557140775, "learning_rate": 0.00020012053385389542, "grad_norm": 0.8388769030570984, "tokens_per_sec": 134385.18453854608, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1764 |
+
{"event": "train", "epoch": 1, "step": 35240, "loss": 1.6459608972072601, "perplexity": 5.1859907175391315, "learning_rate": 0.00020002176473114236, "grad_norm": 2.5568747520446777, "tokens_per_sec": 133710.0476627804, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1765 |
+
{"event": "train", "epoch": 1, "step": 35260, "loss": 1.9784825146198273, "perplexity": 7.231760563508322, "learning_rate": 0.00019992297120073458, "grad_norm": 0.5653070211410522, "tokens_per_sec": 134194.40123884715, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1766 |
+
{"event": "train", "epoch": 1, "step": 35280, "loss": 1.9344411790370941, "perplexity": 6.920175835333937, "learning_rate": 0.00019982415331087767, "grad_norm": 0.48925331234931946, "tokens_per_sec": 131597.7252416968, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1767 |
+
{"event": "train", "epoch": 1, "step": 35300, "loss": 1.7731938362121582, "perplexity": 5.889633880431004, "learning_rate": 0.0001997253111097887, "grad_norm": 0.4606313407421112, "tokens_per_sec": 134568.60512469037, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1768 |
+
{"event": "train", "epoch": 1, "step": 35320, "loss": 1.9655683636665344, "perplexity": 7.138968967878246, "learning_rate": 0.00019962644464569697, "grad_norm": 0.5104071497917175, "tokens_per_sec": 133497.8305194061, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1769 |
+
{"event": "train", "epoch": 1, "step": 35340, "loss": 2.5247022807598114, "perplexity": 12.487177037280874, "learning_rate": 0.00019952755396684328, "grad_norm": 0.7276614904403687, "tokens_per_sec": 132444.72768061922, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1770 |
+
{"event": "train", "epoch": 1, "step": 35360, "loss": 1.7740582823753357, "perplexity": 5.894727353040708, "learning_rate": 0.00019942863912148057, "grad_norm": 0.44693177938461304, "tokens_per_sec": 134470.2536814741, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1771 |
+
{"event": "train", "epoch": 1, "step": 35380, "loss": 1.8993458449840546, "perplexity": 6.68152226109181, "learning_rate": 0.00019932970015787334, "grad_norm": 0.5046491026878357, "tokens_per_sec": 134349.19078238666, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1772 |
+
{"event": "train", "epoch": 1, "step": 35400, "loss": 3.345367968082428, "perplexity": 28.37101337355189, "learning_rate": 0.000199230737124298, "grad_norm": 19.851089477539062, "tokens_per_sec": 132743.93329527928, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1773 |
+
{"event": "train", "epoch": 1, "step": 35420, "loss": 3.2489534616470337, "perplexity": 25.763363455746596, "learning_rate": 0.00019913175006904245, "grad_norm": 1.9639933109283447, "tokens_per_sec": 133521.04543577795, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1774 |
+
{"event": "train", "epoch": 1, "step": 35440, "loss": 3.284035325050354, "perplexity": 26.683231250452934, "learning_rate": 0.00019903273904040678, "grad_norm": 17.609254837036133, "tokens_per_sec": 133811.97976058922, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1775 |
+
{"event": "train", "epoch": 1, "step": 35460, "loss": 3.283729374408722, "perplexity": 26.675068747456226, "learning_rate": 0.0001989337040867024, "grad_norm": 11.593392372131348, "tokens_per_sec": 135377.42602843893, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1776 |
+
{"event": "train", "epoch": 1, "step": 35480, "loss": 1.925680011510849, "perplexity": 6.859811831223926, "learning_rate": 0.00019883464525625232, "grad_norm": 0.8177341222763062, "tokens_per_sec": 134430.79555975928, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1777 |
+
{"event": "train", "epoch": 1, "step": 35500, "loss": 2.2215216755867004, "perplexity": 9.221352101660116, "learning_rate": 0.0001987355625973916, "grad_norm": 0.5391103029251099, "tokens_per_sec": 133894.1069894542, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1778 |
+
{"event": "train", "epoch": 1, "step": 35520, "loss": 2.0015020072460175, "perplexity": 7.4001628538575694, "learning_rate": 0.00019863645615846658, "grad_norm": 0.8578023314476013, "tokens_per_sec": 134203.7047613189, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1779 |
+
{"event": "train", "epoch": 1, "step": 35540, "loss": 1.9952532351016998, "perplexity": 7.3540650995332815, "learning_rate": 0.00019853732598783534, "grad_norm": 0.6817808747291565, "tokens_per_sec": 135200.30679213582, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1780 |
+
{"event": "train", "epoch": 1, "step": 35560, "loss": 2.085732251405716, "perplexity": 8.050484302368377, "learning_rate": 0.0001984381721338676, "grad_norm": 0.5661920309066772, "tokens_per_sec": 133734.63774120633, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1781 |
+
{"event": "train", "epoch": 1, "step": 35580, "loss": 2.2308103442192078, "perplexity": 9.307405226440025, "learning_rate": 0.00019833899464494445, "grad_norm": 0.7827403545379639, "tokens_per_sec": 134248.5369904226, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1782 |
+
{"event": "train", "epoch": 1, "step": 35600, "loss": 2.3053523004055023, "perplexity": 10.027710396639495, "learning_rate": 0.0001982397935694587, "grad_norm": 0.8150985836982727, "tokens_per_sec": 134645.72784779745, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1783 |
+
{"event": "train", "epoch": 1, "step": 35620, "loss": 1.962687075138092, "perplexity": 7.118429143276524, "learning_rate": 0.00019814056895581464, "grad_norm": 0.5112029910087585, "tokens_per_sec": 134798.78447919057, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1784 |
+
{"event": "train", "epoch": 1, "step": 35640, "loss": 2.202931433916092, "perplexity": 9.051508545364342, "learning_rate": 0.0001980413208524278, "grad_norm": 0.5286509990692139, "tokens_per_sec": 134902.38394665113, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1785 |
+
{"event": "train", "epoch": 1, "step": 35660, "loss": 2.31080824136734, "perplexity": 10.08257051323827, "learning_rate": 0.0001979420493077256, "grad_norm": 0.7072645425796509, "tokens_per_sec": 134161.12877379855, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1786 |
+
{"event": "train", "epoch": 1, "step": 35680, "loss": 2.509016513824463, "perplexity": 12.29283428089593, "learning_rate": 0.00019784275437014648, "grad_norm": 0.6212993860244751, "tokens_per_sec": 133807.5503627065, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1787 |
+
{"event": "train", "epoch": 1, "step": 35700, "loss": 2.2301938831806183, "perplexity": 9.301669341903878, "learning_rate": 0.00019774343608814054, "grad_norm": 0.5258610248565674, "tokens_per_sec": 134702.7367797921, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1788 |
+
{"event": "train", "epoch": 1, "step": 35720, "loss": 1.6682372838258743, "perplexity": 5.302812201138089, "learning_rate": 0.00019764409451016924, "grad_norm": 1.3354655504226685, "tokens_per_sec": 133603.59506837223, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1789 |
+
{"event": "train", "epoch": 1, "step": 35740, "loss": 2.025890737771988, "perplexity": 7.582862279207978, "learning_rate": 0.00019754472968470542, "grad_norm": 0.5032340884208679, "tokens_per_sec": 133251.7827040894, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1790 |
+
{"event": "train", "epoch": 1, "step": 35760, "loss": 2.042647272348404, "perplexity": 7.710995307839269, "learning_rate": 0.00019744534166023307, "grad_norm": 0.5140067934989929, "tokens_per_sec": 133833.08856674616, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1791 |
+
{"event": "train", "epoch": 1, "step": 35780, "loss": 2.0253571569919586, "perplexity": 7.578817288898696, "learning_rate": 0.00019734593048524783, "grad_norm": 0.6572225093841553, "tokens_per_sec": 134364.8207383278, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1792 |
+
{"event": "train", "epoch": 1, "step": 35800, "loss": 2.022695094347, "perplexity": 7.558668832625983, "learning_rate": 0.0001972464962082564, "grad_norm": 0.6224313974380493, "tokens_per_sec": 135262.04610203387, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1793 |
+
{"event": "train", "epoch": 1, "step": 35820, "loss": 1.927087515592575, "perplexity": 6.869473842441268, "learning_rate": 0.00019714703887777676, "grad_norm": 0.4812558591365814, "tokens_per_sec": 134309.40991164866, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1794 |
+
{"event": "train", "epoch": 1, "step": 35840, "loss": 2.1334479451179504, "perplexity": 8.443930887256403, "learning_rate": 0.00019704755854233822, "grad_norm": 0.5171895623207092, "tokens_per_sec": 135412.23849839452, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1795 |
+
{"event": "train", "epoch": 1, "step": 35860, "loss": 2.039117008447647, "perplexity": 7.683821453126039, "learning_rate": 0.00019694805525048129, "grad_norm": 0.5471788644790649, "tokens_per_sec": 134221.26703731445, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1796 |
+
{"event": "train", "epoch": 1, "step": 35880, "loss": 1.9660257995128632, "perplexity": 7.142235335209778, "learning_rate": 0.00019684852905075767, "grad_norm": 0.5459998846054077, "tokens_per_sec": 133085.07523566522, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1797 |
+
{"event": "train", "epoch": 1, "step": 35900, "loss": 2.60455122590065, "perplexity": 13.525154201677655, "learning_rate": 0.0001967489799917302, "grad_norm": 0.9323421716690063, "tokens_per_sec": 134697.5881578122, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1798 |
+
{"event": "train", "epoch": 1, "step": 35920, "loss": 3.1516083478927612, "perplexity": 23.37362729009165, "learning_rate": 0.00019664940812197303, "grad_norm": 1.218290090560913, "tokens_per_sec": 134597.3345450842, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1799 |
+
{"event": "train", "epoch": 1, "step": 35940, "loss": 1.6181427389383316, "perplexity": 5.043714118396903, "learning_rate": 0.00019654981349007125, "grad_norm": 0.6891047954559326, "tokens_per_sec": 134483.41153665885, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1800 |
+
{"event": "train", "epoch": 1, "step": 35960, "loss": 2.05167493224144, "perplexity": 7.7809227164311245, "learning_rate": 0.00019645019614462108, "grad_norm": 0.5133351683616638, "tokens_per_sec": 134756.35864054272, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1801 |
+
{"event": "train", "epoch": 1, "step": 35980, "loss": 2.334009885787964, "perplexity": 10.319237645740055, "learning_rate": 0.00019635055613423006, "grad_norm": 0.7203882932662964, "tokens_per_sec": 133971.2418480062, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1802 |
+
{"event": "train", "epoch": 1, "step": 36000, "loss": 1.8362336158752441, "perplexity": 6.272867683504979, "learning_rate": 0.00019625089350751632, "grad_norm": 0.5017813444137573, "tokens_per_sec": 134210.1262545676, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1803 |
+
{"event": "train", "epoch": 1, "step": 36020, "loss": 2.2419239282608032, "perplexity": 9.41142077883178, "learning_rate": 0.0001961512083131095, "grad_norm": 0.968594491481781, "tokens_per_sec": 133854.46476018697, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1804 |
+
{"event": "train", "epoch": 1, "step": 36040, "loss": 2.1078411042690277, "perplexity": 8.230453399732491, "learning_rate": 0.0001960515005996501, "grad_norm": 0.532179594039917, "tokens_per_sec": 133534.0181784088, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1805 |
+
{"event": "train", "epoch": 1, "step": 36060, "loss": 2.3853703439235687, "perplexity": 10.863084997571375, "learning_rate": 0.00019595177041578952, "grad_norm": 0.5954138040542603, "tokens_per_sec": 135015.82447023274, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1806 |
+
{"event": "train", "epoch": 1, "step": 36080, "loss": 1.8199823498725891, "perplexity": 6.171749516756895, "learning_rate": 0.00019585201781019017, "grad_norm": 0.5117174386978149, "tokens_per_sec": 134796.4047532179, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1807 |
+
{"event": "train", "epoch": 1, "step": 36100, "loss": 2.091463655233383, "perplexity": 8.096757357026316, "learning_rate": 0.00019575224283152544, "grad_norm": 0.5800238251686096, "tokens_per_sec": 133480.06813129396, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1808 |
+
{"event": "train", "epoch": 1, "step": 36120, "loss": 2.2208335399627686, "perplexity": 9.215008743573797, "learning_rate": 0.00019565244552847947, "grad_norm": 0.6420395374298096, "tokens_per_sec": 133719.674446933, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1809 |
+
{"event": "train", "epoch": 1, "step": 36140, "loss": 2.224970519542694, "perplexity": 9.25321001102321, "learning_rate": 0.00019555262594974762, "grad_norm": 0.5741497278213501, "tokens_per_sec": 133491.08803446862, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|