Upload hybrid40k/metrics.jsonl with huggingface_hub
Browse files- hybrid40k/metrics.jsonl +84 -0
hybrid40k/metrics.jsonl
CHANGED
|
@@ -1888,3 +1888,87 @@
|
|
| 1888 |
{"event": "train", "epoch": 1, "step": 37720, "loss": 2.582239180803299, "perplexity": 13.226722047559925, "learning_rate": 0.00018760066109437836, "grad_norm": 2.465475559234619, "tokens_per_sec": 134218.3833632, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1889 |
{"event": "train", "epoch": 1, "step": 37740, "loss": 2.0542782843112946, "perplexity": 7.801205587962619, "learning_rate": 0.0001874992181539734, "grad_norm": 0.6344608664512634, "tokens_per_sec": 134007.55599323718, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1890 |
{"event": "train", "epoch": 1, "step": 37760, "loss": 4.825017690658569, "perplexity": 124.58867241936522, "learning_rate": 0.0001873977569161739, "grad_norm": 1.8713860511779785, "tokens_per_sec": 135079.91778775465, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1888 |
{"event": "train", "epoch": 1, "step": 37720, "loss": 2.582239180803299, "perplexity": 13.226722047559925, "learning_rate": 0.00018760066109437836, "grad_norm": 2.465475559234619, "tokens_per_sec": 134218.3833632, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1889 |
{"event": "train", "epoch": 1, "step": 37740, "loss": 2.0542782843112946, "perplexity": 7.801205587962619, "learning_rate": 0.0001874992181539734, "grad_norm": 0.6344608664512634, "tokens_per_sec": 134007.55599323718, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1890 |
{"event": "train", "epoch": 1, "step": 37760, "loss": 4.825017690658569, "perplexity": 124.58867241936522, "learning_rate": 0.0001873977569161739, "grad_norm": 1.8713860511779785, "tokens_per_sec": 135079.91778775465, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1891 |
+
{"event": "train", "epoch": 1, "step": 37780, "loss": 2.5871917009353638, "perplexity": 13.29239013181381, "learning_rate": 0.00018729627743048689, "grad_norm": 0.6686869859695435, "tokens_per_sec": 134316.6291116701, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1892 |
+
{"event": "train", "epoch": 1, "step": 37800, "loss": 3.8882760405540466, "perplexity": 48.82663877961209, "learning_rate": 0.0001871947797464284, "grad_norm": 1.8966728448867798, "tokens_per_sec": 133903.36891906112, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1893 |
+
{"event": "train", "epoch": 1, "step": 37820, "loss": 2.685690224170685, "perplexity": 14.66832231761011, "learning_rate": 0.00018709326391352324, "grad_norm": 0.8877544403076172, "tokens_per_sec": 133885.23761011474, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1894 |
+
{"event": "train", "epoch": 1, "step": 37840, "loss": 2.3363747894763947, "perplexity": 10.343670528229929, "learning_rate": 0.0001869917299813051, "grad_norm": 0.5699828267097473, "tokens_per_sec": 135123.74325506767, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1895 |
+
{"event": "train", "epoch": 1, "step": 37860, "loss": 4.09350460767746, "perplexity": 59.94962388710582, "learning_rate": 0.00018689017799931648, "grad_norm": 3.170365571975708, "tokens_per_sec": 134093.063355162, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1896 |
+
{"event": "train", "epoch": 1, "step": 37880, "loss": 3.9470357298851013, "perplexity": 51.78164432909349, "learning_rate": 0.00018678860801710887, "grad_norm": 1.2862963676452637, "tokens_per_sec": 134087.43796018517, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1897 |
+
{"event": "train", "epoch": 1, "step": 37900, "loss": 2.6917575895786285, "perplexity": 14.757590927818304, "learning_rate": 0.00018668702008424232, "grad_norm": 0.672734260559082, "tokens_per_sec": 134657.07300087492, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1898 |
+
{"event": "train", "epoch": 1, "step": 37920, "loss": 2.9194438457489014, "perplexity": 18.530978510853885, "learning_rate": 0.00018658541425028557, "grad_norm": 0.8451985716819763, "tokens_per_sec": 130585.43793296424, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1899 |
+
{"event": "train", "epoch": 1, "step": 37940, "loss": 2.094615161418915, "perplexity": 8.122314588653666, "learning_rate": 0.00018648379056481642, "grad_norm": 0.572322428226471, "tokens_per_sec": 132807.1705904862, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1900 |
+
{"event": "train", "epoch": 1, "step": 37960, "loss": 2.0331253707408905, "perplexity": 7.637920427253627, "learning_rate": 0.0001863821490774212, "grad_norm": 0.5374829173088074, "tokens_per_sec": 133377.6053879373, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1901 |
+
{"event": "train", "epoch": 1, "step": 37980, "loss": 2.3184870779514313, "perplexity": 10.160290943904815, "learning_rate": 0.00018628048983769483, "grad_norm": 0.9968435764312744, "tokens_per_sec": 134769.30824497528, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1902 |
+
{"event": "train", "epoch": 1, "step": 38000, "loss": 1.9361362755298615, "perplexity": 6.9319161487926575, "learning_rate": 0.00018617881289524103, "grad_norm": 0.4925697147846222, "tokens_per_sec": 134293.00552458115, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1903 |
+
{"event": "train", "epoch": 1, "step": 38020, "loss": 2.234333962202072, "perplexity": 9.340258814624592, "learning_rate": 0.00018607711829967226, "grad_norm": 0.5880957841873169, "tokens_per_sec": 132604.58800702778, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1904 |
+
{"event": "train", "epoch": 1, "step": 38040, "loss": 2.273580640554428, "perplexity": 9.71412139303082, "learning_rate": 0.00018597540610060928, "grad_norm": 0.6031818985939026, "tokens_per_sec": 134256.27423498544, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1905 |
+
{"event": "train", "epoch": 1, "step": 38060, "loss": 2.144183486700058, "perplexity": 8.535069393704038, "learning_rate": 0.0001858736763476817, "grad_norm": 0.5524773001670837, "tokens_per_sec": 133559.452067787, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1906 |
+
{"event": "train", "epoch": 1, "step": 38080, "loss": 2.7147802114486694, "perplexity": 15.101290616331813, "learning_rate": 0.0001857719290905275, "grad_norm": 0.843431293964386, "tokens_per_sec": 133755.5919800533, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1907 |
+
{"event": "train", "epoch": 1, "step": 38100, "loss": 2.04681134223938, "perplexity": 7.7431713764363215, "learning_rate": 0.00018567016437879335, "grad_norm": 0.6099703907966614, "tokens_per_sec": 133953.35326664854, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1908 |
+
{"event": "train", "epoch": 1, "step": 38120, "loss": 2.2890551686286926, "perplexity": 9.865611936584092, "learning_rate": 0.00018556838226213449, "grad_norm": 0.6587672829627991, "tokens_per_sec": 135210.41540529, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1909 |
+
{"event": "train", "epoch": 1, "step": 38140, "loss": 2.147701531648636, "perplexity": 8.565149031204971, "learning_rate": 0.00018546658279021438, "grad_norm": 0.6398254632949829, "tokens_per_sec": 135166.13491343067, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1910 |
+
{"event": "train", "epoch": 1, "step": 38160, "loss": 1.9851835370063782, "perplexity": 7.280383482627711, "learning_rate": 0.00018536476601270526, "grad_norm": 0.5482812523841858, "tokens_per_sec": 133782.54279487333, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1911 |
+
{"event": "train", "epoch": 1, "step": 38180, "loss": 2.493864595890045, "perplexity": 12.107978262897289, "learning_rate": 0.00018526293197928764, "grad_norm": 0.645856499671936, "tokens_per_sec": 133321.5830234857, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1912 |
+
{"event": "train", "epoch": 1, "step": 38200, "loss": 2.308309316635132, "perplexity": 10.057406383147075, "learning_rate": 0.00018516108073965055, "grad_norm": 0.5559004545211792, "tokens_per_sec": 134849.70429974067, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1913 |
+
{"event": "train", "epoch": 1, "step": 38220, "loss": 1.641066074371338, "perplexity": 5.160668236835481, "learning_rate": 0.0001850592123434912, "grad_norm": 0.4569888114929199, "tokens_per_sec": 134821.13156048997, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1914 |
+
{"event": "train", "epoch": 1, "step": 38240, "loss": 2.464301258325577, "perplexity": 11.75526538779654, "learning_rate": 0.00018495732684051553, "grad_norm": 0.7447117567062378, "tokens_per_sec": 133298.30812666152, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1915 |
+
{"event": "train", "epoch": 1, "step": 38260, "loss": 4.823315262794495, "perplexity": 124.37674963470118, "learning_rate": 0.00018485542428043752, "grad_norm": 4.238852024078369, "tokens_per_sec": 134637.02239885737, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1916 |
+
{"event": "train", "epoch": 1, "step": 38280, "loss": 2.3884884417057037, "perplexity": 10.897010022094882, "learning_rate": 0.00018475350471297954, "grad_norm": 0.6209889054298401, "tokens_per_sec": 134759.13334627595, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1917 |
+
{"event": "train", "epoch": 1, "step": 38300, "loss": 2.2912719547748566, "perplexity": 9.887506146873632, "learning_rate": 0.00018465156818787233, "grad_norm": 0.6548249125480652, "tokens_per_sec": 135256.58841787756, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1918 |
+
{"event": "train", "epoch": 1, "step": 38320, "loss": 2.2171832621097565, "perplexity": 9.181432719432523, "learning_rate": 0.00018454961475485488, "grad_norm": 0.5871453881263733, "tokens_per_sec": 134231.2297740886, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1919 |
+
{"event": "train", "epoch": 1, "step": 38340, "loss": 2.9404446482658386, "perplexity": 18.924259080737503, "learning_rate": 0.0001844476444636744, "grad_norm": 0.9699141979217529, "tokens_per_sec": 134706.56549744972, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1920 |
+
{"event": "train", "epoch": 1, "step": 38360, "loss": 2.1032483875751495, "perplexity": 8.192739928939776, "learning_rate": 0.00018434565736408635, "grad_norm": 0.6174697279930115, "tokens_per_sec": 133877.02143957856, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1921 |
+
{"event": "train", "epoch": 1, "step": 38380, "loss": 3.1103126406669617, "perplexity": 22.428055226899346, "learning_rate": 0.00018424365350585436, "grad_norm": 0.9035955667495728, "tokens_per_sec": 133656.4752231839, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1922 |
+
{"event": "train", "epoch": 1, "step": 38400, "loss": 1.7570283114910126, "perplexity": 5.795190280206309, "learning_rate": 0.00018414163293875032, "grad_norm": 0.4909607768058777, "tokens_per_sec": 134139.52360977046, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1923 |
+
{"event": "train", "epoch": 1, "step": 38420, "loss": 2.6286917626857758, "perplexity": 13.855631585853018, "learning_rate": 0.0001840395957125543, "grad_norm": 0.6412473917007446, "tokens_per_sec": 134027.15813452748, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1924 |
+
{"event": "train", "epoch": 1, "step": 38440, "loss": 2.3861907720565796, "perplexity": 10.872001035098567, "learning_rate": 0.00018393754187705425, "grad_norm": 0.6721919775009155, "tokens_per_sec": 134326.60601073137, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1925 |
+
{"event": "train", "epoch": 1, "step": 38460, "loss": 2.2038375437259674, "perplexity": 9.059713922976634, "learning_rate": 0.0001838354714820464, "grad_norm": 0.5844438076019287, "tokens_per_sec": 133511.05814147773, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1926 |
+
{"event": "train", "epoch": 1, "step": 38480, "loss": 3.168699026107788, "perplexity": 23.776531579584713, "learning_rate": 0.00018373338457733512, "grad_norm": 0.8149197101593018, "tokens_per_sec": 134211.567898739, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1927 |
+
{"event": "train", "epoch": 1, "step": 38500, "loss": 2.0381393134593964, "perplexity": 7.676312690638558, "learning_rate": 0.00018363128121273267, "grad_norm": 0.525040328502655, "tokens_per_sec": 133909.76170233497, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1928 |
+
{"event": "train", "epoch": 1, "step": 38520, "loss": 2.1926617324352264, "perplexity": 8.959027941550026, "learning_rate": 0.00018352916143805952, "grad_norm": 0.5846948623657227, "tokens_per_sec": 134028.3344453687, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1929 |
+
{"event": "train", "epoch": 1, "step": 38540, "loss": 2.2199984192848206, "perplexity": 9.207316311726093, "learning_rate": 0.0001834270253031442, "grad_norm": 0.5362977385520935, "tokens_per_sec": 133764.1838142548, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1930 |
+
{"event": "train", "epoch": 1, "step": 38560, "loss": 2.4664388298988342, "perplexity": 11.780419984222663, "learning_rate": 0.00018332487285782287, "grad_norm": 0.6166427731513977, "tokens_per_sec": 134579.2783855847, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1931 |
+
{"event": "train", "epoch": 1, "step": 38580, "loss": 2.7838633954524994, "perplexity": 16.181415550160413, "learning_rate": 0.00018322270415193983, "grad_norm": 0.6322245001792908, "tokens_per_sec": 133788.01240157345, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1932 |
+
{"event": "train", "epoch": 1, "step": 38600, "loss": 1.7984780073165894, "perplexity": 6.040446948569848, "learning_rate": 0.00018312051923534753, "grad_norm": 0.5304988622665405, "tokens_per_sec": 133109.43595802915, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1933 |
+
{"event": "train", "epoch": 1, "step": 38620, "loss": 2.1646067202091217, "perplexity": 8.711175313882809, "learning_rate": 0.000183018318157906, "grad_norm": 0.5664306879043579, "tokens_per_sec": 134259.15953751354, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1934 |
+
{"event": "train", "epoch": 1, "step": 38640, "loss": 2.6397989988327026, "perplexity": 14.010387220508925, "learning_rate": 0.00018291610096948343, "grad_norm": 0.6548998951911926, "tokens_per_sec": 133453.36861821695, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1935 |
+
{"event": "train", "epoch": 1, "step": 38660, "loss": 1.8497258126735687, "perplexity": 6.358075979729946, "learning_rate": 0.00018281386771995563, "grad_norm": 0.57149338722229, "tokens_per_sec": 133335.29315458145, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1936 |
+
{"event": "train", "epoch": 1, "step": 38680, "loss": 1.741002231836319, "perplexity": 5.703056343990243, "learning_rate": 0.0001827116184592065, "grad_norm": 0.5138886570930481, "tokens_per_sec": 133331.54198947232, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1937 |
+
{"event": "train", "epoch": 1, "step": 38700, "loss": 1.9496559798717499, "perplexity": 7.026269986460753, "learning_rate": 0.00018260935323712745, "grad_norm": 0.5707939863204956, "tokens_per_sec": 132844.39715209755, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1938 |
+
{"event": "train", "epoch": 1, "step": 38720, "loss": 1.8682747781276703, "perplexity": 6.477112298725979, "learning_rate": 0.00018250707210361796, "grad_norm": 0.4908169209957123, "tokens_per_sec": 134931.65348690632, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1939 |
+
{"event": "train", "epoch": 1, "step": 38740, "loss": 2.180313318967819, "perplexity": 8.849078408527758, "learning_rate": 0.0001824047751085852, "grad_norm": 0.9385008215904236, "tokens_per_sec": 127446.03714546151, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1940 |
+
{"event": "train", "epoch": 1, "step": 38760, "loss": 2.016059309244156, "perplexity": 7.508677180960553, "learning_rate": 0.00018230246230194395, "grad_norm": 0.5373464226722717, "tokens_per_sec": 134355.75754779324, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1941 |
+
{"event": "train", "epoch": 1, "step": 38780, "loss": 2.198700785636902, "perplexity": 9.013295685892595, "learning_rate": 0.0001822001337336168, "grad_norm": 0.5861776471138, "tokens_per_sec": 134832.3740174938, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1942 |
+
{"event": "train", "epoch": 1, "step": 38800, "loss": 3.342886209487915, "perplexity": 28.300690665363618, "learning_rate": 0.00018209778945353392, "grad_norm": 3.8508758544921875, "tokens_per_sec": 134098.0350273291, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1943 |
+
{"event": "train", "epoch": 1, "step": 38820, "loss": 3.2807307839393616, "perplexity": 26.59520094579957, "learning_rate": 0.0001819954295116334, "grad_norm": 3.464874505996704, "tokens_per_sec": 134689.2719844377, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1944 |
+
{"event": "train", "epoch": 1, "step": 38840, "loss": 3.275813043117523, "perplexity": 26.464733705417157, "learning_rate": 0.00018189305395786094, "grad_norm": 7.449735641479492, "tokens_per_sec": 133334.90509323037, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1945 |
+
{"event": "train", "epoch": 1, "step": 38860, "loss": 3.244731366634369, "perplexity": 25.65481739452838, "learning_rate": 0.00018179066284216945, "grad_norm": 1.9824039936065674, "tokens_per_sec": 134581.65045126912, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1946 |
+
{"event": "train", "epoch": 1, "step": 38880, "loss": 3.2599793076515198, "perplexity": 26.04899812199486, "learning_rate": 0.00018168825621451981, "grad_norm": 8.32889175415039, "tokens_per_sec": 133928.682698473, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1947 |
+
{"event": "train", "epoch": 1, "step": 38900, "loss": 3.271388351917267, "perplexity": 26.347894111258416, "learning_rate": 0.0001815858341248805, "grad_norm": 4.104509353637695, "tokens_per_sec": 134567.5510673254, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1948 |
+
{"event": "train", "epoch": 1, "step": 38920, "loss": 3.232866406440735, "perplexity": 25.352222694267304, "learning_rate": 0.00018148339662322734, "grad_norm": 5.688413619995117, "tokens_per_sec": 134275.68684139053, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1949 |
+
{"event": "train", "epoch": 1, "step": 38940, "loss": 2.0175611674785614, "perplexity": 7.519962622059326, "learning_rate": 0.00018138094375954374, "grad_norm": 0.538337767124176, "tokens_per_sec": 133964.58203687367, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1950 |
+
{"event": "train", "epoch": 1, "step": 38960, "loss": 1.987195760011673, "perplexity": 7.29504798693719, "learning_rate": 0.00018127847558382064, "grad_norm": 0.5649312138557434, "tokens_per_sec": 132908.37285801597, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1951 |
+
{"event": "train", "epoch": 1, "step": 38980, "loss": 1.9517240822315216, "perplexity": 7.040816068208617, "learning_rate": 0.00018117599214605636, "grad_norm": 0.5352293848991394, "tokens_per_sec": 134518.29230937877, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1952 |
+
{"event": "train", "epoch": 1, "step": 39000, "loss": 1.791254460811615, "perplexity": 5.996970714473084, "learning_rate": 0.00018107349349625685, "grad_norm": 0.5356367826461792, "tokens_per_sec": 134969.285486174, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1953 |
+
{"event": "train", "epoch": 1, "step": 39020, "loss": 3.303180515766144, "perplexity": 27.199008373102274, "learning_rate": 0.00018097097968443538, "grad_norm": 8.419857025146484, "tokens_per_sec": 133601.51709643897, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1954 |
+
{"event": "train", "epoch": 1, "step": 39040, "loss": 3.233901858329773, "perplexity": 25.378487296666826, "learning_rate": 0.00018086845076061258, "grad_norm": 3.261282444000244, "tokens_per_sec": 133842.73307695528, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1955 |
+
{"event": "train", "epoch": 1, "step": 39060, "loss": 3.2434861063957214, "perplexity": 25.622890353360365, "learning_rate": 0.00018076590677481636, "grad_norm": 2.112704038619995, "tokens_per_sec": 133151.217951525, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1956 |
+
{"event": "train", "epoch": 1, "step": 39080, "loss": 3.3089935183525085, "perplexity": 27.357576711687866, "learning_rate": 0.00018066334777708235, "grad_norm": 3.9839158058166504, "tokens_per_sec": 133182.055434158, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1957 |
+
{"event": "train", "epoch": 1, "step": 39100, "loss": 2.105506658554077, "perplexity": 8.211262262111271, "learning_rate": 0.00018056077381745306, "grad_norm": 0.5671585202217102, "tokens_per_sec": 132695.3597515998, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1958 |
+
{"event": "train", "epoch": 1, "step": 39120, "loss": 3.044378101825714, "perplexity": 20.99696916488253, "learning_rate": 0.0001804581849459786, "grad_norm": 1.0173366069793701, "tokens_per_sec": 129736.49760895627, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1959 |
+
{"event": "train", "epoch": 1, "step": 39140, "loss": 3.270017981529236, "perplexity": 26.311812465637246, "learning_rate": 0.00018035558121271624, "grad_norm": 2.6950769424438477, "tokens_per_sec": 134810.81660233744, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1960 |
+
{"event": "train", "epoch": 1, "step": 39160, "loss": 2.7977237701416016, "perplexity": 16.40725754448635, "learning_rate": 0.00018025296266773046, "grad_norm": 1.0050984621047974, "tokens_per_sec": 134188.76733829905, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1961 |
+
{"event": "train", "epoch": 1, "step": 39180, "loss": 1.7906794250011444, "perplexity": 5.993523232865606, "learning_rate": 0.00018015032936109313, "grad_norm": 0.5407875776290894, "tokens_per_sec": 133901.15115727368, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1962 |
+
{"event": "train", "epoch": 1, "step": 39200, "loss": 1.9336015284061432, "perplexity": 6.914367744052493, "learning_rate": 0.00018004768134288312, "grad_norm": 0.5587850213050842, "tokens_per_sec": 134860.55452994205, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1963 |
+
{"event": "train", "epoch": 1, "step": 39220, "loss": 1.9560222923755646, "perplexity": 7.071144106705146, "learning_rate": 0.00017994501866318654, "grad_norm": 0.5382916331291199, "tokens_per_sec": 133310.46178110107, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1964 |
+
{"event": "train", "epoch": 1, "step": 39240, "loss": 2.334438532590866, "perplexity": 10.323661902119223, "learning_rate": 0.0001798423413720968, "grad_norm": 0.6996496915817261, "tokens_per_sec": 133769.00093144577, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1965 |
+
{"event": "train", "epoch": 1, "step": 39260, "loss": 2.605969786643982, "perplexity": 13.54435406934526, "learning_rate": 0.00017973964951971424, "grad_norm": 1.342333436012268, "tokens_per_sec": 133172.50590046676, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1966 |
+
{"event": "train", "epoch": 1, "step": 39280, "loss": 2.5746543407440186, "perplexity": 13.126778981547574, "learning_rate": 0.00017963694315614642, "grad_norm": 0.8417346477508545, "tokens_per_sec": 134247.09455193323, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1967 |
+
{"event": "train", "epoch": 1, "step": 39300, "loss": 2.551170229911804, "perplexity": 12.822099811282365, "learning_rate": 0.00017953422233150804, "grad_norm": 0.6029895544052124, "tokens_per_sec": 134222.971084808, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1968 |
+
{"event": "train", "epoch": 1, "step": 39320, "loss": 2.421357661485672, "perplexity": 11.261137754074348, "learning_rate": 0.0001794314870959207, "grad_norm": 0.7152280807495117, "tokens_per_sec": 132112.1899723162, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1969 |
+
{"event": "train", "epoch": 1, "step": 39340, "loss": 2.078507512807846, "perplexity": 7.992531257577595, "learning_rate": 0.0001793287374995131, "grad_norm": 0.5523275136947632, "tokens_per_sec": 134143.97501373757, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1970 |
+
{"event": "train", "epoch": 1, "step": 39360, "loss": 5.015151500701904, "perplexity": 150.67896300543504, "learning_rate": 0.00017922597359242096, "grad_norm": 1.2957948446273804, "tokens_per_sec": 134088.22287068446, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1971 |
+
{"event": "train", "epoch": 1, "step": 39380, "loss": 3.1596679091453552, "perplexity": 23.562769649311445, "learning_rate": 0.000179123195424787, "grad_norm": 1.459262728691101, "tokens_per_sec": 133080.95155154166, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1972 |
+
{"event": "train", "epoch": 1, "step": 39400, "loss": 2.2444751858711243, "perplexity": 9.435462392852674, "learning_rate": 0.00017902040304676077, "grad_norm": 0.5323309302330017, "tokens_per_sec": 133292.49067217013, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1973 |
+
{"event": "train", "epoch": 1, "step": 39420, "loss": 1.914375126361847, "perplexity": 6.7826991426233905, "learning_rate": 0.00017891759650849894, "grad_norm": 0.5142626166343689, "tokens_per_sec": 134376.38136432564, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1974 |
+
{"event": "train", "epoch": 1, "step": 39440, "loss": 1.9836176335811615, "perplexity": 7.2689920264831756, "learning_rate": 0.00017881477586016503, "grad_norm": 0.5103498101234436, "tokens_per_sec": 134252.07765268066, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|