Upload hybrid40k/metrics.jsonl with huggingface_hub
Browse files- hybrid40k/metrics.jsonl +86 -0
hybrid40k/metrics.jsonl
CHANGED
|
@@ -1467,3 +1467,89 @@
|
|
| 1467 |
{"event": "train", "epoch": 0, "step": 29320, "loss": 2.7037989497184753, "perplexity": 14.936366585901776, "learning_rate": 0.00022798770126392746, "grad_norm": 0.7145785689353943, "tokens_per_sec": 133596.45231064133, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1468 |
{"event": "train", "epoch": 0, "step": 29340, "loss": 2.052047997713089, "perplexity": 7.783826051567568, "learning_rate": 0.00022789817821746464, "grad_norm": 0.5364621877670288, "tokens_per_sec": 134002.98298527458, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1469 |
{"event": "train", "epoch": 0, "step": 29360, "loss": 2.2093048989772797, "perplexity": 9.109382250942037, "learning_rate": 0.0002278086171613106, "grad_norm": 0.6387125253677368, "tokens_per_sec": 134636.49483207046, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1467 |
{"event": "train", "epoch": 0, "step": 29320, "loss": 2.7037989497184753, "perplexity": 14.936366585901776, "learning_rate": 0.00022798770126392746, "grad_norm": 0.7145785689353943, "tokens_per_sec": 133596.45231064133, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1468 |
{"event": "train", "epoch": 0, "step": 29340, "loss": 2.052047997713089, "perplexity": 7.783826051567568, "learning_rate": 0.00022789817821746464, "grad_norm": 0.5364621877670288, "tokens_per_sec": 134002.98298527458, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1469 |
{"event": "train", "epoch": 0, "step": 29360, "loss": 2.2093048989772797, "perplexity": 9.109382250942037, "learning_rate": 0.0002278086171613106, "grad_norm": 0.6387125253677368, "tokens_per_sec": 134636.49483207046, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1470 |
+
{"event": "train", "epoch": 0, "step": 29380, "loss": 1.9434591233730316, "perplexity": 6.98286382939998, "learning_rate": 0.00022771901813916582, "grad_norm": 0.49614930152893066, "tokens_per_sec": 134250.24173041907, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1471 |
+
{"event": "train", "epoch": 0, "step": 29400, "loss": 2.590750813484192, "perplexity": 13.339783533532474, "learning_rate": 0.00022762938119474935, "grad_norm": 0.5285899043083191, "tokens_per_sec": 134650.21291237188, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1472 |
+
{"event": "train", "epoch": 0, "step": 29420, "loss": 2.594550222158432, "perplexity": 13.390563228122444, "learning_rate": 0.00022753970637179872, "grad_norm": 0.5037170052528381, "tokens_per_sec": 134145.93896235217, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1473 |
+
{"event": "train", "epoch": 0, "step": 29440, "loss": 1.9861925542354584, "perplexity": 7.287733222379439, "learning_rate": 0.00022744999371406992, "grad_norm": 0.490312397480011, "tokens_per_sec": 131577.44160344952, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1474 |
+
{"event": "train", "epoch": 0, "step": 29460, "loss": 2.170221894979477, "perplexity": 8.760227675631745, "learning_rate": 0.00022736024326533742, "grad_norm": 0.43930214643478394, "tokens_per_sec": 134749.6205451597, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1475 |
+
{"event": "train", "epoch": 0, "step": 29480, "loss": 2.3463255167007446, "perplexity": 10.44711137444529, "learning_rate": 0.00022727045506939404, "grad_norm": 0.483037531375885, "tokens_per_sec": 132971.5096618895, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1476 |
+
{"event": "train", "epoch": 0, "step": 29500, "loss": 2.4872249364852905, "perplexity": 12.027851712020244, "learning_rate": 0.00022718062917005105, "grad_norm": 0.5804214477539062, "tokens_per_sec": 132811.0206465503, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1477 |
+
{"event": "train", "epoch": 0, "step": 29520, "loss": 1.990944653749466, "perplexity": 7.3224476738195445, "learning_rate": 0.00022709076561113834, "grad_norm": 0.4535413980484009, "tokens_per_sec": 134136.11979430483, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1478 |
+
{"event": "train", "epoch": 0, "step": 29540, "loss": 2.2905892729759216, "perplexity": 9.880758429924144, "learning_rate": 0.00022700086443650397, "grad_norm": 0.5413397550582886, "tokens_per_sec": 134741.2979458266, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1479 |
+
{"event": "train", "epoch": 0, "step": 29560, "loss": 2.220239818096161, "perplexity": 9.209539215231715, "learning_rate": 0.00022691092569001437, "grad_norm": 0.5004054307937622, "tokens_per_sec": 133962.49282080724, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1480 |
+
{"event": "train", "epoch": 0, "step": 29580, "loss": 2.550292670726776, "perplexity": 12.810852595592145, "learning_rate": 0.0002268209494155541, "grad_norm": 0.7031934857368469, "tokens_per_sec": 133820.31824630176, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1481 |
+
{"event": "train", "epoch": 0, "step": 29600, "loss": 2.599208116531372, "perplexity": 13.453080543728339, "learning_rate": 0.0002267309356570264, "grad_norm": 0.5326149463653564, "tokens_per_sec": 134681.22079500154, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1482 |
+
{"event": "train", "epoch": 0, "step": 29620, "loss": 2.5313376784324646, "perplexity": 12.570309927607724, "learning_rate": 0.00022664088445835273, "grad_norm": 0.5698063969612122, "tokens_per_sec": 133961.1870938564, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1483 |
+
{"event": "train", "epoch": 0, "step": 29640, "loss": 3.0245341658592224, "perplexity": 20.584413554823705, "learning_rate": 0.00022655079586347276, "grad_norm": 1.0908796787261963, "tokens_per_sec": 134007.42533153537, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1484 |
+
{"event": "train", "epoch": 0, "step": 29660, "loss": 2.7508483231067657, "perplexity": 15.655907520484519, "learning_rate": 0.00022646066991634424, "grad_norm": 0.6867045164108276, "tokens_per_sec": 135097.4445628369, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1485 |
+
{"event": "train", "epoch": 0, "step": 29680, "loss": 2.2375122010707855, "perplexity": 9.369991612171415, "learning_rate": 0.00022637050666094325, "grad_norm": 0.5043866038322449, "tokens_per_sec": 134628.97745456826, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1486 |
+
{"event": "train", "epoch": 0, "step": 29700, "loss": 2.454101026058197, "perplexity": 11.635968413250986, "learning_rate": 0.00022628030614126426, "grad_norm": 0.47670379281044006, "tokens_per_sec": 134686.6321441346, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1487 |
+
{"event": "train", "epoch": 0, "step": 29720, "loss": 2.331036776304245, "perplexity": 10.288602985096748, "learning_rate": 0.00022619006840131963, "grad_norm": 0.5379722118377686, "tokens_per_sec": 134623.70260316267, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1488 |
+
{"event": "train", "epoch": 0, "step": 29740, "loss": 3.0506245493888855, "perplexity": 21.128536116999374, "learning_rate": 0.00022609979348514015, "grad_norm": 1.0311845541000366, "tokens_per_sec": 134056.1798301656, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1489 |
+
{"event": "train", "epoch": 0, "step": 29760, "loss": 2.2480664253234863, "perplexity": 9.469408315133462, "learning_rate": 0.00022600948143677464, "grad_norm": 0.4664955735206604, "tokens_per_sec": 132879.46054240834, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1490 |
+
{"event": "train", "epoch": 0, "step": 29780, "loss": 2.5498796701431274, "perplexity": 12.805562798412979, "learning_rate": 0.00022591913230028996, "grad_norm": 0.7100471258163452, "tokens_per_sec": 134008.47063228415, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1491 |
+
{"event": "train", "epoch": 0, "step": 29800, "loss": 2.5901066660881042, "perplexity": 13.331193513621473, "learning_rate": 0.00022582874611977113, "grad_norm": 0.5545047521591187, "tokens_per_sec": 133796.73865240425, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1492 |
+
{"event": "train", "epoch": 0, "step": 29820, "loss": 2.802011013031006, "perplexity": 16.477750444847242, "learning_rate": 0.00022573832293932119, "grad_norm": 0.6240127086639404, "tokens_per_sec": 133563.8650551548, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1493 |
+
{"event": "train", "epoch": 0, "step": 29840, "loss": 2.090912640094757, "perplexity": 8.092297150082436, "learning_rate": 0.00022564786280306133, "grad_norm": 0.5433758497238159, "tokens_per_sec": 134910.0643163893, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1494 |
+
{"event": "train", "epoch": 0, "step": 29860, "loss": 2.2743693590164185, "perplexity": 9.721786122174873, "learning_rate": 0.0002255573657551307, "grad_norm": 0.5079194903373718, "tokens_per_sec": 133373.20469992742, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1495 |
+
{"event": "train", "epoch": 0, "step": 29880, "loss": 1.9985914528369904, "perplexity": 7.378655591447392, "learning_rate": 0.0002254668318396866, "grad_norm": 0.48601222038269043, "tokens_per_sec": 133929.85728137082, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1496 |
+
{"event": "train", "epoch": 0, "step": 29900, "loss": 2.5969337224960327, "perplexity": 13.422517706724628, "learning_rate": 0.00022537626110090409, "grad_norm": 0.66709965467453, "tokens_per_sec": 133630.0948777009, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1497 |
+
{"event": "train", "epoch": 0, "step": 29920, "loss": 2.6269789338111877, "perplexity": 13.831919573104328, "learning_rate": 0.00022528565358297643, "grad_norm": 0.6176387071609497, "tokens_per_sec": 133771.08411660677, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1498 |
+
{"event": "train", "epoch": 0, "step": 29940, "loss": 2.0786662697792053, "perplexity": 7.993800228359856, "learning_rate": 0.00022519500933011462, "grad_norm": 0.6885706782341003, "tokens_per_sec": 130347.27938953307, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1499 |
+
{"event": "train", "epoch": 0, "step": 29960, "loss": 2.044081747531891, "perplexity": 7.722064476574172, "learning_rate": 0.00022510432838654775, "grad_norm": 0.4763694107532501, "tokens_per_sec": 133975.2902920789, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1500 |
+
{"event": "train", "epoch": 0, "step": 29980, "loss": 3.0517671704292297, "perplexity": 21.152691824700156, "learning_rate": 0.00022501361079652274, "grad_norm": 0.6103853583335876, "tokens_per_sec": 134288.0193851469, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1501 |
+
{"event": "val", "epoch": 0, "step": 29983, "val_loss": 3.0179848670959473, "val_perplexity": 20.450040585256215}
|
| 1502 |
+
{"event": "train", "epoch": 1, "step": 30000, "loss": 2.575128138065338, "perplexity": 13.132999887874586, "learning_rate": 0.00022492285660430435, "grad_norm": 0.6266829371452332, "tokens_per_sec": 134583.1000881299, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1503 |
+
{"event": "train", "epoch": 1, "step": 30020, "loss": 2.9264519810676575, "perplexity": 18.66130224563876, "learning_rate": 0.00022483206585417517, "grad_norm": 0.8411191701889038, "tokens_per_sec": 133897.62898071797, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1504 |
+
{"event": "train", "epoch": 1, "step": 30040, "loss": 2.6877676248550415, "perplexity": 14.698825973618897, "learning_rate": 0.00022474123859043594, "grad_norm": 0.6395593285560608, "tokens_per_sec": 126669.16136524295, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1505 |
+
{"event": "train", "epoch": 1, "step": 30060, "loss": 1.82059708237648, "perplexity": 6.1755446581695965, "learning_rate": 0.0002246503748574048, "grad_norm": 0.5040138959884644, "tokens_per_sec": 134160.08109015657, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1506 |
+
{"event": "train", "epoch": 1, "step": 30080, "loss": 2.2362180352211, "perplexity": 9.357873132367859, "learning_rate": 0.000224559474699418, "grad_norm": 0.6196854114532471, "tokens_per_sec": 134481.17451961557, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1507 |
+
{"event": "train", "epoch": 1, "step": 30100, "loss": 2.445077121257782, "perplexity": 11.53143888361777, "learning_rate": 0.00022446853816082926, "grad_norm": 0.5946804881095886, "tokens_per_sec": 134602.08003321986, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1508 |
+
{"event": "train", "epoch": 1, "step": 30120, "loss": 2.24411278963089, "perplexity": 9.432043636266314, "learning_rate": 0.00022437756528601027, "grad_norm": 1.6111080646514893, "tokens_per_sec": 134328.5753106812, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1509 |
+
{"event": "train", "epoch": 1, "step": 30140, "loss": 2.091070771217346, "perplexity": 8.09357689529621, "learning_rate": 0.00022428655611935036, "grad_norm": 0.5186540484428406, "tokens_per_sec": 134453.28385080895, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1510 |
+
{"event": "train", "epoch": 1, "step": 30160, "loss": 2.2996598184108734, "perplexity": 9.970789998635286, "learning_rate": 0.0002241955107052567, "grad_norm": 0.5503186583518982, "tokens_per_sec": 135115.64004148665, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1511 |
+
{"event": "train", "epoch": 1, "step": 30180, "loss": 2.7645328640937805, "perplexity": 15.871624053138095, "learning_rate": 0.00022410442908815407, "grad_norm": 0.6099770665168762, "tokens_per_sec": 133879.36881397406, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1512 |
+
{"event": "train", "epoch": 1, "step": 30200, "loss": 2.6641003787517548, "perplexity": 14.355029645671245, "learning_rate": 0.0002240133113124849, "grad_norm": 0.7190244197845459, "tokens_per_sec": 134814.12250679274, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1513 |
+
{"event": "train", "epoch": 1, "step": 30220, "loss": 2.2607707381248474, "perplexity": 9.590478066026423, "learning_rate": 0.00022392215742270913, "grad_norm": 0.5235319137573242, "tokens_per_sec": 134793.8929113996, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1514 |
+
{"event": "train", "epoch": 1, "step": 30240, "loss": 2.601980686187744, "perplexity": 13.490431902323243, "learning_rate": 0.00022383096746330454, "grad_norm": 0.609902560710907, "tokens_per_sec": 133405.82846582128, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1515 |
+
{"event": "train", "epoch": 1, "step": 30260, "loss": 2.454616069793701, "perplexity": 11.64196298949071, "learning_rate": 0.00022373974147876636, "grad_norm": 0.5970231294631958, "tokens_per_sec": 134378.6148963505, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1516 |
+
{"event": "train", "epoch": 1, "step": 30280, "loss": 1.9815783202648163, "perplexity": 7.25418337911523, "learning_rate": 0.00022364847951360743, "grad_norm": 0.4716793894767761, "tokens_per_sec": 134347.22087793605, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1517 |
+
{"event": "train", "epoch": 1, "step": 30300, "loss": 2.157701164484024, "perplexity": 8.651227033644384, "learning_rate": 0.00022355718161235836, "grad_norm": 0.541480302810669, "tokens_per_sec": 134855.39383687318, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1518 |
+
{"event": "train", "epoch": 1, "step": 30320, "loss": 1.9747134745121002, "perplexity": 7.204555069400202, "learning_rate": 0.00022346584781956697, "grad_norm": 0.5029744505882263, "tokens_per_sec": 134315.31647212428, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1519 |
+
{"event": "train", "epoch": 1, "step": 30340, "loss": 2.0176945328712463, "perplexity": 7.520965591706627, "learning_rate": 0.00022337447817979872, "grad_norm": 0.5109031200408936, "tokens_per_sec": 134306.9161865301, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1520 |
+
{"event": "train", "epoch": 1, "step": 30360, "loss": 2.8878304958343506, "perplexity": 17.954315355799903, "learning_rate": 0.00022328307273763667, "grad_norm": 0.6485480070114136, "tokens_per_sec": 133869.45823755386, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1521 |
+
{"event": "train", "epoch": 1, "step": 30380, "loss": 2.3933390378952026, "perplexity": 10.949995418878945, "learning_rate": 0.00022319163153768114, "grad_norm": 0.6092353463172913, "tokens_per_sec": 131599.11130857086, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1522 |
+
{"event": "train", "epoch": 1, "step": 30400, "loss": 2.318871319293976, "perplexity": 10.164195697873657, "learning_rate": 0.00022310015462455014, "grad_norm": 0.6422098278999329, "tokens_per_sec": 132886.39835089663, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1523 |
+
{"event": "train", "epoch": 1, "step": 30420, "loss": 2.5883591771125793, "perplexity": 13.30791774292531, "learning_rate": 0.0002230086420428789, "grad_norm": 0.533301055431366, "tokens_per_sec": 134150.39079212194, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1524 |
+
{"event": "train", "epoch": 1, "step": 30440, "loss": 2.509846568107605, "perplexity": 12.303042236635337, "learning_rate": 0.0002229170938373201, "grad_norm": 0.6159729957580566, "tokens_per_sec": 133685.5966601691, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1525 |
+
{"event": "train", "epoch": 1, "step": 30460, "loss": 2.287786513566971, "perplexity": 9.853103813987921, "learning_rate": 0.00022282551005254402, "grad_norm": 0.4965059459209442, "tokens_per_sec": 130782.51576700667, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1526 |
+
{"event": "train", "epoch": 1, "step": 30480, "loss": 2.380585014820099, "perplexity": 10.811225741544613, "learning_rate": 0.00022273389073323784, "grad_norm": 0.5317862033843994, "tokens_per_sec": 134461.5709073975, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1527 |
+
{"event": "train", "epoch": 1, "step": 30500, "loss": 2.5334441661834717, "perplexity": 12.596817040148887, "learning_rate": 0.00022264223592410656, "grad_norm": 0.5851752758026123, "tokens_per_sec": 134057.22589165706, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1528 |
+
{"event": "train", "epoch": 1, "step": 30520, "loss": 1.9616966545581818, "perplexity": 7.111382394754801, "learning_rate": 0.00022255054566987218, "grad_norm": 0.5018113255500793, "tokens_per_sec": 133769.1311286175, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1529 |
+
{"event": "train", "epoch": 1, "step": 30540, "loss": 2.564110517501831, "perplexity": 12.989099652986322, "learning_rate": 0.0002224588200152741, "grad_norm": 0.5683825016021729, "tokens_per_sec": 134692.83593299804, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1530 |
+
{"event": "train", "epoch": 1, "step": 30560, "loss": 1.9759738445281982, "perplexity": 7.213641199329063, "learning_rate": 0.00022236705900506907, "grad_norm": 0.5131218433380127, "tokens_per_sec": 133436.00670680264, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1531 |
+
{"event": "train", "epoch": 1, "step": 30580, "loss": 2.32148215174675, "perplexity": 10.190767381871762, "learning_rate": 0.00022227526268403102, "grad_norm": 0.5647324323654175, "tokens_per_sec": 133813.152297351, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1532 |
+
{"event": "train", "epoch": 1, "step": 30600, "loss": 2.1519905030727386, "perplexity": 8.601963602530695, "learning_rate": 0.0002221834310969511, "grad_norm": 0.5722987055778503, "tokens_per_sec": 135134.9033695492, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1533 |
+
{"event": "train", "epoch": 1, "step": 30620, "loss": 2.3473062813282013, "perplexity": 10.457362557917799, "learning_rate": 0.00022209156428863765, "grad_norm": 0.6166526079177856, "tokens_per_sec": 133618.01277858362, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1534 |
+
{"event": "train", "epoch": 1, "step": 30640, "loss": 2.2317233085632324, "perplexity": 9.315906435607095, "learning_rate": 0.0002219996623039163, "grad_norm": 0.48322954773902893, "tokens_per_sec": 134099.86678895503, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1535 |
+
{"event": "train", "epoch": 1, "step": 30660, "loss": 2.4830154180526733, "perplexity": 11.977326666198376, "learning_rate": 0.00022190772518762976, "grad_norm": 0.7664956450462341, "tokens_per_sec": 134452.10006896788, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1536 |
+
{"event": "train", "epoch": 1, "step": 30680, "loss": 1.9709060788154602, "perplexity": 7.177176630781195, "learning_rate": 0.00022181575298463785, "grad_norm": 0.5996529459953308, "tokens_per_sec": 133738.1513479009, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1537 |
+
{"event": "train", "epoch": 1, "step": 30700, "loss": 2.4698071479797363, "perplexity": 11.82016708872207, "learning_rate": 0.00022172374573981748, "grad_norm": 0.5489583611488342, "tokens_per_sec": 134501.968488094, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1538 |
+
{"event": "train", "epoch": 1, "step": 30720, "loss": 2.4561149775981903, "perplexity": 11.659426303354348, "learning_rate": 0.00022163170349806278, "grad_norm": 0.5742745399475098, "tokens_per_sec": 134844.14754087102, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1539 |
+
{"event": "train", "epoch": 1, "step": 30740, "loss": 2.0876621305942535, "perplexity": 8.066035765877356, "learning_rate": 0.00022153962630428486, "grad_norm": 0.4770941734313965, "tokens_per_sec": 133456.99705098962, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1540 |
+
{"event": "train", "epoch": 1, "step": 30760, "loss": 3.0501307249069214, "perplexity": 21.1181049044028, "learning_rate": 0.00022144751420341208, "grad_norm": 0.6923126578330994, "tokens_per_sec": 134463.41261425905, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1541 |
+
{"event": "train", "epoch": 1, "step": 30780, "loss": 3.2618610858917236, "perplexity": 26.098062709698187, "learning_rate": 0.00022135536724038964, "grad_norm": 0.8170605897903442, "tokens_per_sec": 132295.9484750331, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1542 |
+
{"event": "train", "epoch": 1, "step": 30800, "loss": 2.3676745891571045, "perplexity": 10.67254535296115, "learning_rate": 0.00022126318546017966, "grad_norm": 0.5207446813583374, "tokens_per_sec": 133941.47371047214, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1543 |
+
{"event": "train", "epoch": 1, "step": 30820, "loss": 2.122563898563385, "perplexity": 8.352525085222954, "learning_rate": 0.00022117096890776145, "grad_norm": 0.5109105110168457, "tokens_per_sec": 133719.674446933, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1544 |
+
{"event": "train", "epoch": 1, "step": 30840, "loss": 2.3173975348472595, "perplexity": 10.149226897442784, "learning_rate": 0.00022107871762813133, "grad_norm": 0.5073686242103577, "tokens_per_sec": 134413.17841275057, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1545 |
+
{"event": "train", "epoch": 1, "step": 30860, "loss": 2.4845966696739197, "perplexity": 11.996280815097494, "learning_rate": 0.00022098643166630226, "grad_norm": 0.5953734517097473, "tokens_per_sec": 133578.6636705838, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1546 |
+
{"event": "train", "epoch": 1, "step": 30880, "loss": 2.275309205055237, "perplexity": 9.730927399375739, "learning_rate": 0.0002208941110673044, "grad_norm": 0.5101670622825623, "tokens_per_sec": 132475.3664421457, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1547 |
+
{"event": "train", "epoch": 1, "step": 30900, "loss": 2.0194647908210754, "perplexity": 7.534291432443431, "learning_rate": 0.00022080175587618468, "grad_norm": 0.5513447523117065, "tokens_per_sec": 134354.0501270332, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1548 |
+
{"event": "train", "epoch": 1, "step": 30920, "loss": 2.49491810798645, "perplexity": 12.120740886068784, "learning_rate": 0.0002207093661380071, "grad_norm": 0.5092514753341675, "tokens_per_sec": 134510.1299034816, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1549 |
+
{"event": "train", "epoch": 1, "step": 30940, "loss": 2.139346122741699, "perplexity": 8.493881856506805, "learning_rate": 0.0002206169418978523, "grad_norm": 0.8119030594825745, "tokens_per_sec": 133908.32653458902, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1550 |
+
{"event": "train", "epoch": 1, "step": 30960, "loss": 2.446570634841919, "perplexity": 11.548674111554906, "learning_rate": 0.00022052448320081784, "grad_norm": 0.495049387216568, "tokens_per_sec": 134594.43468927682, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1551 |
+
{"event": "train", "epoch": 1, "step": 30980, "loss": 2.70090788602829, "perplexity": 14.893246959628613, "learning_rate": 0.00022043199009201805, "grad_norm": 1.0165878534317017, "tokens_per_sec": 134682.540596159, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1552 |
+
{"event": "train", "epoch": 1, "step": 31000, "loss": 2.106114536523819, "perplexity": 8.216255224946488, "learning_rate": 0.0002203394626165841, "grad_norm": 0.5046959519386292, "tokens_per_sec": 134416.99068736663, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1553 |
+
{"event": "train", "epoch": 1, "step": 31020, "loss": 2.2266247868537903, "perplexity": 9.26852996202051, "learning_rate": 0.00022024690081966393, "grad_norm": 0.5391517877578735, "tokens_per_sec": 132845.68119886794, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1554 |
+
{"event": "train", "epoch": 1, "step": 31040, "loss": 2.329028010368347, "perplexity": 10.267956333979713, "learning_rate": 0.00022015430474642213, "grad_norm": 0.5895096063613892, "tokens_per_sec": 134217.596928128, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|
| 1555 |
+
{"event": "train", "epoch": 1, "step": 31060, "loss": 2.0381290912628174, "perplexity": 7.676234222262293, "learning_rate": 0.00022006167444204016, "grad_norm": 0.5365936160087585, "tokens_per_sec": 134469.858985598, "gpu_mem_alloc_gb": 4.000064849853516, "gpu_mem_reserved_gb": 53.087890625, "grad_scale": 1.0}
|