Instructions to use SinhalaMMLU-SharedTask/team-sinbotics with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use SinhalaMMLU-SharedTask/team-sinbotics with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Download adapter/train_log.jsonl from SinhalaMMLU-SharedTask/team-sinbotics: direct link, hf CLI and curl.
- Browser
- Download file 21.1 kB
-
https://huggingface.co/SinhalaMMLU-SharedTask/team-sinbotics/resolve/main/adapter/train_log.jsonl
- Command line
-
hf download hf://SinhalaMMLU-SharedTask/team-sinbotics/adapter/train_log.jsonl
-
curl -L -o train_log.jsonl https://huggingface.co/SinhalaMMLU-SharedTask/team-sinbotics/resolve/main/adapter/train_log.jsonl
21.1 kB
| {"step": 0, "val_loss": 1.3938243966719275, "val_acc": 0.44371584699453553} | |
| {"step": 10, "of": 807, "epoch": 1, "loss": 1.3117294669151307, "acc": 0.440625, "lr": 4e-05, "padded_tok_per_s": 184.02152841475322, "elapsed_min": 13.182243804136911, "eta_min": 1050.6248311897118, "gpu_mem_gb": 14.327464580535889} | |
| {"step": 20, "of": 807, "epoch": 1, "loss": 1.2411161199212075, "acc": 0.425, "lr": 8e-05, "padded_tok_per_s": 230.56646485425148, "elapsed_min": 23.55315886338552, "eta_min": 926.8168012742202, "gpu_mem_gb": 14.451435565948486} | |
| {"step": 30, "of": 807, "epoch": 1, "loss": 1.1908718969672918, "acc": 0.43125, "lr": 9.998991324077907e-05, "padded_tok_per_s": 218.87162699441572, "elapsed_min": 34.52261076370875, "eta_min": 894.1356187800565, "gpu_mem_gb": 14.451435565948486} | |
| {"step": 40, "of": 807, "epoch": 1, "loss": 1.2263891153037547, "acc": 0.396875, "lr": 9.990924358362036e-05, "padded_tok_per_s": 333.30316130757126, "elapsed_min": 41.39569125970205, "eta_min": 793.7623799047868, "gpu_mem_gb": 14.465251922607422} | |
| {"step": 50, "of": 807, "epoch": 1, "loss": 1.0954111099243165, "acc": 0.525, "lr": 9.974803444743616e-05, "padded_tok_per_s": 326.983231470789, "elapsed_min": 48.80810874700546, "eta_min": 738.9547664296628, "gpu_mem_gb": 14.465251922607422, "val_loss": 1.191572536579681, "val_acc": 0.4837887067395264} | |
| {"step": 60, "of": 807, "epoch": 1, "loss": 1.205327045172453, "acc": 0.453125, "lr": 9.950654597842208e-05, "padded_tok_per_s": 308.03831808922746, "elapsed_min": 63.87387245496114, "eta_min": 795.2297120642662, "gpu_mem_gb": 14.465251922607422} | |
| {"step": 70, "of": 807, "epoch": 1, "loss": 1.1317465111613274, "acc": 0.46875, "lr": 9.918516787103323e-05, "padded_tok_per_s": 322.05456422301285, "elapsed_min": 70.96118895610174, "eta_min": 747.1199465806711, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 80, "of": 807, "epoch": 1, "loss": 1.177012603613548, "acc": 0.509375, "lr": 9.878441873912712e-05, "padded_tok_per_s": 425.2665113280193, "elapsed_min": 76.36792519887288, "eta_min": 693.9935202447573, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 90, "of": 807, "epoch": 1, "loss": 1.1985178332775832, "acc": 0.471875, "lr": 9.83049452790667e-05, "padded_tok_per_s": 378.9315422591666, "elapsed_min": 83.14189272721609, "eta_min": 662.3637453934881, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 100, "of": 807, "epoch": 1, "loss": 1.1924124173820019, "acc": 0.465625, "lr": 9.77475212261344e-05, "padded_tok_per_s": 563.7694606597805, "elapsed_min": 87.41454010804495, "eta_min": 618.0207985638776, "gpu_mem_gb": 14.480856895446777, "val_loss": 1.1497736048394431, "val_acc": 0.4743169398907104} | |
| {"step": 110, "of": 807, "epoch": 1, "loss": 1.0819737900048494, "acc": 0.51875, "lr": 9.711304610594104e-05, "padded_tok_per_s": 480.3097353454058, "elapsed_min": 99.73373437722525, "eta_min": 631.9492078265998, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 120, "of": 807, "epoch": 1, "loss": 1.1716542847454547, "acc": 0.475, "lr": 9.640254378284448e-05, "padded_tok_per_s": 491.15794000148935, "elapsed_min": 104.40247062444686, "eta_min": 597.7041443249583, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 130, "of": 807, "epoch": 1, "loss": 1.1087913170456887, "acc": 0.490625, "lr": 9.561716080772071e-05, "padded_tok_per_s": 454.28693914017737, "elapsed_min": 109.60150483051936, "eta_min": 570.7709136173969, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 140, "of": 807, "epoch": 1, "loss": 1.0659179601818323, "acc": 0.540625, "lr": 9.475816456775313e-05, "padded_tok_per_s": 464.83490633249727, "elapsed_min": 114.58460727930068, "eta_min": 545.9138075378112, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 150, "of": 807, "epoch": 1, "loss": 1.1376219194382429, "acc": 0.484375, "lr": 9.382694124122623e-05, "padded_tok_per_s": 466.2440396519109, "elapsed_min": 119.57170494397481, "eta_min": 523.7240676546096, "gpu_mem_gb": 14.480856895446777, "val_loss": 1.12948377501552, "val_acc": 0.48233151183970857} | |
| {"step": 160, "of": 807, "epoch": 1, "loss": 1.1701789483428002, "acc": 0.475, "lr": 9.282499356062385e-05, "padded_tok_per_s": 431.4498021215981, "elapsed_min": 132.21478342612585, "eta_min": 534.6435304793964, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 170, "of": 807, "epoch": 1, "loss": 1.1481772746890784, "acc": 0.46875, "lr": 9.175393838764153e-05, "padded_tok_per_s": 432.7066142698438, "elapsed_min": 137.7327718337377, "eta_min": 516.09279798877, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 180, "of": 807, "epoch": 1, "loss": 1.1237864576280117, "acc": 0.475, "lr": 9.061550410402678e-05, "padded_tok_per_s": 405.5768836288263, "elapsed_min": 143.36862078905105, "eta_min": 499.4006957485278, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 190, "of": 807, "epoch": 1, "loss": 1.1155502110719682, "acc": 0.528125, "lr": 8.941152782245698e-05, "padded_tok_per_s": 422.09055526292735, "elapsed_min": 149.01295543511708, "eta_min": 483.89996580772237, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 200, "of": 807, "epoch": 1, "loss": 1.181915134936571, "acc": 0.46875, "lr": 8.814395242195642e-05, "padded_tok_per_s": 510.8044128183797, "elapsed_min": 153.90488751331966, "eta_min": 467.10133360292514, "gpu_mem_gb": 14.480856895446777, "val_loss": 1.1201430734172328, "val_acc": 0.4994535519125683} | |
| {"step": 210, "of": 807, "epoch": 1, "loss": 1.1033317286521196, "acc": 0.5, "lr": 8.681482341263609e-05, "padded_tok_per_s": 589.103756974828, "elapsed_min": 165.25787717103958, "eta_min": 469.8045365290982, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 220, "of": 807, "epoch": 1, "loss": 1.1278775550425053, "acc": 0.496875, "lr": 8.542628563481576e-05, "padded_tok_per_s": 465.9597870637458, "elapsed_min": 170.6510549346606, "eta_min": 455.32804203020805, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 230, "of": 807, "epoch": 1, "loss": 1.0743585035204888, "acc": 0.55, "lr": 8.398057979785515e-05, "padded_tok_per_s": 435.0375770237834, "elapsed_min": 176.24889421860377, "eta_min": 442.1548346266712, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 240, "of": 807, "epoch": 1, "loss": 1.138508414104581, "acc": 0.484375, "lr": 8.248003886427926e-05, "padded_tok_per_s": 457.43299241502245, "elapsed_min": 181.65399349133173, "eta_min": 429.15755962327125, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 250, "of": 807, "epoch": 1, "loss": 1.114440492540598, "acc": 0.528125, "lr": 8.092708428503324e-05, "padded_tok_per_s": 509.7721787748801, "elapsed_min": 186.28169031540554, "eta_min": 415.0356060227235, "gpu_mem_gb": 14.480856895446777, "val_loss": 1.106039493157781, "val_acc": 0.5063752276867031} | |
| {"step": 260, "of": 807, "epoch": 1, "loss": 1.1505409348756075, "acc": 0.50625, "lr": 7.932422209194171e-05, "padded_tok_per_s": 557.4145521990091, "elapsed_min": 197.9298733552297, "eta_min": 416.4140027896563, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 270, "of": 807, "epoch": 1, "loss": 1.0737882636487484, "acc": 0.50625, "lr": 7.767403885367832e-05, "padded_tok_per_s": 507.9106860733123, "elapsed_min": 202.56330711444218, "eta_min": 402.87591081650163, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 280, "of": 807, "epoch": 1, "loss": 1.07132619433105, "acc": 0.521875, "lr": 7.597919750177168e-05, "padded_tok_per_s": 561.3820189345303, "elapsed_min": 206.85382834275563, "eta_min": 389.32845548797224, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 290, "of": 807, "epoch": 1, "loss": 1.1702354542911053, "acc": 0.409375, "lr": 7.42424330333829e-05, "padded_tok_per_s": 578.074904524351, "elapsed_min": 211.04011671940486, "eta_min": 376.23358739287, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 300, "of": 807, "epoch": 1, "loss": 1.1146250456571578, "acc": 0.4875, "lr": 7.24665480977895e-05, "padded_tok_per_s": 575.0449769965712, "elapsed_min": 215.28587992986044, "eta_min": 363.83313708146414, "gpu_mem_gb": 14.480856895446777, "val_loss": 1.095462341343336, "val_acc": 0.516575591985428} | |
| {"step": 310, "of": 807, "epoch": 1, "loss": 1.1228520199656487, "acc": 0.515625, "lr": 7.065440847369808e-05, "padded_tok_per_s": 562.073332234046, "elapsed_min": 226.88907970587414, "eta_min": 363.7544277865143, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 320, "of": 807, "epoch": 1, "loss": 1.0953711645677686, "acc": 0.484375, "lr": 6.88089384446835e-05, "padded_tok_per_s": 508.87602533228755, "elapsed_min": 231.718162214756, "eta_min": 352.64607812058176, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 330, "of": 807, "epoch": 1, "loss": 1.0769723623991012, "acc": 0.55, "lr": 6.69331160802179e-05, "padded_tok_per_s": 511.89627760303887, "elapsed_min": 236.5996936003367, "eta_min": 341.9941025677594, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 340, "of": 807, "epoch": 1, "loss": 1.0623440779745579, "acc": 0.525, "lr": 6.50299684299043e-05, "padded_tok_per_s": 466.912946799171, "elapsed_min": 241.8479316711426, "eta_min": 332.1852473247753, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 350, "of": 807, "epoch": 1, "loss": 1.1283749528229237, "acc": 0.478125, "lr": 6.31025666386702e-05, "padded_tok_per_s": 561.8206151109382, "elapsed_min": 246.353411591053, "eta_min": 321.6671688488892, "gpu_mem_gb": 14.480856895446777, "val_loss": 1.099407977397759, "val_acc": 0.521311475409836} | |
| {"step": 360, "of": 807, "epoch": 1, "loss": 1.1078926883637905, "acc": 0.540625, "lr": 6.115402099080345e-05, "padded_tok_per_s": 555.5764269500036, "elapsed_min": 257.85023884773256, "eta_min": 320.16404656926795, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 370, "of": 807, "epoch": 1, "loss": 1.0793228903785348, "acc": 0.509375, "lr": 5.918747589082853e-05, "padded_tok_per_s": 506.79501479795755, "elapsed_min": 262.5967424670855, "eta_min": 310.14804448139563, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 380, "of": 807, "epoch": 1, "loss": 1.106640174239874, "acc": 0.50625, "lr": 5.7206104789322104e-05, "padded_tok_per_s": 522.2945920531247, "elapsed_min": 267.3102141022682, "eta_min": 300.37226689912774, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 390, "of": 807, "epoch": 1, "loss": 1.1322766944766045, "acc": 0.4875, "lr": 5.521310506185661e-05, "padded_tok_per_s": 567.9394256347903, "elapsed_min": 271.6169609308243, "eta_min": 290.421212072189, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 400, "of": 807, "epoch": 1, "loss": 1.1097250901162625, "acc": 0.5, "lr": 5.321169284933543e-05, "padded_tok_per_s": 582.0787124216063, "elapsed_min": 275.70874023040136, "eta_min": 280.5336431844334, "gpu_mem_gb": 14.480856895446777, "val_loss": 1.0869499809320724, "val_acc": 0.5169398907103825} | |
| {"step": 410, "of": 807, "epoch": 1, "loss": 1.095520031824708, "acc": 0.534375, "lr": 5.1205097868046344e-05, "padded_tok_per_s": 509.31807653642954, "elapsed_min": 287.4269513050715, "eta_min": 278.31341382466684, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 420, "of": 807, "epoch": 1, "loss": 1.1091913033276797, "acc": 0.490625, "lr": 4.919655819780792e-05, "padded_tok_per_s": 509.145887688829, "elapsed_min": 292.0311075886091, "eta_min": 269.0858062780755, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 430, "of": 807, "epoch": 1, "loss": 1.0361009538173676, "acc": 0.55, "lr": 4.718931505661961e-05, "padded_tok_per_s": 561.9929168309919, "elapsed_min": 296.40907764434814, "eta_min": 259.8749355160913, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 440, "of": 807, "epoch": 1, "loss": 1.1656339701265097, "acc": 0.49375, "lr": 4.518660757024774e-05, "padded_tok_per_s": 508.4819770705449, "elapsed_min": 301.12996735970177, "eta_min": 251.16976822956946, "gpu_mem_gb": 14.480856895446777} | |
| {"step": 450, "of": 807, "epoch": 1, "loss": 1.0878755021840334, "acc": 0.484375, "lr": 4.319166754518768e-05, "padded_tok_per_s": 601.9254755572032, "elapsed_min": 305.1191463748614, "eta_min": 242.06118945739004, "gpu_mem_gb": 14.480856895446777, "val_loss": 1.0705646049346647, "val_acc": 0.5242258652094718} | |
| {"step": 460, "of": 807, "epoch": 1, "loss": 1.079693019017577, "acc": 0.515625, "lr": 4.120771425343733e-05, "padded_tok_per_s": 584.2484248920043, "elapsed_min": 315.84177558024726, "eta_min": 238.2545567964039, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 470, "of": 807, "epoch": 1, "loss": 1.09283931478858, "acc": 0.525, "lr": 3.923794923749775e-05, "padded_tok_per_s": 563.2674145778598, "elapsed_min": 319.91684671640394, "eta_min": 229.38718583708115, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 480, "of": 807, "epoch": 1, "loss": 1.1360433649271726, "acc": 0.4875, "lr": 3.728555114398419e-05, "padded_tok_per_s": 565.3030961108067, "elapsed_min": 324.1816764990489, "eta_min": 220.84876711497705, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 490, "of": 807, "epoch": 1, "loss": 1.0516227819025517, "acc": 0.534375, "lr": 3.5353670594184625e-05, "padded_tok_per_s": 560.7985725755549, "elapsed_min": 328.6273099263509, "eta_min": 212.60174948296577, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 500, "of": 807, "epoch": 1, "loss": 1.1114140950143336, "acc": 0.521875, "lr": 3.344542509984334e-05, "padded_tok_per_s": 501.0444762875511, "elapsed_min": 333.1264855146408, "eta_min": 204.53966210598944, "gpu_mem_gb": 14.48595380783081, "val_loss": 1.0717405824713369, "val_acc": 0.5275045537340619} | |
| {"step": 510, "of": 807, "epoch": 1, "loss": 1.0064323019236325, "acc": 0.609375, "lr": 3.156389403237397e-05, "padded_tok_per_s": 483.45628934297946, "elapsed_min": 345.3806813081106, "eta_min": 201.13345558531145, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 520, "of": 807, "epoch": 1, "loss": 1.0289957866072654, "acc": 0.546875, "lr": 2.9712113653620277e-05, "padded_tok_per_s": 583.462758615968, "elapsed_min": 349.48880681594216, "eta_min": 192.89093760802962, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 530, "of": 807, "epoch": 1, "loss": 1.0371111802756787, "acc": 0.540625, "lr": 2.789307221618369e-05, "padded_tok_per_s": 508.3846755863565, "elapsed_min": 354.3570765415827, "eta_min": 185.2017173622989, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 540, "of": 807, "epoch": 1, "loss": 1.0956390708684922, "acc": 0.525, "lr": 2.6109705141224257e-05, "padded_tok_per_s": 569.3882914084584, "elapsed_min": 358.63161383867265, "eta_min": 177.323409064677, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 550, "of": 807, "epoch": 1, "loss": 1.0185340899508446, "acc": 0.54375, "lr": 2.4364890281516635e-05, "padded_tok_per_s": 505.17711566444143, "elapsed_min": 363.2106762131055, "eta_min": 169.7184432486693, "gpu_mem_gb": 14.48595380783081, "val_loss": 1.0632437256081726, "val_acc": 0.5369763205828779} | |
| {"step": 560, "of": 807, "epoch": 1, "loss": 1.0866477228701115, "acc": 0.50625, "lr": 2.266144327740531e-05, "padded_tok_per_s": 561.876717737169, "elapsed_min": 374.87537591060004, "eta_min": 165.34681758913968, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 570, "of": 807, "epoch": 1, "loss": 1.0797979846596717, "acc": 0.49375, "lr": 2.1002113013153147e-05, "padded_tok_per_s": 559.4100452144551, "elapsed_min": 379.1945180654526, "eta_min": 157.6650890903724, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 580, "of": 807, "epoch": 1, "loss": 1.0135206323117019, "acc": 0.54375, "lr": 1.9389577181015493e-05, "padded_tok_per_s": 565.4599555591585, "elapsed_min": 383.2516664981842, "eta_min": 149.99677292256519, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 590, "of": 807, "epoch": 1, "loss": 1.0779679216444493, "acc": 0.5375, "lr": 1.782643796019814e-05, "padded_tok_per_s": 511.28487363569076, "elapsed_min": 388.11129457553227, "eta_min": 142.74601851337374, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 600, "of": 807, "epoch": 1, "loss": 1.0782918907701968, "acc": 0.528125, "lr": 1.631521781767214e-05, "padded_tok_per_s": 466.30328986128796, "elapsed_min": 393.26174202760063, "eta_min": 135.6753009995222, "gpu_mem_gb": 14.48595380783081, "val_loss": 1.0616528655227633, "val_acc": 0.531511839708561} | |
| {"step": 610, "of": 807, "epoch": 1, "loss": 1.037769677862525, "acc": 0.534375, "lr": 1.4858355437621663e-05, "padded_tok_per_s": 485.22052431331434, "elapsed_min": 405.88277370929717, "eta_min": 131.08017446021566, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 620, "of": 807, "epoch": 1, "loss": 1.031372894719243, "acc": 0.546875, "lr": 1.3458201786093794e-05, "padded_tok_per_s": 506.14137797497244, "elapsed_min": 410.7040634791056, "eta_min": 123.87364495256897, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 630, "of": 807, "epoch": 1, "loss": 1.095178310573101, "acc": 0.515625, "lr": 1.2117016317200703e-05, "padded_tok_per_s": 523.007959904971, "elapsed_min": 415.5148021618525, "eta_min": 116.73987298832999, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 640, "of": 807, "epoch": 1, "loss": 1.1232219096273184, "acc": 0.496875, "lr": 1.083696332699628e-05, "padded_tok_per_s": 568.8469511350721, "elapsed_min": 419.6774414459864, "eta_min": 109.5095823773121, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 650, "of": 807, "epoch": 1, "loss": 1.01499842107296, "acc": 0.56875, "lr": 9.62010846091118e-06, "padded_tok_per_s": 514.7036280409466, "elapsed_min": 424.3786023815473, "eta_min": 102.50375472908144, "gpu_mem_gb": 14.48595380783081, "val_loss": 1.052715630001492, "val_acc": 0.5442622950819672} | |
| {"step": 660, "of": 807, "epoch": 1, "loss": 1.0831996731460094, "acc": 0.546875, "lr": 8.4684153803822e-06, "padded_tok_per_s": 568.3497458772008, "elapsed_min": 435.69815833965936, "eta_min": 97.04186253928778, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 670, "of": 807, "epoch": 1, "loss": 1.0186325158923863, "acc": 0.534375, "lr": 7.383742594055076e-06, "padded_tok_per_s": 569.1281530091816, "elapsed_min": 440.01822514533995, "eta_min": 89.97387588792773, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 680, "of": 807, "epoch": 1, "loss": 1.100569846481085, "acc": 0.45625, "lr": 6.367840458674401e-06, "padded_tok_per_s": 491.48746160020136, "elapsed_min": 444.93249946832657, "eta_min": 83.09768740070217, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 690, "of": 807, "epoch": 1, "loss": 1.0568060830235482, "acc": 0.5375, "lr": 5.4223483545002174e-06, "padded_tok_per_s": 609.9569608274077, "elapsed_min": 448.9427892843882, "eta_min": 76.12508166126582, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 700, "of": 807, "epoch": 1, "loss": 1.1300180625170468, "acc": 0.465625, "lr": 4.548792039809447e-06, "padded_tok_per_s": 566.7358260918663, "elapsed_min": 453.03803279002506, "eta_min": 69.25009929790384, "gpu_mem_gb": 14.48595380783081, "val_loss": 1.0506058856220628, "val_acc": 0.5446265938069217} | |
| {"step": 710, "of": 807, "epoch": 1, "loss": 1.0422977663576602, "acc": 0.5125, "lr": 3.748581188751271e-06, "padded_tok_per_s": 583.2430454794273, "elapsed_min": 464.2381695389748, "eta_min": 63.424087951099374, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 720, "of": 807, "epoch": 1, "loss": 1.036707292869687, "acc": 0.525, "lr": 3.0230071165295803e-06, "padded_tok_per_s": 584.633893315937, "elapsed_min": 468.275576198101, "eta_min": 56.58329879060388, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 730, "of": 807, "epoch": 1, "loss": 1.1012982964515685, "acc": 0.54375, "lr": 2.373240695583534e-06, "padded_tok_per_s": 543.4509343295705, "elapsed_min": 472.8451474706332, "eta_min": 49.8754470619709, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 740, "of": 807, "epoch": 1, "loss": 1.0159414909780025, "acc": 0.5875, "lr": 1.8003304661288078e-06, "padded_tok_per_s": 613.2440993811867, "elapsed_min": 476.88229132493336, "eta_min": 43.177180430770996, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 750, "of": 807, "epoch": 1, "loss": 1.052791463583708, "acc": 0.565625, "lr": 1.3052009441086532e-06, "padded_tok_per_s": 603.6848431137026, "elapsed_min": 481.0605837702751, "eta_min": 36.560604366540915, "gpu_mem_gb": 14.48595380783081, "val_loss": 1.04905437198493, "val_acc": 0.5479052823315118} | |
| {"step": 760, "of": 807, "epoch": 1, "loss": 1.0636690109968185, "acc": 0.521875, "lr": 8.886511292852395e-07, "padded_tok_per_s": 599.6054246464406, "elapsed_min": 492.2240912040075, "eta_min": 30.440174061300464, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 770, "of": 807, "epoch": 1, "loss": 1.0642237523570657, "acc": 0.553125, "lr": 5.513532158788193e-07, "padded_tok_per_s": 569.059655683085, "elapsed_min": 496.6623281002045, "eta_min": 23.865592389230603, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 780, "of": 807, "epoch": 1, "loss": 1.0682742193341255, "acc": 0.51875, "lr": 2.938515078353521e-07, "padded_tok_per_s": 578.6264589339154, "elapsed_min": 500.94382549524306, "eta_min": 17.34036319021995, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 790, "of": 807, "epoch": 1, "loss": 1.0605528172105552, "acc": 0.53125, "lr": 1.1656154047303691e-07, "padded_tok_per_s": 579.3193322256193, "elapsed_min": 504.93273838758466, "eta_min": 10.865641205808783, "gpu_mem_gb": 14.48595380783081} | |
| {"step": 800, "of": 807, "epoch": 1, "loss": 0.9551678024232387, "acc": 0.584375, "lr": 1.976940992523546e-08, "padded_tok_per_s": 570.7104214163245, "elapsed_min": 509.2565688411395, "eta_min": 4.45599497735997, "gpu_mem_gb": 14.48595380783081, "val_loss": 1.0486477551347353, "val_acc": 0.546448087431694} | |
| {"step": 807, "of": 807, "epoch": 1, "loss": 1.0337329821370953, "acc": 0.542713567839196, "lr": 0.0, "padded_tok_per_s": 487.9246289982748, "elapsed_min": 519.6681627035141, "eta_min": 0.0, "gpu_mem_gb": 14.48595380783081, "val_loss": 1.0490453588072286, "val_acc": 0.5475409836065573} | |