minmingzhu02's picture
Upload folder using huggingface_hub
7958e73 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9883864591055103,
"eval_steps": 500,
"global_step": 1000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"grad_norm": 0.8518019318580627,
"learning_rate": 5.6012058970266934e-05,
"loss": 1.7421,
"max_memory_allocated (GB)": 91.86,
"memory_allocated (GB)": 24.39,
"step": 10,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.02,
"grad_norm": 0.8390570878982544,
"learning_rate": 7.287336883921704e-05,
"loss": 1.5281,
"max_memory_allocated (GB)": 91.86,
"memory_allocated (GB)": 24.39,
"step": 20,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.03,
"grad_norm": 0.3700675666332245,
"learning_rate": 8.273660282559241e-05,
"loss": 1.3485,
"max_memory_allocated (GB)": 91.86,
"memory_allocated (GB)": 24.39,
"step": 30,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.04,
"grad_norm": 0.3168916404247284,
"learning_rate": 8.973467870816715e-05,
"loss": 1.2968,
"max_memory_allocated (GB)": 91.86,
"memory_allocated (GB)": 24.39,
"step": 40,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.05,
"grad_norm": 0.24861344695091248,
"learning_rate": 9.516280807158375e-05,
"loss": 1.2689,
"max_memory_allocated (GB)": 91.86,
"memory_allocated (GB)": 24.39,
"step": 50,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.06,
"grad_norm": 0.22251686453819275,
"learning_rate": 9.959791269454252e-05,
"loss": 1.2434,
"max_memory_allocated (GB)": 91.86,
"memory_allocated (GB)": 24.39,
"step": 60,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.07,
"grad_norm": 0.23426611721515656,
"learning_rate": 9.959204487506375e-05,
"loss": 1.2152,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 70,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.08,
"grad_norm": 0.45850667357444763,
"learning_rate": 9.908210096889343e-05,
"loss": 1.2108,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 80,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.09,
"grad_norm": 0.4196653366088867,
"learning_rate": 9.85721570627231e-05,
"loss": 1.1913,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 90,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.1,
"grad_norm": 0.5248636603355408,
"learning_rate": 9.806221315655279e-05,
"loss": 1.1924,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 100,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.11,
"grad_norm": 0.3434283137321472,
"learning_rate": 9.755226925038246e-05,
"loss": 1.1558,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 110,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.12,
"grad_norm": 0.47737815976142883,
"learning_rate": 9.704232534421214e-05,
"loss": 1.1492,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 120,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.13,
"grad_norm": 0.47788286209106445,
"learning_rate": 9.653238143804181e-05,
"loss": 1.1486,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 130,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.14,
"grad_norm": 0.45408132672309875,
"learning_rate": 9.60224375318715e-05,
"loss": 1.1456,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 140,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.15,
"grad_norm": 0.4091607630252838,
"learning_rate": 9.551249362570118e-05,
"loss": 1.1365,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 150,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.16,
"grad_norm": 0.5064594745635986,
"learning_rate": 9.500254971953085e-05,
"loss": 1.137,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 160,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.17,
"grad_norm": 0.4288266897201538,
"learning_rate": 9.449260581336054e-05,
"loss": 1.1181,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 170,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.18,
"grad_norm": 0.3854447901248932,
"learning_rate": 9.398266190719021e-05,
"loss": 1.1091,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 180,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.19,
"grad_norm": 0.4143249988555908,
"learning_rate": 9.347271800101989e-05,
"loss": 1.1156,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 190,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.2,
"grad_norm": 0.521230161190033,
"learning_rate": 9.296277409484956e-05,
"loss": 1.1117,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 200,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.21,
"grad_norm": 0.487106055021286,
"learning_rate": 9.245283018867925e-05,
"loss": 1.1003,
"max_memory_allocated (GB)": 91.87,
"memory_allocated (GB)": 24.39,
"step": 210,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.22,
"grad_norm": 0.4616335928440094,
"learning_rate": 9.194288628250894e-05,
"loss": 1.0992,
"max_memory_allocated (GB)": 91.88,
"memory_allocated (GB)": 24.39,
"step": 220,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.23,
"grad_norm": 0.3908211290836334,
"learning_rate": 9.14329423763386e-05,
"loss": 1.1074,
"max_memory_allocated (GB)": 91.88,
"memory_allocated (GB)": 24.39,
"step": 230,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.24,
"grad_norm": 0.4411673843860626,
"learning_rate": 9.092299847016829e-05,
"loss": 1.1055,
"max_memory_allocated (GB)": 91.88,
"memory_allocated (GB)": 24.39,
"step": 240,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.25,
"grad_norm": 0.4123621881008148,
"learning_rate": 9.041305456399796e-05,
"loss": 1.0883,
"max_memory_allocated (GB)": 91.88,
"memory_allocated (GB)": 24.39,
"step": 250,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.26,
"grad_norm": 0.5461438298225403,
"learning_rate": 8.990311065782764e-05,
"loss": 1.0928,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 260,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.27,
"grad_norm": 0.4907448887825012,
"learning_rate": 8.939316675165733e-05,
"loss": 1.0912,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 270,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.28,
"grad_norm": 0.45152169466018677,
"learning_rate": 8.8883222845487e-05,
"loss": 1.0891,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 280,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.29,
"grad_norm": 0.41472557187080383,
"learning_rate": 8.837327893931669e-05,
"loss": 1.0864,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 290,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.3,
"grad_norm": 0.45566004514694214,
"learning_rate": 8.786333503314635e-05,
"loss": 1.0776,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 300,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.31,
"grad_norm": 0.3909231424331665,
"learning_rate": 8.735339112697604e-05,
"loss": 1.0801,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 310,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.32,
"grad_norm": 0.39705774188041687,
"learning_rate": 8.684344722080571e-05,
"loss": 1.0746,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 320,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.33,
"grad_norm": 0.4257935881614685,
"learning_rate": 8.633350331463539e-05,
"loss": 1.0738,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 330,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.34,
"grad_norm": 0.41336777806282043,
"learning_rate": 8.582355940846507e-05,
"loss": 1.0811,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 340,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.35,
"grad_norm": 0.3621828854084015,
"learning_rate": 8.531361550229475e-05,
"loss": 1.0762,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 350,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.36,
"grad_norm": 0.398189902305603,
"learning_rate": 8.480367159612444e-05,
"loss": 1.0622,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 360,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.37,
"grad_norm": 0.37738627195358276,
"learning_rate": 8.42937276899541e-05,
"loss": 1.06,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 370,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.38,
"grad_norm": 0.40790703892707825,
"learning_rate": 8.378378378378379e-05,
"loss": 1.0768,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 380,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.39,
"grad_norm": 0.35230451822280884,
"learning_rate": 8.327383987761347e-05,
"loss": 1.0631,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 390,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.4,
"grad_norm": 0.37737661600112915,
"learning_rate": 8.276389597144315e-05,
"loss": 1.0665,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 400,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.41,
"grad_norm": 0.39823117852211,
"learning_rate": 8.225395206527282e-05,
"loss": 1.0739,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 410,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.42,
"grad_norm": 0.38277310132980347,
"learning_rate": 8.17440081591025e-05,
"loss": 1.07,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 420,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.43,
"grad_norm": 0.34220802783966064,
"learning_rate": 8.123406425293219e-05,
"loss": 1.0698,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 430,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.43,
"grad_norm": 0.3858403265476227,
"learning_rate": 8.072412034676186e-05,
"loss": 1.0488,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 440,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.44,
"grad_norm": 0.36855727434158325,
"learning_rate": 8.021417644059154e-05,
"loss": 1.0612,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 450,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.45,
"grad_norm": 0.4122312664985657,
"learning_rate": 7.970423253442122e-05,
"loss": 1.0566,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 460,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.46,
"grad_norm": 0.38682645559310913,
"learning_rate": 7.91942886282509e-05,
"loss": 1.0575,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 470,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.47,
"grad_norm": 0.38858598470687866,
"learning_rate": 7.868434472208057e-05,
"loss": 1.0579,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 480,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.48,
"grad_norm": 0.3749813139438629,
"learning_rate": 7.817440081591025e-05,
"loss": 1.0531,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 490,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.49,
"grad_norm": 0.36404120922088623,
"learning_rate": 7.766445690973994e-05,
"loss": 1.0447,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 500,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.5,
"grad_norm": 0.4445250332355499,
"learning_rate": 7.715451300356961e-05,
"loss": 1.0526,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 510,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.51,
"grad_norm": 0.3644183278083801,
"learning_rate": 7.664456909739929e-05,
"loss": 1.0494,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 520,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.52,
"grad_norm": 0.34624868631362915,
"learning_rate": 7.613462519122897e-05,
"loss": 1.0572,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 530,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.53,
"grad_norm": 0.3788256347179413,
"learning_rate": 7.562468128505865e-05,
"loss": 1.0502,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 540,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.54,
"grad_norm": 0.3667903542518616,
"learning_rate": 7.511473737888832e-05,
"loss": 1.0505,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 550,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.55,
"grad_norm": 0.37510526180267334,
"learning_rate": 7.460479347271801e-05,
"loss": 1.045,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 560,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.56,
"grad_norm": 0.3509054183959961,
"learning_rate": 7.409484956654769e-05,
"loss": 1.0504,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 570,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.57,
"grad_norm": 0.3294220268726349,
"learning_rate": 7.358490566037736e-05,
"loss": 1.0573,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 580,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.58,
"grad_norm": 0.34325262904167175,
"learning_rate": 7.307496175420703e-05,
"loss": 1.0445,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 590,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.59,
"grad_norm": 0.3679581880569458,
"learning_rate": 7.256501784803672e-05,
"loss": 1.0445,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 600,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.6,
"grad_norm": 0.3220757246017456,
"learning_rate": 7.20550739418664e-05,
"loss": 1.0458,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 610,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.61,
"grad_norm": 0.3660426139831543,
"learning_rate": 7.154513003569607e-05,
"loss": 1.0447,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 620,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.62,
"grad_norm": 0.32533150911331177,
"learning_rate": 7.103518612952576e-05,
"loss": 1.0471,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 630,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.63,
"grad_norm": 0.33115923404693604,
"learning_rate": 7.052524222335543e-05,
"loss": 1.0431,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 640,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.64,
"grad_norm": 0.337576299905777,
"learning_rate": 7.001529831718512e-05,
"loss": 1.057,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 650,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.65,
"grad_norm": 0.3337574303150177,
"learning_rate": 6.950535441101478e-05,
"loss": 1.0408,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 660,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.66,
"grad_norm": 0.35560840368270874,
"learning_rate": 6.899541050484447e-05,
"loss": 1.0363,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 670,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.67,
"grad_norm": 0.3454528748989105,
"learning_rate": 6.848546659867415e-05,
"loss": 1.0412,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 680,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.68,
"grad_norm": 0.3608352541923523,
"learning_rate": 6.797552269250382e-05,
"loss": 1.0578,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 690,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.69,
"grad_norm": 0.332792729139328,
"learning_rate": 6.746557878633351e-05,
"loss": 1.0426,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 700,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.7,
"grad_norm": 0.4059067666530609,
"learning_rate": 6.695563488016318e-05,
"loss": 1.0441,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 710,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.71,
"grad_norm": 0.3741580843925476,
"learning_rate": 6.644569097399287e-05,
"loss": 1.0525,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 720,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.72,
"grad_norm": 0.3646301329135895,
"learning_rate": 6.593574706782255e-05,
"loss": 1.0302,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 730,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.73,
"grad_norm": 0.35956060886383057,
"learning_rate": 6.542580316165222e-05,
"loss": 1.0439,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 740,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.74,
"grad_norm": 0.3517419099807739,
"learning_rate": 6.491585925548191e-05,
"loss": 1.0314,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 750,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.75,
"grad_norm": 0.33927640318870544,
"learning_rate": 6.440591534931157e-05,
"loss": 1.042,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 760,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.76,
"grad_norm": 0.3502146005630493,
"learning_rate": 6.389597144314126e-05,
"loss": 1.0416,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 770,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.77,
"grad_norm": 0.37221387028694153,
"learning_rate": 6.338602753697093e-05,
"loss": 1.0453,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 780,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.78,
"grad_norm": 0.3718739449977875,
"learning_rate": 6.287608363080062e-05,
"loss": 1.0392,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 790,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.79,
"grad_norm": 0.35249418020248413,
"learning_rate": 6.23661397246303e-05,
"loss": 1.0413,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 800,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.8,
"grad_norm": 0.35906028747558594,
"learning_rate": 6.185619581845997e-05,
"loss": 1.0375,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 810,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.81,
"grad_norm": 0.33932170271873474,
"learning_rate": 6.134625191228966e-05,
"loss": 1.0286,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 820,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.82,
"grad_norm": 0.33107632398605347,
"learning_rate": 6.0836308006119326e-05,
"loss": 1.0319,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 830,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.83,
"grad_norm": 0.32848185300827026,
"learning_rate": 6.032636409994901e-05,
"loss": 1.0329,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 840,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.84,
"grad_norm": 0.33085334300994873,
"learning_rate": 5.981642019377869e-05,
"loss": 1.0326,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 850,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.85,
"grad_norm": 0.3043057322502136,
"learning_rate": 5.930647628760837e-05,
"loss": 1.0379,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 860,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.86,
"grad_norm": 0.3407464027404785,
"learning_rate": 5.879653238143804e-05,
"loss": 1.0336,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 870,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.87,
"grad_norm": 0.34069886803627014,
"learning_rate": 5.8286588475267726e-05,
"loss": 1.0294,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 880,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.88,
"grad_norm": 0.4303439259529114,
"learning_rate": 5.777664456909741e-05,
"loss": 1.0223,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 890,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.89,
"grad_norm": 0.3378705382347107,
"learning_rate": 5.7266700662927075e-05,
"loss": 1.042,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 900,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.9,
"grad_norm": 0.4227118194103241,
"learning_rate": 5.6756756756756757e-05,
"loss": 1.0301,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 910,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.91,
"grad_norm": 0.36343687772750854,
"learning_rate": 5.624681285058644e-05,
"loss": 1.0249,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 920,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.92,
"grad_norm": 0.37661993503570557,
"learning_rate": 5.573686894441612e-05,
"loss": 1.0201,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 930,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.93,
"grad_norm": 0.38610127568244934,
"learning_rate": 5.5226925038245794e-05,
"loss": 1.0351,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 940,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.94,
"grad_norm": 0.32767486572265625,
"learning_rate": 5.4716981132075475e-05,
"loss": 1.0364,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 950,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.95,
"grad_norm": 0.36714789271354675,
"learning_rate": 5.4207037225905157e-05,
"loss": 1.0252,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 960,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.96,
"grad_norm": 0.34143558144569397,
"learning_rate": 5.369709331973484e-05,
"loss": 1.0266,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 970,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.97,
"grad_norm": 0.3287556767463684,
"learning_rate": 5.3187149413564506e-05,
"loss": 1.0265,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 980,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.98,
"grad_norm": 0.33613139390945435,
"learning_rate": 5.267720550739419e-05,
"loss": 1.0215,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 990,
"total_memory_available (GB)": 94.62
},
{
"epoch": 0.99,
"grad_norm": 0.32623520493507385,
"learning_rate": 5.216726160122387e-05,
"loss": 1.0213,
"max_memory_allocated (GB)": 91.9,
"memory_allocated (GB)": 24.39,
"step": 1000,
"total_memory_available (GB)": 94.62
}
],
"logging_steps": 10,
"max_steps": 2022,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 1000,
"total_flos": 1.119482194910249e+19,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}