{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9963706750544397,
  "eval_steps": 100,
  "global_step": 387,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03871279941930801,
      "grad_norm": 132.01553344726562,
      "learning_rate": 2.5e-06,
      "loss": 12.7967,
      "step": 5
    },
    {
      "epoch": 0.07742559883861602,
      "grad_norm": 132.22860717773438,
      "learning_rate": 5e-06,
      "loss": 12.7632,
      "step": 10
    },
    {
      "epoch": 0.11613839825792402,
      "grad_norm": 127.19441986083984,
      "learning_rate": 7.500000000000001e-06,
      "loss": 10.7405,
      "step": 15
    },
    {
      "epoch": 0.15485119767723204,
      "grad_norm": 131.84519958496094,
      "learning_rate": 1e-05,
      "loss": 7.2418,
      "step": 20
    },
    {
      "epoch": 0.19356399709654004,
      "grad_norm": 45.38945007324219,
      "learning_rate": 9.863760217983652e-06,
      "loss": 3.0355,
      "step": 25
    },
    {
      "epoch": 0.23227679651584804,
      "grad_norm": 52.082942962646484,
      "learning_rate": 9.727520435967303e-06,
      "loss": 1.3251,
      "step": 30
    },
    {
      "epoch": 0.27098959593515604,
      "grad_norm": 11.499299049377441,
      "learning_rate": 9.591280653950955e-06,
      "loss": 0.6864,
      "step": 35
    },
    {
      "epoch": 0.3097023953544641,
      "grad_norm": 18.093923568725586,
      "learning_rate": 9.455040871934606e-06,
      "loss": 0.652,
      "step": 40
    },
    {
      "epoch": 0.3484151947737721,
      "grad_norm": 3.510300397872925,
      "learning_rate": 9.318801089918257e-06,
      "loss": 0.6286,
      "step": 45
    },
    {
      "epoch": 0.3871279941930801,
      "grad_norm": 5.945786952972412,
      "learning_rate": 9.182561307901908e-06,
      "loss": 0.4977,
      "step": 50
    },
    {
      "epoch": 0.4258407936123881,
      "grad_norm": 37.19482421875,
      "learning_rate": 9.04632152588556e-06,
      "loss": 0.6305,
      "step": 55
    },
    {
      "epoch": 0.4645535930316961,
      "grad_norm": 5.250940799713135,
      "learning_rate": 8.91008174386921e-06,
      "loss": 0.693,
      "step": 60
    },
    {
      "epoch": 0.5032663924510041,
      "grad_norm": 15.312704086303711,
      "learning_rate": 8.773841961852862e-06,
      "loss": 0.6779,
      "step": 65
    },
    {
      "epoch": 0.5419791918703121,
      "grad_norm": 14.1633882522583,
      "learning_rate": 8.637602179836513e-06,
      "loss": 0.6297,
      "step": 70
    },
    {
      "epoch": 0.5806919912896201,
      "grad_norm": 16.27649688720703,
      "learning_rate": 8.501362397820165e-06,
      "loss": 0.5674,
      "step": 75
    },
    {
      "epoch": 0.6194047907089282,
      "grad_norm": 18.839599609375,
      "learning_rate": 8.365122615803816e-06,
      "loss": 0.735,
      "step": 80
    },
    {
      "epoch": 0.6581175901282361,
      "grad_norm": 4.531907081604004,
      "learning_rate": 8.228882833787467e-06,
      "loss": 0.4994,
      "step": 85
    },
    {
      "epoch": 0.6968303895475442,
      "grad_norm": 3.412825345993042,
      "learning_rate": 8.092643051771117e-06,
      "loss": 0.6938,
      "step": 90
    },
    {
      "epoch": 0.7355431889668521,
      "grad_norm": 11.98742389678955,
      "learning_rate": 7.95640326975477e-06,
      "loss": 0.6628,
      "step": 95
    },
    {
      "epoch": 0.7742559883861602,
      "grad_norm": 7.5615081787109375,
      "learning_rate": 7.82016348773842e-06,
      "loss": 0.5611,
      "step": 100
    },
    {
      "epoch": 0.7742559883861602,
      "eval_loss": 0.6137279868125916,
      "eval_mse": 0.6137279992816091,
      "eval_runtime": 12.4934,
      "eval_samples_per_second": 34.818,
      "eval_steps_per_second": 17.449,
      "step": 100
    },
    {
      "epoch": 0.8129687878054682,
      "grad_norm": 5.634002208709717,
      "learning_rate": 7.683923705722072e-06,
      "loss": 0.5883,
      "step": 105
    },
    {
      "epoch": 0.8516815872247762,
      "grad_norm": 8.587458610534668,
      "learning_rate": 7.547683923705723e-06,
      "loss": 0.5996,
      "step": 110
    },
    {
      "epoch": 0.8903943866440842,
      "grad_norm": 6.751793384552002,
      "learning_rate": 7.411444141689374e-06,
      "loss": 0.5587,
      "step": 115
    },
    {
      "epoch": 0.9291071860633922,
      "grad_norm": 3.9238288402557373,
      "learning_rate": 7.275204359673025e-06,
      "loss": 0.66,
      "step": 120
    },
    {
      "epoch": 0.9678199854827002,
      "grad_norm": 2.3443965911865234,
      "learning_rate": 7.138964577656676e-06,
      "loss": 0.523,
      "step": 125
    },
    {
      "epoch": 1.0065327849020083,
      "grad_norm": 9.468040466308594,
      "learning_rate": 7.002724795640327e-06,
      "loss": 0.6157,
      "step": 130
    },
    {
      "epoch": 1.0452455843213162,
      "grad_norm": 10.286754608154297,
      "learning_rate": 6.8664850136239795e-06,
      "loss": 0.5813,
      "step": 135
    },
    {
      "epoch": 1.0839583837406241,
      "grad_norm": 1.447935700416565,
      "learning_rate": 6.730245231607629e-06,
      "loss": 0.5564,
      "step": 140
    },
    {
      "epoch": 1.1226711831599323,
      "grad_norm": 4.448881149291992,
      "learning_rate": 6.594005449591281e-06,
      "loss": 0.5708,
      "step": 145
    },
    {
      "epoch": 1.1613839825792402,
      "grad_norm": 0.6417679190635681,
      "learning_rate": 6.457765667574932e-06,
      "loss": 0.6145,
      "step": 150
    },
    {
      "epoch": 1.2000967819985482,
      "grad_norm": 1.2481282949447632,
      "learning_rate": 6.321525885558584e-06,
      "loss": 0.5985,
      "step": 155
    },
    {
      "epoch": 1.2388095814178564,
      "grad_norm": 8.027632713317871,
      "learning_rate": 6.185286103542235e-06,
      "loss": 0.6178,
      "step": 160
    },
    {
      "epoch": 1.2775223808371643,
      "grad_norm": 7.15224027633667,
      "learning_rate": 6.049046321525886e-06,
      "loss": 0.7308,
      "step": 165
    },
    {
      "epoch": 1.3162351802564722,
      "grad_norm": 10.559642791748047,
      "learning_rate": 5.9128065395095365e-06,
      "loss": 0.6057,
      "step": 170
    },
    {
      "epoch": 1.3549479796757802,
      "grad_norm": 3.033139705657959,
      "learning_rate": 5.776566757493189e-06,
      "loss": 0.5388,
      "step": 175
    },
    {
      "epoch": 1.3936607790950883,
      "grad_norm": 9.217206954956055,
      "learning_rate": 5.64032697547684e-06,
      "loss": 0.4886,
      "step": 180
    },
    {
      "epoch": 1.4323735785143963,
      "grad_norm": 8.655097007751465,
      "learning_rate": 5.504087193460491e-06,
      "loss": 0.5852,
      "step": 185
    },
    {
      "epoch": 1.4710863779337044,
      "grad_norm": 14.92773723602295,
      "learning_rate": 5.367847411444142e-06,
      "loss": 0.615,
      "step": 190
    },
    {
      "epoch": 1.5097991773530124,
      "grad_norm": 6.135091781616211,
      "learning_rate": 5.231607629427793e-06,
      "loss": 0.6194,
      "step": 195
    },
    {
      "epoch": 1.5485119767723203,
      "grad_norm": 14.746587753295898,
      "learning_rate": 5.095367847411444e-06,
      "loss": 0.6542,
      "step": 200
    },
    {
      "epoch": 1.5485119767723203,
      "eval_loss": 0.6139479875564575,
      "eval_mse": 0.6139480064655173,
      "eval_runtime": 12.9867,
      "eval_samples_per_second": 33.496,
      "eval_steps_per_second": 16.786,
      "step": 200
    },
    {
      "epoch": 1.5872247761916283,
      "grad_norm": 6.090452194213867,
      "learning_rate": 4.959128065395096e-06,
      "loss": 0.5262,
      "step": 205
    },
    {
      "epoch": 1.6259375756109362,
      "grad_norm": 9.420876502990723,
      "learning_rate": 4.822888283378747e-06,
      "loss": 0.5827,
      "step": 210
    },
    {
      "epoch": 1.6646503750302444,
      "grad_norm": 5.127752304077148,
      "learning_rate": 4.686648501362398e-06,
      "loss": 0.5495,
      "step": 215
    },
    {
      "epoch": 1.7033631744495525,
      "grad_norm": 13.193638801574707,
      "learning_rate": 4.55040871934605e-06,
      "loss": 0.7189,
      "step": 220
    },
    {
      "epoch": 1.7420759738688605,
      "grad_norm": 6.717041492462158,
      "learning_rate": 4.414168937329701e-06,
      "loss": 0.6618,
      "step": 225
    },
    {
      "epoch": 1.7807887732881684,
      "grad_norm": 3.5996382236480713,
      "learning_rate": 4.2779291553133515e-06,
      "loss": 0.5368,
      "step": 230
    },
    {
      "epoch": 1.8195015727074764,
      "grad_norm": 13.474601745605469,
      "learning_rate": 4.141689373297003e-06,
      "loss": 0.5235,
      "step": 235
    },
    {
      "epoch": 1.8582143721267843,
      "grad_norm": 4.9880852699279785,
      "learning_rate": 4.005449591280654e-06,
      "loss": 0.6603,
      "step": 240
    },
    {
      "epoch": 1.8969271715460925,
      "grad_norm": 18.385284423828125,
      "learning_rate": 3.869209809264305e-06,
      "loss": 0.5856,
      "step": 245
    },
    {
      "epoch": 1.9356399709654004,
      "grad_norm": 8.442005157470703,
      "learning_rate": 3.732970027247957e-06,
      "loss": 0.6516,
      "step": 250
    },
    {
      "epoch": 1.9743527703847086,
      "grad_norm": 7.920212268829346,
      "learning_rate": 3.5967302452316077e-06,
      "loss": 0.6733,
      "step": 255
    },
    {
      "epoch": 2.0130655698040165,
      "grad_norm": 5.7283430099487305,
      "learning_rate": 3.460490463215259e-06,
      "loss": 0.6598,
      "step": 260
    },
    {
      "epoch": 2.0517783692233245,
      "grad_norm": 9.823247909545898,
      "learning_rate": 3.3242506811989107e-06,
      "loss": 0.5799,
      "step": 265
    },
    {
      "epoch": 2.0904911686426324,
      "grad_norm": 10.975919723510742,
      "learning_rate": 3.1880108991825615e-06,
      "loss": 0.6606,
      "step": 270
    },
    {
      "epoch": 2.1292039680619403,
      "grad_norm": 12.75275707244873,
      "learning_rate": 3.0517711171662127e-06,
      "loss": 0.5614,
      "step": 275
    },
    {
      "epoch": 2.1679167674812483,
      "grad_norm": 6.546001434326172,
      "learning_rate": 2.9155313351498636e-06,
      "loss": 0.5947,
      "step": 280
    },
    {
      "epoch": 2.2066295669005567,
      "grad_norm": 6.290523052215576,
      "learning_rate": 2.7792915531335152e-06,
      "loss": 0.6092,
      "step": 285
    },
    {
      "epoch": 2.2453423663198646,
      "grad_norm": 2.127336025238037,
      "learning_rate": 2.6430517711171665e-06,
      "loss": 0.5901,
      "step": 290
    },
    {
      "epoch": 2.2840551657391726,
      "grad_norm": 5.803460121154785,
      "learning_rate": 2.5068119891008173e-06,
      "loss": 0.5735,
      "step": 295
    },
    {
      "epoch": 2.3227679651584805,
      "grad_norm": 3.169969081878662,
      "learning_rate": 2.370572207084469e-06,
      "loss": 0.5106,
      "step": 300
    },
    {
      "epoch": 2.3227679651584805,
      "eval_loss": 0.6125330924987793,
      "eval_mse": 0.6125331133261495,
      "eval_runtime": 13.1593,
      "eval_samples_per_second": 33.057,
      "eval_steps_per_second": 16.566,
      "step": 300
    },
    {
      "epoch": 2.3614807645777884,
      "grad_norm": 3.102710485458374,
      "learning_rate": 2.2343324250681202e-06,
      "loss": 0.5843,
      "step": 305
    },
    {
      "epoch": 2.4001935639970964,
      "grad_norm": 2.053990602493286,
      "learning_rate": 2.098092643051771e-06,
      "loss": 0.6371,
      "step": 310
    },
    {
      "epoch": 2.4389063634164048,
      "grad_norm": 10.483580589294434,
      "learning_rate": 1.9618528610354227e-06,
      "loss": 0.5718,
      "step": 315
    },
    {
      "epoch": 2.4776191628357127,
      "grad_norm": 3.1228301525115967,
      "learning_rate": 1.8256130790190738e-06,
      "loss": 0.5231,
      "step": 320
    },
    {
      "epoch": 2.5163319622550206,
      "grad_norm": 5.304292678833008,
      "learning_rate": 1.689373297002725e-06,
      "loss": 0.6116,
      "step": 325
    },
    {
      "epoch": 2.5550447616743286,
      "grad_norm": 6.294493675231934,
      "learning_rate": 1.553133514986376e-06,
      "loss": 0.6674,
      "step": 330
    },
    {
      "epoch": 2.5937575610936365,
      "grad_norm": 3.730954647064209,
      "learning_rate": 1.4168937329700275e-06,
      "loss": 0.6522,
      "step": 335
    },
    {
      "epoch": 2.6324703605129445,
      "grad_norm": 1.1117771863937378,
      "learning_rate": 1.2806539509536785e-06,
      "loss": 0.7333,
      "step": 340
    },
    {
      "epoch": 2.6711831599322524,
      "grad_norm": 2.0916991233825684,
      "learning_rate": 1.1444141689373298e-06,
      "loss": 0.6361,
      "step": 345
    },
    {
      "epoch": 2.7098959593515604,
      "grad_norm": 1.0104436874389648,
      "learning_rate": 1.008174386920981e-06,
      "loss": 0.621,
      "step": 350
    },
    {
      "epoch": 2.7486087587708687,
      "grad_norm": 10.215568542480469,
      "learning_rate": 8.719346049046322e-07,
      "loss": 0.5874,
      "step": 355
    },
    {
      "epoch": 2.7873215581901767,
      "grad_norm": 5.2254557609558105,
      "learning_rate": 7.356948228882835e-07,
      "loss": 0.621,
      "step": 360
    },
    {
      "epoch": 2.8260343576094846,
      "grad_norm": 5.230953693389893,
      "learning_rate": 5.994550408719347e-07,
      "loss": 0.5851,
      "step": 365
    },
    {
      "epoch": 2.8647471570287926,
      "grad_norm": 1.5109760761260986,
      "learning_rate": 4.6321525885558585e-07,
      "loss": 0.5377,
      "step": 370
    },
    {
      "epoch": 2.9034599564481005,
      "grad_norm": 5.254393100738525,
      "learning_rate": 3.2697547683923705e-07,
      "loss": 0.6476,
      "step": 375
    },
    {
      "epoch": 2.942172755867409,
      "grad_norm": 7.337405681610107,
      "learning_rate": 1.907356948228883e-07,
      "loss": 0.5664,
      "step": 380
    },
    {
      "epoch": 2.980885555286717,
      "grad_norm": 4.144803524017334,
      "learning_rate": 5.449591280653951e-08,
      "loss": 0.5508,
      "step": 385
    },
    {
      "epoch": 2.9963706750544397,
      "step": 387,
      "total_flos": 2.606459925823488e+16,
      "train_loss": 1.1786008090627902,
      "train_runtime": 1155.1053,
      "train_samples_per_second": 21.466,
      "train_steps_per_second": 0.335
    }
  ],
  "logging_steps": 5,
  "max_steps": 387,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.606459925823488e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}