{
  "best_metric": 2.872375965118408,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.004827326530021144,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.654653060042287e-06,
      "eval_loss": 3.0490081310272217,
      "eval_runtime": 599.4901,
      "eval_samples_per_second": 72.748,
      "eval_steps_per_second": 18.187,
      "step": 1
    },
    {
      "epoch": 9.654653060042287e-05,
      "grad_norm": 9.069512367248535,
      "learning_rate": 4.12e-05,
      "loss": 5.2993,
      "step": 10
    },
    {
      "epoch": 0.00019309306120084574,
      "grad_norm": 12.16044807434082,
      "learning_rate": 8.24e-05,
      "loss": 5.2249,
      "step": 20
    },
    {
      "epoch": 0.00028963959180126864,
      "grad_norm": 14.883082389831543,
      "learning_rate": 0.0001236,
      "loss": 5.539,
      "step": 30
    },
    {
      "epoch": 0.0003861861224016915,
      "grad_norm": 16.756444931030273,
      "learning_rate": 0.0001648,
      "loss": 6.6809,
      "step": 40
    },
    {
      "epoch": 0.0004827326530021144,
      "grad_norm": 19.068893432617188,
      "learning_rate": 0.000206,
      "loss": 7.8567,
      "step": 50
    },
    {
      "epoch": 0.0004827326530021144,
      "eval_loss": 3.0399818420410156,
      "eval_runtime": 598.5166,
      "eval_samples_per_second": 72.867,
      "eval_steps_per_second": 18.217,
      "step": 50
    },
    {
      "epoch": 0.0005792791836025373,
      "grad_norm": 26.745712280273438,
      "learning_rate": 0.0002057490971767619,
      "loss": 5.1007,
      "step": 60
    },
    {
      "epoch": 0.0006758257142029601,
      "grad_norm": 39.823272705078125,
      "learning_rate": 0.00020499761108038175,
      "loss": 5.3979,
      "step": 70
    },
    {
      "epoch": 0.000772372244803383,
      "grad_norm": 35.91092300415039,
      "learning_rate": 0.00020374920287558198,
      "loss": 5.5911,
      "step": 80
    },
    {
      "epoch": 0.0008689187754038058,
      "grad_norm": 69.34488677978516,
      "learning_rate": 0.00020200995468164684,
      "loss": 6.2759,
      "step": 90
    },
    {
      "epoch": 0.0009654653060042288,
      "grad_norm": 22.20043182373047,
      "learning_rate": 0.00019978833994094855,
      "loss": 7.4368,
      "step": 100
    },
    {
      "epoch": 0.0009654653060042288,
      "eval_loss": 3.062361240386963,
      "eval_runtime": 601.2603,
      "eval_samples_per_second": 72.534,
      "eval_steps_per_second": 18.134,
      "step": 100
    },
    {
      "epoch": 0.0010620118366046515,
      "grad_norm": 32.1593132019043,
      "learning_rate": 0.00019709518213718787,
      "loss": 5.3581,
      "step": 110
    },
    {
      "epoch": 0.0011585583672050746,
      "grad_norm": 26.68710708618164,
      "learning_rate": 0.00019394360206446948,
      "loss": 5.1333,
      "step": 120
    },
    {
      "epoch": 0.0012551048978054974,
      "grad_norm": 22.648284912109375,
      "learning_rate": 0.00019034895390411186,
      "loss": 5.7831,
      "step": 130
    },
    {
      "epoch": 0.0013516514284059203,
      "grad_norm": 23.975393295288086,
      "learning_rate": 0.0001863287504206196,
      "loss": 6.2112,
      "step": 140
    },
    {
      "epoch": 0.0014481979590063431,
      "grad_norm": 48.25133514404297,
      "learning_rate": 0.00018190257764125471,
      "loss": 7.9916,
      "step": 150
    },
    {
      "epoch": 0.0014481979590063431,
      "eval_loss": 3.3823323249816895,
      "eval_runtime": 600.8813,
      "eval_samples_per_second": 72.58,
      "eval_steps_per_second": 18.145,
      "step": 150
    },
    {
      "epoch": 0.001544744489606766,
      "grad_norm": 12.734755516052246,
      "learning_rate": 0.00017709199943488106,
      "loss": 5.746,
      "step": 160
    },
    {
      "epoch": 0.0016412910202071888,
      "grad_norm": 19.810941696166992,
      "learning_rate": 0.00017192045245496238,
      "loss": 5.7286,
      "step": 170
    },
    {
      "epoch": 0.0017378375508076116,
      "grad_norm": 19.0549259185791,
      "learning_rate": 0.00016641313195854277,
      "loss": 5.7489,
      "step": 180
    },
    {
      "epoch": 0.0018343840814080345,
      "grad_norm": 13.497769355773926,
      "learning_rate": 0.0001605968690574869,
      "loss": 6.5552,
      "step": 190
    },
    {
      "epoch": 0.0019309306120084576,
      "grad_norm": 48.43019485473633,
      "learning_rate": 0.0001545,
      "loss": 7.6411,
      "step": 200
    },
    {
      "epoch": 0.0019309306120084576,
      "eval_loss": 3.024033784866333,
      "eval_runtime": 598.9829,
      "eval_samples_per_second": 72.81,
      "eval_steps_per_second": 18.203,
      "step": 200
    },
    {
      "epoch": 0.00202747714260888,
      "grad_norm": 16.620399475097656,
      "learning_rate": 0.00014815222811927496,
      "loss": 5.3396,
      "step": 210
    },
    {
      "epoch": 0.002124023673209303,
      "grad_norm": 14.036992073059082,
      "learning_rate": 0.00014158447912183896,
      "loss": 5.2628,
      "step": 220
    },
    {
      "epoch": 0.0022205702038097263,
      "grad_norm": 13.502534866333008,
      "learning_rate": 0.00013482875042061958,
      "loss": 5.545,
      "step": 230
    },
    {
      "epoch": 0.002317116734410149,
      "grad_norm": 15.779216766357422,
      "learning_rate": 0.00012791795524676576,
      "loss": 5.9849,
      "step": 240
    },
    {
      "epoch": 0.002413663265010572,
      "grad_norm": 23.224111557006836,
      "learning_rate": 0.00012088576229969385,
      "loss": 7.1386,
      "step": 250
    },
    {
      "epoch": 0.002413663265010572,
      "eval_loss": 2.9750823974609375,
      "eval_runtime": 594.6214,
      "eval_samples_per_second": 73.344,
      "eval_steps_per_second": 18.336,
      "step": 250
    },
    {
      "epoch": 0.002510209795610995,
      "grad_norm": 10.431509017944336,
      "learning_rate": 0.0001137664317165683,
      "loss": 5.563,
      "step": 260
    },
    {
      "epoch": 0.0026067563262114177,
      "grad_norm": 12.937127113342285,
      "learning_rate": 0.00010659464816035761,
      "loss": 5.4473,
      "step": 270
    },
    {
      "epoch": 0.0027033028568118405,
      "grad_norm": 10.73960018157959,
      "learning_rate": 9.940535183964242e-05,
      "loss": 5.499,
      "step": 280
    },
    {
      "epoch": 0.0027998493874122634,
      "grad_norm": 12.294966697692871,
      "learning_rate": 9.22335682834317e-05,
      "loss": 6.223,
      "step": 290
    },
    {
      "epoch": 0.0028963959180126862,
      "grad_norm": 25.903270721435547,
      "learning_rate": 8.511423770030617e-05,
      "loss": 7.2314,
      "step": 300
    },
    {
      "epoch": 0.0028963959180126862,
      "eval_loss": 2.911633014678955,
      "eval_runtime": 591.9056,
      "eval_samples_per_second": 73.681,
      "eval_steps_per_second": 18.42,
      "step": 300
    },
    {
      "epoch": 0.002992942448613109,
      "grad_norm": 13.487019538879395,
      "learning_rate": 7.808204475323423e-05,
      "loss": 5.2185,
      "step": 310
    },
    {
      "epoch": 0.003089488979213532,
      "grad_norm": 19.71841049194336,
      "learning_rate": 7.117124957938042e-05,
      "loss": 5.3138,
      "step": 320
    },
    {
      "epoch": 0.0031860355098139548,
      "grad_norm": 18.53927230834961,
      "learning_rate": 6.441552087816105e-05,
      "loss": 5.4884,
      "step": 330
    },
    {
      "epoch": 0.0032825820404143776,
      "grad_norm": 17.105976104736328,
      "learning_rate": 5.784777188072502e-05,
      "loss": 5.8266,
      "step": 340
    },
    {
      "epoch": 0.0033791285710148005,
      "grad_norm": 32.33679962158203,
      "learning_rate": 5.150000000000002e-05,
      "loss": 6.5896,
      "step": 350
    },
    {
      "epoch": 0.0033791285710148005,
      "eval_loss": 2.8866002559661865,
      "eval_runtime": 591.3638,
      "eval_samples_per_second": 73.748,
      "eval_steps_per_second": 18.437,
      "step": 350
    },
    {
      "epoch": 0.0034756751016152233,
      "grad_norm": 18.319353103637695,
      "learning_rate": 4.540313094251309e-05,
      "loss": 5.55,
      "step": 360
    },
    {
      "epoch": 0.003572221632215646,
      "grad_norm": 17.83504295349121,
      "learning_rate": 3.958686804145719e-05,
      "loss": 5.0744,
      "step": 370
    },
    {
      "epoch": 0.003668768162816069,
      "grad_norm": 22.843358993530273,
      "learning_rate": 3.4079547545037634e-05,
      "loss": 5.3819,
      "step": 380
    },
    {
      "epoch": 0.0037653146934164923,
      "grad_norm": 28.16783332824707,
      "learning_rate": 2.8908000565118947e-05,
      "loss": 5.9155,
      "step": 390
    },
    {
      "epoch": 0.003861861224016915,
      "grad_norm": 37.42588424682617,
      "learning_rate": 2.4097422358745275e-05,
      "loss": 6.9787,
      "step": 400
    },
    {
      "epoch": 0.003861861224016915,
      "eval_loss": 2.877124786376953,
      "eval_runtime": 595.4552,
      "eval_samples_per_second": 73.241,
      "eval_steps_per_second": 18.31,
      "step": 400
    },
    {
      "epoch": 0.003958407754617338,
      "grad_norm": 13.854421615600586,
      "learning_rate": 1.9671249579380422e-05,
      "loss": 5.1705,
      "step": 410
    },
    {
      "epoch": 0.00405495428521776,
      "grad_norm": 16.01457977294922,
      "learning_rate": 1.5651046095888127e-05,
      "loss": 5.1288,
      "step": 420
    },
    {
      "epoch": 0.004151500815818184,
      "grad_norm": 13.360790252685547,
      "learning_rate": 1.205639793553052e-05,
      "loss": 5.3445,
      "step": 430
    },
    {
      "epoch": 0.004248047346418606,
      "grad_norm": 15.994139671325684,
      "learning_rate": 8.904817862812098e-06,
      "loss": 5.7003,
      "step": 440
    },
    {
      "epoch": 0.004344593877019029,
      "grad_norm": 25.979543685913086,
      "learning_rate": 6.211660059051443e-06,
      "loss": 6.8299,
      "step": 450
    },
    {
      "epoch": 0.004344593877019029,
      "eval_loss": 2.874143123626709,
      "eval_runtime": 602.9673,
      "eval_samples_per_second": 72.329,
      "eval_steps_per_second": 18.082,
      "step": 450
    },
    {
      "epoch": 0.004441140407619453,
      "grad_norm": 12.285646438598633,
      "learning_rate": 3.990045318353154e-06,
      "loss": 5.1388,
      "step": 460
    },
    {
      "epoch": 0.004537686938219875,
      "grad_norm": 9.6546049118042,
      "learning_rate": 2.250797124418014e-06,
      "loss": 5.3243,
      "step": 470
    },
    {
      "epoch": 0.004634233468820298,
      "grad_norm": 15.964618682861328,
      "learning_rate": 1.0023889196182526e-06,
      "loss": 5.4568,
      "step": 480
    },
    {
      "epoch": 0.004730779999420721,
      "grad_norm": 16.29486656188965,
      "learning_rate": 2.5090282323810766e-07,
      "loss": 6.1612,
      "step": 490
    },
    {
      "epoch": 0.004827326530021144,
      "grad_norm": 21.052181243896484,
      "learning_rate": 0.0,
      "loss": 6.7968,
      "step": 500
    },
    {
      "epoch": 0.004827326530021144,
      "eval_loss": 2.872375965118408,
      "eval_runtime": 592.4933,
      "eval_samples_per_second": 73.608,
      "eval_steps_per_second": 18.402,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5128671190843392.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}