{
  "best_metric": 1.4547858238220215,
  "best_model_checkpoint": "miner_id_24/checkpoint-500",
  "epoch": 0.11757789535567313,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00023515579071134627,
      "eval_loss": 1.8474098443984985,
      "eval_runtime": 139.4088,
      "eval_samples_per_second": 12.847,
      "eval_steps_per_second": 3.214,
      "step": 1
    },
    {
      "epoch": 0.0023515579071134627,
      "grad_norm": 1.3727734088897705,
      "learning_rate": 4.02e-05,
      "loss": 1.6701,
      "step": 10
    },
    {
      "epoch": 0.004703115814226925,
      "grad_norm": 1.3558775186538696,
      "learning_rate": 8.04e-05,
      "loss": 1.7967,
      "step": 20
    },
    {
      "epoch": 0.007054673721340388,
      "grad_norm": 1.5860555171966553,
      "learning_rate": 0.0001206,
      "loss": 1.453,
      "step": 30
    },
    {
      "epoch": 0.00940623162845385,
      "grad_norm": 2.401226282119751,
      "learning_rate": 0.0001608,
      "loss": 1.6286,
      "step": 40
    },
    {
      "epoch": 0.011757789535567314,
      "grad_norm": 10.817525863647461,
      "learning_rate": 0.000201,
      "loss": 1.7866,
      "step": 50
    },
    {
      "epoch": 0.011757789535567314,
      "eval_loss": 1.7583913803100586,
      "eval_runtime": 139.0671,
      "eval_samples_per_second": 12.879,
      "eval_steps_per_second": 3.221,
      "step": 50
    },
    {
      "epoch": 0.014109347442680775,
      "grad_norm": 1.2017964124679565,
      "learning_rate": 0.00020075518705111234,
      "loss": 1.6984,
      "step": 60
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 1.2934519052505493,
      "learning_rate": 0.00020002194090852784,
      "loss": 1.6231,
      "step": 70
    },
    {
      "epoch": 0.0188124632569077,
      "grad_norm": 2.057098150253296,
      "learning_rate": 0.00019880383387374748,
      "loss": 1.5534,
      "step": 80
    },
    {
      "epoch": 0.021164021164021163,
      "grad_norm": 3.3056421279907227,
      "learning_rate": 0.00019710680044180106,
      "loss": 1.6198,
      "step": 90
    },
    {
      "epoch": 0.023515579071134628,
      "grad_norm": 5.115019798278809,
      "learning_rate": 0.0001949391083889838,
      "loss": 1.8859,
      "step": 100
    },
    {
      "epoch": 0.023515579071134628,
      "eval_loss": 1.7752360105514526,
      "eval_runtime": 139.3423,
      "eval_samples_per_second": 12.853,
      "eval_steps_per_second": 3.215,
      "step": 100
    },
    {
      "epoch": 0.02586713697824809,
      "grad_norm": 1.8005762100219727,
      "learning_rate": 0.00019231131849308138,
      "loss": 1.6405,
      "step": 110
    },
    {
      "epoch": 0.02821869488536155,
      "grad_norm": 1.5779751539230347,
      "learning_rate": 0.00018923623308232218,
      "loss": 1.4996,
      "step": 120
    },
    {
      "epoch": 0.030570252792475015,
      "grad_norm": 1.7320655584335327,
      "learning_rate": 0.00018572883366372081,
      "loss": 1.4329,
      "step": 130
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 2.5049355030059814,
      "learning_rate": 0.00018180620793468224,
      "loss": 1.5624,
      "step": 140
    },
    {
      "epoch": 0.03527336860670194,
      "grad_norm": 4.385132789611816,
      "learning_rate": 0.00017748746653345728,
      "loss": 1.8239,
      "step": 150
    },
    {
      "epoch": 0.03527336860670194,
      "eval_loss": 1.7706470489501953,
      "eval_runtime": 139.1635,
      "eval_samples_per_second": 12.87,
      "eval_steps_per_second": 3.219,
      "step": 150
    },
    {
      "epoch": 0.0376249265138154,
      "grad_norm": 1.335118293762207,
      "learning_rate": 0.00017279364993403443,
      "loss": 1.7053,
      "step": 160
    },
    {
      "epoch": 0.03997648442092887,
      "grad_norm": 1.6531046628952026,
      "learning_rate": 0.00016774762593906525,
      "loss": 1.6957,
      "step": 170
    },
    {
      "epoch": 0.042328042328042326,
      "grad_norm": 2.4578635692596436,
      "learning_rate": 0.00016237397827022866,
      "loss": 1.4472,
      "step": 180
    },
    {
      "epoch": 0.04467960023515579,
      "grad_norm": 2.4931116104125977,
      "learning_rate": 0.00015669888679881007,
      "loss": 1.6961,
      "step": 190
    },
    {
      "epoch": 0.047031158142269255,
      "grad_norm": 4.947767734527588,
      "learning_rate": 0.00015075,
      "loss": 1.7062,
      "step": 200
    },
    {
      "epoch": 0.047031158142269255,
      "eval_loss": 1.6969531774520874,
      "eval_runtime": 139.1313,
      "eval_samples_per_second": 12.873,
      "eval_steps_per_second": 3.22,
      "step": 200
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 1.2136039733886719,
      "learning_rate": 0.00014455630025230227,
      "loss": 1.6657,
      "step": 210
    },
    {
      "epoch": 0.05173427395649618,
      "grad_norm": 1.4564621448516846,
      "learning_rate": 0.00013814796263829918,
      "loss": 1.5076,
      "step": 220
    },
    {
      "epoch": 0.05408583186360964,
      "grad_norm": 1.7527103424072266,
      "learning_rate": 0.00013155620793468223,
      "loss": 1.3779,
      "step": 230
    },
    {
      "epoch": 0.0564373897707231,
      "grad_norm": 2.388731002807617,
      "learning_rate": 0.0001248131505077666,
      "loss": 1.5202,
      "step": 240
    },
    {
      "epoch": 0.058788947677836566,
      "grad_norm": 5.406064987182617,
      "learning_rate": 0.00011795164185552652,
      "loss": 1.7411,
      "step": 250
    },
    {
      "epoch": 0.058788947677836566,
      "eval_loss": 1.6722558736801147,
      "eval_runtime": 139.3413,
      "eval_samples_per_second": 12.853,
      "eval_steps_per_second": 3.215,
      "step": 250
    },
    {
      "epoch": 0.06114050558495003,
      "grad_norm": 1.5381439924240112,
      "learning_rate": 0.00011100511055839919,
      "loss": 1.5832,
      "step": 260
    },
    {
      "epoch": 0.06349206349206349,
      "grad_norm": 1.3887097835540771,
      "learning_rate": 0.00010400739941860137,
      "loss": 2.0576,
      "step": 270
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 1.7877354621887207,
      "learning_rate": 9.699260058139868e-05,
      "loss": 1.317,
      "step": 280
    },
    {
      "epoch": 0.06819517930629042,
      "grad_norm": 2.398676633834839,
      "learning_rate": 8.999488944160085e-05,
      "loss": 1.454,
      "step": 290
    },
    {
      "epoch": 0.07054673721340388,
      "grad_norm": 6.929559707641602,
      "learning_rate": 8.30483581444735e-05,
      "loss": 1.6048,
      "step": 300
    },
    {
      "epoch": 0.07054673721340388,
      "eval_loss": 1.5543087720870972,
      "eval_runtime": 139.2716,
      "eval_samples_per_second": 12.86,
      "eval_steps_per_second": 3.217,
      "step": 300
    },
    {
      "epoch": 0.07289829512051735,
      "grad_norm": 1.3065669536590576,
      "learning_rate": 7.618684949223341e-05,
      "loss": 1.6877,
      "step": 310
    },
    {
      "epoch": 0.0752498530276308,
      "grad_norm": 1.3205331563949585,
      "learning_rate": 6.94437920653178e-05,
      "loss": 1.5787,
      "step": 320
    },
    {
      "epoch": 0.07760141093474426,
      "grad_norm": 1.617138147354126,
      "learning_rate": 6.285203736170084e-05,
      "loss": 1.3306,
      "step": 330
    },
    {
      "epoch": 0.07995296884185774,
      "grad_norm": 2.009467124938965,
      "learning_rate": 5.6443699747697714e-05,
      "loss": 1.3956,
      "step": 340
    },
    {
      "epoch": 0.0823045267489712,
      "grad_norm": 5.774706840515137,
      "learning_rate": 5.025000000000002e-05,
      "loss": 1.6202,
      "step": 350
    },
    {
      "epoch": 0.0823045267489712,
      "eval_loss": 1.511150598526001,
      "eval_runtime": 139.0382,
      "eval_samples_per_second": 12.881,
      "eval_steps_per_second": 3.222,
      "step": 350
    },
    {
      "epoch": 0.08465608465608465,
      "grad_norm": 1.2580466270446777,
      "learning_rate": 4.430111320118996e-05,
      "loss": 1.5981,
      "step": 360
    },
    {
      "epoch": 0.08700764256319812,
      "grad_norm": 1.1004513502120972,
      "learning_rate": 3.862602172977134e-05,
      "loss": 1.4624,
      "step": 370
    },
    {
      "epoch": 0.08935920047031158,
      "grad_norm": 1.8977166414260864,
      "learning_rate": 3.325237406093478e-05,
      "loss": 1.34,
      "step": 380
    },
    {
      "epoch": 0.09171075837742504,
      "grad_norm": 1.999081015586853,
      "learning_rate": 2.820635006596558e-05,
      "loss": 1.3471,
      "step": 390
    },
    {
      "epoch": 0.09406231628453851,
      "grad_norm": 4.451892375946045,
      "learning_rate": 2.351253346654272e-05,
      "loss": 1.7322,
      "step": 400
    },
    {
      "epoch": 0.09406231628453851,
      "eval_loss": 1.4810150861740112,
      "eval_runtime": 139.1645,
      "eval_samples_per_second": 12.87,
      "eval_steps_per_second": 3.219,
      "step": 400
    },
    {
      "epoch": 0.09641387419165197,
      "grad_norm": 1.2609442472457886,
      "learning_rate": 1.9193792065317794e-05,
      "loss": 1.5948,
      "step": 410
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.9971499443054199,
      "learning_rate": 1.5271166336279193e-05,
      "loss": 1.5449,
      "step": 420
    },
    {
      "epoch": 0.1011169900058789,
      "grad_norm": 1.2529296875,
      "learning_rate": 1.1763766917677837e-05,
      "loss": 1.2434,
      "step": 430
    },
    {
      "epoch": 0.10346854791299236,
      "grad_norm": 2.082249402999878,
      "learning_rate": 8.688681506918602e-06,
      "loss": 1.3649,
      "step": 440
    },
    {
      "epoch": 0.10582010582010581,
      "grad_norm": 5.3249969482421875,
      "learning_rate": 6.060891611016215e-06,
      "loss": 1.5949,
      "step": 450
    },
    {
      "epoch": 0.10582010582010581,
      "eval_loss": 1.4705545902252197,
      "eval_runtime": 139.4853,
      "eval_samples_per_second": 12.84,
      "eval_steps_per_second": 3.212,
      "step": 450
    },
    {
      "epoch": 0.10817166372721929,
      "grad_norm": 1.2663040161132812,
      "learning_rate": 3.893199558198952e-06,
      "loss": 1.6161,
      "step": 460
    },
    {
      "epoch": 0.11052322163433274,
      "grad_norm": 1.5854358673095703,
      "learning_rate": 2.1961661262525285e-06,
      "loss": 1.4234,
      "step": 470
    },
    {
      "epoch": 0.1128747795414462,
      "grad_norm": 1.9589043855667114,
      "learning_rate": 9.780590914721787e-07,
      "loss": 1.2863,
      "step": 480
    },
    {
      "epoch": 0.11522633744855967,
      "grad_norm": 2.290048122406006,
      "learning_rate": 2.4481294888766817e-07,
      "loss": 1.3127,
      "step": 490
    },
    {
      "epoch": 0.11757789535567313,
      "grad_norm": 3.8831582069396973,
      "learning_rate": 0.0,
      "loss": 1.5305,
      "step": 500
    },
    {
      "epoch": 0.11757789535567313,
      "eval_loss": 1.4547858238220215,
      "eval_runtime": 138.9243,
      "eval_samples_per_second": 12.892,
      "eval_steps_per_second": 3.225,
      "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": 1.2398095975317504e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}