{
  "best_metric": 0.29931360483169556,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.2466091245376079,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004932182490752158,
      "grad_norm": 1.8534983396530151,
      "learning_rate": 5e-05,
      "loss": 1.1438,
      "step": 1
    },
    {
      "epoch": 0.004932182490752158,
      "eval_loss": 1.414349913597107,
      "eval_runtime": 20.7051,
      "eval_samples_per_second": 65.974,
      "eval_steps_per_second": 8.259,
      "step": 1
    },
    {
      "epoch": 0.009864364981504316,
      "grad_norm": 1.8421441316604614,
      "learning_rate": 0.0001,
      "loss": 1.1763,
      "step": 2
    },
    {
      "epoch": 0.014796547472256474,
      "grad_norm": 1.5805590152740479,
      "learning_rate": 9.989294616193017e-05,
      "loss": 1.1488,
      "step": 3
    },
    {
      "epoch": 0.01972872996300863,
      "grad_norm": 1.2270656824111938,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.9757,
      "step": 4
    },
    {
      "epoch": 0.02466091245376079,
      "grad_norm": 1.2160286903381348,
      "learning_rate": 9.903926402016153e-05,
      "loss": 0.8759,
      "step": 5
    },
    {
      "epoch": 0.029593094944512947,
      "grad_norm": 1.2084640264511108,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.7989,
      "step": 6
    },
    {
      "epoch": 0.0345252774352651,
      "grad_norm": 1.0644646883010864,
      "learning_rate": 9.73465064747553e-05,
      "loss": 0.7208,
      "step": 7
    },
    {
      "epoch": 0.03945745992601726,
      "grad_norm": 1.1075224876403809,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.6503,
      "step": 8
    },
    {
      "epoch": 0.04438964241676942,
      "grad_norm": 1.0241856575012207,
      "learning_rate": 9.484363707663442e-05,
      "loss": 0.604,
      "step": 9
    },
    {
      "epoch": 0.04932182490752158,
      "grad_norm": 1.1344308853149414,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5534,
      "step": 10
    },
    {
      "epoch": 0.05425400739827373,
      "grad_norm": 1.2645190954208374,
      "learning_rate": 9.157348061512727e-05,
      "loss": 0.5682,
      "step": 11
    },
    {
      "epoch": 0.059186189889025895,
      "grad_norm": 1.148837685585022,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.5713,
      "step": 12
    },
    {
      "epoch": 0.06411837237977805,
      "grad_norm": 1.8091137409210205,
      "learning_rate": 8.759199037394887e-05,
      "loss": 0.3916,
      "step": 13
    },
    {
      "epoch": 0.0690505548705302,
      "grad_norm": 1.0642383098602295,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.3792,
      "step": 14
    },
    {
      "epoch": 0.07398273736128237,
      "grad_norm": 0.8615063428878784,
      "learning_rate": 8.296729075500344e-05,
      "loss": 0.3716,
      "step": 15
    },
    {
      "epoch": 0.07891491985203453,
      "grad_norm": 0.7969047427177429,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.3794,
      "step": 16
    },
    {
      "epoch": 0.08384710234278668,
      "grad_norm": 0.6164565682411194,
      "learning_rate": 7.777851165098012e-05,
      "loss": 0.3569,
      "step": 17
    },
    {
      "epoch": 0.08877928483353884,
      "grad_norm": 0.545974850654602,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3355,
      "step": 18
    },
    {
      "epoch": 0.093711467324291,
      "grad_norm": 0.604865312576294,
      "learning_rate": 7.211443451095007e-05,
      "loss": 0.364,
      "step": 19
    },
    {
      "epoch": 0.09864364981504316,
      "grad_norm": 0.4479445517063141,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.3048,
      "step": 20
    },
    {
      "epoch": 0.10357583230579531,
      "grad_norm": 0.47299858927726746,
      "learning_rate": 6.607197326515808e-05,
      "loss": 0.3388,
      "step": 21
    },
    {
      "epoch": 0.10850801479654747,
      "grad_norm": 0.6112440228462219,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.3445,
      "step": 22
    },
    {
      "epoch": 0.11344019728729964,
      "grad_norm": 0.5682258605957031,
      "learning_rate": 5.9754516100806423e-05,
      "loss": 0.3287,
      "step": 23
    },
    {
      "epoch": 0.11837237977805179,
      "grad_norm": 0.6382001638412476,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.4193,
      "step": 24
    },
    {
      "epoch": 0.12330456226880394,
      "grad_norm": 0.9506509304046631,
      "learning_rate": 5.327015646150716e-05,
      "loss": 0.3309,
      "step": 25
    },
    {
      "epoch": 0.12330456226880394,
      "eval_loss": 0.3264453411102295,
      "eval_runtime": 20.7046,
      "eval_samples_per_second": 65.976,
      "eval_steps_per_second": 8.259,
      "step": 25
    },
    {
      "epoch": 0.1282367447595561,
      "grad_norm": 0.9833061099052429,
      "learning_rate": 5e-05,
      "loss": 0.2972,
      "step": 26
    },
    {
      "epoch": 0.13316892725030827,
      "grad_norm": 0.5445727109909058,
      "learning_rate": 4.6729843538492847e-05,
      "loss": 0.3072,
      "step": 27
    },
    {
      "epoch": 0.1381011097410604,
      "grad_norm": 0.45085957646369934,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.3154,
      "step": 28
    },
    {
      "epoch": 0.14303329223181258,
      "grad_norm": 0.4187468886375427,
      "learning_rate": 4.0245483899193595e-05,
      "loss": 0.3152,
      "step": 29
    },
    {
      "epoch": 0.14796547472256474,
      "grad_norm": 0.530508816242218,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.2981,
      "step": 30
    },
    {
      "epoch": 0.15289765721331688,
      "grad_norm": 0.5742602348327637,
      "learning_rate": 3.392802673484193e-05,
      "loss": 0.3106,
      "step": 31
    },
    {
      "epoch": 0.15782983970406905,
      "grad_norm": 0.5346381068229675,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.3015,
      "step": 32
    },
    {
      "epoch": 0.16276202219482122,
      "grad_norm": 0.510138213634491,
      "learning_rate": 2.7885565489049946e-05,
      "loss": 0.2997,
      "step": 33
    },
    {
      "epoch": 0.16769420468557336,
      "grad_norm": 0.5187305212020874,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2958,
      "step": 34
    },
    {
      "epoch": 0.17262638717632553,
      "grad_norm": 0.6758659482002258,
      "learning_rate": 2.2221488349019903e-05,
      "loss": 0.3302,
      "step": 35
    },
    {
      "epoch": 0.17755856966707767,
      "grad_norm": 0.64849853515625,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.3236,
      "step": 36
    },
    {
      "epoch": 0.18249075215782984,
      "grad_norm": 1.5516417026519775,
      "learning_rate": 1.703270924499656e-05,
      "loss": 0.3867,
      "step": 37
    },
    {
      "epoch": 0.187422934648582,
      "grad_norm": 0.4901440739631653,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.2712,
      "step": 38
    },
    {
      "epoch": 0.19235511713933415,
      "grad_norm": 0.6335827708244324,
      "learning_rate": 1.2408009626051137e-05,
      "loss": 0.2839,
      "step": 39
    },
    {
      "epoch": 0.19728729963008632,
      "grad_norm": 0.6401152610778809,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.2847,
      "step": 40
    },
    {
      "epoch": 0.20221948212083848,
      "grad_norm": 0.8192377686500549,
      "learning_rate": 8.426519384872733e-06,
      "loss": 0.3056,
      "step": 41
    },
    {
      "epoch": 0.20715166461159062,
      "grad_norm": 0.6731242537498474,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2911,
      "step": 42
    },
    {
      "epoch": 0.2120838471023428,
      "grad_norm": 0.5072233080863953,
      "learning_rate": 5.156362923365588e-06,
      "loss": 0.2869,
      "step": 43
    },
    {
      "epoch": 0.21701602959309493,
      "grad_norm": 0.5785501599311829,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.3052,
      "step": 44
    },
    {
      "epoch": 0.2219482120838471,
      "grad_norm": 0.509354293346405,
      "learning_rate": 2.653493525244721e-06,
      "loss": 0.2929,
      "step": 45
    },
    {
      "epoch": 0.22688039457459927,
      "grad_norm": 0.45205190777778625,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.2788,
      "step": 46
    },
    {
      "epoch": 0.2318125770653514,
      "grad_norm": 0.5393781065940857,
      "learning_rate": 9.607359798384785e-07,
      "loss": 0.3092,
      "step": 47
    },
    {
      "epoch": 0.23674475955610358,
      "grad_norm": 0.41067972779273987,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.2925,
      "step": 48
    },
    {
      "epoch": 0.24167694204685575,
      "grad_norm": 0.4790079593658447,
      "learning_rate": 1.0705383806982606e-07,
      "loss": 0.374,
      "step": 49
    },
    {
      "epoch": 0.2466091245376079,
      "grad_norm": 0.3280869424343109,
      "learning_rate": 0.0,
      "loss": 0.2887,
      "step": 50
    },
    {
      "epoch": 0.2466091245376079,
      "eval_loss": 0.29931360483169556,
      "eval_runtime": 20.742,
      "eval_samples_per_second": 65.857,
      "eval_steps_per_second": 8.244,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 5.80081729709015e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}