{
  "best_metric": 2.2589545249938965,
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
  "epoch": 0.8658008658008658,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017316017316017316,
      "grad_norm": 2.8331797122955322,
      "learning_rate": 1e-05,
      "loss": 2.1187,
      "step": 1
    },
    {
      "epoch": 0.017316017316017316,
      "eval_loss": 3.7099266052246094,
      "eval_runtime": 4.4282,
      "eval_samples_per_second": 22.131,
      "eval_steps_per_second": 5.646,
      "step": 1
    },
    {
      "epoch": 0.03463203463203463,
      "grad_norm": 5.01226806640625,
      "learning_rate": 2e-05,
      "loss": 2.7977,
      "step": 2
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 4.797194480895996,
      "learning_rate": 3e-05,
      "loss": 2.7871,
      "step": 3
    },
    {
      "epoch": 0.06926406926406926,
      "grad_norm": 4.131883144378662,
      "learning_rate": 4e-05,
      "loss": 2.7443,
      "step": 4
    },
    {
      "epoch": 0.08658008658008658,
      "grad_norm": 3.087463855743408,
      "learning_rate": 5e-05,
      "loss": 2.8541,
      "step": 5
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 2.660694122314453,
      "learning_rate": 6e-05,
      "loss": 2.9244,
      "step": 6
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.8298134803771973,
      "learning_rate": 7e-05,
      "loss": 2.6589,
      "step": 7
    },
    {
      "epoch": 0.13852813852813853,
      "grad_norm": 3.4778504371643066,
      "learning_rate": 8e-05,
      "loss": 2.8337,
      "step": 8
    },
    {
      "epoch": 0.15584415584415584,
      "grad_norm": 3.807507038116455,
      "learning_rate": 9e-05,
      "loss": 2.892,
      "step": 9
    },
    {
      "epoch": 0.17316017316017315,
      "grad_norm": 3.6214892864227295,
      "learning_rate": 0.0001,
      "loss": 2.8247,
      "step": 10
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 3.1061809062957764,
      "learning_rate": 9.999071352056675e-05,
      "loss": 2.5751,
      "step": 11
    },
    {
      "epoch": 0.2077922077922078,
      "grad_norm": 4.615087509155273,
      "learning_rate": 9.9962857531815e-05,
      "loss": 2.7903,
      "step": 12
    },
    {
      "epoch": 0.22510822510822512,
      "grad_norm": 4.513574600219727,
      "learning_rate": 9.99164423811074e-05,
      "loss": 2.8595,
      "step": 13
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 5.717080593109131,
      "learning_rate": 9.985148530977767e-05,
      "loss": 3.224,
      "step": 14
    },
    {
      "epoch": 0.2597402597402597,
      "grad_norm": 1.9179377555847168,
      "learning_rate": 9.976801044672608e-05,
      "loss": 1.8395,
      "step": 15
    },
    {
      "epoch": 0.27705627705627706,
      "grad_norm": 1.8630417585372925,
      "learning_rate": 9.966604879945659e-05,
      "loss": 2.4277,
      "step": 16
    },
    {
      "epoch": 0.2943722943722944,
      "grad_norm": 1.6356393098831177,
      "learning_rate": 9.954563824255878e-05,
      "loss": 2.3636,
      "step": 17
    },
    {
      "epoch": 0.3116883116883117,
      "grad_norm": 1.710647463798523,
      "learning_rate": 9.940682350363912e-05,
      "loss": 2.2757,
      "step": 18
    },
    {
      "epoch": 0.329004329004329,
      "grad_norm": 1.6765035390853882,
      "learning_rate": 9.924965614670629e-05,
      "loss": 2.1883,
      "step": 19
    },
    {
      "epoch": 0.3463203463203463,
      "grad_norm": 1.8588552474975586,
      "learning_rate": 9.907419455301741e-05,
      "loss": 2.0356,
      "step": 20
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 2.132901191711426,
      "learning_rate": 9.888050389939172e-05,
      "loss": 2.3527,
      "step": 21
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.075359582901001,
      "learning_rate": 9.866865613400008e-05,
      "loss": 2.3003,
      "step": 22
    },
    {
      "epoch": 0.39826839826839827,
      "grad_norm": 2.2094523906707764,
      "learning_rate": 9.843872994963911e-05,
      "loss": 2.3735,
      "step": 23
    },
    {
      "epoch": 0.4155844155844156,
      "grad_norm": 2.4340925216674805,
      "learning_rate": 9.819081075450014e-05,
      "loss": 2.5142,
      "step": 24
    },
    {
      "epoch": 0.4329004329004329,
      "grad_norm": 2.3378214836120605,
      "learning_rate": 9.792499064044342e-05,
      "loss": 2.5139,
      "step": 25
    },
    {
      "epoch": 0.45021645021645024,
      "grad_norm": 2.4948999881744385,
      "learning_rate": 9.764136834878986e-05,
      "loss": 2.5467,
      "step": 26
    },
    {
      "epoch": 0.4675324675324675,
      "grad_norm": 2.667940139770508,
      "learning_rate": 9.734004923364257e-05,
      "loss": 2.4101,
      "step": 27
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 5.119446277618408,
      "learning_rate": 9.702114522275216e-05,
      "loss": 3.1252,
      "step": 28
    },
    {
      "epoch": 0.5021645021645021,
      "grad_norm": 1.3318713903427124,
      "learning_rate": 9.66847747759402e-05,
      "loss": 1.6226,
      "step": 29
    },
    {
      "epoch": 0.5194805194805194,
      "grad_norm": 2.2476823329925537,
      "learning_rate": 9.63310628410961e-05,
      "loss": 2.2634,
      "step": 30
    },
    {
      "epoch": 0.5367965367965368,
      "grad_norm": 1.6670700311660767,
      "learning_rate": 9.596014080776423e-05,
      "loss": 2.0752,
      "step": 31
    },
    {
      "epoch": 0.5541125541125541,
      "grad_norm": 1.5613207817077637,
      "learning_rate": 9.557214645833792e-05,
      "loss": 2.0647,
      "step": 32
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.5586175918579102,
      "learning_rate": 9.516722391687902e-05,
      "loss": 2.0191,
      "step": 33
    },
    {
      "epoch": 0.5887445887445888,
      "grad_norm": 1.7481515407562256,
      "learning_rate": 9.474552359558166e-05,
      "loss": 2.0408,
      "step": 34
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 1.908803939819336,
      "learning_rate": 9.43072021389003e-05,
      "loss": 2.251,
      "step": 35
    },
    {
      "epoch": 0.6233766233766234,
      "grad_norm": 1.9676694869995117,
      "learning_rate": 9.38524223653626e-05,
      "loss": 2.1518,
      "step": 36
    },
    {
      "epoch": 0.6406926406926406,
      "grad_norm": 2.245049238204956,
      "learning_rate": 9.338135320708911e-05,
      "loss": 2.3752,
      "step": 37
    },
    {
      "epoch": 0.658008658008658,
      "grad_norm": 2.3313148021698,
      "learning_rate": 9.289416964704185e-05,
      "loss": 2.6293,
      "step": 38
    },
    {
      "epoch": 0.6753246753246753,
      "grad_norm": 2.3561019897460938,
      "learning_rate": 9.239105265402525e-05,
      "loss": 2.3578,
      "step": 39
    },
    {
      "epoch": 0.6926406926406926,
      "grad_norm": 2.4642536640167236,
      "learning_rate": 9.187218911546362e-05,
      "loss": 2.3347,
      "step": 40
    },
    {
      "epoch": 0.70995670995671,
      "grad_norm": 2.577402353286743,
      "learning_rate": 9.133777176798013e-05,
      "loss": 2.3815,
      "step": 41
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 4.283364772796631,
      "learning_rate": 9.078799912580304e-05,
      "loss": 2.3154,
      "step": 42
    },
    {
      "epoch": 0.7445887445887446,
      "grad_norm": 1.0042027235031128,
      "learning_rate": 9.022307540702576e-05,
      "loss": 1.7462,
      "step": 43
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 1.7617307901382446,
      "learning_rate": 8.964321045774807e-05,
      "loss": 2.0569,
      "step": 44
    },
    {
      "epoch": 0.7792207792207793,
      "grad_norm": 1.7388392686843872,
      "learning_rate": 8.904861967412703e-05,
      "loss": 2.0223,
      "step": 45
    },
    {
      "epoch": 0.7965367965367965,
      "grad_norm": 1.6279188394546509,
      "learning_rate": 8.843952392236594e-05,
      "loss": 1.8667,
      "step": 46
    },
    {
      "epoch": 0.8138528138528138,
      "grad_norm": 1.613118290901184,
      "learning_rate": 8.781614945667169e-05,
      "loss": 2.1793,
      "step": 47
    },
    {
      "epoch": 0.8311688311688312,
      "grad_norm": 1.5092192888259888,
      "learning_rate": 8.717872783521047e-05,
      "loss": 2.0122,
      "step": 48
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 1.6618455648422241,
      "learning_rate": 8.65274958340934e-05,
      "loss": 1.8772,
      "step": 49
    },
    {
      "epoch": 0.8658008658008658,
      "grad_norm": 1.820896863937378,
      "learning_rate": 8.586269535942385e-05,
      "loss": 2.1534,
      "step": 50
    },
    {
      "epoch": 0.8658008658008658,
      "eval_loss": 2.2589545249938965,
      "eval_runtime": 4.4124,
      "eval_samples_per_second": 22.21,
      "eval_steps_per_second": 5.666,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 173,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.07184013033472e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}