{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.635593220338983,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00211864406779661,
      "grad_norm": 6772.94736433113,
      "learning_rate": 5.263157894736842e-06,
      "loss": 5.4426,
      "step": 1
    },
    {
      "epoch": 0.0211864406779661,
      "grad_norm": 43.76552598391156,
      "learning_rate": 5.263157894736842e-05,
      "loss": 6.5697,
      "step": 10
    },
    {
      "epoch": 0.0423728813559322,
      "grad_norm": 1.4214989301078385,
      "learning_rate": 0.00010526315789473683,
      "loss": 5.8015,
      "step": 20
    },
    {
      "epoch": 0.0635593220338983,
      "grad_norm": 1.8559172078320925,
      "learning_rate": 0.00015789473684210527,
      "loss": 4.6978,
      "step": 30
    },
    {
      "epoch": 0.0847457627118644,
      "grad_norm": 0.9523887604864526,
      "learning_rate": 0.00021052631578947367,
      "loss": 3.9616,
      "step": 40
    },
    {
      "epoch": 0.1059322033898305,
      "grad_norm": 0.5313592686196623,
      "learning_rate": 0.0002631578947368421,
      "loss": 3.2816,
      "step": 50
    },
    {
      "epoch": 0.1271186440677966,
      "grad_norm": 0.9882421975844679,
      "learning_rate": 0.00031578947368421053,
      "loss": 2.9453,
      "step": 60
    },
    {
      "epoch": 0.1483050847457627,
      "grad_norm": 1.3764980998221854,
      "learning_rate": 0.00036842105263157896,
      "loss": 2.7478,
      "step": 70
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 0.6188567319965684,
      "learning_rate": 0.00042105263157894734,
      "loss": 2.6778,
      "step": 80
    },
    {
      "epoch": 0.1906779661016949,
      "grad_norm": 0.45391127998861047,
      "learning_rate": 0.00047368421052631577,
      "loss": 2.6651,
      "step": 90
    },
    {
      "epoch": 0.211864406779661,
      "grad_norm": 0.3359651886818045,
      "learning_rate": 0.0004999904062938913,
      "loss": 2.6871,
      "step": 100
    },
    {
      "epoch": 0.2330508474576271,
      "grad_norm": 0.2538059916992196,
      "learning_rate": 0.0004999136610628463,
      "loss": 2.6047,
      "step": 110
    },
    {
      "epoch": 0.2542372881355932,
      "grad_norm": 0.7420239318499638,
      "learning_rate": 0.0004997601941609823,
      "loss": 2.6122,
      "step": 120
    },
    {
      "epoch": 0.2754237288135593,
      "grad_norm": 1.0130312150097984,
      "learning_rate": 0.0004995300527015189,
      "loss": 2.8314,
      "step": 130
    },
    {
      "epoch": 0.2966101694915254,
      "grad_norm": 0.45185267289061176,
      "learning_rate": 0.0004992233073362051,
      "loss": 2.7241,
      "step": 140
    },
    {
      "epoch": 0.3177966101694915,
      "grad_norm": 1.2647337895757225,
      "learning_rate": 0.0004988400522336304,
      "loss": 2.6269,
      "step": 150
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 1.8112639454685833,
      "learning_rate": 0.0004983804050503152,
      "loss": 2.5217,
      "step": 160
    },
    {
      "epoch": 0.3601694915254237,
      "grad_norm": 3.7153319991642295,
      "learning_rate": 0.0004978445068945918,
      "loss": 2.6363,
      "step": 170
    },
    {
      "epoch": 0.3813559322033898,
      "grad_norm": 1.791954534899048,
      "learning_rate": 0.0004972325222832848,
      "loss": 2.6156,
      "step": 180
    },
    {
      "epoch": 0.4025423728813559,
      "grad_norm": 0.30066185600399886,
      "learning_rate": 0.0004965446390912051,
      "loss": 2.5443,
      "step": 190
    },
    {
      "epoch": 0.423728813559322,
      "grad_norm": 0.155337614316216,
      "learning_rate": 0.0004957810684934746,
      "loss": 2.4791,
      "step": 200
    },
    {
      "epoch": 0.4449152542372881,
      "grad_norm": 0.10527493629733332,
      "learning_rate": 0.0004949420449006968,
      "loss": 2.4345,
      "step": 210
    },
    {
      "epoch": 0.4661016949152542,
      "grad_norm": 0.06207368975658736,
      "learning_rate": 0.0004940278258869937,
      "loss": 2.4284,
      "step": 220
    },
    {
      "epoch": 0.4872881355932203,
      "grad_norm": 0.06174468192832609,
      "learning_rate": 0.0004930386921109333,
      "loss": 2.3855,
      "step": 230
    },
    {
      "epoch": 0.5084745762711864,
      "grad_norm": 0.04921797570119065,
      "learning_rate": 0.0004919749472293693,
      "loss": 2.3648,
      "step": 240
    },
    {
      "epoch": 0.5296610169491526,
      "grad_norm": 0.06272467077360039,
      "learning_rate": 0.00049083691780422,
      "loss": 2.3618,
      "step": 250
    },
    {
      "epoch": 0.5508474576271186,
      "grad_norm": 0.06952127682493715,
      "learning_rate": 0.0004896249532022172,
      "loss": 2.3344,
      "step": 260
    },
    {
      "epoch": 0.5720338983050848,
      "grad_norm": 0.05291425745739597,
      "learning_rate": 0.0004883394254876522,
      "loss": 2.3401,
      "step": 270
    },
    {
      "epoch": 0.5932203389830508,
      "grad_norm": 0.09403878675057362,
      "learning_rate": 0.0004869807293081555,
      "loss": 2.3351,
      "step": 280
    },
    {
      "epoch": 0.614406779661017,
      "grad_norm": 0.07509078154330293,
      "learning_rate": 0.00048554928177354254,
      "loss": 2.3067,
      "step": 290
    },
    {
      "epoch": 0.635593220338983,
      "grad_norm": 0.1705698396439175,
      "learning_rate": 0.0004840455223277639,
      "loss": 2.3114,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 1888,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7434066550849536.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}