{
  "best_metric": 1.4567363262176514,
  "best_model_checkpoint": "miner_id_24/checkpoint-400",
  "epoch": 0.5009230769230769,
  "eval_steps": 50,
  "global_step": 407,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0012307692307692308,
      "eval_loss": 1.7939045429229736,
      "eval_runtime": 27.5844,
      "eval_samples_per_second": 6.235,
      "eval_steps_per_second": 1.559,
      "step": 1
    },
    {
      "epoch": 0.012307692307692308,
      "grad_norm": 0.5439819097518921,
      "learning_rate": 4.2600000000000005e-05,
      "loss": 1.6815,
      "step": 10
    },
    {
      "epoch": 0.024615384615384615,
      "grad_norm": 0.6933808922767639,
      "learning_rate": 8.520000000000001e-05,
      "loss": 1.711,
      "step": 20
    },
    {
      "epoch": 0.036923076923076927,
      "grad_norm": 0.6192981600761414,
      "learning_rate": 0.0001278,
      "loss": 1.5149,
      "step": 30
    },
    {
      "epoch": 0.04923076923076923,
      "grad_norm": 0.6547725200653076,
      "learning_rate": 0.00017040000000000002,
      "loss": 1.5514,
      "step": 40
    },
    {
      "epoch": 0.06153846153846154,
      "grad_norm": 0.5849578976631165,
      "learning_rate": 0.000213,
      "loss": 1.6271,
      "step": 50
    },
    {
      "epoch": 0.06153846153846154,
      "eval_loss": 1.5897082090377808,
      "eval_runtime": 27.3561,
      "eval_samples_per_second": 6.287,
      "eval_steps_per_second": 1.572,
      "step": 50
    },
    {
      "epoch": 0.07384615384615385,
      "grad_norm": 0.7208651304244995,
      "learning_rate": 0.00021258789997222896,
      "loss": 1.6167,
      "step": 60
    },
    {
      "epoch": 0.08615384615384615,
      "grad_norm": 0.6750473976135254,
      "learning_rate": 0.0002113547891177025,
      "loss": 1.6708,
      "step": 70
    },
    {
      "epoch": 0.09846153846153846,
      "grad_norm": 0.7576515674591064,
      "learning_rate": 0.00020931021044144212,
      "loss": 1.6455,
      "step": 80
    },
    {
      "epoch": 0.11076923076923077,
      "grad_norm": 0.6720758080482483,
      "learning_rate": 0.00020646998687169697,
      "loss": 1.5812,
      "step": 90
    },
    {
      "epoch": 0.12307692307692308,
      "grad_norm": 0.86794513463974,
      "learning_rate": 0.00020285609880681382,
      "loss": 1.6535,
      "step": 100
    },
    {
      "epoch": 0.12307692307692308,
      "eval_loss": 1.6505258083343506,
      "eval_runtime": 27.6521,
      "eval_samples_per_second": 6.22,
      "eval_steps_per_second": 1.555,
      "step": 100
    },
    {
      "epoch": 0.13538461538461538,
      "grad_norm": 0.6903553009033203,
      "learning_rate": 0.00019849651400964533,
      "loss": 1.5973,
      "step": 110
    },
    {
      "epoch": 0.1476923076923077,
      "grad_norm": 0.6118985414505005,
      "learning_rate": 0.00019342497116593764,
      "loss": 1.5198,
      "step": 120
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.553017795085907,
      "learning_rate": 0.0001876807187817326,
      "loss": 1.573,
      "step": 130
    },
    {
      "epoch": 0.1723076923076923,
      "grad_norm": 0.5370417833328247,
      "learning_rate": 0.00018130821144044925,
      "loss": 1.5846,
      "step": 140
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.6245121955871582,
      "learning_rate": 0.00017435676577029992,
      "loss": 1.5261,
      "step": 150
    },
    {
      "epoch": 0.18461538461538463,
      "eval_loss": 1.544323205947876,
      "eval_runtime": 27.299,
      "eval_samples_per_second": 6.301,
      "eval_steps_per_second": 1.575,
      "step": 150
    },
    {
      "epoch": 0.19692307692307692,
      "grad_norm": 0.5361499786376953,
      "learning_rate": 0.00016688017878450004,
      "loss": 1.545,
      "step": 160
    },
    {
      "epoch": 0.20923076923076922,
      "grad_norm": 0.5619227886199951,
      "learning_rate": 0.00015893631154792243,
      "loss": 1.5772,
      "step": 170
    },
    {
      "epoch": 0.22153846153846155,
      "grad_norm": 0.6957938075065613,
      "learning_rate": 0.00015058664139218787,
      "loss": 1.6559,
      "step": 180
    },
    {
      "epoch": 0.23384615384615384,
      "grad_norm": 0.6685720682144165,
      "learning_rate": 0.00014189578614458374,
      "loss": 1.5962,
      "step": 190
    },
    {
      "epoch": 0.24615384615384617,
      "grad_norm": 0.8288447856903076,
      "learning_rate": 0.00013293100405278884,
      "loss": 1.6537,
      "step": 200
    },
    {
      "epoch": 0.24615384615384617,
      "eval_loss": 1.5585774183273315,
      "eval_runtime": 27.2807,
      "eval_samples_per_second": 6.305,
      "eval_steps_per_second": 1.576,
      "step": 200
    },
    {
      "epoch": 0.25846153846153846,
      "grad_norm": 0.5318108797073364,
      "learning_rate": 0.0001237616732754696,
      "loss": 1.5638,
      "step": 210
    },
    {
      "epoch": 0.27076923076923076,
      "grad_norm": 0.5150880217552185,
      "learning_rate": 0.0001144587549669542,
      "loss": 1.4456,
      "step": 220
    },
    {
      "epoch": 0.28307692307692306,
      "grad_norm": 0.5536653399467468,
      "learning_rate": 0.00010509424411115418,
      "loss": 1.499,
      "step": 230
    },
    {
      "epoch": 0.2953846153846154,
      "grad_norm": 0.5529115200042725,
      "learning_rate": 9.574061235471257e-05,
      "loss": 1.4513,
      "step": 240
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.5359371304512024,
      "learning_rate": 8.647024715127413e-05,
      "loss": 1.5566,
      "step": 250
    },
    {
      "epoch": 0.3076923076923077,
      "eval_loss": 1.494085669517517,
      "eval_runtime": 27.0653,
      "eval_samples_per_second": 6.355,
      "eval_steps_per_second": 1.589,
      "step": 250
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.5753491520881653,
      "learning_rate": 7.735489155732317e-05,
      "loss": 1.5377,
      "step": 260
    },
    {
      "epoch": 0.3323076923076923,
      "grad_norm": 0.5393943190574646,
      "learning_rate": 6.846508901498943e-05,
      "loss": 1.5158,
      "step": 270
    },
    {
      "epoch": 0.3446153846153846,
      "grad_norm": 0.5714206099510193,
      "learning_rate": 5.986963741863112e-05,
      "loss": 1.4651,
      "step": 280
    },
    {
      "epoch": 0.3569230769230769,
      "grad_norm": 0.5942085981369019,
      "learning_rate": 5.1635056690155563e-05,
      "loss": 1.5368,
      "step": 290
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.7914677858352661,
      "learning_rate": 4.38250739834949e-05,
      "loss": 1.5954,
      "step": 300
    },
    {
      "epoch": 0.36923076923076925,
      "eval_loss": 1.4894136190414429,
      "eval_runtime": 27.3264,
      "eval_samples_per_second": 6.294,
      "eval_steps_per_second": 1.574,
      "step": 300
    },
    {
      "epoch": 0.38153846153846155,
      "grad_norm": 0.4883591830730438,
      "learning_rate": 3.650013050222297e-05,
      "loss": 1.5128,
      "step": 310
    },
    {
      "epoch": 0.39384615384615385,
      "grad_norm": 0.46697500348091125,
      "learning_rate": 2.971691374703558e-05,
      "loss": 1.4536,
      "step": 320
    },
    {
      "epoch": 0.40615384615384614,
      "grad_norm": 0.476484090089798,
      "learning_rate": 2.3527918813016095e-05,
      "loss": 1.4595,
      "step": 330
    },
    {
      "epoch": 0.41846153846153844,
      "grad_norm": 0.4911190867424011,
      "learning_rate": 1.7981042131792456e-05,
      "loss": 1.4094,
      "step": 340
    },
    {
      "epoch": 0.4307692307692308,
      "grad_norm": 0.47842007875442505,
      "learning_rate": 1.3119210802601695e-05,
      "loss": 1.4179,
      "step": 350
    },
    {
      "epoch": 0.4307692307692308,
      "eval_loss": 1.4607428312301636,
      "eval_runtime": 27.3564,
      "eval_samples_per_second": 6.287,
      "eval_steps_per_second": 1.572,
      "step": 350
    },
    {
      "epoch": 0.4430769230769231,
      "grad_norm": 0.5161571502685547,
      "learning_rate": 8.980050380857488e-06,
      "loss": 1.573,
      "step": 360
    },
    {
      "epoch": 0.4553846153846154,
      "grad_norm": 0.5097351670265198,
      "learning_rate": 5.59559369519364e-06,
      "loss": 1.4451,
      "step": 370
    },
    {
      "epoch": 0.4676923076923077,
      "grad_norm": 0.5645511150360107,
      "learning_rate": 2.992032946439276e-06,
      "loss": 1.4605,
      "step": 380
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.5901855826377869,
      "learning_rate": 1.1895170070238124e-06,
      "loss": 1.5374,
      "step": 390
    },
    {
      "epoch": 0.49230769230769234,
      "grad_norm": 0.6915972828865051,
      "learning_rate": 2.019954895048029e-07,
      "loss": 1.6148,
      "step": 400
    },
    {
      "epoch": 0.49230769230769234,
      "eval_loss": 1.4567363262176514,
      "eval_runtime": 27.6482,
      "eval_samples_per_second": 6.221,
      "eval_steps_per_second": 1.555,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 407,
  "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": 1.116721010222039e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}