{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.054945054945054944,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001098901098901099,
      "grad_norm": 4.387043476104736,
      "learning_rate": 5.4945054945054946e-08,
      "loss": 0.8831,
      "step": 20
    },
    {
      "epoch": 0.002197802197802198,
      "grad_norm": 3.8907365798950195,
      "learning_rate": 1.0989010989010989e-07,
      "loss": 0.8866,
      "step": 40
    },
    {
      "epoch": 0.0032967032967032967,
      "grad_norm": 3.2492220401763916,
      "learning_rate": 1.6483516483516484e-07,
      "loss": 0.8454,
      "step": 60
    },
    {
      "epoch": 0.004395604395604396,
      "grad_norm": 3.0804762840270996,
      "learning_rate": 2.1978021978021978e-07,
      "loss": 0.8267,
      "step": 80
    },
    {
      "epoch": 0.005494505494505495,
      "grad_norm": 2.037411689758301,
      "learning_rate": 2.7472527472527475e-07,
      "loss": 0.7371,
      "step": 100
    },
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.5473365783691406,
      "learning_rate": 3.296703296703297e-07,
      "loss": 0.6765,
      "step": 120
    },
    {
      "epoch": 0.007692307692307693,
      "grad_norm": 1.1062999963760376,
      "learning_rate": 3.846153846153847e-07,
      "loss": 0.5946,
      "step": 140
    },
    {
      "epoch": 0.008791208791208791,
      "grad_norm": 1.363224744796753,
      "learning_rate": 4.3956043956043957e-07,
      "loss": 0.5402,
      "step": 160
    },
    {
      "epoch": 0.00989010989010989,
      "grad_norm": 0.9122905731201172,
      "learning_rate": 4.945054945054946e-07,
      "loss": 0.464,
      "step": 180
    },
    {
      "epoch": 0.01098901098901099,
      "grad_norm": 0.676691472530365,
      "learning_rate": 5.494505494505495e-07,
      "loss": 0.4041,
      "step": 200
    },
    {
      "epoch": 0.012087912087912088,
      "grad_norm": 0.5926629900932312,
      "learning_rate": 6.043956043956044e-07,
      "loss": 0.3727,
      "step": 220
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 0.635013997554779,
      "learning_rate": 6.593406593406594e-07,
      "loss": 0.3609,
      "step": 240
    },
    {
      "epoch": 0.014285714285714285,
      "grad_norm": 0.5836207270622253,
      "learning_rate": 7.142857142857143e-07,
      "loss": 0.3331,
      "step": 260
    },
    {
      "epoch": 0.015384615384615385,
      "grad_norm": 0.548773467540741,
      "learning_rate": 7.692307692307694e-07,
      "loss": 0.3201,
      "step": 280
    },
    {
      "epoch": 0.016483516483516484,
      "grad_norm": 0.5962342023849487,
      "learning_rate": 8.241758241758242e-07,
      "loss": 0.2993,
      "step": 300
    },
    {
      "epoch": 0.017582417582417582,
      "grad_norm": 0.5346819162368774,
      "learning_rate": 8.791208791208791e-07,
      "loss": 0.2792,
      "step": 320
    },
    {
      "epoch": 0.01868131868131868,
      "grad_norm": 0.569210946559906,
      "learning_rate": 9.340659340659341e-07,
      "loss": 0.273,
      "step": 340
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.5142342448234558,
      "learning_rate": 9.890109890109891e-07,
      "loss": 0.2621,
      "step": 360
    },
    {
      "epoch": 0.020879120879120878,
      "grad_norm": 0.5067290663719177,
      "learning_rate": 1.043956043956044e-06,
      "loss": 0.2641,
      "step": 380
    },
    {
      "epoch": 0.02197802197802198,
      "grad_norm": 0.44699764251708984,
      "learning_rate": 1.098901098901099e-06,
      "loss": 0.2553,
      "step": 400
    },
    {
      "epoch": 0.023076923076923078,
      "grad_norm": 0.5279501080513,
      "learning_rate": 1.153846153846154e-06,
      "loss": 0.2488,
      "step": 420
    },
    {
      "epoch": 0.024175824175824177,
      "grad_norm": 0.5009133219718933,
      "learning_rate": 1.2087912087912089e-06,
      "loss": 0.2499,
      "step": 440
    },
    {
      "epoch": 0.025274725274725275,
      "grad_norm": 0.5484806895256042,
      "learning_rate": 1.263736263736264e-06,
      "loss": 0.2485,
      "step": 460
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 0.44114941358566284,
      "learning_rate": 1.3186813186813187e-06,
      "loss": 0.2499,
      "step": 480
    },
    {
      "epoch": 0.027472527472527472,
      "grad_norm": 0.5557438731193542,
      "learning_rate": 1.3736263736263736e-06,
      "loss": 0.2455,
      "step": 500
    },
    {
      "epoch": 0.02857142857142857,
      "grad_norm": 0.5493007898330688,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 0.2396,
      "step": 520
    },
    {
      "epoch": 0.02967032967032967,
      "grad_norm": 0.5284810662269592,
      "learning_rate": 1.4835164835164835e-06,
      "loss": 0.2383,
      "step": 540
    },
    {
      "epoch": 0.03076923076923077,
      "grad_norm": 0.5073139667510986,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 0.2389,
      "step": 560
    },
    {
      "epoch": 0.031868131868131866,
      "grad_norm": 0.5186975002288818,
      "learning_rate": 1.5934065934065933e-06,
      "loss": 0.2372,
      "step": 580
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.5739095211029053,
      "learning_rate": 1.6483516483516484e-06,
      "loss": 0.2358,
      "step": 600
    },
    {
      "epoch": 0.03406593406593406,
      "grad_norm": 0.5144438147544861,
      "learning_rate": 1.7032967032967032e-06,
      "loss": 0.2319,
      "step": 620
    },
    {
      "epoch": 0.035164835164835165,
      "grad_norm": 0.4886190593242645,
      "learning_rate": 1.7582417582417583e-06,
      "loss": 0.2297,
      "step": 640
    },
    {
      "epoch": 0.03626373626373627,
      "grad_norm": 0.6088211536407471,
      "learning_rate": 1.8131868131868135e-06,
      "loss": 0.2356,
      "step": 660
    },
    {
      "epoch": 0.03736263736263736,
      "grad_norm": 0.4712292551994324,
      "learning_rate": 1.8681318681318681e-06,
      "loss": 0.2334,
      "step": 680
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 0.5712177157402039,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 0.2302,
      "step": 700
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.5427699089050293,
      "learning_rate": 1.9780219780219782e-06,
      "loss": 0.2248,
      "step": 720
    },
    {
      "epoch": 0.04065934065934066,
      "grad_norm": 0.6642568707466125,
      "learning_rate": 2.032967032967033e-06,
      "loss": 0.2291,
      "step": 740
    },
    {
      "epoch": 0.041758241758241756,
      "grad_norm": 0.5859007239341736,
      "learning_rate": 2.087912087912088e-06,
      "loss": 0.227,
      "step": 760
    },
    {
      "epoch": 0.04285714285714286,
      "grad_norm": 0.6507712602615356,
      "learning_rate": 2.142857142857143e-06,
      "loss": 0.227,
      "step": 780
    },
    {
      "epoch": 0.04395604395604396,
      "grad_norm": 0.5675429105758667,
      "learning_rate": 2.197802197802198e-06,
      "loss": 0.2259,
      "step": 800
    },
    {
      "epoch": 0.045054945054945054,
      "grad_norm": 0.6223055124282837,
      "learning_rate": 2.252747252747253e-06,
      "loss": 0.2283,
      "step": 820
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5504657030105591,
      "learning_rate": 2.307692307692308e-06,
      "loss": 0.2246,
      "step": 840
    },
    {
      "epoch": 0.04725274725274725,
      "grad_norm": 0.48020097613334656,
      "learning_rate": 2.3626373626373625e-06,
      "loss": 0.225,
      "step": 860
    },
    {
      "epoch": 0.04835164835164835,
      "grad_norm": 0.4979713261127472,
      "learning_rate": 2.4175824175824177e-06,
      "loss": 0.2212,
      "step": 880
    },
    {
      "epoch": 0.04945054945054945,
      "grad_norm": 0.49497634172439575,
      "learning_rate": 2.4725274725274726e-06,
      "loss": 0.2234,
      "step": 900
    },
    {
      "epoch": 0.05054945054945055,
      "grad_norm": 0.6207996010780334,
      "learning_rate": 2.527472527472528e-06,
      "loss": 0.2256,
      "step": 920
    },
    {
      "epoch": 0.051648351648351645,
      "grad_norm": 0.530981719493866,
      "learning_rate": 2.5824175824175822e-06,
      "loss": 0.2231,
      "step": 940
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.5495067834854126,
      "learning_rate": 2.6373626373626375e-06,
      "loss": 0.223,
      "step": 960
    },
    {
      "epoch": 0.05384615384615385,
      "grad_norm": 0.5651763081550598,
      "learning_rate": 2.6923076923076928e-06,
      "loss": 0.2213,
      "step": 980
    },
    {
      "epoch": 0.054945054945054944,
      "grad_norm": 0.553247332572937,
      "learning_rate": 2.747252747252747e-06,
      "loss": 0.2219,
      "step": 1000
    }
  ],
  "logging_steps": 20,
  "max_steps": 91000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 6.336356548608e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}