{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 4.71875,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.1991,
      "step": 50
    },
    {
      "epoch": 0.1,
      "grad_norm": 7.03125,
      "learning_rate": 0.000196,
      "loss": 0.5348,
      "step": 100
    },
    {
      "epoch": 0.15,
      "grad_norm": 13.625,
      "learning_rate": 0.000194,
      "loss": 0.7719,
      "step": 150
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.7578125,
      "learning_rate": 0.000192,
      "loss": 0.5357,
      "step": 200
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.52734375,
      "learning_rate": 0.00019,
      "loss": 0.5368,
      "step": 250
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.34375,
      "learning_rate": 0.000188,
      "loss": 0.447,
      "step": 300
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.9140625,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.4369,
      "step": 350
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.2421875,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.5182,
      "step": 400
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.90625,
      "learning_rate": 0.000182,
      "loss": 0.4342,
      "step": 450
    },
    {
      "epoch": 0.5,
      "grad_norm": 3.265625,
      "learning_rate": 0.00018,
      "loss": 0.4876,
      "step": 500
    },
    {
      "epoch": 0.55,
      "grad_norm": 2.1875,
      "learning_rate": 0.00017800000000000002,
      "loss": 0.6829,
      "step": 550
    },
    {
      "epoch": 0.6,
      "grad_norm": 29.125,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.5333,
      "step": 600
    },
    {
      "epoch": 0.65,
      "grad_norm": 4.34375,
      "learning_rate": 0.000174,
      "loss": 0.544,
      "step": 650
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.4453125,
      "learning_rate": 0.000172,
      "loss": 0.4168,
      "step": 700
    },
    {
      "epoch": 0.75,
      "grad_norm": 4.1875,
      "learning_rate": 0.00017,
      "loss": 0.503,
      "step": 750
    },
    {
      "epoch": 0.8,
      "grad_norm": 5.6875,
      "learning_rate": 0.000168,
      "loss": 0.619,
      "step": 800
    },
    {
      "epoch": 0.85,
      "grad_norm": 1.1171875,
      "learning_rate": 0.000166,
      "loss": 0.4079,
      "step": 850
    },
    {
      "epoch": 0.9,
      "grad_norm": 2.46875,
      "learning_rate": 0.000164,
      "loss": 0.3853,
      "step": 900
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.0078125,
      "learning_rate": 0.000162,
      "loss": 0.4464,
      "step": 950
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.64453125,
      "learning_rate": 0.00016,
      "loss": 0.3638,
      "step": 1000
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.52734375,
      "learning_rate": 0.00015800000000000002,
      "loss": 0.3634,
      "step": 1050
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.6875,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.3604,
      "step": 1100
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.337890625,
      "learning_rate": 0.000154,
      "loss": 0.3328,
      "step": 1150
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.078125,
      "learning_rate": 0.000152,
      "loss": 0.4488,
      "step": 1200
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.859375,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.5788,
      "step": 1250
    },
    {
      "epoch": 1.3,
      "grad_norm": 2.140625,
      "learning_rate": 0.000148,
      "loss": 0.3634,
      "step": 1300
    },
    {
      "epoch": 1.35,
      "grad_norm": 17.5,
      "learning_rate": 0.000146,
      "loss": 0.4267,
      "step": 1350
    },
    {
      "epoch": 1.4,
      "grad_norm": 1.859375,
      "learning_rate": 0.000144,
      "loss": 0.6031,
      "step": 1400
    },
    {
      "epoch": 1.45,
      "grad_norm": 32.5,
      "learning_rate": 0.000142,
      "loss": 0.6059,
      "step": 1450
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.8125,
      "learning_rate": 0.00014,
      "loss": 0.655,
      "step": 1500
    },
    {
      "epoch": 1.55,
      "grad_norm": 1.2109375,
      "learning_rate": 0.000138,
      "loss": 0.5061,
      "step": 1550
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.64453125,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.4995,
      "step": 1600
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.8359375,
      "learning_rate": 0.000134,
      "loss": 0.5439,
      "step": 1650
    },
    {
      "epoch": 1.7,
      "grad_norm": 1.21875,
      "learning_rate": 0.000132,
      "loss": 0.3714,
      "step": 1700
    },
    {
      "epoch": 1.75,
      "grad_norm": 1.0703125,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.4673,
      "step": 1750
    },
    {
      "epoch": 1.8,
      "grad_norm": 2.421875,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.3626,
      "step": 1800
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.70703125,
      "learning_rate": 0.000126,
      "loss": 0.6073,
      "step": 1850
    },
    {
      "epoch": 1.9,
      "grad_norm": 1.421875,
      "learning_rate": 0.000124,
      "loss": 0.4671,
      "step": 1900
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.859375,
      "learning_rate": 0.000122,
      "loss": 0.3424,
      "step": 1950
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.7421875,
      "learning_rate": 0.00012,
      "loss": 0.3802,
      "step": 2000
    },
    {
      "epoch": 2.05,
      "grad_norm": 0.4375,
      "learning_rate": 0.000118,
      "loss": 0.3936,
      "step": 2050
    },
    {
      "epoch": 2.1,
      "grad_norm": 1.0546875,
      "learning_rate": 0.000116,
      "loss": 0.3808,
      "step": 2100
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.78125,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.3487,
      "step": 2150
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.7265625,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.3627,
      "step": 2200
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.67578125,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.3638,
      "step": 2250
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.58203125,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.3568,
      "step": 2300
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.71484375,
      "learning_rate": 0.00010600000000000002,
      "loss": 0.4174,
      "step": 2350
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.69140625,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.3676,
      "step": 2400
    },
    {
      "epoch": 2.45,
      "grad_norm": 4.625,
      "learning_rate": 0.00010200000000000001,
      "loss": 0.3714,
      "step": 2450
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.8046875,
      "learning_rate": 0.0001,
      "loss": 0.4879,
      "step": 2500
    },
    {
      "epoch": 2.55,
      "grad_norm": 4.59375,
      "learning_rate": 9.8e-05,
      "loss": 0.5212,
      "step": 2550
    },
    {
      "epoch": 2.6,
      "grad_norm": 5.03125,
      "learning_rate": 9.6e-05,
      "loss": 0.5051,
      "step": 2600
    },
    {
      "epoch": 2.65,
      "grad_norm": 0.8203125,
      "learning_rate": 9.4e-05,
      "loss": 0.4212,
      "step": 2650
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.66796875,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.3505,
      "step": 2700
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.90234375,
      "learning_rate": 9e-05,
      "loss": 0.3521,
      "step": 2750
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.7265625,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.3495,
      "step": 2800
    },
    {
      "epoch": 2.85,
      "grad_norm": 0.5,
      "learning_rate": 8.6e-05,
      "loss": 0.3034,
      "step": 2850
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.65625,
      "learning_rate": 8.4e-05,
      "loss": 0.636,
      "step": 2900
    },
    {
      "epoch": 2.95,
      "grad_norm": 3.171875,
      "learning_rate": 8.2e-05,
      "loss": 0.5193,
      "step": 2950
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.65625,
      "learning_rate": 8e-05,
      "loss": 0.4152,
      "step": 3000
    },
    {
      "epoch": 3.05,
      "grad_norm": 1.140625,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.4252,
      "step": 3050
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.78515625,
      "learning_rate": 7.6e-05,
      "loss": 0.3521,
      "step": 3100
    },
    {
      "epoch": 3.15,
      "grad_norm": 0.76171875,
      "learning_rate": 7.4e-05,
      "loss": 0.3409,
      "step": 3150
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.7734375,
      "learning_rate": 7.2e-05,
      "loss": 0.3497,
      "step": 3200
    },
    {
      "epoch": 3.25,
      "grad_norm": 0.53125,
      "learning_rate": 7e-05,
      "loss": 0.3548,
      "step": 3250
    },
    {
      "epoch": 3.3,
      "grad_norm": 0.5390625,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.3416,
      "step": 3300
    },
    {
      "epoch": 3.35,
      "grad_norm": 0.55859375,
      "learning_rate": 6.6e-05,
      "loss": 0.3448,
      "step": 3350
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.75,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.3453,
      "step": 3400
    },
    {
      "epoch": 3.45,
      "grad_norm": 0.50390625,
      "learning_rate": 6.2e-05,
      "loss": 0.3461,
      "step": 3450
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.5859375,
      "learning_rate": 6e-05,
      "loss": 0.3597,
      "step": 3500
    },
    {
      "epoch": 3.55,
      "grad_norm": 0.546875,
      "learning_rate": 5.8e-05,
      "loss": 0.3448,
      "step": 3550
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.58203125,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.3486,
      "step": 3600
    },
    {
      "epoch": 3.65,
      "grad_norm": 0.51171875,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.3503,
      "step": 3650
    },
    {
      "epoch": 3.7,
      "grad_norm": 0.53515625,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.3457,
      "step": 3700
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.51171875,
      "learning_rate": 5e-05,
      "loss": 0.347,
      "step": 3750
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.57421875,
      "learning_rate": 4.8e-05,
      "loss": 0.3489,
      "step": 3800
    },
    {
      "epoch": 3.85,
      "grad_norm": 0.53515625,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.3488,
      "step": 3850
    },
    {
      "epoch": 3.9,
      "grad_norm": 0.55859375,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.3504,
      "step": 3900
    },
    {
      "epoch": 3.95,
      "grad_norm": 0.5078125,
      "learning_rate": 4.2e-05,
      "loss": 0.3465,
      "step": 3950
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.65625,
      "learning_rate": 4e-05,
      "loss": 0.3474,
      "step": 4000
    },
    {
      "epoch": 4.05,
      "grad_norm": 0.53515625,
      "learning_rate": 3.8e-05,
      "loss": 0.3433,
      "step": 4050
    },
    {
      "epoch": 4.1,
      "grad_norm": 0.5546875,
      "learning_rate": 3.6e-05,
      "loss": 0.3431,
      "step": 4100
    },
    {
      "epoch": 4.15,
      "grad_norm": 0.73828125,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.3436,
      "step": 4150
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.6015625,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.3447,
      "step": 4200
    },
    {
      "epoch": 4.25,
      "grad_norm": 0.53515625,
      "learning_rate": 3e-05,
      "loss": 0.3436,
      "step": 4250
    },
    {
      "epoch": 4.3,
      "grad_norm": 0.6875,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.3494,
      "step": 4300
    },
    {
      "epoch": 4.35,
      "grad_norm": 0.55078125,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.343,
      "step": 4350
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.6015625,
      "learning_rate": 2.4e-05,
      "loss": 0.3465,
      "step": 4400
    },
    {
      "epoch": 4.45,
      "grad_norm": 0.59375,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.3521,
      "step": 4450
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.59375,
      "learning_rate": 2e-05,
      "loss": 0.3431,
      "step": 4500
    },
    {
      "epoch": 4.55,
      "grad_norm": 0.578125,
      "learning_rate": 1.8e-05,
      "loss": 0.3395,
      "step": 4550
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.62890625,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.3409,
      "step": 4600
    },
    {
      "epoch": 4.65,
      "grad_norm": 0.5703125,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.3463,
      "step": 4650
    },
    {
      "epoch": 4.7,
      "grad_norm": 0.6796875,
      "learning_rate": 1.2e-05,
      "loss": 0.3521,
      "step": 4700
    },
    {
      "epoch": 4.75,
      "grad_norm": 0.546875,
      "learning_rate": 1e-05,
      "loss": 0.34,
      "step": 4750
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.54296875,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.3486,
      "step": 4800
    },
    {
      "epoch": 4.85,
      "grad_norm": 0.578125,
      "learning_rate": 6e-06,
      "loss": 0.3537,
      "step": 4850
    },
    {
      "epoch": 4.9,
      "grad_norm": 0.64453125,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.3435,
      "step": 4900
    },
    {
      "epoch": 4.95,
      "grad_norm": 0.5703125,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.3514,
      "step": 4950
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.578125,
      "learning_rate": 0.0,
      "loss": 0.3446,
      "step": 5000
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.14270352818176e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}