{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 0.3724094033241272,
      "learning_rate": 2e-05,
      "loss": 1.5349,
      "step": 5
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.26067793369293213,
      "learning_rate": 2e-05,
      "loss": 1.3942,
      "step": 10
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 0.3689556419849396,
      "learning_rate": 2e-05,
      "loss": 1.3743,
      "step": 15
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 0.24060697853565216,
      "learning_rate": 2e-05,
      "loss": 1.2528,
      "step": 20
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 0.21089781820774078,
      "learning_rate": 2e-05,
      "loss": 1.2474,
      "step": 25
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.27054956555366516,
      "learning_rate": 2e-05,
      "loss": 1.2748,
      "step": 30
    },
    {
      "epoch": 0.16279069767441862,
      "grad_norm": 0.25132614374160767,
      "learning_rate": 2e-05,
      "loss": 1.254,
      "step": 35
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 0.20504344999790192,
      "learning_rate": 2e-05,
      "loss": 1.1509,
      "step": 40
    },
    {
      "epoch": 0.20930232558139536,
      "grad_norm": 0.22182047367095947,
      "learning_rate": 2e-05,
      "loss": 1.159,
      "step": 45
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.3401654362678528,
      "learning_rate": 2e-05,
      "loss": 1.2327,
      "step": 50
    },
    {
      "epoch": 0.2558139534883721,
      "grad_norm": 0.22995007038116455,
      "learning_rate": 2e-05,
      "loss": 1.0826,
      "step": 55
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 0.22365306317806244,
      "learning_rate": 2e-05,
      "loss": 1.1389,
      "step": 60
    },
    {
      "epoch": 0.3023255813953488,
      "grad_norm": 0.3217207193374634,
      "learning_rate": 2e-05,
      "loss": 1.1764,
      "step": 65
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 0.28037896752357483,
      "learning_rate": 2e-05,
      "loss": 1.1417,
      "step": 70
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 0.21693165600299835,
      "learning_rate": 2e-05,
      "loss": 1.0699,
      "step": 75
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 0.38298916816711426,
      "learning_rate": 2e-05,
      "loss": 1.1218,
      "step": 80
    },
    {
      "epoch": 0.3953488372093023,
      "grad_norm": 0.2960298955440521,
      "learning_rate": 2e-05,
      "loss": 1.1903,
      "step": 85
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 0.2717413604259491,
      "learning_rate": 2e-05,
      "loss": 1.086,
      "step": 90
    },
    {
      "epoch": 0.4418604651162791,
      "grad_norm": 0.2703586518764496,
      "learning_rate": 2e-05,
      "loss": 1.1053,
      "step": 95
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.40586695075035095,
      "learning_rate": 2e-05,
      "loss": 1.1559,
      "step": 100
    },
    {
      "epoch": 0.4883720930232558,
      "grad_norm": 0.24370810389518738,
      "learning_rate": 2e-05,
      "loss": 1.088,
      "step": 105
    },
    {
      "epoch": 0.5116279069767442,
      "grad_norm": 0.23648591339588165,
      "learning_rate": 2e-05,
      "loss": 1.0866,
      "step": 110
    },
    {
      "epoch": 0.5348837209302325,
      "grad_norm": 0.33186522126197815,
      "learning_rate": 2e-05,
      "loss": 1.1505,
      "step": 115
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 0.2656863331794739,
      "learning_rate": 2e-05,
      "loss": 1.1016,
      "step": 120
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 0.2450995147228241,
      "learning_rate": 2e-05,
      "loss": 1.0614,
      "step": 125
    },
    {
      "epoch": 0.6046511627906976,
      "grad_norm": 0.33901068568229675,
      "learning_rate": 2e-05,
      "loss": 1.0513,
      "step": 130
    },
    {
      "epoch": 0.627906976744186,
      "grad_norm": 0.29623690247535706,
      "learning_rate": 2e-05,
      "loss": 1.1418,
      "step": 135
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 0.2740626633167267,
      "learning_rate": 2e-05,
      "loss": 1.0751,
      "step": 140
    },
    {
      "epoch": 0.6744186046511628,
      "grad_norm": 0.3096587657928467,
      "learning_rate": 2e-05,
      "loss": 1.1081,
      "step": 145
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 0.37749382853507996,
      "learning_rate": 2e-05,
      "loss": 1.1435,
      "step": 150
    },
    {
      "epoch": 0.7209302325581395,
      "grad_norm": 0.29796457290649414,
      "learning_rate": 2e-05,
      "loss": 1.0263,
      "step": 155
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 0.2795608341693878,
      "learning_rate": 2e-05,
      "loss": 1.0689,
      "step": 160
    },
    {
      "epoch": 0.7674418604651163,
      "grad_norm": 0.3110540211200714,
      "learning_rate": 2e-05,
      "loss": 1.1006,
      "step": 165
    },
    {
      "epoch": 0.7906976744186046,
      "grad_norm": 0.3028092086315155,
      "learning_rate": 2e-05,
      "loss": 1.1031,
      "step": 170
    },
    {
      "epoch": 0.813953488372093,
      "grad_norm": 0.3238154351711273,
      "learning_rate": 2e-05,
      "loss": 1.0344,
      "step": 175
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 0.30875471234321594,
      "learning_rate": 2e-05,
      "loss": 1.0912,
      "step": 180
    },
    {
      "epoch": 0.8604651162790697,
      "grad_norm": 0.31477639079093933,
      "learning_rate": 2e-05,
      "loss": 1.1346,
      "step": 185
    },
    {
      "epoch": 0.8837209302325582,
      "grad_norm": 0.2805086374282837,
      "learning_rate": 2e-05,
      "loss": 1.0635,
      "step": 190
    },
    {
      "epoch": 0.9069767441860465,
      "grad_norm": 0.34058037400245667,
      "learning_rate": 2e-05,
      "loss": 1.0619,
      "step": 195
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 3.391491651535034,
      "learning_rate": 2e-05,
      "loss": 1.154,
      "step": 200
    },
    {
      "epoch": 0.9534883720930233,
      "grad_norm": 0.31490182876586914,
      "learning_rate": 2e-05,
      "loss": 1.0534,
      "step": 205
    },
    {
      "epoch": 0.9767441860465116,
      "grad_norm": 0.27165260910987854,
      "learning_rate": 2e-05,
      "loss": 1.0711,
      "step": 210
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3866237699985504,
      "learning_rate": 2e-05,
      "loss": 1.1221,
      "step": 215
    }
  ],
  "logging_steps": 5,
  "max_steps": 215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 99999,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.303415539208028e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}