{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 195,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005128205128205128,
      "grad_norm": 0.7734681367874146,
      "learning_rate": 1.4999999999999999e-05,
      "loss": 2.2537,
      "step": 1
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 0.9921783804893494,
      "learning_rate": 7.5e-05,
      "loss": 2.2441,
      "step": 5
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 1.209192156791687,
      "learning_rate": 0.00015,
      "loss": 2.1391,
      "step": 10
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 1.4021319150924683,
      "learning_rate": 0.000225,
      "loss": 1.6962,
      "step": 15
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 2.129197359085083,
      "learning_rate": 0.0003,
      "loss": 1.2642,
      "step": 20
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 0.6822463870048523,
      "learning_rate": 0.00029939614409928584,
      "loss": 1.15,
      "step": 25
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.5067035555839539,
      "learning_rate": 0.00029758943828979444,
      "loss": 1.078,
      "step": 30
    },
    {
      "epoch": 0.1794871794871795,
      "grad_norm": 0.40783199667930603,
      "learning_rate": 0.00029459442910437797,
      "loss": 1.0186,
      "step": 35
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.274424284696579,
      "learning_rate": 0.00029043523059596053,
      "loss": 0.9822,
      "step": 40
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.241612508893013,
      "learning_rate": 0.0002851453301853628,
      "loss": 0.9603,
      "step": 45
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.18045982718467712,
      "learning_rate": 0.0002787673190402799,
      "loss": 0.9451,
      "step": 50
    },
    {
      "epoch": 0.28205128205128205,
      "grad_norm": 0.24599388241767883,
      "learning_rate": 0.0002713525491562421,
      "loss": 0.9247,
      "step": 55
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.23441565036773682,
      "learning_rate": 0.00026296071990054165,
      "loss": 0.9203,
      "step": 60
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.20591339468955994,
      "learning_rate": 0.0002536593973480297,
      "loss": 0.9067,
      "step": 65
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 0.46566951274871826,
      "learning_rate": 0.00024352347027881003,
      "loss": 0.9017,
      "step": 70
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.21229182183742523,
      "learning_rate": 0.00023263454721781537,
      "loss": 0.9016,
      "step": 75
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.22548721730709076,
      "learning_rate": 0.0002210802993709498,
      "loss": 0.8903,
      "step": 80
    },
    {
      "epoch": 0.4358974358974359,
      "grad_norm": 0.18637174367904663,
      "learning_rate": 0.00020895375474808852,
      "loss": 0.8883,
      "step": 85
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.1939140409231186,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.8799,
      "step": 90
    },
    {
      "epoch": 0.48717948717948717,
      "grad_norm": 0.2150397151708603,
      "learning_rate": 0.00018337814009344714,
      "loss": 0.8776,
      "step": 95
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.21106576919555664,
      "learning_rate": 0.00017013498987264832,
      "loss": 0.8775,
      "step": 100
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.21716269850730896,
      "learning_rate": 0.00015672972455257723,
      "loss": 0.8734,
      "step": 105
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 0.22086042165756226,
      "learning_rate": 0.0001432702754474228,
      "loss": 0.8512,
      "step": 110
    },
    {
      "epoch": 0.5897435897435898,
      "grad_norm": 0.232639878988266,
      "learning_rate": 0.0001298650101273517,
      "loss": 0.8718,
      "step": 115
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.21026825904846191,
      "learning_rate": 0.00011662185990655284,
      "loss": 0.8579,
      "step": 120
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 0.19612908363342285,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.859,
      "step": 125
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.21048156917095184,
      "learning_rate": 9.104624525191145e-05,
      "loss": 0.8543,
      "step": 130
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.18239416182041168,
      "learning_rate": 7.89197006290502e-05,
      "loss": 0.8531,
      "step": 135
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.18775755167007446,
      "learning_rate": 6.736545278218463e-05,
      "loss": 0.858,
      "step": 140
    },
    {
      "epoch": 0.7435897435897436,
      "grad_norm": 0.20988330245018005,
      "learning_rate": 5.6476529721189974e-05,
      "loss": 0.8532,
      "step": 145
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.20845285058021545,
      "learning_rate": 4.63406026519703e-05,
      "loss": 0.8562,
      "step": 150
    },
    {
      "epoch": 0.7948717948717948,
      "grad_norm": 0.1928585022687912,
      "learning_rate": 3.7039280099458366e-05,
      "loss": 0.8567,
      "step": 155
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.19923464953899384,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.8492,
      "step": 160
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.17737220227718353,
      "learning_rate": 2.1232680959720082e-05,
      "loss": 0.8404,
      "step": 165
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 0.18061356246471405,
      "learning_rate": 1.4854669814637143e-05,
      "loss": 0.8493,
      "step": 170
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 0.17233729362487793,
      "learning_rate": 9.564769404039419e-06,
      "loss": 0.849,
      "step": 175
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.20439976453781128,
      "learning_rate": 5.405570895622013e-06,
      "loss": 0.8434,
      "step": 180
    },
    {
      "epoch": 0.9487179487179487,
      "grad_norm": 0.1979411542415619,
      "learning_rate": 2.4105617102055496e-06,
      "loss": 0.8441,
      "step": 185
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 0.18543799221515656,
      "learning_rate": 6.038559007141397e-07,
      "loss": 0.8526,
      "step": 190
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.225219264626503,
      "learning_rate": 0.0,
      "loss": 0.8469,
      "step": 195
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.0160739421844482,
      "eval_runtime": 1.1142,
      "eval_samples_per_second": 8.975,
      "eval_steps_per_second": 0.897,
      "step": 195
    },
    {
      "epoch": 1.0,
      "step": 195,
      "total_flos": 5.7571792321406566e+17,
      "train_loss": 0.9914888846568573,
      "train_runtime": 2084.3097,
      "train_samples_per_second": 5.986,
      "train_steps_per_second": 0.094
    }
  ],
  "logging_steps": 5,
  "max_steps": 195,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.7571792321406566e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}