{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.9786476868327405,
  "eval_steps": 35,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1423487544483986,
      "grad_norm": 0.9279331564903259,
      "learning_rate": 2.380952380952381e-05,
      "loss": 2.8997,
      "step": 5
    },
    {
      "epoch": 0.2846975088967972,
      "grad_norm": 1.3731201887130737,
      "learning_rate": 4.761904761904762e-05,
      "loss": 2.8225,
      "step": 10
    },
    {
      "epoch": 0.42704626334519574,
      "grad_norm": 1.0099289417266846,
      "learning_rate": 7.142857142857143e-05,
      "loss": 2.5438,
      "step": 15
    },
    {
      "epoch": 0.5693950177935944,
      "grad_norm": 0.9636003971099854,
      "learning_rate": 9.523809523809524e-05,
      "loss": 2.1964,
      "step": 20
    },
    {
      "epoch": 0.7117437722419929,
      "grad_norm": 0.49576738476753235,
      "learning_rate": 9.988952191691925e-05,
      "loss": 1.8465,
      "step": 25
    },
    {
      "epoch": 0.8540925266903915,
      "grad_norm": 0.45192059874534607,
      "learning_rate": 9.944154131125642e-05,
      "loss": 1.7222,
      "step": 30
    },
    {
      "epoch": 0.99644128113879,
      "grad_norm": 0.34899845719337463,
      "learning_rate": 9.865224352899119e-05,
      "loss": 1.7363,
      "step": 35
    },
    {
      "epoch": 0.99644128113879,
      "eval_loss": 1.633471965789795,
      "eval_runtime": 3.0147,
      "eval_samples_per_second": 15.258,
      "eval_steps_per_second": 15.258,
      "step": 35
    },
    {
      "epoch": 1.1387900355871885,
      "grad_norm": 0.33272063732147217,
      "learning_rate": 9.752707744739145e-05,
      "loss": 1.6902,
      "step": 40
    },
    {
      "epoch": 1.281138790035587,
      "grad_norm": 0.37461546063423157,
      "learning_rate": 9.607381059352038e-05,
      "loss": 1.6266,
      "step": 45
    },
    {
      "epoch": 1.4234875444839858,
      "grad_norm": 0.3448285460472107,
      "learning_rate": 9.430247552150673e-05,
      "loss": 1.6271,
      "step": 50
    },
    {
      "epoch": 1.5658362989323842,
      "grad_norm": 0.37999773025512695,
      "learning_rate": 9.22253005533154e-05,
      "loss": 1.5952,
      "step": 55
    },
    {
      "epoch": 1.708185053380783,
      "grad_norm": 0.39842531085014343,
      "learning_rate": 8.985662536114613e-05,
      "loss": 1.5983,
      "step": 60
    },
    {
      "epoch": 1.8505338078291815,
      "grad_norm": 0.3690396845340729,
      "learning_rate": 8.721280197423258e-05,
      "loss": 1.5535,
      "step": 65
    },
    {
      "epoch": 1.99288256227758,
      "grad_norm": 0.38522452116012573,
      "learning_rate": 8.43120818934367e-05,
      "loss": 1.5711,
      "step": 70
    },
    {
      "epoch": 1.99288256227758,
      "eval_loss": 1.523573637008667,
      "eval_runtime": 2.9825,
      "eval_samples_per_second": 15.424,
      "eval_steps_per_second": 15.424,
      "step": 70
    },
    {
      "epoch": 2.135231316725979,
      "grad_norm": 0.3965684473514557,
      "learning_rate": 8.117449009293668e-05,
      "loss": 1.4586,
      "step": 75
    },
    {
      "epoch": 2.277580071174377,
      "grad_norm": 0.46490275859832764,
      "learning_rate": 7.782168677883206e-05,
      "loss": 1.4704,
      "step": 80
    },
    {
      "epoch": 2.419928825622776,
      "grad_norm": 0.5263304114341736,
      "learning_rate": 7.427681785900761e-05,
      "loss": 1.5124,
      "step": 85
    },
    {
      "epoch": 2.562277580071174,
      "grad_norm": 0.5867888927459717,
      "learning_rate": 7.056435515653059e-05,
      "loss": 1.4698,
      "step": 90
    },
    {
      "epoch": 2.704626334519573,
      "grad_norm": 0.602433979511261,
      "learning_rate": 6.670992746965938e-05,
      "loss": 1.4395,
      "step": 95
    },
    {
      "epoch": 2.8469750889679717,
      "grad_norm": 0.5787069201469421,
      "learning_rate": 6.274014364473274e-05,
      "loss": 1.4544,
      "step": 100
    },
    {
      "epoch": 2.9893238434163703,
      "grad_norm": 0.6700984239578247,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.4657,
      "step": 105
    },
    {
      "epoch": 2.9893238434163703,
      "eval_loss": 1.502173662185669,
      "eval_runtime": 2.9977,
      "eval_samples_per_second": 15.345,
      "eval_steps_per_second": 15.345,
      "step": 105
    },
    {
      "epoch": 3.131672597864769,
      "grad_norm": 0.6033971905708313,
      "learning_rate": 5.456473555193242e-05,
      "loss": 1.3647,
      "step": 110
    },
    {
      "epoch": 3.2740213523131674,
      "grad_norm": 0.6693300008773804,
      "learning_rate": 5.041554979980486e-05,
      "loss": 1.346,
      "step": 115
    },
    {
      "epoch": 3.416370106761566,
      "grad_norm": 0.7680426836013794,
      "learning_rate": 4.626349532067879e-05,
      "loss": 1.3392,
      "step": 120
    },
    {
      "epoch": 3.5587188612099645,
      "grad_norm": 0.800693690776825,
      "learning_rate": 4.213723561238074e-05,
      "loss": 1.3507,
      "step": 125
    },
    {
      "epoch": 3.701067615658363,
      "grad_norm": 0.8501924872398376,
      "learning_rate": 3.806525609984312e-05,
      "loss": 1.3136,
      "step": 130
    },
    {
      "epoch": 3.8434163701067616,
      "grad_norm": 0.8718882203102112,
      "learning_rate": 3.4075667487415785e-05,
      "loss": 1.3249,
      "step": 135
    },
    {
      "epoch": 3.98576512455516,
      "grad_norm": 0.8544139266014099,
      "learning_rate": 3.019601169804216e-05,
      "loss": 1.2867,
      "step": 140
    },
    {
      "epoch": 3.98576512455516,
      "eval_loss": 1.5092459917068481,
      "eval_runtime": 3.0,
      "eval_samples_per_second": 15.333,
      "eval_steps_per_second": 15.333,
      "step": 140
    },
    {
      "epoch": 4.128113879003559,
      "grad_norm": 0.8437187671661377,
      "learning_rate": 2.645307173898901e-05,
      "loss": 1.2288,
      "step": 145
    },
    {
      "epoch": 4.270462633451958,
      "grad_norm": 0.9426507949829102,
      "learning_rate": 2.2872686806712035e-05,
      "loss": 1.2517,
      "step": 150
    },
    {
      "epoch": 4.412811387900356,
      "grad_norm": 1.0104249715805054,
      "learning_rate": 1.947957390727185e-05,
      "loss": 1.208,
      "step": 155
    },
    {
      "epoch": 4.555160142348754,
      "grad_norm": 0.9811246991157532,
      "learning_rate": 1.629715722373423e-05,
      "loss": 1.2316,
      "step": 160
    },
    {
      "epoch": 4.697508896797153,
      "grad_norm": 1.0006216764450073,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 1.2008,
      "step": 165
    },
    {
      "epoch": 4.839857651245552,
      "grad_norm": 1.0489338636398315,
      "learning_rate": 1.0650684916965559e-05,
      "loss": 1.2036,
      "step": 170
    },
    {
      "epoch": 4.98220640569395,
      "grad_norm": 0.977066159248352,
      "learning_rate": 8.225609429353187e-06,
      "loss": 1.2283,
      "step": 175
    },
    {
      "epoch": 4.98220640569395,
      "eval_loss": 1.5431582927703857,
      "eval_runtime": 3.0522,
      "eval_samples_per_second": 15.071,
      "eval_steps_per_second": 15.071,
      "step": 175
    },
    {
      "epoch": 5.124555160142349,
      "grad_norm": 1.0375797748565674,
      "learning_rate": 6.088921331488568e-06,
      "loss": 1.1602,
      "step": 180
    },
    {
      "epoch": 5.266903914590747,
      "grad_norm": 1.0365866422653198,
      "learning_rate": 4.255371141448272e-06,
      "loss": 1.1792,
      "step": 185
    },
    {
      "epoch": 5.409252669039146,
      "grad_norm": 1.1315181255340576,
      "learning_rate": 2.737616680113758e-06,
      "loss": 1.1598,
      "step": 190
    },
    {
      "epoch": 5.551601423487544,
      "grad_norm": 1.0719408988952637,
      "learning_rate": 1.5461356885461075e-06,
      "loss": 1.1685,
      "step": 195
    },
    {
      "epoch": 5.693950177935943,
      "grad_norm": 1.0842665433883667,
      "learning_rate": 6.891534954310885e-07,
      "loss": 1.1541,
      "step": 200
    },
    {
      "epoch": 5.8362989323843415,
      "grad_norm": 1.1403180360794067,
      "learning_rate": 1.725862339392259e-07,
      "loss": 1.1508,
      "step": 205
    },
    {
      "epoch": 5.9786476868327405,
      "grad_norm": 1.0521795749664307,
      "learning_rate": 0.0,
      "loss": 1.1824,
      "step": 210
    },
    {
      "epoch": 5.9786476868327405,
      "eval_loss": 1.5571128129959106,
      "eval_runtime": 3.0104,
      "eval_samples_per_second": 15.28,
      "eval_steps_per_second": 15.28,
      "step": 210
    },
    {
      "epoch": 5.9786476868327405,
      "step": 210,
      "total_flos": 2.5945177356867994e+17,
      "train_loss": 1.50793886638823,
      "train_runtime": 3222.8617,
      "train_samples_per_second": 8.344,
      "train_steps_per_second": 0.065
    }
  ],
  "logging_steps": 5,
  "max_steps": 210,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 35,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5945177356867994e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}