{
  "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": 3.915436267852783,
      "learning_rate": 2.380952380952381e-05,
      "loss": 4.6057,
      "step": 5
    },
    {
      "epoch": 0.2846975088967972,
      "grad_norm": 4.926669597625732,
      "learning_rate": 4.761904761904762e-05,
      "loss": 4.3259,
      "step": 10
    },
    {
      "epoch": 0.42704626334519574,
      "grad_norm": 3.071687936782837,
      "learning_rate": 7.142857142857143e-05,
      "loss": 3.5782,
      "step": 15
    },
    {
      "epoch": 0.5693950177935944,
      "grad_norm": 1.5628787279129028,
      "learning_rate": 9.523809523809524e-05,
      "loss": 2.542,
      "step": 20
    },
    {
      "epoch": 0.7117437722419929,
      "grad_norm": 0.6052073240280151,
      "learning_rate": 9.988952191691925e-05,
      "loss": 2.0288,
      "step": 25
    },
    {
      "epoch": 0.8540925266903915,
      "grad_norm": 0.4768967032432556,
      "learning_rate": 9.944154131125642e-05,
      "loss": 1.9283,
      "step": 30
    },
    {
      "epoch": 0.99644128113879,
      "grad_norm": 0.3471652865409851,
      "learning_rate": 9.865224352899119e-05,
      "loss": 1.9221,
      "step": 35
    },
    {
      "epoch": 0.99644128113879,
      "eval_loss": 1.9122635126113892,
      "eval_runtime": 2.7209,
      "eval_samples_per_second": 16.906,
      "eval_steps_per_second": 16.906,
      "step": 35
    },
    {
      "epoch": 1.1387900355871885,
      "grad_norm": 0.3238619863986969,
      "learning_rate": 9.752707744739145e-05,
      "loss": 1.8485,
      "step": 40
    },
    {
      "epoch": 1.281138790035587,
      "grad_norm": 0.3222252130508423,
      "learning_rate": 9.607381059352038e-05,
      "loss": 1.8223,
      "step": 45
    },
    {
      "epoch": 1.4234875444839858,
      "grad_norm": 0.30783718824386597,
      "learning_rate": 9.430247552150673e-05,
      "loss": 1.7991,
      "step": 50
    },
    {
      "epoch": 1.5658362989323842,
      "grad_norm": 0.33385950326919556,
      "learning_rate": 9.22253005533154e-05,
      "loss": 1.7761,
      "step": 55
    },
    {
      "epoch": 1.708185053380783,
      "grad_norm": 0.3235575258731842,
      "learning_rate": 8.985662536114613e-05,
      "loss": 1.7781,
      "step": 60
    },
    {
      "epoch": 1.8505338078291815,
      "grad_norm": 0.31781575083732605,
      "learning_rate": 8.721280197423258e-05,
      "loss": 1.7457,
      "step": 65
    },
    {
      "epoch": 1.99288256227758,
      "grad_norm": 0.3225061297416687,
      "learning_rate": 8.43120818934367e-05,
      "loss": 1.7521,
      "step": 70
    },
    {
      "epoch": 1.99288256227758,
      "eval_loss": 1.7631458044052124,
      "eval_runtime": 2.707,
      "eval_samples_per_second": 16.993,
      "eval_steps_per_second": 16.993,
      "step": 70
    },
    {
      "epoch": 2.135231316725979,
      "grad_norm": 0.3239762783050537,
      "learning_rate": 8.117449009293668e-05,
      "loss": 1.6471,
      "step": 75
    },
    {
      "epoch": 2.277580071174377,
      "grad_norm": 0.348884642124176,
      "learning_rate": 7.782168677883206e-05,
      "loss": 1.7,
      "step": 80
    },
    {
      "epoch": 2.419928825622776,
      "grad_norm": 0.3774774372577667,
      "learning_rate": 7.427681785900761e-05,
      "loss": 1.7183,
      "step": 85
    },
    {
      "epoch": 2.562277580071174,
      "grad_norm": 0.39107823371887207,
      "learning_rate": 7.056435515653059e-05,
      "loss": 1.6825,
      "step": 90
    },
    {
      "epoch": 2.704626334519573,
      "grad_norm": 0.5160859823226929,
      "learning_rate": 6.670992746965938e-05,
      "loss": 1.664,
      "step": 95
    },
    {
      "epoch": 2.8469750889679717,
      "grad_norm": 0.4094185531139374,
      "learning_rate": 6.274014364473274e-05,
      "loss": 1.6662,
      "step": 100
    },
    {
      "epoch": 2.9893238434163703,
      "grad_norm": 0.4102707803249359,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.6831,
      "step": 105
    },
    {
      "epoch": 2.9893238434163703,
      "eval_loss": 1.691434621810913,
      "eval_runtime": 2.7669,
      "eval_samples_per_second": 16.625,
      "eval_steps_per_second": 16.625,
      "step": 105
    },
    {
      "epoch": 3.131672597864769,
      "grad_norm": 0.41169798374176025,
      "learning_rate": 5.456473555193242e-05,
      "loss": 1.6085,
      "step": 110
    },
    {
      "epoch": 3.2740213523131674,
      "grad_norm": 0.5937510132789612,
      "learning_rate": 5.041554979980486e-05,
      "loss": 1.6105,
      "step": 115
    },
    {
      "epoch": 3.416370106761566,
      "grad_norm": 0.4580947160720825,
      "learning_rate": 4.626349532067879e-05,
      "loss": 1.6227,
      "step": 120
    },
    {
      "epoch": 3.5587188612099645,
      "grad_norm": 0.4503268599510193,
      "learning_rate": 4.213723561238074e-05,
      "loss": 1.6202,
      "step": 125
    },
    {
      "epoch": 3.701067615658363,
      "grad_norm": 0.5091418623924255,
      "learning_rate": 3.806525609984312e-05,
      "loss": 1.6178,
      "step": 130
    },
    {
      "epoch": 3.8434163701067616,
      "grad_norm": 0.5050191283226013,
      "learning_rate": 3.4075667487415785e-05,
      "loss": 1.6023,
      "step": 135
    },
    {
      "epoch": 3.98576512455516,
      "grad_norm": 0.502037525177002,
      "learning_rate": 3.019601169804216e-05,
      "loss": 1.5566,
      "step": 140
    },
    {
      "epoch": 3.98576512455516,
      "eval_loss": 1.6648945808410645,
      "eval_runtime": 2.7182,
      "eval_samples_per_second": 16.923,
      "eval_steps_per_second": 16.923,
      "step": 140
    },
    {
      "epoch": 4.128113879003559,
      "grad_norm": 0.4845784604549408,
      "learning_rate": 2.645307173898901e-05,
      "loss": 1.5459,
      "step": 145
    },
    {
      "epoch": 4.270462633451958,
      "grad_norm": 0.4947628378868103,
      "learning_rate": 2.2872686806712035e-05,
      "loss": 1.5934,
      "step": 150
    },
    {
      "epoch": 4.412811387900356,
      "grad_norm": 0.5146717429161072,
      "learning_rate": 1.947957390727185e-05,
      "loss": 1.543,
      "step": 155
    },
    {
      "epoch": 4.555160142348754,
      "grad_norm": 0.4881040155887604,
      "learning_rate": 1.629715722373423e-05,
      "loss": 1.568,
      "step": 160
    },
    {
      "epoch": 4.697508896797153,
      "grad_norm": 0.514570951461792,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 1.5337,
      "step": 165
    },
    {
      "epoch": 4.839857651245552,
      "grad_norm": 0.5478077530860901,
      "learning_rate": 1.0650684916965559e-05,
      "loss": 1.5442,
      "step": 170
    },
    {
      "epoch": 4.98220640569395,
      "grad_norm": 0.47540614008903503,
      "learning_rate": 8.225609429353187e-06,
      "loss": 1.562,
      "step": 175
    },
    {
      "epoch": 4.98220640569395,
      "eval_loss": 1.6638323068618774,
      "eval_runtime": 2.7058,
      "eval_samples_per_second": 17.001,
      "eval_steps_per_second": 17.001,
      "step": 175
    },
    {
      "epoch": 5.124555160142349,
      "grad_norm": 0.5304147005081177,
      "learning_rate": 6.088921331488568e-06,
      "loss": 1.525,
      "step": 180
    },
    {
      "epoch": 5.266903914590747,
      "grad_norm": 0.5111469626426697,
      "learning_rate": 4.255371141448272e-06,
      "loss": 1.5231,
      "step": 185
    },
    {
      "epoch": 5.409252669039146,
      "grad_norm": 0.5378378629684448,
      "learning_rate": 2.737616680113758e-06,
      "loss": 1.5374,
      "step": 190
    },
    {
      "epoch": 5.551601423487544,
      "grad_norm": 0.5272733569145203,
      "learning_rate": 1.5461356885461075e-06,
      "loss": 1.5275,
      "step": 195
    },
    {
      "epoch": 5.693950177935943,
      "grad_norm": 0.5704510807991028,
      "learning_rate": 6.891534954310885e-07,
      "loss": 1.5365,
      "step": 200
    },
    {
      "epoch": 5.8362989323843415,
      "grad_norm": 0.528024435043335,
      "learning_rate": 1.725862339392259e-07,
      "loss": 1.5085,
      "step": 205
    },
    {
      "epoch": 5.9786476868327405,
      "grad_norm": 0.526282548904419,
      "learning_rate": 0.0,
      "loss": 1.5573,
      "step": 210
    },
    {
      "epoch": 5.9786476868327405,
      "eval_loss": 1.6644203662872314,
      "eval_runtime": 2.8579,
      "eval_samples_per_second": 16.096,
      "eval_steps_per_second": 16.096,
      "step": 210
    },
    {
      "epoch": 5.9786476868327405,
      "step": 210,
      "total_flos": 1.7533662523283866e+17,
      "train_loss": 1.8585307757059732,
      "train_runtime": 2890.6103,
      "train_samples_per_second": 9.303,
      "train_steps_per_second": 0.073
    }
  ],
  "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": 1.7533662523283866e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}