{
  "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": 5.176560878753662,
      "learning_rate": 2.380952380952381e-05,
      "loss": 2.7275,
      "step": 5
    },
    {
      "epoch": 0.2846975088967972,
      "grad_norm": 3.7604565620422363,
      "learning_rate": 4.761904761904762e-05,
      "loss": 2.3848,
      "step": 10
    },
    {
      "epoch": 0.42704626334519574,
      "grad_norm": 1.9476191997528076,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.9534,
      "step": 15
    },
    {
      "epoch": 0.5693950177935944,
      "grad_norm": 1.1864774227142334,
      "learning_rate": 9.523809523809524e-05,
      "loss": 1.7776,
      "step": 20
    },
    {
      "epoch": 0.7117437722419929,
      "grad_norm": 1.2619398832321167,
      "learning_rate": 9.988952191691925e-05,
      "loss": 1.6551,
      "step": 25
    },
    {
      "epoch": 0.8540925266903915,
      "grad_norm": 1.204907774925232,
      "learning_rate": 9.944154131125642e-05,
      "loss": 1.6106,
      "step": 30
    },
    {
      "epoch": 0.99644128113879,
      "grad_norm": 1.030988097190857,
      "learning_rate": 9.865224352899119e-05,
      "loss": 1.6196,
      "step": 35
    },
    {
      "epoch": 0.99644128113879,
      "eval_loss": 1.531648874282837,
      "eval_runtime": 3.1223,
      "eval_samples_per_second": 14.733,
      "eval_steps_per_second": 14.733,
      "step": 35
    },
    {
      "epoch": 1.1387900355871885,
      "grad_norm": 1.0289065837860107,
      "learning_rate": 9.752707744739145e-05,
      "loss": 1.4904,
      "step": 40
    },
    {
      "epoch": 1.281138790035587,
      "grad_norm": 1.2606865167617798,
      "learning_rate": 9.607381059352038e-05,
      "loss": 1.4244,
      "step": 45
    },
    {
      "epoch": 1.4234875444839858,
      "grad_norm": 1.2899017333984375,
      "learning_rate": 9.430247552150673e-05,
      "loss": 1.4003,
      "step": 50
    },
    {
      "epoch": 1.5658362989323842,
      "grad_norm": 1.3828767538070679,
      "learning_rate": 9.22253005533154e-05,
      "loss": 1.3709,
      "step": 55
    },
    {
      "epoch": 1.708185053380783,
      "grad_norm": 1.5857073068618774,
      "learning_rate": 8.985662536114613e-05,
      "loss": 1.3789,
      "step": 60
    },
    {
      "epoch": 1.8505338078291815,
      "grad_norm": 1.4692878723144531,
      "learning_rate": 8.721280197423258e-05,
      "loss": 1.3579,
      "step": 65
    },
    {
      "epoch": 1.99288256227758,
      "grad_norm": 1.452291488647461,
      "learning_rate": 8.43120818934367e-05,
      "loss": 1.3654,
      "step": 70
    },
    {
      "epoch": 1.99288256227758,
      "eval_loss": 1.4582531452178955,
      "eval_runtime": 3.0596,
      "eval_samples_per_second": 15.035,
      "eval_steps_per_second": 15.035,
      "step": 70
    },
    {
      "epoch": 2.135231316725979,
      "grad_norm": 1.4234528541564941,
      "learning_rate": 8.117449009293668e-05,
      "loss": 1.1069,
      "step": 75
    },
    {
      "epoch": 2.277580071174377,
      "grad_norm": 1.9852792024612427,
      "learning_rate": 7.782168677883206e-05,
      "loss": 1.0865,
      "step": 80
    },
    {
      "epoch": 2.419928825622776,
      "grad_norm": 2.1242332458496094,
      "learning_rate": 7.427681785900761e-05,
      "loss": 1.1173,
      "step": 85
    },
    {
      "epoch": 2.562277580071174,
      "grad_norm": 2.085472583770752,
      "learning_rate": 7.056435515653059e-05,
      "loss": 1.0808,
      "step": 90
    },
    {
      "epoch": 2.704626334519573,
      "grad_norm": 2.2084648609161377,
      "learning_rate": 6.670992746965938e-05,
      "loss": 1.0482,
      "step": 95
    },
    {
      "epoch": 2.8469750889679717,
      "grad_norm": 2.2010068893432617,
      "learning_rate": 6.274014364473274e-05,
      "loss": 1.0735,
      "step": 100
    },
    {
      "epoch": 2.9893238434163703,
      "grad_norm": 2.187283515930176,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.0796,
      "step": 105
    },
    {
      "epoch": 2.9893238434163703,
      "eval_loss": 1.5236175060272217,
      "eval_runtime": 3.0398,
      "eval_samples_per_second": 15.132,
      "eval_steps_per_second": 15.132,
      "step": 105
    },
    {
      "epoch": 3.131672597864769,
      "grad_norm": 2.2142372131347656,
      "learning_rate": 5.456473555193242e-05,
      "loss": 0.855,
      "step": 110
    },
    {
      "epoch": 3.2740213523131674,
      "grad_norm": 3.484597682952881,
      "learning_rate": 5.041554979980486e-05,
      "loss": 0.8003,
      "step": 115
    },
    {
      "epoch": 3.416370106761566,
      "grad_norm": 2.9119606018066406,
      "learning_rate": 4.626349532067879e-05,
      "loss": 0.8118,
      "step": 120
    },
    {
      "epoch": 3.5587188612099645,
      "grad_norm": 2.787829637527466,
      "learning_rate": 4.213723561238074e-05,
      "loss": 0.7847,
      "step": 125
    },
    {
      "epoch": 3.701067615658363,
      "grad_norm": 3.064790964126587,
      "learning_rate": 3.806525609984312e-05,
      "loss": 0.7769,
      "step": 130
    },
    {
      "epoch": 3.8434163701067616,
      "grad_norm": 3.0857157707214355,
      "learning_rate": 3.4075667487415785e-05,
      "loss": 0.7938,
      "step": 135
    },
    {
      "epoch": 3.98576512455516,
      "grad_norm": 3.0351779460906982,
      "learning_rate": 3.019601169804216e-05,
      "loss": 0.7613,
      "step": 140
    },
    {
      "epoch": 3.98576512455516,
      "eval_loss": 1.7009425163269043,
      "eval_runtime": 3.0814,
      "eval_samples_per_second": 14.928,
      "eval_steps_per_second": 14.928,
      "step": 140
    },
    {
      "epoch": 4.128113879003559,
      "grad_norm": 2.882894277572632,
      "learning_rate": 2.645307173898901e-05,
      "loss": 0.623,
      "step": 145
    },
    {
      "epoch": 4.270462633451958,
      "grad_norm": 3.9134538173675537,
      "learning_rate": 2.2872686806712035e-05,
      "loss": 0.5953,
      "step": 150
    },
    {
      "epoch": 4.412811387900356,
      "grad_norm": 3.915339469909668,
      "learning_rate": 1.947957390727185e-05,
      "loss": 0.5766,
      "step": 155
    },
    {
      "epoch": 4.555160142348754,
      "grad_norm": 3.3042285442352295,
      "learning_rate": 1.629715722373423e-05,
      "loss": 0.5776,
      "step": 160
    },
    {
      "epoch": 4.697508896797153,
      "grad_norm": 3.5540361404418945,
      "learning_rate": 1.3347406408508695e-05,
      "loss": 0.5623,
      "step": 165
    },
    {
      "epoch": 4.839857651245552,
      "grad_norm": 3.638845920562744,
      "learning_rate": 1.0650684916965559e-05,
      "loss": 0.5588,
      "step": 170
    },
    {
      "epoch": 4.98220640569395,
      "grad_norm": 3.2837841510772705,
      "learning_rate": 8.225609429353187e-06,
      "loss": 0.5639,
      "step": 175
    },
    {
      "epoch": 4.98220640569395,
      "eval_loss": 1.8933742046356201,
      "eval_runtime": 3.087,
      "eval_samples_per_second": 14.901,
      "eval_steps_per_second": 14.901,
      "step": 175
    },
    {
      "epoch": 5.124555160142349,
      "grad_norm": 3.3770246505737305,
      "learning_rate": 6.088921331488568e-06,
      "loss": 0.4838,
      "step": 180
    },
    {
      "epoch": 5.266903914590747,
      "grad_norm": 3.4890530109405518,
      "learning_rate": 4.255371141448272e-06,
      "loss": 0.4729,
      "step": 185
    },
    {
      "epoch": 5.409252669039146,
      "grad_norm": 3.741734266281128,
      "learning_rate": 2.737616680113758e-06,
      "loss": 0.4591,
      "step": 190
    },
    {
      "epoch": 5.551601423487544,
      "grad_norm": 3.9344441890716553,
      "learning_rate": 1.5461356885461075e-06,
      "loss": 0.473,
      "step": 195
    },
    {
      "epoch": 5.693950177935943,
      "grad_norm": 3.7438364028930664,
      "learning_rate": 6.891534954310885e-07,
      "loss": 0.4638,
      "step": 200
    },
    {
      "epoch": 5.8362989323843415,
      "grad_norm": 4.057279109954834,
      "learning_rate": 1.725862339392259e-07,
      "loss": 0.4604,
      "step": 205
    },
    {
      "epoch": 5.9786476868327405,
      "grad_norm": 3.701946258544922,
      "learning_rate": 0.0,
      "loss": 0.4648,
      "step": 210
    },
    {
      "epoch": 5.9786476868327405,
      "eval_loss": 2.0316998958587646,
      "eval_runtime": 3.0694,
      "eval_samples_per_second": 14.987,
      "eval_steps_per_second": 14.987,
      "step": 210
    },
    {
      "epoch": 5.9786476868327405,
      "step": 210,
      "total_flos": 2.961277350201262e+17,
      "train_loss": 1.0483045907247635,
      "train_runtime": 3678.5963,
      "train_samples_per_second": 7.31,
      "train_steps_per_second": 0.057
    }
  ],
  "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": 2.961277350201262e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}