{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 5,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 0.5405484437942505,
      "learning_rate": 0.0,
      "loss": 0.98583984375,
      "step": 1
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.557485044002533,
      "learning_rate": 5e-05,
      "loss": 1.02197265625,
      "step": 2
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": 0.5275048017501831,
      "learning_rate": 4.9822580779575757e-05,
      "loss": 0.98681640625,
      "step": 3
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.5154790878295898,
      "learning_rate": 4.9293121125394203e-05,
      "loss": 0.979736328125,
      "step": 4
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 0.4462888538837433,
      "learning_rate": 4.841997093248566e-05,
      "loss": 0.8876953125,
      "step": 5
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3854300379753113,
      "learning_rate": 4.7216900300986936e-05,
      "loss": 0.841796875,
      "step": 6
    },
    {
      "epoch": 0.23076923076923078,
      "eval_loss": 0.832275390625,
      "eval_runtime": 3.0946,
      "eval_samples_per_second": 9.694,
      "eval_steps_per_second": 1.293,
      "step": 6
    },
    {
      "epoch": 0.2692307692307692,
      "grad_norm": 0.33021295070648193,
      "learning_rate": 4.570288237343632e-05,
      "loss": 0.82958984375,
      "step": 7
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.2690589725971222,
      "learning_rate": 4.390179411698176e-05,
      "loss": 0.8037109375,
      "step": 8
    },
    {
      "epoch": 0.34615384615384615,
      "grad_norm": 0.20216020941734314,
      "learning_rate": 4.184203976934552e-05,
      "loss": 0.7578125,
      "step": 9
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.1557544320821762,
      "learning_rate": 3.955610288702742e-05,
      "loss": 0.759765625,
      "step": 10
    },
    {
      "epoch": 0.4230769230769231,
      "grad_norm": 0.1768254041671753,
      "learning_rate": 3.708003406021414e-05,
      "loss": 0.767578125,
      "step": 11
    },
    {
      "epoch": 0.4230769230769231,
      "eval_loss": 0.741943359375,
      "eval_runtime": 3.0797,
      "eval_samples_per_second": 9.741,
      "eval_steps_per_second": 1.299,
      "step": 11
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.22737468779087067,
      "learning_rate": 3.4452882373436316e-05,
      "loss": 0.77001953125,
      "step": 12
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.23847055435180664,
      "learning_rate": 3.171607957817881e-05,
      "loss": 0.74462890625,
      "step": 13
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.2252526879310608,
      "learning_rate": 2.8912786689409556e-05,
      "loss": 0.7294921875,
      "step": 14
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 0.23651787638664246,
      "learning_rate": 2.6087213310590453e-05,
      "loss": 0.72509765625,
      "step": 15
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.25553977489471436,
      "learning_rate": 2.3283920421821192e-05,
      "loss": 0.7255859375,
      "step": 16
    },
    {
      "epoch": 0.6153846153846154,
      "eval_loss": 0.72833251953125,
      "eval_runtime": 3.0754,
      "eval_samples_per_second": 9.755,
      "eval_steps_per_second": 1.301,
      "step": 16
    },
    {
      "epoch": 0.6538461538461539,
      "grad_norm": 0.21480755507946014,
      "learning_rate": 2.054711762656369e-05,
      "loss": 0.744140625,
      "step": 17
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.21713541448116302,
      "learning_rate": 1.7919965939785866e-05,
      "loss": 0.71337890625,
      "step": 18
    },
    {
      "epoch": 0.7307692307692307,
      "grad_norm": 0.19087308645248413,
      "learning_rate": 1.544389711297257e-05,
      "loss": 0.73583984375,
      "step": 19
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.2052358239889145,
      "learning_rate": 1.3157960230654482e-05,
      "loss": 0.72216796875,
      "step": 20
    },
    {
      "epoch": 0.8076923076923077,
      "grad_norm": 0.17521782219409943,
      "learning_rate": 1.1098205883018244e-05,
      "loss": 0.6826171875,
      "step": 21
    },
    {
      "epoch": 0.8076923076923077,
      "eval_loss": 0.72039794921875,
      "eval_runtime": 3.0688,
      "eval_samples_per_second": 9.776,
      "eval_steps_per_second": 1.303,
      "step": 21
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.17916646599769592,
      "learning_rate": 9.297117626563687e-06,
      "loss": 0.72265625,
      "step": 22
    },
    {
      "epoch": 0.8846153846153846,
      "grad_norm": 0.15662069618701935,
      "learning_rate": 7.783099699013075e-06,
      "loss": 0.69775390625,
      "step": 23
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.14258837699890137,
      "learning_rate": 6.580029067514346e-06,
      "loss": 0.70654296875,
      "step": 24
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 0.14059694111347198,
      "learning_rate": 5.706878874605801e-06,
      "loss": 0.7177734375,
      "step": 25
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.11894142627716064,
      "learning_rate": 5.177419220424251e-06,
      "loss": 0.71630859375,
      "step": 26
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.7149658203125,
      "eval_runtime": 3.0697,
      "eval_samples_per_second": 9.773,
      "eval_steps_per_second": 1.303,
      "step": 26
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 26,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.4426803039266406e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}