{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.968944099378882,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024844720496894408,
      "grad_norm": 1.9734776712043933,
      "learning_rate": 1.25e-06,
      "loss": 2.0829,
      "step": 1
    },
    {
      "epoch": 0.12422360248447205,
      "grad_norm": 0.9368516431423844,
      "learning_rate": 6.25e-06,
      "loss": 1.9731,
      "step": 5
    },
    {
      "epoch": 0.2484472049689441,
      "grad_norm": 0.5576632754036136,
      "learning_rate": 9.980973490458728e-06,
      "loss": 1.1249,
      "step": 10
    },
    {
      "epoch": 0.37267080745341613,
      "grad_norm": 0.1453744774874373,
      "learning_rate": 9.768584753741134e-06,
      "loss": 0.7005,
      "step": 15
    },
    {
      "epoch": 0.4968944099378882,
      "grad_norm": 0.10656016351841575,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.6578,
      "step": 20
    },
    {
      "epoch": 0.6211180124223602,
      "grad_norm": 0.10627315554959688,
      "learning_rate": 8.68638668405062e-06,
      "loss": 0.5548,
      "step": 25
    },
    {
      "epoch": 0.7453416149068323,
      "grad_norm": 0.10926487518378508,
      "learning_rate": 7.86788218175523e-06,
      "loss": 0.5338,
      "step": 30
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.07210231467569433,
      "learning_rate": 6.913417161825449e-06,
      "loss": 0.4813,
      "step": 35
    },
    {
      "epoch": 0.9937888198757764,
      "grad_norm": 0.09012608754106587,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.4656,
      "step": 40
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.4435769021511078,
      "eval_runtime": 19.9199,
      "eval_samples_per_second": 19.177,
      "eval_steps_per_second": 4.819,
      "step": 41
    },
    {
      "epoch": 1.0993788819875776,
      "grad_norm": 0.09092482381263875,
      "learning_rate": 4.781903063173321e-06,
      "loss": 0.447,
      "step": 45
    },
    {
      "epoch": 1.2236024844720497,
      "grad_norm": 0.06782242173154653,
      "learning_rate": 3.705904774487396e-06,
      "loss": 0.4056,
      "step": 50
    },
    {
      "epoch": 1.3478260869565217,
      "grad_norm": 0.07918994779734262,
      "learning_rate": 2.6912569338248317e-06,
      "loss": 0.4241,
      "step": 55
    },
    {
      "epoch": 1.4720496894409938,
      "grad_norm": 0.07558285891702508,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 0.3841,
      "step": 60
    },
    {
      "epoch": 1.5962732919254659,
      "grad_norm": 0.07726156050690504,
      "learning_rate": 1.0332332985438248e-06,
      "loss": 0.4462,
      "step": 65
    },
    {
      "epoch": 1.720496894409938,
      "grad_norm": 0.08049537015564708,
      "learning_rate": 4.6846106481675035e-07,
      "loss": 0.4152,
      "step": 70
    },
    {
      "epoch": 1.84472049689441,
      "grad_norm": 0.08353339510279191,
      "learning_rate": 1.185199644003332e-07,
      "loss": 0.4127,
      "step": 75
    },
    {
      "epoch": 1.968944099378882,
      "grad_norm": 0.07436382991416793,
      "learning_rate": 0.0,
      "loss": 0.4086,
      "step": 80
    },
    {
      "epoch": 1.968944099378882,
      "eval_loss": 0.4148392975330353,
      "eval_runtime": 19.7438,
      "eval_samples_per_second": 19.348,
      "eval_steps_per_second": 4.862,
      "step": 80
    },
    {
      "epoch": 1.968944099378882,
      "step": 80,
      "total_flos": 2.069930497277952e+17,
      "train_loss": 0.6160678043961525,
      "train_runtime": 1072.8229,
      "train_samples_per_second": 3.598,
      "train_steps_per_second": 0.075
    }
  ],
  "logging_steps": 5,
  "max_steps": 80,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.069930497277952e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}