{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9893238434163703,
  "eval_steps": 35,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1423487544483986,
      "grad_norm": 2.9529099464416504,
      "learning_rate": 2.380952380952381e-05,
      "loss": 2.9157,
      "step": 5
    },
    {
      "epoch": 0.2846975088967972,
      "grad_norm": 3.1487812995910645,
      "learning_rate": 4.761904761904762e-05,
      "loss": 2.7556,
      "step": 10
    },
    {
      "epoch": 0.42704626334519574,
      "grad_norm": 1.5218528509140015,
      "learning_rate": 7.142857142857143e-05,
      "loss": 2.3324,
      "step": 15
    },
    {
      "epoch": 0.5693950177935944,
      "grad_norm": 1.0471426248550415,
      "learning_rate": 9.523809523809524e-05,
      "loss": 1.9683,
      "step": 20
    },
    {
      "epoch": 0.7117437722419929,
      "grad_norm": 0.6459335088729858,
      "learning_rate": 9.988952191691925e-05,
      "loss": 1.8017,
      "step": 25
    },
    {
      "epoch": 0.8540925266903915,
      "grad_norm": 0.5955364108085632,
      "learning_rate": 9.944154131125642e-05,
      "loss": 1.718,
      "step": 30
    },
    {
      "epoch": 0.99644128113879,
      "grad_norm": 0.4893205463886261,
      "learning_rate": 9.865224352899119e-05,
      "loss": 1.7323,
      "step": 35
    },
    {
      "epoch": 0.99644128113879,
      "eval_loss": 1.6576381921768188,
      "eval_runtime": 2.8184,
      "eval_samples_per_second": 16.321,
      "eval_steps_per_second": 16.321,
      "step": 35
    },
    {
      "epoch": 1.1387900355871885,
      "grad_norm": 0.5405563712120056,
      "learning_rate": 9.752707744739145e-05,
      "loss": 1.6641,
      "step": 40
    },
    {
      "epoch": 1.281138790035587,
      "grad_norm": 0.550575315952301,
      "learning_rate": 9.607381059352038e-05,
      "loss": 1.5968,
      "step": 45
    },
    {
      "epoch": 1.4234875444839858,
      "grad_norm": 0.5504499673843384,
      "learning_rate": 9.430247552150673e-05,
      "loss": 1.5915,
      "step": 50
    },
    {
      "epoch": 1.5658362989323842,
      "grad_norm": 0.5838366746902466,
      "learning_rate": 9.22253005533154e-05,
      "loss": 1.5751,
      "step": 55
    },
    {
      "epoch": 1.708185053380783,
      "grad_norm": 0.6889703273773193,
      "learning_rate": 8.985662536114613e-05,
      "loss": 1.568,
      "step": 60
    },
    {
      "epoch": 1.8505338078291815,
      "grad_norm": 0.6529588103294373,
      "learning_rate": 8.721280197423258e-05,
      "loss": 1.5322,
      "step": 65
    },
    {
      "epoch": 1.99288256227758,
      "grad_norm": 0.6893957257270813,
      "learning_rate": 8.43120818934367e-05,
      "loss": 1.5369,
      "step": 70
    },
    {
      "epoch": 1.99288256227758,
      "eval_loss": 1.5468653440475464,
      "eval_runtime": 2.8123,
      "eval_samples_per_second": 16.357,
      "eval_steps_per_second": 16.357,
      "step": 70
    },
    {
      "epoch": 2.135231316725979,
      "grad_norm": 0.6486149430274963,
      "learning_rate": 8.117449009293668e-05,
      "loss": 1.4022,
      "step": 75
    },
    {
      "epoch": 2.277580071174377,
      "grad_norm": 0.7535184621810913,
      "learning_rate": 7.782168677883206e-05,
      "loss": 1.4028,
      "step": 80
    },
    {
      "epoch": 2.419928825622776,
      "grad_norm": 0.8721055388450623,
      "learning_rate": 7.427681785900761e-05,
      "loss": 1.4379,
      "step": 85
    },
    {
      "epoch": 2.562277580071174,
      "grad_norm": 0.8978091478347778,
      "learning_rate": 7.056435515653059e-05,
      "loss": 1.3932,
      "step": 90
    },
    {
      "epoch": 2.704626334519573,
      "grad_norm": 0.9783418774604797,
      "learning_rate": 6.670992746965938e-05,
      "loss": 1.363,
      "step": 95
    },
    {
      "epoch": 2.8469750889679717,
      "grad_norm": 1.1025798320770264,
      "learning_rate": 6.274014364473274e-05,
      "loss": 1.3864,
      "step": 100
    },
    {
      "epoch": 2.9893238434163703,
      "grad_norm": 0.9893730282783508,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.3988,
      "step": 105
    },
    {
      "epoch": 2.9893238434163703,
      "eval_loss": 1.5315250158309937,
      "eval_runtime": 2.8087,
      "eval_samples_per_second": 16.378,
      "eval_steps_per_second": 16.378,
      "step": 105
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3920788662832333e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}