{
  "best_global_step": 140,
  "best_metric": 1.5339595079421997,
  "best_model_checkpoint": "/workspace/scripts/soutputs/a0b6e564-b8fd-4183-aee5-1faf9aaeb03b_1/checkpoint-140",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 140,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03571428571428571,
      "grad_norm": 7.25,
      "learning_rate": 1.7282221535766407e-05,
      "loss": 2.4878,
      "step": 5
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 3.796875,
      "learning_rate": 3.8884998455474416e-05,
      "loss": 2.0894,
      "step": 10
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 2.59375,
      "learning_rate": 6.048777537518243e-05,
      "loss": 1.8327,
      "step": 15
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.328125,
      "learning_rate": 8.209055229489044e-05,
      "loss": 1.7142,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 2.3125,
      "learning_rate": 9.072217152864162e-05,
      "loss": 1.7116,
      "step": 25
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 2.203125,
      "learning_rate": 9.066418688520791e-05,
      "loss": 1.6992,
      "step": 30
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.109375,
      "learning_rate": 9.055358042067075e-05,
      "loss": 1.6577,
      "step": 35
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.203125,
      "learning_rate": 9.039052353801518e-05,
      "loss": 1.7096,
      "step": 40
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 1.921875,
      "learning_rate": 9.017526892081207e-05,
      "loss": 1.6655,
      "step": 45
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 1.984375,
      "learning_rate": 8.990815014164321e-05,
      "loss": 1.6398,
      "step": 50
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 1.8515625,
      "learning_rate": 8.958958114517544e-05,
      "loss": 1.6751,
      "step": 55
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.859375,
      "learning_rate": 8.922005560668503e-05,
      "loss": 1.6014,
      "step": 60
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 2.140625,
      "learning_rate": 8.880014616702638e-05,
      "loss": 1.6526,
      "step": 65
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.9453125,
      "learning_rate": 8.833050354523036e-05,
      "loss": 1.6497,
      "step": 70
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 1.890625,
      "learning_rate": 8.781185553010768e-05,
      "loss": 1.6217,
      "step": 75
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.8515625,
      "learning_rate": 8.724500585242e-05,
      "loss": 1.6049,
      "step": 80
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 1.8984375,
      "learning_rate": 8.663083293936631e-05,
      "loss": 1.6001,
      "step": 85
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 1.953125,
      "learning_rate": 8.597028855331493e-05,
      "loss": 1.592,
      "step": 90
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 1.8203125,
      "learning_rate": 8.526439631689045e-05,
      "loss": 1.5843,
      "step": 95
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.9375,
      "learning_rate": 8.451425012670155e-05,
      "loss": 1.6343,
      "step": 100
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.71875,
      "learning_rate": 8.372101245816741e-05,
      "loss": 1.5486,
      "step": 105
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 1.921875,
      "learning_rate": 8.288591256407006e-05,
      "loss": 1.563,
      "step": 110
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 1.796875,
      "learning_rate": 8.201024456962423e-05,
      "loss": 1.5587,
      "step": 115
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.78125,
      "learning_rate": 8.109536546701654e-05,
      "loss": 1.5525,
      "step": 120
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 1.7734375,
      "learning_rate": 8.014269301252197e-05,
      "loss": 1.558,
      "step": 125
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 1.734375,
      "learning_rate": 7.915370352945638e-05,
      "loss": 1.5347,
      "step": 130
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 1.75,
      "learning_rate": 7.812992962036967e-05,
      "loss": 1.5636,
      "step": 135
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.7265625,
      "learning_rate": 7.707295779202505e-05,
      "loss": 1.5403,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.5339595079421997,
      "eval_runtime": 0.4733,
      "eval_samples_per_second": 10.564,
      "eval_steps_per_second": 10.564,
      "step": 140
    }
  ],
  "logging_steps": 5,
  "max_steps": 420,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0739329642921984e+17,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}