{
  "best_global_step": 140,
  "best_metric": 1.5463721752166748,
  "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": 8.0,
      "learning_rate": 1.0369332921459845e-05,
      "loss": 2.5081,
      "step": 5
    },
    {
      "epoch": 0.07142857142857142,
      "grad_norm": 5.46875,
      "learning_rate": 2.3330999073284648e-05,
      "loss": 2.2579,
      "step": 10
    },
    {
      "epoch": 0.10714285714285714,
      "grad_norm": 2.640625,
      "learning_rate": 3.629266522510946e-05,
      "loss": 1.972,
      "step": 15
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 2.453125,
      "learning_rate": 4.925433137693426e-05,
      "loss": 1.7655,
      "step": 20
    },
    {
      "epoch": 0.17857142857142858,
      "grad_norm": 2.546875,
      "learning_rate": 6.221599752875907e-05,
      "loss": 1.7359,
      "step": 25
    },
    {
      "epoch": 0.21428571428571427,
      "grad_norm": 2.234375,
      "learning_rate": 7.517766368058388e-05,
      "loss": 1.7058,
      "step": 30
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.421875,
      "learning_rate": 8.813932983240868e-05,
      "loss": 1.6527,
      "step": 35
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 2.125,
      "learning_rate": 9.07135404898808e-05,
      "loss": 1.7085,
      "step": 40
    },
    {
      "epoch": 0.32142857142857145,
      "grad_norm": 2.0,
      "learning_rate": 9.063995062320487e-05,
      "loss": 1.6629,
      "step": 45
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 2.03125,
      "learning_rate": 9.050988319073264e-05,
      "loss": 1.6445,
      "step": 50
    },
    {
      "epoch": 0.39285714285714285,
      "grad_norm": 1.859375,
      "learning_rate": 9.032355467686922e-05,
      "loss": 1.6803,
      "step": 55
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.9453125,
      "learning_rate": 9.00812752070373e-05,
      "loss": 1.6111,
      "step": 60
    },
    {
      "epoch": 0.4642857142857143,
      "grad_norm": 2.015625,
      "learning_rate": 8.978344803150407e-05,
      "loss": 1.657,
      "step": 65
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.9375,
      "learning_rate": 8.943056885421092e-05,
      "loss": 1.6561,
      "step": 70
    },
    {
      "epoch": 0.5357142857142857,
      "grad_norm": 1.9453125,
      "learning_rate": 8.902322500772306e-05,
      "loss": 1.6301,
      "step": 75
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 1.8828125,
      "learning_rate": 8.856209447567256e-05,
      "loss": 1.6164,
      "step": 80
    },
    {
      "epoch": 0.6071428571428571,
      "grad_norm": 1.9296875,
      "learning_rate": 8.804794476432144e-05,
      "loss": 1.6095,
      "step": 85
    },
    {
      "epoch": 0.6428571428571429,
      "grad_norm": 1.984375,
      "learning_rate": 8.748163162512321e-05,
      "loss": 1.5982,
      "step": 90
    },
    {
      "epoch": 0.6785714285714286,
      "grad_norm": 1.8125,
      "learning_rate": 8.686409763040914e-05,
      "loss": 1.5923,
      "step": 95
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.9375,
      "learning_rate": 8.619637060456948e-05,
      "loss": 1.6454,
      "step": 100
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.78125,
      "learning_rate": 8.547956191334132e-05,
      "loss": 1.5571,
      "step": 105
    },
    {
      "epoch": 0.7857142857142857,
      "grad_norm": 1.953125,
      "learning_rate": 8.471486461404997e-05,
      "loss": 1.5717,
      "step": 110
    },
    {
      "epoch": 0.8214285714285714,
      "grad_norm": 1.859375,
      "learning_rate": 8.390355146988274e-05,
      "loss": 1.569,
      "step": 115
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 1.875,
      "learning_rate": 8.304697283150032e-05,
      "loss": 1.561,
      "step": 120
    },
    {
      "epoch": 0.8928571428571429,
      "grad_norm": 1.7890625,
      "learning_rate": 8.214655438951125e-05,
      "loss": 1.5627,
      "step": 125
    },
    {
      "epoch": 0.9285714285714286,
      "grad_norm": 1.7890625,
      "learning_rate": 8.120379480155064e-05,
      "loss": 1.5441,
      "step": 130
    },
    {
      "epoch": 0.9642857142857143,
      "grad_norm": 1.75,
      "learning_rate": 8.022026319791254e-05,
      "loss": 1.5703,
      "step": 135
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.75,
      "learning_rate": 7.919759656988726e-05,
      "loss": 1.5482,
      "step": 140
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.5463721752166748,
      "eval_runtime": 0.4756,
      "eval_samples_per_second": 10.514,
      "eval_steps_per_second": 10.514,
      "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
}