{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017770597738287562,
  "eval_steps": 1,
  "global_step": 11,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016155088852988692,
      "grad_norm": 10.710270881652832,
      "learning_rate": 2.6666666666666664e-06,
      "loss": 1.8319,
      "step": 1
    },
    {
      "epoch": 0.0016155088852988692,
      "eval_loss": 1.8248138427734375,
      "eval_runtime": 220.146,
      "eval_samples_per_second": 0.454,
      "eval_steps_per_second": 0.059,
      "step": 1
    },
    {
      "epoch": 0.0032310177705977385,
      "grad_norm": 9.534977912902832,
      "learning_rate": 5.333333333333333e-06,
      "loss": 1.8296,
      "step": 2
    },
    {
      "epoch": 0.0032310177705977385,
      "eval_loss": 1.816626787185669,
      "eval_runtime": 220.6901,
      "eval_samples_per_second": 0.453,
      "eval_steps_per_second": 0.059,
      "step": 2
    },
    {
      "epoch": 0.004846526655896607,
      "grad_norm": 9.70173168182373,
      "learning_rate": 8e-06,
      "loss": 1.7468,
      "step": 3
    },
    {
      "epoch": 0.004846526655896607,
      "eval_loss": 1.8004165887832642,
      "eval_runtime": 220.5949,
      "eval_samples_per_second": 0.453,
      "eval_steps_per_second": 0.059,
      "step": 3
    },
    {
      "epoch": 0.006462035541195477,
      "grad_norm": 9.628801345825195,
      "learning_rate": 7.529411764705882e-06,
      "loss": 1.4906,
      "step": 4
    },
    {
      "epoch": 0.006462035541195477,
      "eval_loss": 1.7767361402511597,
      "eval_runtime": 220.4948,
      "eval_samples_per_second": 0.454,
      "eval_steps_per_second": 0.059,
      "step": 4
    },
    {
      "epoch": 0.008077544426494346,
      "grad_norm": 9.02491283416748,
      "learning_rate": 7.058823529411764e-06,
      "loss": 1.7261,
      "step": 5
    },
    {
      "epoch": 0.008077544426494346,
      "eval_loss": 1.7553186416625977,
      "eval_runtime": 220.7639,
      "eval_samples_per_second": 0.453,
      "eval_steps_per_second": 0.059,
      "step": 5
    },
    {
      "epoch": 0.009693053311793215,
      "grad_norm": 8.989361763000488,
      "learning_rate": 6.588235294117646e-06,
      "loss": 1.8311,
      "step": 6
    },
    {
      "epoch": 0.009693053311793215,
      "eval_loss": 1.7363536357879639,
      "eval_runtime": 220.3852,
      "eval_samples_per_second": 0.454,
      "eval_steps_per_second": 0.059,
      "step": 6
    },
    {
      "epoch": 0.011308562197092083,
      "grad_norm": 8.91972541809082,
      "learning_rate": 6.1176470588235285e-06,
      "loss": 1.8441,
      "step": 7
    },
    {
      "epoch": 0.011308562197092083,
      "eval_loss": 1.720198631286621,
      "eval_runtime": 220.8055,
      "eval_samples_per_second": 0.453,
      "eval_steps_per_second": 0.059,
      "step": 7
    },
    {
      "epoch": 0.012924071082390954,
      "grad_norm": 5.602985858917236,
      "learning_rate": 5.647058823529412e-06,
      "loss": 1.6051,
      "step": 8
    },
    {
      "epoch": 0.012924071082390954,
      "eval_loss": 1.7061126232147217,
      "eval_runtime": 220.3213,
      "eval_samples_per_second": 0.454,
      "eval_steps_per_second": 0.059,
      "step": 8
    },
    {
      "epoch": 0.014539579967689823,
      "grad_norm": 4.554469108581543,
      "learning_rate": 5.176470588235294e-06,
      "loss": 1.6065,
      "step": 9
    },
    {
      "epoch": 0.014539579967689823,
      "eval_loss": 1.69382643699646,
      "eval_runtime": 220.1928,
      "eval_samples_per_second": 0.454,
      "eval_steps_per_second": 0.059,
      "step": 9
    },
    {
      "epoch": 0.01615508885298869,
      "grad_norm": 4.634820461273193,
      "learning_rate": 4.705882352941176e-06,
      "loss": 1.6142,
      "step": 10
    },
    {
      "epoch": 0.01615508885298869,
      "eval_loss": 1.6832895278930664,
      "eval_runtime": 220.9396,
      "eval_samples_per_second": 0.453,
      "eval_steps_per_second": 0.059,
      "step": 10
    },
    {
      "epoch": 0.017770597738287562,
      "grad_norm": 3.6815476417541504,
      "learning_rate": 4.235294117647058e-06,
      "loss": 1.3256,
      "step": 11
    },
    {
      "epoch": 0.017770597738287562,
      "eval_loss": 1.6742274761199951,
      "eval_runtime": 220.8408,
      "eval_samples_per_second": 0.453,
      "eval_steps_per_second": 0.059,
      "step": 11
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1,
  "total_flos": 4063376418275328.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}