{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009706381946129581,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000970638194612958,
      "grad_norm": 3.451270341873169,
      "learning_rate": 2e-05,
      "loss": 4.7588,
      "step": 1
    },
    {
      "epoch": 0.000970638194612958,
      "eval_loss": 4.881191253662109,
      "eval_runtime": 5.3945,
      "eval_samples_per_second": 80.452,
      "eval_steps_per_second": 40.226,
      "step": 1
    },
    {
      "epoch": 0.001941276389225916,
      "grad_norm": 3.561099052429199,
      "learning_rate": 4e-05,
      "loss": 4.7651,
      "step": 2
    },
    {
      "epoch": 0.002911914583838874,
      "grad_norm": 3.193682909011841,
      "learning_rate": 6e-05,
      "loss": 4.584,
      "step": 3
    },
    {
      "epoch": 0.002911914583838874,
      "eval_loss": 4.869575023651123,
      "eval_runtime": 4.4386,
      "eval_samples_per_second": 97.779,
      "eval_steps_per_second": 48.889,
      "step": 3
    },
    {
      "epoch": 0.003882552778451832,
      "grad_norm": 3.3053483963012695,
      "learning_rate": 8e-05,
      "loss": 4.7285,
      "step": 4
    },
    {
      "epoch": 0.0048531909730647905,
      "grad_norm": 3.4134633541107178,
      "learning_rate": 0.0001,
      "loss": 4.7789,
      "step": 5
    },
    {
      "epoch": 0.005823829167677748,
      "grad_norm": 3.0485000610351562,
      "learning_rate": 0.00012,
      "loss": 4.5668,
      "step": 6
    },
    {
      "epoch": 0.005823829167677748,
      "eval_loss": 4.634877681732178,
      "eval_runtime": 4.613,
      "eval_samples_per_second": 94.083,
      "eval_steps_per_second": 47.041,
      "step": 6
    },
    {
      "epoch": 0.006794467362290706,
      "grad_norm": 3.587212324142456,
      "learning_rate": 0.00014,
      "loss": 4.593,
      "step": 7
    },
    {
      "epoch": 0.007765105556903664,
      "grad_norm": 3.538506507873535,
      "learning_rate": 0.00016,
      "loss": 4.1848,
      "step": 8
    },
    {
      "epoch": 0.008735743751516622,
      "grad_norm": 3.0586044788360596,
      "learning_rate": 0.00018,
      "loss": 4.1642,
      "step": 9
    },
    {
      "epoch": 0.008735743751516622,
      "eval_loss": 3.8936328887939453,
      "eval_runtime": 4.585,
      "eval_samples_per_second": 94.656,
      "eval_steps_per_second": 47.328,
      "step": 9
    },
    {
      "epoch": 0.009706381946129581,
      "grad_norm": 3.112541913986206,
      "learning_rate": 0.0002,
      "loss": 3.6771,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 50581659451392.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}