{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03707823507601038,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007415647015202076,
      "eval_loss": 3.6060941219329834,
      "eval_runtime": 40.8556,
      "eval_samples_per_second": 13.903,
      "eval_steps_per_second": 6.951,
      "step": 1
    },
    {
      "epoch": 0.0037078235076010383,
      "grad_norm": 70.09471893310547,
      "learning_rate": 5e-05,
      "loss": 13.9556,
      "step": 5
    },
    {
      "epoch": 0.007415647015202077,
      "grad_norm": 34.09231948852539,
      "learning_rate": 0.0001,
      "loss": 10.4656,
      "step": 10
    },
    {
      "epoch": 0.007415647015202077,
      "eval_loss": 1.6744259595870972,
      "eval_runtime": 42.8143,
      "eval_samples_per_second": 13.267,
      "eval_steps_per_second": 6.633,
      "step": 10
    },
    {
      "epoch": 0.011123470522803115,
      "grad_norm": 32.743377685546875,
      "learning_rate": 9.619397662556435e-05,
      "loss": 5.0849,
      "step": 15
    },
    {
      "epoch": 0.014831294030404153,
      "grad_norm": 22.76828956604004,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.9268,
      "step": 20
    },
    {
      "epoch": 0.014831294030404153,
      "eval_loss": 1.1096298694610596,
      "eval_runtime": 43.6146,
      "eval_samples_per_second": 13.023,
      "eval_steps_per_second": 6.512,
      "step": 20
    },
    {
      "epoch": 0.01853911753800519,
      "grad_norm": 24.94118309020996,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.9926,
      "step": 25
    },
    {
      "epoch": 0.02224694104560623,
      "grad_norm": 26.482688903808594,
      "learning_rate": 5e-05,
      "loss": 4.5293,
      "step": 30
    },
    {
      "epoch": 0.02224694104560623,
      "eval_loss": 1.0691455602645874,
      "eval_runtime": 44.1038,
      "eval_samples_per_second": 12.879,
      "eval_steps_per_second": 6.439,
      "step": 30
    },
    {
      "epoch": 0.025954764553207266,
      "grad_norm": 31.178747177124023,
      "learning_rate": 3.086582838174551e-05,
      "loss": 4.4932,
      "step": 35
    },
    {
      "epoch": 0.029662588060808306,
      "grad_norm": 16.739856719970703,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.9006,
      "step": 40
    },
    {
      "epoch": 0.029662588060808306,
      "eval_loss": 1.0363116264343262,
      "eval_runtime": 44.3005,
      "eval_samples_per_second": 12.822,
      "eval_steps_per_second": 6.411,
      "step": 40
    },
    {
      "epoch": 0.03337041156840934,
      "grad_norm": 22.390703201293945,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 4.3885,
      "step": 45
    },
    {
      "epoch": 0.03707823507601038,
      "grad_norm": 18.154996871948242,
      "learning_rate": 0.0,
      "loss": 4.0374,
      "step": 50
    },
    {
      "epoch": 0.03707823507601038,
      "eval_loss": 1.031516671180725,
      "eval_runtime": 44.1384,
      "eval_samples_per_second": 12.869,
      "eval_steps_per_second": 6.434,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8767214400307200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}