{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03673094582185491,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036730945821854912,
      "grad_norm": 3.766998767852783,
      "learning_rate": 2e-05,
      "loss": 3.4229,
      "step": 1
    },
    {
      "epoch": 0.0036730945821854912,
      "eval_loss": 3.481534481048584,
      "eval_runtime": 3.8184,
      "eval_samples_per_second": 30.117,
      "eval_steps_per_second": 15.19,
      "step": 1
    },
    {
      "epoch": 0.0073461891643709825,
      "grad_norm": 3.6023616790771484,
      "learning_rate": 4e-05,
      "loss": 3.6684,
      "step": 2
    },
    {
      "epoch": 0.011019283746556474,
      "grad_norm": 2.8920462131500244,
      "learning_rate": 6e-05,
      "loss": 3.2205,
      "step": 3
    },
    {
      "epoch": 0.011019283746556474,
      "eval_loss": 3.4574167728424072,
      "eval_runtime": 2.3829,
      "eval_samples_per_second": 48.261,
      "eval_steps_per_second": 24.34,
      "step": 3
    },
    {
      "epoch": 0.014692378328741965,
      "grad_norm": 2.4809694290161133,
      "learning_rate": 8e-05,
      "loss": 3.3259,
      "step": 4
    },
    {
      "epoch": 0.018365472910927456,
      "grad_norm": 2.2063894271850586,
      "learning_rate": 0.0001,
      "loss": 3.1661,
      "step": 5
    },
    {
      "epoch": 0.02203856749311295,
      "grad_norm": 1.9333349466323853,
      "learning_rate": 0.00012,
      "loss": 3.4017,
      "step": 6
    },
    {
      "epoch": 0.02203856749311295,
      "eval_loss": 3.259284019470215,
      "eval_runtime": 2.492,
      "eval_samples_per_second": 46.148,
      "eval_steps_per_second": 23.275,
      "step": 6
    },
    {
      "epoch": 0.025711662075298437,
      "grad_norm": 1.358789324760437,
      "learning_rate": 0.00014,
      "loss": 3.2451,
      "step": 7
    },
    {
      "epoch": 0.02938475665748393,
      "grad_norm": 0.9608637690544128,
      "learning_rate": 0.00016,
      "loss": 3.0121,
      "step": 8
    },
    {
      "epoch": 0.03305785123966942,
      "grad_norm": 1.4823637008666992,
      "learning_rate": 0.00018,
      "loss": 3.2918,
      "step": 9
    },
    {
      "epoch": 0.03305785123966942,
      "eval_loss": 3.0797324180603027,
      "eval_runtime": 2.4446,
      "eval_samples_per_second": 47.042,
      "eval_steps_per_second": 23.726,
      "step": 9
    },
    {
      "epoch": 0.03673094582185491,
      "grad_norm": 1.1794862747192383,
      "learning_rate": 0.0002,
      "loss": 3.0823,
      "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": 88232372994048.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}