{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005037719927960605,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.037719927960605e-05,
      "grad_norm": 4.267588138580322,
      "learning_rate": 2e-05,
      "loss": 2.7055,
      "step": 1
    },
    {
      "epoch": 0.0001007543985592121,
      "grad_norm": 5.172199249267578,
      "learning_rate": 4e-05,
      "loss": 2.8561,
      "step": 2
    },
    {
      "epoch": 0.00015113159783881815,
      "grad_norm": 2.740839719772339,
      "learning_rate": 6e-05,
      "loss": 2.0648,
      "step": 3
    },
    {
      "epoch": 0.00015113159783881815,
      "eval_loss": 2.6448538303375244,
      "eval_runtime": 547.2683,
      "eval_samples_per_second": 15.272,
      "eval_steps_per_second": 7.636,
      "step": 3
    },
    {
      "epoch": 0.0002015087971184242,
      "grad_norm": 3.562958240509033,
      "learning_rate": 8e-05,
      "loss": 2.2551,
      "step": 4
    },
    {
      "epoch": 0.00025188599639803025,
      "grad_norm": 5.027293682098389,
      "learning_rate": 0.0001,
      "loss": 3.0778,
      "step": 5
    },
    {
      "epoch": 0.0003022631956776363,
      "grad_norm": 4.130077362060547,
      "learning_rate": 0.00012,
      "loss": 1.996,
      "step": 6
    },
    {
      "epoch": 0.0003022631956776363,
      "eval_loss": 2.434586524963379,
      "eval_runtime": 549.8312,
      "eval_samples_per_second": 15.201,
      "eval_steps_per_second": 7.601,
      "step": 6
    },
    {
      "epoch": 0.00035264039495724235,
      "grad_norm": 4.90592622756958,
      "learning_rate": 0.00014,
      "loss": 2.6438,
      "step": 7
    },
    {
      "epoch": 0.0004030175942368484,
      "grad_norm": 5.635626792907715,
      "learning_rate": 0.00016,
      "loss": 2.3923,
      "step": 8
    },
    {
      "epoch": 0.00045339479351645445,
      "grad_norm": 5.06250524520874,
      "learning_rate": 0.00018,
      "loss": 2.3509,
      "step": 9
    },
    {
      "epoch": 0.00045339479351645445,
      "eval_loss": 1.971940040588379,
      "eval_runtime": 552.0684,
      "eval_samples_per_second": 15.139,
      "eval_steps_per_second": 7.57,
      "step": 9
    },
    {
      "epoch": 0.0005037719927960605,
      "grad_norm": 3.5257229804992676,
      "learning_rate": 0.0002,
      "loss": 1.5893,
      "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": 489477793382400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}