{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.029404557706444498,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00098015192354815,
      "eval_loss": 5.129547595977783,
      "eval_runtime": 119.2044,
      "eval_samples_per_second": 3.607,
      "eval_steps_per_second": 1.804,
      "step": 1
    },
    {
      "epoch": 0.00294045577064445,
      "grad_norm": 8.38568115234375,
      "learning_rate": 6e-05,
      "loss": 5.1198,
      "step": 3
    },
    {
      "epoch": 0.0058809115412889,
      "grad_norm": 6.9044060707092285,
      "learning_rate": 0.00012,
      "loss": 4.2093,
      "step": 6
    },
    {
      "epoch": 0.0078412153883852,
      "eval_loss": 2.8930578231811523,
      "eval_runtime": 120.2336,
      "eval_samples_per_second": 3.576,
      "eval_steps_per_second": 1.788,
      "step": 8
    },
    {
      "epoch": 0.008821367311933349,
      "grad_norm": 8.349801063537598,
      "learning_rate": 0.00018,
      "loss": 2.9034,
      "step": 9
    },
    {
      "epoch": 0.0117618230825778,
      "grad_norm": 10.611321449279785,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.2044,
      "step": 12
    },
    {
      "epoch": 0.014702278853222249,
      "grad_norm": 3.2068185806274414,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.309,
      "step": 15
    },
    {
      "epoch": 0.0156824307767704,
      "eval_loss": 1.2882230281829834,
      "eval_runtime": 120.158,
      "eval_samples_per_second": 3.579,
      "eval_steps_per_second": 1.789,
      "step": 16
    },
    {
      "epoch": 0.017642734623866698,
      "grad_norm": 1.7966519594192505,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.202,
      "step": 18
    },
    {
      "epoch": 0.02058319039451115,
      "grad_norm": 1.691860556602478,
      "learning_rate": 8.435655349597689e-05,
      "loss": 1.2074,
      "step": 21
    },
    {
      "epoch": 0.0235236461651556,
      "grad_norm": 1.7501243352890015,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.195,
      "step": 24
    },
    {
      "epoch": 0.0235236461651556,
      "eval_loss": 1.148852825164795,
      "eval_runtime": 120.4004,
      "eval_samples_per_second": 3.571,
      "eval_steps_per_second": 1.786,
      "step": 24
    },
    {
      "epoch": 0.02646410193580005,
      "grad_norm": 1.4713298082351685,
      "learning_rate": 1.0899347581163221e-05,
      "loss": 1.1689,
      "step": 27
    },
    {
      "epoch": 0.029404557706444498,
      "grad_norm": 1.6153112649917603,
      "learning_rate": 0.0,
      "loss": 1.0901,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.150341542313984e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}