{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0008194874106246543,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6389748212493087e-05,
      "eval_loss": 10.37437915802002,
      "eval_runtime": 157.419,
      "eval_samples_per_second": 163.195,
      "eval_steps_per_second": 81.598,
      "step": 1
    },
    {
      "epoch": 8.194874106246543e-05,
      "grad_norm": 0.01229150965809822,
      "learning_rate": 5e-05,
      "loss": 10.3759,
      "step": 5
    },
    {
      "epoch": 0.00016389748212493086,
      "grad_norm": 0.016654420644044876,
      "learning_rate": 0.0001,
      "loss": 10.3743,
      "step": 10
    },
    {
      "epoch": 0.00016389748212493086,
      "eval_loss": 10.374303817749023,
      "eval_runtime": 157.9315,
      "eval_samples_per_second": 162.665,
      "eval_steps_per_second": 81.333,
      "step": 10
    },
    {
      "epoch": 0.0002458462231873963,
      "grad_norm": 0.016905885189771652,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3771,
      "step": 15
    },
    {
      "epoch": 0.0003277949642498617,
      "grad_norm": 0.018392696976661682,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3759,
      "step": 20
    },
    {
      "epoch": 0.0003277949642498617,
      "eval_loss": 10.37414264678955,
      "eval_runtime": 159.4468,
      "eval_samples_per_second": 161.12,
      "eval_steps_per_second": 80.56,
      "step": 20
    },
    {
      "epoch": 0.00040974370531232716,
      "grad_norm": 0.01654849573969841,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3734,
      "step": 25
    },
    {
      "epoch": 0.0004916924463747926,
      "grad_norm": 0.01693384349346161,
      "learning_rate": 5e-05,
      "loss": 10.3732,
      "step": 30
    },
    {
      "epoch": 0.0004916924463747926,
      "eval_loss": 10.374007225036621,
      "eval_runtime": 159.206,
      "eval_samples_per_second": 161.363,
      "eval_steps_per_second": 80.682,
      "step": 30
    },
    {
      "epoch": 0.000573641187437258,
      "grad_norm": 0.015700476244091988,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.3749,
      "step": 35
    },
    {
      "epoch": 0.0006555899284997234,
      "grad_norm": 0.0546281561255455,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3726,
      "step": 40
    },
    {
      "epoch": 0.0006555899284997234,
      "eval_loss": 10.373948097229004,
      "eval_runtime": 158.4799,
      "eval_samples_per_second": 162.103,
      "eval_steps_per_second": 81.051,
      "step": 40
    },
    {
      "epoch": 0.0007375386695621888,
      "grad_norm": 0.020957553759217262,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.3757,
      "step": 45
    },
    {
      "epoch": 0.0008194874106246543,
      "grad_norm": 0.0168288666754961,
      "learning_rate": 0.0,
      "loss": 10.3729,
      "step": 50
    },
    {
      "epoch": 0.0008194874106246543,
      "eval_loss": 10.373937606811523,
      "eval_runtime": 158.8125,
      "eval_samples_per_second": 161.763,
      "eval_steps_per_second": 80.882,
      "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": 963352657920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}