{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7912484717522958,
  "eval_steps": 7000,
  "global_step": 63000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.19902760797247732,
      "grad_norm": 0.4141775667667389,
      "learning_rate": 9.944562899786782e-06,
      "loss": 0.0076,
      "step": 7000
    },
    {
      "epoch": 0.19902760797247732,
      "eval_loss": 0.002747271442785859,
      "eval_runtime": 441.3391,
      "eval_samples_per_second": 159.381,
      "eval_steps_per_second": 19.923,
      "step": 7000
    },
    {
      "epoch": 0.39805521594495463,
      "grad_norm": 0.001612484105862677,
      "learning_rate": 8.900911431595243e-06,
      "loss": 0.0022,
      "step": 14000
    },
    {
      "epoch": 0.39805521594495463,
      "eval_loss": 0.0019201049581170082,
      "eval_runtime": 543.6718,
      "eval_samples_per_second": 129.381,
      "eval_steps_per_second": 16.173,
      "step": 14000
    },
    {
      "epoch": 0.597082823917432,
      "grad_norm": 0.10798920691013336,
      "learning_rate": 7.795504446585686e-06,
      "loss": 0.0016,
      "step": 21000
    },
    {
      "epoch": 0.597082823917432,
      "eval_loss": 0.0012514982372522354,
      "eval_runtime": 441.7894,
      "eval_samples_per_second": 159.218,
      "eval_steps_per_second": 19.903,
      "step": 21000
    },
    {
      "epoch": 0.7961104318899093,
      "grad_norm": 0.0025300488341599703,
      "learning_rate": 6.6900974615761295e-06,
      "loss": 0.0013,
      "step": 28000
    },
    {
      "epoch": 0.7961104318899093,
      "eval_loss": 0.0010735790710896254,
      "eval_runtime": 438.1392,
      "eval_samples_per_second": 160.545,
      "eval_steps_per_second": 20.069,
      "step": 28000
    },
    {
      "epoch": 0.9951380398623866,
      "grad_norm": 0.0008487554732710123,
      "learning_rate": 5.584690476566573e-06,
      "loss": 0.0012,
      "step": 35000
    },
    {
      "epoch": 0.9951380398623866,
      "eval_loss": 0.0007883219514042139,
      "eval_runtime": 448.1544,
      "eval_samples_per_second": 156.957,
      "eval_steps_per_second": 19.62,
      "step": 35000
    },
    {
      "epoch": 1.194165647834864,
      "grad_norm": 0.0005068560712970793,
      "learning_rate": 4.479283491557016e-06,
      "loss": 0.0007,
      "step": 42000
    },
    {
      "epoch": 1.194165647834864,
      "eval_loss": 0.0007334980182349682,
      "eval_runtime": 450.6386,
      "eval_samples_per_second": 156.092,
      "eval_steps_per_second": 19.512,
      "step": 42000
    },
    {
      "epoch": 1.3931932558073412,
      "grad_norm": 0.00018214000738225877,
      "learning_rate": 3.3740344669625798e-06,
      "loss": 0.0004,
      "step": 49000
    },
    {
      "epoch": 1.3931932558073412,
      "eval_loss": 0.0009056200506165624,
      "eval_runtime": 439.7889,
      "eval_samples_per_second": 159.943,
      "eval_steps_per_second": 19.994,
      "step": 49000
    },
    {
      "epoch": 1.5922208637798185,
      "grad_norm": 0.000712706649210304,
      "learning_rate": 2.2687854423681427e-06,
      "loss": 0.0004,
      "step": 56000
    },
    {
      "epoch": 1.5922208637798185,
      "eval_loss": 0.0006670919246971607,
      "eval_runtime": 444.6001,
      "eval_samples_per_second": 158.212,
      "eval_steps_per_second": 19.777,
      "step": 56000
    },
    {
      "epoch": 1.7912484717522958,
      "grad_norm": 0.00034176826011389494,
      "learning_rate": 1.163378457358586e-06,
      "loss": 0.0003,
      "step": 63000
    },
    {
      "epoch": 1.7912484717522958,
      "eval_loss": 0.0006322154076769948,
      "eval_runtime": 439.8053,
      "eval_samples_per_second": 159.937,
      "eval_steps_per_second": 19.993,
      "step": 63000
    }
  ],
  "logging_steps": 7000,
  "max_steps": 70342,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 7000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}