{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1978021978021978,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 5.459638595581055,
      "learning_rate": 0.0,
      "loss": 5.1572,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 4.408932209014893,
      "learning_rate": 4e-05,
      "loss": 4.941,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 5.487926959991455,
      "learning_rate": 8e-05,
      "loss": 5.5698,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 5.361940860748291,
      "learning_rate": 0.00012,
      "loss": 5.4254,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 5.856925010681152,
      "learning_rate": 0.00016,
      "loss": 4.9638,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 6.2031073570251465,
      "learning_rate": 0.0002,
      "loss": 4.1384,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 6.153454780578613,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.5665,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.060917615890503,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.335,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.5414468050003052,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2202,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 2.760967493057251,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3177,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.4582066535949707,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.1973,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.800369918346405,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1367,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.8436974287033081,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.2465,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.9210023283958435,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0176,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.8066878318786621,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.9148,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.8594912886619568,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0468,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.6237018704414368,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0676,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.6330975294113159,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9913,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.7443146705627441,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.8187,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.7366983890533447,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.1666,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.571020781993866,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9126,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.6713335514068604,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.7393,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.5838486552238464,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.9377,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.6766859889030457,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.1663,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.6486108303070068,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8836,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.6390822529792786,
      "learning_rate": 0.00019113082039911309,
      "loss": 1.0328,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.6051312685012817,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.1173,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.539639949798584,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.8195,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.6244184970855713,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9956,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.5312393307685852,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.9427,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3284015614623744.0,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}