{
  "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": 1.2240082025527954,
      "learning_rate": 0.0,
      "loss": 3.2004,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.1817413568496704,
      "learning_rate": 4e-05,
      "loss": 2.9195,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.089200496673584,
      "learning_rate": 8e-05,
      "loss": 2.9322,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.23591947555542,
      "learning_rate": 0.00012,
      "loss": 2.493,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.2914438247680664,
      "learning_rate": 0.00016,
      "loss": 2.6719,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.425159215927124,
      "learning_rate": 0.0002,
      "loss": 2.0729,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 1.8763092756271362,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.063,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.2933986186981201,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.4339,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.5251818895339966,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.5351,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.9210705161094666,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.1847,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.8823724389076233,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.9696,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.8065115809440613,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.0103,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.8599637150764465,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.7631,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.7091007232666016,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.774,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5932487845420837,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.7102,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5805957317352295,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.8034,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.5351698398590088,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.7074,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.5085647106170654,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7856,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4852818250656128,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.6869,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.4774964451789856,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.5578,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.4320865273475647,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.6558,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.5121509432792664,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.7886,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.43891361355781555,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.6733,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.4488874077796936,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.6966,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.42902886867523193,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.75,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.42811888456344604,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.5749,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.38084888458251953,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.6558,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.39865079522132874,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.6655,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.29908454418182373,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.5844,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.38320380449295044,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.6285,
      "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": 1.1832737003974656e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}