{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008,
      "grad_norm": 15.428410530090332,
      "learning_rate": 0.0,
      "loss": 5.2835,
      "step": 1
    },
    {
      "epoch": 0.016,
      "grad_norm": 15.426681518554688,
      "learning_rate": 4e-05,
      "loss": 5.2835,
      "step": 2
    },
    {
      "epoch": 0.024,
      "grad_norm": 16.885461807250977,
      "learning_rate": 8e-05,
      "loss": 4.9305,
      "step": 3
    },
    {
      "epoch": 0.032,
      "grad_norm": 8.955594062805176,
      "learning_rate": 0.00012,
      "loss": 3.6748,
      "step": 4
    },
    {
      "epoch": 0.04,
      "grad_norm": 9.647289276123047,
      "learning_rate": 0.00016,
      "loss": 2.6065,
      "step": 5
    },
    {
      "epoch": 0.048,
      "grad_norm": 6.1404500007629395,
      "learning_rate": 0.0002,
      "loss": 1.7512,
      "step": 6
    },
    {
      "epoch": 0.056,
      "grad_norm": 9.074440956115723,
      "learning_rate": 0.000192,
      "loss": 0.8787,
      "step": 7
    },
    {
      "epoch": 0.064,
      "grad_norm": 4.00243616104126,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.4512,
      "step": 8
    },
    {
      "epoch": 0.072,
      "grad_norm": 1.3253382444381714,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.0879,
      "step": 9
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.162848949432373,
      "learning_rate": 0.000168,
      "loss": 0.0525,
      "step": 10
    },
    {
      "epoch": 0.088,
      "grad_norm": 1.1460442543029785,
      "learning_rate": 0.00016,
      "loss": 0.0412,
      "step": 11
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.5914936661720276,
      "learning_rate": 0.000152,
      "loss": 0.0232,
      "step": 12
    },
    {
      "epoch": 0.104,
      "grad_norm": 0.40345266461372375,
      "learning_rate": 0.000144,
      "loss": 0.0131,
      "step": 13
    },
    {
      "epoch": 0.112,
      "grad_norm": 0.5011171698570251,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.008,
      "step": 14
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.4873741865158081,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.0059,
      "step": 15
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.27999016642570496,
      "learning_rate": 0.00012,
      "loss": 0.0032,
      "step": 16
    },
    {
      "epoch": 0.136,
      "grad_norm": 0.16314102709293365,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.0018,
      "step": 17
    },
    {
      "epoch": 0.144,
      "grad_norm": 0.10664301365613937,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.0012,
      "step": 18
    },
    {
      "epoch": 0.152,
      "grad_norm": 0.04609872028231621,
      "learning_rate": 9.6e-05,
      "loss": 0.0007,
      "step": 19
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.03019017167389393,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.0005,
      "step": 20
    },
    {
      "epoch": 0.168,
      "grad_norm": 0.01985774375498295,
      "learning_rate": 8e-05,
      "loss": 0.0004,
      "step": 21
    },
    {
      "epoch": 0.176,
      "grad_norm": 0.015222536399960518,
      "learning_rate": 7.2e-05,
      "loss": 0.0003,
      "step": 22
    },
    {
      "epoch": 0.184,
      "grad_norm": 0.012847527861595154,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.0003,
      "step": 23
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.011019011028110981,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.0002,
      "step": 24
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.009830518625676632,
      "learning_rate": 4.8e-05,
      "loss": 0.0002,
      "step": 25
    },
    {
      "epoch": 0.208,
      "grad_norm": 0.008783610537648201,
      "learning_rate": 4e-05,
      "loss": 0.0002,
      "step": 26
    },
    {
      "epoch": 0.216,
      "grad_norm": 0.009143549017608166,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.0002,
      "step": 27
    },
    {
      "epoch": 0.224,
      "grad_norm": 0.009110250510275364,
      "learning_rate": 2.4e-05,
      "loss": 0.0002,
      "step": 28
    },
    {
      "epoch": 0.232,
      "grad_norm": 0.00845172069966793,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.0002,
      "step": 29
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.008985675871372223,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.0002,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 525137523027840.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}