{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0031338138514572234,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00031338138514572234,
      "grad_norm": 3.002257823944092,
      "learning_rate": 2e-05,
      "loss": 3.4776,
      "step": 1
    },
    {
      "epoch": 0.00031338138514572234,
      "eval_loss": 3.1475110054016113,
      "eval_runtime": 24.7478,
      "eval_samples_per_second": 54.308,
      "eval_steps_per_second": 27.154,
      "step": 1
    },
    {
      "epoch": 0.0006267627702914447,
      "grad_norm": 2.85823917388916,
      "learning_rate": 4e-05,
      "loss": 2.9316,
      "step": 2
    },
    {
      "epoch": 0.000940144155437167,
      "grad_norm": 2.3006677627563477,
      "learning_rate": 6e-05,
      "loss": 3.1294,
      "step": 3
    },
    {
      "epoch": 0.000940144155437167,
      "eval_loss": 3.1223630905151367,
      "eval_runtime": 23.6933,
      "eval_samples_per_second": 56.725,
      "eval_steps_per_second": 28.362,
      "step": 3
    },
    {
      "epoch": 0.0012535255405828893,
      "grad_norm": 3.09515643119812,
      "learning_rate": 8e-05,
      "loss": 3.6862,
      "step": 4
    },
    {
      "epoch": 0.0015669069257286117,
      "grad_norm": 3.6554713249206543,
      "learning_rate": 0.0001,
      "loss": 3.1474,
      "step": 5
    },
    {
      "epoch": 0.001880288310874334,
      "grad_norm": 1.4472362995147705,
      "learning_rate": 0.00012,
      "loss": 3.0702,
      "step": 6
    },
    {
      "epoch": 0.001880288310874334,
      "eval_loss": 2.9717817306518555,
      "eval_runtime": 23.7909,
      "eval_samples_per_second": 56.492,
      "eval_steps_per_second": 28.246,
      "step": 6
    },
    {
      "epoch": 0.0021936696960200563,
      "grad_norm": 0.923194408416748,
      "learning_rate": 0.00014,
      "loss": 2.8183,
      "step": 7
    },
    {
      "epoch": 0.0025070510811657787,
      "grad_norm": 0.8299164175987244,
      "learning_rate": 0.00016,
      "loss": 2.8295,
      "step": 8
    },
    {
      "epoch": 0.002820432466311501,
      "grad_norm": 0.7389281988143921,
      "learning_rate": 0.00018,
      "loss": 2.8696,
      "step": 9
    },
    {
      "epoch": 0.002820432466311501,
      "eval_loss": 2.91095232963562,
      "eval_runtime": 24.0355,
      "eval_samples_per_second": 55.917,
      "eval_steps_per_second": 27.959,
      "step": 9
    },
    {
      "epoch": 0.0031338138514572234,
      "grad_norm": 0.7449145317077637,
      "learning_rate": 0.0002,
      "loss": 2.9361,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 153447605207040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}