{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 135,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007407407407407408,
      "grad_norm": 15.093496322631836,
      "learning_rate": 0.0,
      "loss": 3.1025,
      "step": 1
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 5.202989101409912,
      "learning_rate": 1.2857142857142859e-05,
      "loss": 2.833,
      "step": 10
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 7.5872626304626465,
      "learning_rate": 1.9915854864676665e-05,
      "loss": 2.2228,
      "step": 20
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 7.160677433013916,
      "learning_rate": 1.9251166435386837e-05,
      "loss": 1.9658,
      "step": 30
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 4.033580780029297,
      "learning_rate": 1.796634556457236e-05,
      "loss": 1.7456,
      "step": 40
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.7138469219207764,
      "learning_rate": 1.614751751104301e-05,
      "loss": 1.6527,
      "step": 50
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.0834147930145264,
      "learning_rate": 1.3916603579471705e-05,
      "loss": 1.6036,
      "step": 60
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 1.5917985439300537,
      "learning_rate": 1.1423148382732854e-05,
      "loss": 1.559,
      "step": 70
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 1.3988016843795776,
      "learning_rate": 8.83429543400241e-06,
      "loss": 1.5159,
      "step": 80
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 1.077965497970581,
      "learning_rate": 6.323583033672799e-06,
      "loss": 1.504,
      "step": 90
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.0065542459487915,
      "learning_rate": 4.059311495186338e-06,
      "loss": 1.482,
      "step": 100
    },
    {
      "epoch": 0.7407407407407407,
      "eval_loss": 1.4770615100860596,
      "eval_runtime": 2.7359,
      "eval_samples_per_second": 340.288,
      "eval_steps_per_second": 2.924,
      "step": 100
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.8746654987335205,
      "learning_rate": 2.1932614882827196e-06,
      "loss": 1.4691,
      "step": 110
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.8962180614471436,
      "learning_rate": 8.505197417404687e-07,
      "loss": 1.4602,
      "step": 120
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 0.8950978517532349,
      "learning_rate": 1.2109411818274851e-07,
      "loss": 1.4526,
      "step": 130
    },
    {
      "epoch": 1.0,
      "step": 135,
      "total_flos": 5.022030486516531e+16,
      "train_loss": 1.7195094338169805,
      "train_runtime": 501.5523,
      "train_samples_per_second": 34.284,
      "train_steps_per_second": 0.269
    }
  ],
  "logging_steps": 10,
  "max_steps": 135,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.022030486516531e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}