{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9907235621521338,
  "eval_steps": 500,
  "global_step": 201,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14842300556586271,
      "grad_norm": 8.770494049160096,
      "learning_rate": 5e-06,
      "loss": 0.7728,
      "step": 10
    },
    {
      "epoch": 0.29684601113172543,
      "grad_norm": 5.239180384850786,
      "learning_rate": 5e-06,
      "loss": 0.7163,
      "step": 20
    },
    {
      "epoch": 0.4452690166975881,
      "grad_norm": 1.2130700854178535,
      "learning_rate": 5e-06,
      "loss": 0.6781,
      "step": 30
    },
    {
      "epoch": 0.5936920222634509,
      "grad_norm": 1.0745174920296572,
      "learning_rate": 5e-06,
      "loss": 0.6678,
      "step": 40
    },
    {
      "epoch": 0.7421150278293135,
      "grad_norm": 0.8867357173198487,
      "learning_rate": 5e-06,
      "loss": 0.6594,
      "step": 50
    },
    {
      "epoch": 0.8905380333951762,
      "grad_norm": 1.2379194861360832,
      "learning_rate": 5e-06,
      "loss": 0.6453,
      "step": 60
    },
    {
      "epoch": 0.9944341372912802,
      "eval_loss": 0.6419587731361389,
      "eval_runtime": 72.5933,
      "eval_samples_per_second": 25.016,
      "eval_steps_per_second": 0.399,
      "step": 67
    },
    {
      "epoch": 1.0426716141001855,
      "grad_norm": 1.1230378978262539,
      "learning_rate": 5e-06,
      "loss": 0.6781,
      "step": 70
    },
    {
      "epoch": 1.1910946196660483,
      "grad_norm": 0.9315188359610128,
      "learning_rate": 5e-06,
      "loss": 0.5789,
      "step": 80
    },
    {
      "epoch": 1.339517625231911,
      "grad_norm": 0.7280697861125209,
      "learning_rate": 5e-06,
      "loss": 0.5768,
      "step": 90
    },
    {
      "epoch": 1.4879406307977736,
      "grad_norm": 0.7574742425182042,
      "learning_rate": 5e-06,
      "loss": 0.5637,
      "step": 100
    },
    {
      "epoch": 1.6363636363636362,
      "grad_norm": 0.639849134642834,
      "learning_rate": 5e-06,
      "loss": 0.5671,
      "step": 110
    },
    {
      "epoch": 1.784786641929499,
      "grad_norm": 0.6958680579149541,
      "learning_rate": 5e-06,
      "loss": 0.5709,
      "step": 120
    },
    {
      "epoch": 1.9332096474953617,
      "grad_norm": 0.540531330356496,
      "learning_rate": 5e-06,
      "loss": 0.568,
      "step": 130
    },
    {
      "epoch": 1.9925788497217067,
      "eval_loss": 0.6242453455924988,
      "eval_runtime": 73.2468,
      "eval_samples_per_second": 24.793,
      "eval_steps_per_second": 0.396,
      "step": 134
    },
    {
      "epoch": 2.085343228200371,
      "grad_norm": 0.778875955578771,
      "learning_rate": 5e-06,
      "loss": 0.5879,
      "step": 140
    },
    {
      "epoch": 2.2337662337662336,
      "grad_norm": 0.756734990400302,
      "learning_rate": 5e-06,
      "loss": 0.507,
      "step": 150
    },
    {
      "epoch": 2.3821892393320967,
      "grad_norm": 0.619492041600219,
      "learning_rate": 5e-06,
      "loss": 0.5063,
      "step": 160
    },
    {
      "epoch": 2.5306122448979593,
      "grad_norm": 0.843944094594807,
      "learning_rate": 5e-06,
      "loss": 0.5001,
      "step": 170
    },
    {
      "epoch": 2.679035250463822,
      "grad_norm": 0.860609592948253,
      "learning_rate": 5e-06,
      "loss": 0.5013,
      "step": 180
    },
    {
      "epoch": 2.8274582560296846,
      "grad_norm": 0.7816936988629369,
      "learning_rate": 5e-06,
      "loss": 0.5063,
      "step": 190
    },
    {
      "epoch": 2.9758812615955472,
      "grad_norm": 0.7099567262640085,
      "learning_rate": 5e-06,
      "loss": 0.5028,
      "step": 200
    },
    {
      "epoch": 2.9907235621521338,
      "eval_loss": 0.6297215223312378,
      "eval_runtime": 71.9347,
      "eval_samples_per_second": 25.245,
      "eval_steps_per_second": 0.403,
      "step": 201
    },
    {
      "epoch": 2.9907235621521338,
      "step": 201,
      "total_flos": 336473106677760.0,
      "train_loss": 0.592634052186463,
      "train_runtime": 12077.2754,
      "train_samples_per_second": 8.567,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 201,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 336473106677760.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}