{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 287,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03488118596032265,
      "grad_norm": 0.3421550691127777,
      "learning_rate": 3e-05,
      "loss": 0.3705,
      "step": 10
    },
    {
      "epoch": 0.0697623719206453,
      "grad_norm": 0.2182866334915161,
      "learning_rate": 4.997332437005931e-05,
      "loss": 0.3007,
      "step": 20
    },
    {
      "epoch": 0.10464355788096795,
      "grad_norm": 2.077357769012451,
      "learning_rate": 4.967387692220614e-05,
      "loss": 0.257,
      "step": 30
    },
    {
      "epoch": 0.1395247438412906,
      "grad_norm": 0.18195165693759918,
      "learning_rate": 4.9045641079320484e-05,
      "loss": 0.2452,
      "step": 40
    },
    {
      "epoch": 0.17440592980161326,
      "grad_norm": 0.18397241830825806,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.2286,
      "step": 50
    },
    {
      "epoch": 0.2092871157619359,
      "grad_norm": 0.1943083554506302,
      "learning_rate": 4.684055976615924e-05,
      "loss": 0.2368,
      "step": 60
    },
    {
      "epoch": 0.24416830172225856,
      "grad_norm": 0.1737656444311142,
      "learning_rate": 4.529309780736654e-05,
      "loss": 0.222,
      "step": 70
    },
    {
      "epoch": 0.2790494876825812,
      "grad_norm": 0.1842474490404129,
      "learning_rate": 4.347522293051648e-05,
      "loss": 0.2178,
      "step": 80
    },
    {
      "epoch": 0.31393067364290383,
      "grad_norm": 0.20107556879520416,
      "learning_rate": 4.141115898032607e-05,
      "loss": 0.2184,
      "step": 90
    },
    {
      "epoch": 0.3488118596032265,
      "grad_norm": 0.4136504530906677,
      "learning_rate": 3.91284103605648e-05,
      "loss": 0.217,
      "step": 100
    },
    {
      "epoch": 0.38369304556354916,
      "grad_norm": 0.16409939527511597,
      "learning_rate": 3.66573955278587e-05,
      "loss": 0.2101,
      "step": 110
    },
    {
      "epoch": 0.4185742315238718,
      "grad_norm": 0.19704529643058777,
      "learning_rate": 3.403104165467883e-05,
      "loss": 0.2017,
      "step": 120
    },
    {
      "epoch": 0.4534554174841945,
      "grad_norm": 0.1826065629720688,
      "learning_rate": 3.128434586277757e-05,
      "loss": 0.202,
      "step": 130
    },
    {
      "epoch": 0.4883366034445171,
      "grad_norm": 0.1781151294708252,
      "learning_rate": 2.8453908873797058e-05,
      "loss": 0.1964,
      "step": 140
    },
    {
      "epoch": 0.5232177894048398,
      "grad_norm": 0.1823512762784958,
      "learning_rate": 2.557744729132503e-05,
      "loss": 0.1935,
      "step": 150
    },
    {
      "epoch": 0.5580989753651624,
      "grad_norm": 0.18696753680706024,
      "learning_rate": 2.2693291013417453e-05,
      "loss": 0.1841,
      "step": 160
    },
    {
      "epoch": 0.592980161325485,
      "grad_norm": 0.15684251487255096,
      "learning_rate": 1.9839872472749013e-05,
      "loss": 0.1824,
      "step": 170
    },
    {
      "epoch": 0.6278613472858077,
      "grad_norm": 0.17977288365364075,
      "learning_rate": 1.705521451045246e-05,
      "loss": 0.1862,
      "step": 180
    },
    {
      "epoch": 0.6627425332461304,
      "grad_norm": 0.16611480712890625,
      "learning_rate": 1.437642370791446e-05,
      "loss": 0.1839,
      "step": 190
    },
    {
      "epoch": 0.697623719206453,
      "grad_norm": 0.15906041860580444,
      "learning_rate": 1.1839195928066102e-05,
      "loss": 0.1754,
      "step": 200
    },
    {
      "epoch": 0.7325049051667757,
      "grad_norm": 0.17589956521987915,
      "learning_rate": 9.477340655010716e-06,
      "loss": 0.1674,
      "step": 210
    },
    {
      "epoch": 0.7673860911270983,
      "grad_norm": 0.1716720014810562,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.17,
      "step": 220
    },
    {
      "epoch": 0.802267277087421,
      "grad_norm": 0.17009420692920685,
      "learning_rate": 5.4028816695051635e-06,
      "loss": 0.179,
      "step": 230
    },
    {
      "epoch": 0.8371484630477436,
      "grad_norm": 0.16394925117492676,
      "learning_rate": 3.7445716067596503e-06,
      "loss": 0.1603,
      "step": 240
    },
    {
      "epoch": 0.8720296490080662,
      "grad_norm": 0.16140860319137573,
      "learning_rate": 2.3694978675629478e-06,
      "loss": 0.1646,
      "step": 250
    },
    {
      "epoch": 0.906910834968389,
      "grad_norm": 0.1722809225320816,
      "learning_rate": 1.2959838102258536e-06,
      "loss": 0.1754,
      "step": 260
    },
    {
      "epoch": 0.9417920209287116,
      "grad_norm": 0.4494320750236511,
      "learning_rate": 5.383344004847773e-07,
      "loss": 0.1616,
      "step": 270
    },
    {
      "epoch": 0.9766732068890343,
      "grad_norm": 0.17471113801002502,
      "learning_rate": 1.0664559262413831e-07,
      "loss": 0.1682,
      "step": 280
    },
    {
      "epoch": 1.0,
      "step": 287,
      "total_flos": 1067962052116480.0,
      "train_loss": 0.20536177831244384,
      "train_runtime": 28151.8512,
      "train_samples_per_second": 1.304,
      "train_steps_per_second": 0.01
    }
  ],
  "logging_steps": 10,
  "max_steps": 287,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1067962052116480.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}