{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9990586758707248,
  "eval_steps": 500,
  "global_step": 398,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.025101976780671477,
      "grad_norm": 11.570974273934945,
      "learning_rate": 5e-06,
      "loss": 0.9144,
      "step": 10
    },
    {
      "epoch": 0.050203953561342954,
      "grad_norm": 3.2868828349894663,
      "learning_rate": 5e-06,
      "loss": 0.7934,
      "step": 20
    },
    {
      "epoch": 0.07530593034201444,
      "grad_norm": 1.3621580098977089,
      "learning_rate": 5e-06,
      "loss": 0.7581,
      "step": 30
    },
    {
      "epoch": 0.10040790712268591,
      "grad_norm": 1.1465743337293792,
      "learning_rate": 5e-06,
      "loss": 0.718,
      "step": 40
    },
    {
      "epoch": 0.12550988390335738,
      "grad_norm": 1.8313362803176332,
      "learning_rate": 5e-06,
      "loss": 0.6988,
      "step": 50
    },
    {
      "epoch": 0.15061186068402888,
      "grad_norm": 0.8106493906617342,
      "learning_rate": 5e-06,
      "loss": 0.6753,
      "step": 60
    },
    {
      "epoch": 0.17571383746470035,
      "grad_norm": 1.3540466482658315,
      "learning_rate": 5e-06,
      "loss": 0.6672,
      "step": 70
    },
    {
      "epoch": 0.20081581424537182,
      "grad_norm": 0.5964949627381437,
      "learning_rate": 5e-06,
      "loss": 0.6551,
      "step": 80
    },
    {
      "epoch": 0.2259177910260433,
      "grad_norm": 0.5688152556152026,
      "learning_rate": 5e-06,
      "loss": 0.6532,
      "step": 90
    },
    {
      "epoch": 0.25101976780671476,
      "grad_norm": 0.6773755092137309,
      "learning_rate": 5e-06,
      "loss": 0.6464,
      "step": 100
    },
    {
      "epoch": 0.27612174458738625,
      "grad_norm": 0.5774859088110325,
      "learning_rate": 5e-06,
      "loss": 0.6405,
      "step": 110
    },
    {
      "epoch": 0.30122372136805775,
      "grad_norm": 0.5522163553259679,
      "learning_rate": 5e-06,
      "loss": 0.6312,
      "step": 120
    },
    {
      "epoch": 0.3263256981487292,
      "grad_norm": 0.5727079237004361,
      "learning_rate": 5e-06,
      "loss": 0.6291,
      "step": 130
    },
    {
      "epoch": 0.3514276749294007,
      "grad_norm": 0.5373258099366229,
      "learning_rate": 5e-06,
      "loss": 0.6348,
      "step": 140
    },
    {
      "epoch": 0.3765296517100722,
      "grad_norm": 0.5642619689588081,
      "learning_rate": 5e-06,
      "loss": 0.6252,
      "step": 150
    },
    {
      "epoch": 0.40163162849074363,
      "grad_norm": 0.647603552543901,
      "learning_rate": 5e-06,
      "loss": 0.6219,
      "step": 160
    },
    {
      "epoch": 0.42673360527141513,
      "grad_norm": 0.6137422702457818,
      "learning_rate": 5e-06,
      "loss": 0.6234,
      "step": 170
    },
    {
      "epoch": 0.4518355820520866,
      "grad_norm": 0.5654990824228964,
      "learning_rate": 5e-06,
      "loss": 0.6139,
      "step": 180
    },
    {
      "epoch": 0.47693755883275807,
      "grad_norm": 0.7024949610501936,
      "learning_rate": 5e-06,
      "loss": 0.6195,
      "step": 190
    },
    {
      "epoch": 0.5020395356134295,
      "grad_norm": 0.5820569269038963,
      "learning_rate": 5e-06,
      "loss": 0.6125,
      "step": 200
    },
    {
      "epoch": 0.527141512394101,
      "grad_norm": 0.7020933693248848,
      "learning_rate": 5e-06,
      "loss": 0.6086,
      "step": 210
    },
    {
      "epoch": 0.5522434891747725,
      "grad_norm": 0.604199603689463,
      "learning_rate": 5e-06,
      "loss": 0.6188,
      "step": 220
    },
    {
      "epoch": 0.577345465955444,
      "grad_norm": 0.5647954363455674,
      "learning_rate": 5e-06,
      "loss": 0.6032,
      "step": 230
    },
    {
      "epoch": 0.6024474427361155,
      "grad_norm": 0.62231194375424,
      "learning_rate": 5e-06,
      "loss": 0.6097,
      "step": 240
    },
    {
      "epoch": 0.627549419516787,
      "grad_norm": 0.6954867326199731,
      "learning_rate": 5e-06,
      "loss": 0.6062,
      "step": 250
    },
    {
      "epoch": 0.6526513962974584,
      "grad_norm": 0.6683159364143533,
      "learning_rate": 5e-06,
      "loss": 0.6081,
      "step": 260
    },
    {
      "epoch": 0.6777533730781299,
      "grad_norm": 0.7460632306114617,
      "learning_rate": 5e-06,
      "loss": 0.6051,
      "step": 270
    },
    {
      "epoch": 0.7028553498588014,
      "grad_norm": 0.5069551815996469,
      "learning_rate": 5e-06,
      "loss": 0.6035,
      "step": 280
    },
    {
      "epoch": 0.7279573266394729,
      "grad_norm": 0.7002297529886885,
      "learning_rate": 5e-06,
      "loss": 0.6037,
      "step": 290
    },
    {
      "epoch": 0.7530593034201444,
      "grad_norm": 0.6956058201700761,
      "learning_rate": 5e-06,
      "loss": 0.5979,
      "step": 300
    },
    {
      "epoch": 0.7781612802008158,
      "grad_norm": 0.5991932647306116,
      "learning_rate": 5e-06,
      "loss": 0.5981,
      "step": 310
    },
    {
      "epoch": 0.8032632569814873,
      "grad_norm": 0.5275465592448361,
      "learning_rate": 5e-06,
      "loss": 0.5933,
      "step": 320
    },
    {
      "epoch": 0.8283652337621588,
      "grad_norm": 0.6290119559084576,
      "learning_rate": 5e-06,
      "loss": 0.5945,
      "step": 330
    },
    {
      "epoch": 0.8534672105428303,
      "grad_norm": 0.5130802873233022,
      "learning_rate": 5e-06,
      "loss": 0.5936,
      "step": 340
    },
    {
      "epoch": 0.8785691873235018,
      "grad_norm": 0.7421613361549775,
      "learning_rate": 5e-06,
      "loss": 0.5948,
      "step": 350
    },
    {
      "epoch": 0.9036711641041733,
      "grad_norm": 0.6153969499038726,
      "learning_rate": 5e-06,
      "loss": 0.5824,
      "step": 360
    },
    {
      "epoch": 0.9287731408848446,
      "grad_norm": 0.6034204487183606,
      "learning_rate": 5e-06,
      "loss": 0.5847,
      "step": 370
    },
    {
      "epoch": 0.9538751176655161,
      "grad_norm": 0.592301687922246,
      "learning_rate": 5e-06,
      "loss": 0.5908,
      "step": 380
    },
    {
      "epoch": 0.9789770944461876,
      "grad_norm": 0.6008165953019412,
      "learning_rate": 5e-06,
      "loss": 0.5911,
      "step": 390
    },
    {
      "epoch": 0.9990586758707248,
      "eval_loss": 0.5867129564285278,
      "eval_runtime": 271.3794,
      "eval_samples_per_second": 39.553,
      "eval_steps_per_second": 0.619,
      "step": 398
    }
  ],
  "logging_steps": 10,
  "max_steps": 1194,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 667083582996480.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}