{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 309,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09744214372716199,
      "grad_norm": 0.10498138517141342,
      "learning_rate": 2.9032258064516133e-05,
      "loss": 1.6591840744018556,
      "step": 10
    },
    {
      "epoch": 0.19488428745432398,
      "grad_norm": 0.06061352789402008,
      "learning_rate": 6.129032258064517e-05,
      "loss": 1.513698673248291,
      "step": 20
    },
    {
      "epoch": 0.292326431181486,
      "grad_norm": 0.06488917768001556,
      "learning_rate": 9.35483870967742e-05,
      "loss": 1.4184258460998536,
      "step": 30
    },
    {
      "epoch": 0.38976857490864797,
      "grad_norm": 0.0749744325876236,
      "learning_rate": 9.979581007037776e-05,
      "loss": 1.3041383743286132,
      "step": 40
    },
    {
      "epoch": 0.48721071863581,
      "grad_norm": 0.07460002601146698,
      "learning_rate": 9.896914594073703e-05,
      "loss": 1.2645663261413573,
      "step": 50
    },
    {
      "epoch": 0.584652862362972,
      "grad_norm": 0.07611106336116791,
      "learning_rate": 9.751778332739033e-05,
      "loss": 1.2547479629516602,
      "step": 60
    },
    {
      "epoch": 0.682095006090134,
      "grad_norm": 0.07656759023666382,
      "learning_rate": 9.546023723619386e-05,
      "loss": 1.1752987861633302,
      "step": 70
    },
    {
      "epoch": 0.7795371498172959,
      "grad_norm": 0.09050241112709045,
      "learning_rate": 9.282275574435281e-05,
      "loss": 1.2098669052124023,
      "step": 80
    },
    {
      "epoch": 0.876979293544458,
      "grad_norm": 0.09291807562112808,
      "learning_rate": 8.963898515418884e-05,
      "loss": 1.1355886459350586,
      "step": 90
    },
    {
      "epoch": 0.97442143727162,
      "grad_norm": 0.09804459661245346,
      "learning_rate": 8.594954076788736e-05,
      "loss": 1.0925632476806642,
      "step": 100
    },
    {
      "epoch": 1.0682095006090133,
      "grad_norm": 0.0993494838476181,
      "learning_rate": 8.18014887588431e-05,
      "loss": 1.0427302360534667,
      "step": 110
    },
    {
      "epoch": 1.1656516443361755,
      "grad_norm": 0.10639823228120804,
      "learning_rate": 7.724774574936188e-05,
      "loss": 1.0110761642456054,
      "step": 120
    },
    {
      "epoch": 1.2630937880633373,
      "grad_norm": 0.11075429618358612,
      "learning_rate": 7.234640375429427e-05,
      "loss": 1.0307095527648926,
      "step": 130
    },
    {
      "epoch": 1.3605359317904995,
      "grad_norm": 0.13242679834365845,
      "learning_rate": 6.715998910228296e-05,
      "loss": 1.0275198936462402,
      "step": 140
    },
    {
      "epoch": 1.4579780755176615,
      "grad_norm": 0.12440798431634903,
      "learning_rate": 6.17546647885516e-05,
      "loss": 0.9846453666687012,
      "step": 150
    },
    {
      "epoch": 1.5554202192448234,
      "grad_norm": 0.1317114233970642,
      "learning_rate": 5.619938643480561e-05,
      "loss": 0.9936046600341797,
      "step": 160
    },
    {
      "epoch": 1.6528623629719854,
      "grad_norm": 0.13666915893554688,
      "learning_rate": 5.0565022623648995e-05,
      "loss": 1.0225310325622559,
      "step": 170
    },
    {
      "epoch": 1.7503045066991474,
      "grad_norm": 0.12991490960121155,
      "learning_rate": 4.4923450829394605e-05,
      "loss": 1.0015269279479981,
      "step": 180
    },
    {
      "epoch": 1.8477466504263094,
      "grad_norm": 0.13253197073936462,
      "learning_rate": 3.934664047846156e-05,
      "loss": 0.9895278930664062,
      "step": 190
    },
    {
      "epoch": 1.9451887941534713,
      "grad_norm": 0.11419489234685898,
      "learning_rate": 3.390573483674142e-05,
      "loss": 0.9593095779418945,
      "step": 200
    },
    {
      "epoch": 2.038976857490865,
      "grad_norm": 0.12307924777269363,
      "learning_rate": 2.8670143436278756e-05,
      "loss": 0.8937208175659179,
      "step": 210
    },
    {
      "epoch": 2.1364190012180266,
      "grad_norm": 0.15227432548999786,
      "learning_rate": 2.3706656619162278e-05,
      "loss": 0.8942792892456055,
      "step": 220
    },
    {
      "epoch": 2.233861144945189,
      "grad_norm": 0.13321051001548767,
      "learning_rate": 1.907859349437336e-05,
      "loss": 0.8793990135192871,
      "step": 230
    },
    {
      "epoch": 2.331303288672351,
      "grad_norm": 0.13967254757881165,
      "learning_rate": 1.484499417709087e-05,
      "loss": 0.856902027130127,
      "step": 240
    },
    {
      "epoch": 2.428745432399513,
      "grad_norm": 0.14552684128284454,
      "learning_rate": 1.1059866615040204e-05,
      "loss": 0.9242639541625977,
      "step": 250
    },
    {
      "epoch": 2.5261875761266745,
      "grad_norm": 0.13452662527561188,
      "learning_rate": 7.77149761010898e-06,
      "loss": 0.8745415687561036,
      "step": 260
    },
    {
      "epoch": 2.6236297198538368,
      "grad_norm": 0.14857880771160126,
      "learning_rate": 5.021836824513759e-06,
      "loss": 0.8519741058349609,
      "step": 270
    },
    {
      "epoch": 2.721071863580999,
      "grad_norm": 0.14847053587436676,
      "learning_rate": 2.8459616297395466e-06,
      "loss": 0.8284287452697754,
      "step": 280
    },
    {
      "epoch": 2.8185140073081607,
      "grad_norm": 0.13416051864624023,
      "learning_rate": 1.2716296251644e-06,
      "loss": 0.8645434379577637,
      "step": 290
    },
    {
      "epoch": 2.915956151035323,
      "grad_norm": 0.1331121027469635,
      "learning_rate": 3.1892453488058803e-07,
      "loss": 0.9010993003845215,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 309,
  "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": 6.317731244054938e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}