{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4878048780487805,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024390243902439025,
      "grad_norm": 0.2627893388271332,
      "learning_rate": 0.00019631901840490797,
      "loss": 2.6021,
      "step": 20
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 0.22776605188846588,
      "learning_rate": 0.0001914110429447853,
      "loss": 2.3247,
      "step": 40
    },
    {
      "epoch": 0.07317073170731707,
      "grad_norm": 0.219473734498024,
      "learning_rate": 0.00018650306748466258,
      "loss": 2.327,
      "step": 60
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.2347700446844101,
      "learning_rate": 0.00018159509202453987,
      "loss": 2.2708,
      "step": 80
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 0.22764651477336884,
      "learning_rate": 0.0001766871165644172,
      "loss": 2.2459,
      "step": 100
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 0.2603573799133301,
      "learning_rate": 0.0001717791411042945,
      "loss": 2.1985,
      "step": 120
    },
    {
      "epoch": 0.17073170731707318,
      "grad_norm": 0.30507025122642517,
      "learning_rate": 0.00016687116564417177,
      "loss": 2.297,
      "step": 140
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.21570216119289398,
      "learning_rate": 0.00016196319018404909,
      "loss": 2.188,
      "step": 160
    },
    {
      "epoch": 0.21951219512195122,
      "grad_norm": 0.3292004466056824,
      "learning_rate": 0.0001570552147239264,
      "loss": 2.1902,
      "step": 180
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.24518953263759613,
      "learning_rate": 0.0001521472392638037,
      "loss": 2.2467,
      "step": 200
    },
    {
      "epoch": 0.2682926829268293,
      "grad_norm": 0.23216311633586884,
      "learning_rate": 0.00014723926380368098,
      "loss": 2.2083,
      "step": 220
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.20361796021461487,
      "learning_rate": 0.00014233128834355828,
      "loss": 2.1973,
      "step": 240
    },
    {
      "epoch": 0.3170731707317073,
      "grad_norm": 0.24827799201011658,
      "learning_rate": 0.0001374233128834356,
      "loss": 2.1774,
      "step": 260
    },
    {
      "epoch": 0.34146341463414637,
      "grad_norm": 0.20967458188533783,
      "learning_rate": 0.00013251533742331288,
      "loss": 2.1627,
      "step": 280
    },
    {
      "epoch": 0.36585365853658536,
      "grad_norm": 0.2206897735595703,
      "learning_rate": 0.00012760736196319017,
      "loss": 2.1811,
      "step": 300
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.23732008039951324,
      "learning_rate": 0.0001226993865030675,
      "loss": 2.1742,
      "step": 320
    },
    {
      "epoch": 0.4146341463414634,
      "grad_norm": 0.22148175537586212,
      "learning_rate": 0.0001177914110429448,
      "loss": 2.2337,
      "step": 340
    },
    {
      "epoch": 0.43902439024390244,
      "grad_norm": 0.2142496407032013,
      "learning_rate": 0.00011288343558282209,
      "loss": 2.1012,
      "step": 360
    },
    {
      "epoch": 0.4634146341463415,
      "grad_norm": 0.2130177915096283,
      "learning_rate": 0.00010797546012269939,
      "loss": 2.2286,
      "step": 380
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.2707054018974304,
      "learning_rate": 0.0001030674846625767,
      "loss": 2.2509,
      "step": 400
    }
  ],
  "logging_steps": 20,
  "max_steps": 820,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.74215443382272e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}