{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2166108913903255,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.048676604806814724,
      "grad_norm": 1.8046875,
      "learning_rate": 1.027027027027027e-05,
      "loss": 1.7832,
      "step": 20
    },
    {
      "epoch": 0.09735320961362945,
      "grad_norm": 1.7890625,
      "learning_rate": 1.996655518394649e-05,
      "loss": 1.7722,
      "step": 40
    },
    {
      "epoch": 0.1460298144204442,
      "grad_norm": 1.796875,
      "learning_rate": 1.9632107023411374e-05,
      "loss": 1.7743,
      "step": 60
    },
    {
      "epoch": 0.1947064192272589,
      "grad_norm": 1.703125,
      "learning_rate": 1.9297658862876256e-05,
      "loss": 1.7206,
      "step": 80
    },
    {
      "epoch": 0.24338302403407364,
      "grad_norm": 1.921875,
      "learning_rate": 1.896321070234114e-05,
      "loss": 1.7695,
      "step": 100
    },
    {
      "epoch": 0.2920596288408884,
      "grad_norm": 1.8359375,
      "learning_rate": 1.8628762541806024e-05,
      "loss": 1.7434,
      "step": 120
    },
    {
      "epoch": 0.34073623364770306,
      "grad_norm": 1.828125,
      "learning_rate": 1.8294314381270902e-05,
      "loss": 1.7553,
      "step": 140
    },
    {
      "epoch": 0.3894128384545178,
      "grad_norm": 1.734375,
      "learning_rate": 1.7959866220735788e-05,
      "loss": 1.7411,
      "step": 160
    },
    {
      "epoch": 0.43808944326133253,
      "grad_norm": 1.8359375,
      "learning_rate": 1.762541806020067e-05,
      "loss": 1.74,
      "step": 180
    },
    {
      "epoch": 0.4867660480681473,
      "grad_norm": 1.75,
      "learning_rate": 1.729096989966555e-05,
      "loss": 1.7305,
      "step": 200
    },
    {
      "epoch": 0.535442652874962,
      "grad_norm": 1.8359375,
      "learning_rate": 1.6956521739130437e-05,
      "loss": 1.8263,
      "step": 220
    },
    {
      "epoch": 0.5841192576817767,
      "grad_norm": 1.71875,
      "learning_rate": 1.662207357859532e-05,
      "loss": 1.7434,
      "step": 240
    },
    {
      "epoch": 0.6327958624885914,
      "grad_norm": 1.6953125,
      "learning_rate": 1.6287625418060204e-05,
      "loss": 1.8066,
      "step": 260
    },
    {
      "epoch": 0.6814724672954061,
      "grad_norm": 1.7421875,
      "learning_rate": 1.5953177257525086e-05,
      "loss": 1.7684,
      "step": 280
    },
    {
      "epoch": 0.7301490721022209,
      "grad_norm": 1.7734375,
      "learning_rate": 1.5618729096989968e-05,
      "loss": 1.7585,
      "step": 300
    },
    {
      "epoch": 0.7788256769090356,
      "grad_norm": 1.859375,
      "learning_rate": 1.5284280936454853e-05,
      "loss": 1.7534,
      "step": 320
    },
    {
      "epoch": 0.8275022817158503,
      "grad_norm": 1.59375,
      "learning_rate": 1.4949832775919733e-05,
      "loss": 1.7249,
      "step": 340
    },
    {
      "epoch": 0.8761788865226651,
      "grad_norm": 1.71875,
      "learning_rate": 1.4615384615384615e-05,
      "loss": 1.6967,
      "step": 360
    },
    {
      "epoch": 0.9248554913294798,
      "grad_norm": 1.890625,
      "learning_rate": 1.4280936454849499e-05,
      "loss": 1.7558,
      "step": 380
    },
    {
      "epoch": 0.9735320961362945,
      "grad_norm": 1.7734375,
      "learning_rate": 1.3946488294314383e-05,
      "loss": 1.77,
      "step": 400
    },
    {
      "epoch": 1.0219044721630666,
      "grad_norm": 1.75,
      "learning_rate": 1.3612040133779264e-05,
      "loss": 1.749,
      "step": 420
    },
    {
      "epoch": 1.0705810769698814,
      "grad_norm": 1.7421875,
      "learning_rate": 1.3277591973244148e-05,
      "loss": 1.7204,
      "step": 440
    },
    {
      "epoch": 1.1192576817766962,
      "grad_norm": 1.84375,
      "learning_rate": 1.2943143812709032e-05,
      "loss": 1.7572,
      "step": 460
    },
    {
      "epoch": 1.1679342865835107,
      "grad_norm": 1.796875,
      "learning_rate": 1.2608695652173915e-05,
      "loss": 1.6993,
      "step": 480
    },
    {
      "epoch": 1.2166108913903255,
      "grad_norm": 1.8046875,
      "learning_rate": 1.2274247491638797e-05,
      "loss": 1.7129,
      "step": 500
    }
  ],
  "logging_steps": 20,
  "max_steps": 1233,
  "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": 6.43897600990249e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}