{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9292149292149292,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05148005148005148,
      "grad_norm": 3.805959701538086,
      "learning_rate": 2.435897435897436e-06,
      "loss": 3.0721,
      "step": 20
    },
    {
      "epoch": 0.10296010296010295,
      "grad_norm": 2.047661066055298,
      "learning_rate": 5e-06,
      "loss": 2.7096,
      "step": 40
    },
    {
      "epoch": 0.15444015444015444,
      "grad_norm": 1.883644938468933,
      "learning_rate": 7.564102564102564e-06,
      "loss": 2.3981,
      "step": 60
    },
    {
      "epoch": 0.2059202059202059,
      "grad_norm": 2.1643970012664795,
      "learning_rate": 9.999949644960027e-06,
      "loss": 2.1589,
      "step": 80
    },
    {
      "epoch": 0.2574002574002574,
      "grad_norm": 2.4580767154693604,
      "learning_rate": 9.9778098230154e-06,
      "loss": 1.9609,
      "step": 100
    },
    {
      "epoch": 0.3088803088803089,
      "grad_norm": 2.061549186706543,
      "learning_rate": 9.915591603280632e-06,
      "loss": 1.917,
      "step": 120
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 2.2059481143951416,
      "learning_rate": 9.813795930277306e-06,
      "loss": 1.8609,
      "step": 140
    },
    {
      "epoch": 0.4118404118404118,
      "grad_norm": 3.432741403579712,
      "learning_rate": 9.673242402909555e-06,
      "loss": 1.7972,
      "step": 160
    },
    {
      "epoch": 0.46332046332046334,
      "grad_norm": 2.5304017066955566,
      "learning_rate": 9.495062675535614e-06,
      "loss": 1.7804,
      "step": 180
    },
    {
      "epoch": 0.5148005148005148,
      "grad_norm": 2.3981094360351562,
      "learning_rate": 9.280691346552308e-06,
      "loss": 1.7499,
      "step": 200
    },
    {
      "epoch": 0.5662805662805663,
      "grad_norm": 2.79345440864563,
      "learning_rate": 9.031854407852317e-06,
      "loss": 1.7623,
      "step": 220
    },
    {
      "epoch": 0.6177606177606177,
      "grad_norm": 2.7196028232574463,
      "learning_rate": 8.750555348152299e-06,
      "loss": 1.7245,
      "step": 240
    },
    {
      "epoch": 0.6692406692406693,
      "grad_norm": 3.4595141410827637,
      "learning_rate": 8.439059022079789e-06,
      "loss": 1.7307,
      "step": 260
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 2.5787878036499023,
      "learning_rate": 8.099873414895453e-06,
      "loss": 1.7234,
      "step": 280
    },
    {
      "epoch": 0.7722007722007722,
      "grad_norm": 2.179560422897339,
      "learning_rate": 7.73572944967043e-06,
      "loss": 1.6921,
      "step": 300
    },
    {
      "epoch": 0.8236808236808236,
      "grad_norm": 2.5689198970794678,
      "learning_rate": 7.3495589994995274e-06,
      "loss": 1.6596,
      "step": 320
    },
    {
      "epoch": 0.8751608751608752,
      "grad_norm": 2.540849447250366,
      "learning_rate": 6.944471281782975e-06,
      "loss": 1.6428,
      "step": 340
    },
    {
      "epoch": 0.9266409266409267,
      "grad_norm": 3.2991511821746826,
      "learning_rate": 6.523727824636103e-06,
      "loss": 1.6623,
      "step": 360
    },
    {
      "epoch": 0.9781209781209781,
      "grad_norm": 2.4058475494384766,
      "learning_rate": 6.090716206982714e-06,
      "loss": 1.6637,
      "step": 380
    },
    {
      "epoch": 1.0283140283140284,
      "grad_norm": 2.8208141326904297,
      "learning_rate": 5.648922783761443e-06,
      "loss": 1.6323,
      "step": 400
    },
    {
      "epoch": 1.0797940797940797,
      "grad_norm": 2.442612886428833,
      "learning_rate": 5.201904615845743e-06,
      "loss": 1.5962,
      "step": 420
    },
    {
      "epoch": 1.1312741312741312,
      "grad_norm": 2.94942307472229,
      "learning_rate": 4.753260830681247e-06,
      "loss": 1.5622,
      "step": 440
    },
    {
      "epoch": 1.1827541827541828,
      "grad_norm": 2.8817596435546875,
      "learning_rate": 4.306603644227821e-06,
      "loss": 1.574,
      "step": 460
    },
    {
      "epoch": 1.2342342342342343,
      "grad_norm": 2.556431293487549,
      "learning_rate": 3.8655292775206185e-06,
      "loss": 1.5766,
      "step": 480
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 3.112046718597412,
      "learning_rate": 3.4335890020128382e-06,
      "loss": 1.5691,
      "step": 500
    },
    {
      "epoch": 1.3371943371943371,
      "grad_norm": 2.709402322769165,
      "learning_rate": 3.0142605468260976e-06,
      "loss": 1.5375,
      "step": 520
    },
    {
      "epoch": 1.3886743886743886,
      "grad_norm": 2.6925084590911865,
      "learning_rate": 2.610920098120424e-06,
      "loss": 1.5389,
      "step": 540
    },
    {
      "epoch": 1.4401544401544402,
      "grad_norm": 2.4258522987365723,
      "learning_rate": 2.2268151160284508e-06,
      "loss": 1.5367,
      "step": 560
    },
    {
      "epoch": 1.4916344916344917,
      "grad_norm": 3.074117660522461,
      "learning_rate": 1.8650381880159108e-06,
      "loss": 1.556,
      "step": 580
    },
    {
      "epoch": 1.5431145431145432,
      "grad_norm": 3.0699758529663086,
      "learning_rate": 1.5285021291857705e-06,
      "loss": 1.5257,
      "step": 600
    },
    {
      "epoch": 1.5945945945945947,
      "grad_norm": 2.5055222511291504,
      "learning_rate": 1.2199165300037358e-06,
      "loss": 1.5375,
      "step": 620
    },
    {
      "epoch": 1.646074646074646,
      "grad_norm": 2.867077350616455,
      "learning_rate": 9.417659402690254e-07,
      "loss": 1.5361,
      "step": 640
    },
    {
      "epoch": 1.6975546975546976,
      "grad_norm": 2.823442220687866,
      "learning_rate": 6.962898649802824e-07,
      "loss": 1.5663,
      "step": 660
    },
    {
      "epoch": 1.7490347490347489,
      "grad_norm": 3.6031746864318848,
      "learning_rate": 4.854647331581385e-07,
      "loss": 1.5092,
      "step": 680
    },
    {
      "epoch": 1.8005148005148004,
      "grad_norm": 2.782688617706299,
      "learning_rate": 3.109879848008557e-07,
      "loss": 1.5553,
      "step": 700
    },
    {
      "epoch": 1.851994851994852,
      "grad_norm": 2.91386079788208,
      "learning_rate": 1.742644040955399e-07,
      "loss": 1.5208,
      "step": 720
    },
    {
      "epoch": 1.9034749034749034,
      "grad_norm": 2.826528787612915,
      "learning_rate": 7.639480892186634e-08,
      "loss": 1.5415,
      "step": 740
    }
  ],
  "logging_steps": 20,
  "max_steps": 778,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.478999410119066e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}