{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.6718146718146718,
  "eval_steps": 500,
  "global_step": 650,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05148005148005148,
      "grad_norm": 3.7984347343444824,
      "learning_rate": 2.435897435897436e-06,
      "loss": 3.0721,
      "step": 20
    },
    {
      "epoch": 0.10296010296010295,
      "grad_norm": 2.0532360076904297,
      "learning_rate": 5e-06,
      "loss": 2.7105,
      "step": 40
    },
    {
      "epoch": 0.15444015444015444,
      "grad_norm": 1.889143466949463,
      "learning_rate": 7.564102564102564e-06,
      "loss": 2.397,
      "step": 60
    },
    {
      "epoch": 0.2059202059202059,
      "grad_norm": 2.206676959991455,
      "learning_rate": 9.999949644960027e-06,
      "loss": 2.1587,
      "step": 80
    },
    {
      "epoch": 0.2574002574002574,
      "grad_norm": 2.4184727668762207,
      "learning_rate": 9.9778098230154e-06,
      "loss": 1.9613,
      "step": 100
    },
    {
      "epoch": 0.3088803088803089,
      "grad_norm": 2.1078503131866455,
      "learning_rate": 9.915591603280632e-06,
      "loss": 1.9187,
      "step": 120
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 2.228259801864624,
      "learning_rate": 9.813795930277306e-06,
      "loss": 1.863,
      "step": 140
    },
    {
      "epoch": 0.4118404118404118,
      "grad_norm": 3.990351438522339,
      "learning_rate": 9.673242402909555e-06,
      "loss": 1.7983,
      "step": 160
    },
    {
      "epoch": 0.46332046332046334,
      "grad_norm": 2.6102797985076904,
      "learning_rate": 9.495062675535614e-06,
      "loss": 1.7845,
      "step": 180
    },
    {
      "epoch": 0.5148005148005148,
      "grad_norm": 2.4415857791900635,
      "learning_rate": 9.280691346552308e-06,
      "loss": 1.7541,
      "step": 200
    },
    {
      "epoch": 0.5662805662805663,
      "grad_norm": 2.875765800476074,
      "learning_rate": 9.031854407852317e-06,
      "loss": 1.7665,
      "step": 220
    },
    {
      "epoch": 0.6177606177606177,
      "grad_norm": 2.55922269821167,
      "learning_rate": 8.750555348152299e-06,
      "loss": 1.7272,
      "step": 240
    },
    {
      "epoch": 0.6692406692406693,
      "grad_norm": 3.4958205223083496,
      "learning_rate": 8.439059022079789e-06,
      "loss": 1.7349,
      "step": 260
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 2.582611560821533,
      "learning_rate": 8.099873414895453e-06,
      "loss": 1.7273,
      "step": 280
    },
    {
      "epoch": 0.7722007722007722,
      "grad_norm": 2.274104595184326,
      "learning_rate": 7.73572944967043e-06,
      "loss": 1.695,
      "step": 300
    },
    {
      "epoch": 0.8236808236808236,
      "grad_norm": 2.8610410690307617,
      "learning_rate": 7.3495589994995274e-06,
      "loss": 1.663,
      "step": 320
    },
    {
      "epoch": 0.8751608751608752,
      "grad_norm": 2.4936399459838867,
      "learning_rate": 6.944471281782975e-06,
      "loss": 1.6462,
      "step": 340
    },
    {
      "epoch": 0.9266409266409267,
      "grad_norm": 3.510580062866211,
      "learning_rate": 6.523727824636103e-06,
      "loss": 1.6662,
      "step": 360
    },
    {
      "epoch": 0.9781209781209781,
      "grad_norm": 2.398237943649292,
      "learning_rate": 6.090716206982714e-06,
      "loss": 1.6664,
      "step": 380
    },
    {
      "epoch": 1.0283140283140284,
      "grad_norm": 2.8953514099121094,
      "learning_rate": 5.648922783761443e-06,
      "loss": 1.6363,
      "step": 400
    },
    {
      "epoch": 1.0797940797940797,
      "grad_norm": 2.4946253299713135,
      "learning_rate": 5.201904615845743e-06,
      "loss": 1.5998,
      "step": 420
    },
    {
      "epoch": 1.1312741312741312,
      "grad_norm": 2.965862512588501,
      "learning_rate": 4.753260830681247e-06,
      "loss": 1.5663,
      "step": 440
    },
    {
      "epoch": 1.1827541827541828,
      "grad_norm": 2.843411922454834,
      "learning_rate": 4.306603644227821e-06,
      "loss": 1.578,
      "step": 460
    },
    {
      "epoch": 1.2342342342342343,
      "grad_norm": 2.5591073036193848,
      "learning_rate": 3.8655292775206185e-06,
      "loss": 1.5821,
      "step": 480
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 3.3472440242767334,
      "learning_rate": 3.4335890020128382e-06,
      "loss": 1.5743,
      "step": 500
    },
    {
      "epoch": 1.3371943371943371,
      "grad_norm": 2.687406063079834,
      "learning_rate": 3.0142605468260976e-06,
      "loss": 1.5407,
      "step": 520
    },
    {
      "epoch": 1.3886743886743886,
      "grad_norm": 2.7775464057922363,
      "learning_rate": 2.610920098120424e-06,
      "loss": 1.5429,
      "step": 540
    },
    {
      "epoch": 1.4401544401544402,
      "grad_norm": 2.49112606048584,
      "learning_rate": 2.2268151160284508e-06,
      "loss": 1.5408,
      "step": 560
    },
    {
      "epoch": 1.4916344916344917,
      "grad_norm": 2.938004493713379,
      "learning_rate": 1.8650381880159108e-06,
      "loss": 1.5605,
      "step": 580
    },
    {
      "epoch": 1.5431145431145432,
      "grad_norm": 2.910888910293579,
      "learning_rate": 1.5285021291857705e-06,
      "loss": 1.53,
      "step": 600
    },
    {
      "epoch": 1.5945945945945947,
      "grad_norm": 2.5734620094299316,
      "learning_rate": 1.2199165300037358e-06,
      "loss": 1.5425,
      "step": 620
    },
    {
      "epoch": 1.646074646074646,
      "grad_norm": 2.9094061851501465,
      "learning_rate": 9.417659402690254e-07,
      "loss": 1.5401,
      "step": 640
    }
  ],
  "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": 4.743984506608435e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}