{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15634771732332708,
  "eval_steps": 500,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003908692933083177,
      "grad_norm": 0.6370952129364014,
      "learning_rate": 4.98240400406663e-05,
      "loss": 1.4791,
      "step": 100
    },
    {
      "epoch": 0.007817385866166354,
      "grad_norm": 0.27393946051597595,
      "learning_rate": 4.9628528974739973e-05,
      "loss": 1.3743,
      "step": 200
    },
    {
      "epoch": 0.01172607879924953,
      "grad_norm": 0.364713191986084,
      "learning_rate": 4.943301790881364e-05,
      "loss": 1.3525,
      "step": 300
    },
    {
      "epoch": 0.015634771732332707,
      "grad_norm": 0.33364734053611755,
      "learning_rate": 4.923750684288731e-05,
      "loss": 1.3457,
      "step": 400
    },
    {
      "epoch": 0.019543464665415886,
      "grad_norm": 0.3672705292701721,
      "learning_rate": 4.904199577696098e-05,
      "loss": 1.3375,
      "step": 500
    },
    {
      "epoch": 0.02345215759849906,
      "grad_norm": 0.16828787326812744,
      "learning_rate": 4.884648471103465e-05,
      "loss": 1.3348,
      "step": 600
    },
    {
      "epoch": 0.02736085053158224,
      "grad_norm": 0.24634529650211334,
      "learning_rate": 4.8650973645108314e-05,
      "loss": 1.3343,
      "step": 700
    },
    {
      "epoch": 0.031269543464665414,
      "grad_norm": 0.5399248003959656,
      "learning_rate": 4.845546257918198e-05,
      "loss": 1.3287,
      "step": 800
    },
    {
      "epoch": 0.03517823639774859,
      "grad_norm": 0.5724157691001892,
      "learning_rate": 4.825995151325565e-05,
      "loss": 1.3236,
      "step": 900
    },
    {
      "epoch": 0.03908692933083177,
      "grad_norm": 0.5199714303016663,
      "learning_rate": 4.8064440447329324e-05,
      "loss": 1.3189,
      "step": 1000
    },
    {
      "epoch": 0.04299562226391495,
      "grad_norm": 0.30912989377975464,
      "learning_rate": 4.786892938140299e-05,
      "loss": 1.315,
      "step": 1100
    },
    {
      "epoch": 0.04690431519699812,
      "grad_norm": 0.37046098709106445,
      "learning_rate": 4.767341831547666e-05,
      "loss": 1.3151,
      "step": 1200
    },
    {
      "epoch": 0.0508130081300813,
      "grad_norm": 0.26445892453193665,
      "learning_rate": 4.747790724955033e-05,
      "loss": 1.3118,
      "step": 1300
    },
    {
      "epoch": 0.05472170106316448,
      "grad_norm": 0.3207770586013794,
      "learning_rate": 4.728239618362399e-05,
      "loss": 1.3087,
      "step": 1400
    },
    {
      "epoch": 0.05863039399624766,
      "grad_norm": 0.4711158573627472,
      "learning_rate": 4.7086885117697664e-05,
      "loss": 1.31,
      "step": 1500
    },
    {
      "epoch": 0.06253908692933083,
      "grad_norm": 0.524340808391571,
      "learning_rate": 4.689137405177133e-05,
      "loss": 1.3062,
      "step": 1600
    },
    {
      "epoch": 0.06644777986241401,
      "grad_norm": 0.3912469744682312,
      "learning_rate": 4.6695862985845e-05,
      "loss": 1.3078,
      "step": 1700
    },
    {
      "epoch": 0.07035647279549719,
      "grad_norm": 0.3625667691230774,
      "learning_rate": 4.6500351919918674e-05,
      "loss": 1.3039,
      "step": 1800
    },
    {
      "epoch": 0.07426516572858036,
      "grad_norm": 0.3897973299026489,
      "learning_rate": 4.630484085399234e-05,
      "loss": 1.3027,
      "step": 1900
    },
    {
      "epoch": 0.07817385866166354,
      "grad_norm": 0.30837342143058777,
      "learning_rate": 4.6109329788066005e-05,
      "loss": 1.3055,
      "step": 2000
    },
    {
      "epoch": 0.08208255159474671,
      "grad_norm": 0.3017924129962921,
      "learning_rate": 4.591381872213967e-05,
      "loss": 1.3021,
      "step": 2100
    },
    {
      "epoch": 0.0859912445278299,
      "grad_norm": 0.5234686136245728,
      "learning_rate": 4.571830765621334e-05,
      "loss": 1.3054,
      "step": 2200
    },
    {
      "epoch": 0.08989993746091307,
      "grad_norm": 0.3180347681045532,
      "learning_rate": 4.5522796590287015e-05,
      "loss": 1.3016,
      "step": 2300
    },
    {
      "epoch": 0.09380863039399624,
      "grad_norm": 0.22097885608673096,
      "learning_rate": 4.532728552436068e-05,
      "loss": 1.3014,
      "step": 2400
    },
    {
      "epoch": 0.09771732332707943,
      "grad_norm": 0.3503361642360687,
      "learning_rate": 4.513177445843435e-05,
      "loss": 1.3004,
      "step": 2500
    },
    {
      "epoch": 0.1016260162601626,
      "grad_norm": 0.3880802392959595,
      "learning_rate": 4.493626339250802e-05,
      "loss": 1.2992,
      "step": 2600
    },
    {
      "epoch": 0.10553470919324578,
      "grad_norm": 0.3632693886756897,
      "learning_rate": 4.474075232658168e-05,
      "loss": 1.3009,
      "step": 2700
    },
    {
      "epoch": 0.10944340212632896,
      "grad_norm": 0.4512663781642914,
      "learning_rate": 4.4545241260655355e-05,
      "loss": 1.2999,
      "step": 2800
    },
    {
      "epoch": 0.11335209505941213,
      "grad_norm": 0.3041514456272125,
      "learning_rate": 4.434973019472902e-05,
      "loss": 1.3007,
      "step": 2900
    },
    {
      "epoch": 0.11726078799249531,
      "grad_norm": 0.34578946232795715,
      "learning_rate": 4.415421912880269e-05,
      "loss": 1.2985,
      "step": 3000
    },
    {
      "epoch": 0.12116948092557848,
      "grad_norm": 0.2616026997566223,
      "learning_rate": 4.3958708062876365e-05,
      "loss": 1.2984,
      "step": 3100
    },
    {
      "epoch": 0.12507817385866166,
      "grad_norm": 0.253749817609787,
      "learning_rate": 4.376319699695003e-05,
      "loss": 1.2963,
      "step": 3200
    },
    {
      "epoch": 0.12898686679174484,
      "grad_norm": 0.24605727195739746,
      "learning_rate": 4.35676859310237e-05,
      "loss": 1.3005,
      "step": 3300
    },
    {
      "epoch": 0.13289555972482803,
      "grad_norm": 0.31458768248558044,
      "learning_rate": 4.337217486509736e-05,
      "loss": 1.3008,
      "step": 3400
    },
    {
      "epoch": 0.13680425265791119,
      "grad_norm": 0.23786158859729767,
      "learning_rate": 4.3176663799171034e-05,
      "loss": 1.2975,
      "step": 3500
    },
    {
      "epoch": 0.14071294559099437,
      "grad_norm": 0.3280108869075775,
      "learning_rate": 4.2981152733244706e-05,
      "loss": 1.2987,
      "step": 3600
    },
    {
      "epoch": 0.14462163852407756,
      "grad_norm": 0.25433337688446045,
      "learning_rate": 4.278564166731837e-05,
      "loss": 1.2972,
      "step": 3700
    },
    {
      "epoch": 0.1485303314571607,
      "grad_norm": 0.2792419493198395,
      "learning_rate": 4.2590130601392044e-05,
      "loss": 1.2944,
      "step": 3800
    },
    {
      "epoch": 0.1524390243902439,
      "grad_norm": 0.34164726734161377,
      "learning_rate": 4.239461953546571e-05,
      "loss": 1.298,
      "step": 3900
    },
    {
      "epoch": 0.15634771732332708,
      "grad_norm": 0.2886170744895935,
      "learning_rate": 4.219910846953938e-05,
      "loss": 1.2948,
      "step": 4000
    }
  ],
  "logging_steps": 100,
  "max_steps": 25584,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2809713917952000.0,
  "train_batch_size": 48,
  "trial_name": null,
  "trial_params": null
}