{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.98876404494382,
  "eval_steps": 500,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.149812734082397,
      "grad_norm": 0.4184725571262891,
      "learning_rate": 1.1764705882352942e-05,
      "loss": 2.3268,
      "step": 10
    },
    {
      "epoch": 0.299625468164794,
      "grad_norm": 0.12556571666759556,
      "learning_rate": 1.9995466947279753e-05,
      "loss": 2.0458,
      "step": 20
    },
    {
      "epoch": 0.449438202247191,
      "grad_norm": 0.1032725365344677,
      "learning_rate": 1.9914993620144055e-05,
      "loss": 2.007,
      "step": 30
    },
    {
      "epoch": 0.599250936329588,
      "grad_norm": 0.10112743125926799,
      "learning_rate": 1.9734718376564386e-05,
      "loss": 1.9764,
      "step": 40
    },
    {
      "epoch": 0.7490636704119851,
      "grad_norm": 0.09677639814846642,
      "learning_rate": 1.945645582333587e-05,
      "loss": 1.9402,
      "step": 50
    },
    {
      "epoch": 0.898876404494382,
      "grad_norm": 0.09349049831355143,
      "learning_rate": 1.9083006883701688e-05,
      "loss": 1.9291,
      "step": 60
    },
    {
      "epoch": 1.0599250936329587,
      "grad_norm": 0.09530169707212147,
      "learning_rate": 1.8618130603940386e-05,
      "loss": 2.087,
      "step": 70
    },
    {
      "epoch": 1.2097378277153559,
      "grad_norm": 0.0960045045097405,
      "learning_rate": 1.806650631571943e-05,
      "loss": 1.8295,
      "step": 80
    },
    {
      "epoch": 1.3595505617977528,
      "grad_norm": 0.09889278672822154,
      "learning_rate": 1.7433686535079736e-05,
      "loss": 1.8156,
      "step": 90
    },
    {
      "epoch": 1.5093632958801497,
      "grad_norm": 0.10298966494546878,
      "learning_rate": 1.672604107215848e-05,
      "loss": 1.7925,
      "step": 100
    },
    {
      "epoch": 1.6591760299625467,
      "grad_norm": 0.09784827661958026,
      "learning_rate": 1.595069291422807e-05,
      "loss": 1.7833,
      "step": 110
    },
    {
      "epoch": 1.8089887640449438,
      "grad_norm": 0.09878958227415378,
      "learning_rate": 1.5115446527437193e-05,
      "loss": 1.8037,
      "step": 120
    },
    {
      "epoch": 1.958801498127341,
      "grad_norm": 0.09398266158095946,
      "learning_rate": 1.4228709298950998e-05,
      "loss": 1.8121,
      "step": 130
    },
    {
      "epoch": 2.1198501872659175,
      "grad_norm": 0.10366869896633626,
      "learning_rate": 1.3299406910234917e-05,
      "loss": 1.8657,
      "step": 140
    },
    {
      "epoch": 2.2696629213483144,
      "grad_norm": 0.10727907000563858,
      "learning_rate": 1.2336893493313946e-05,
      "loss": 1.6461,
      "step": 150
    },
    {
      "epoch": 2.4194756554307117,
      "grad_norm": 0.10569188044597796,
      "learning_rate": 1.1350857474352734e-05,
      "loss": 1.6554,
      "step": 160
    },
    {
      "epoch": 2.5692883895131087,
      "grad_norm": 0.1057429048746636,
      "learning_rate": 1.035122405231209e-05,
      "loss": 1.6432,
      "step": 170
    },
    {
      "epoch": 2.7191011235955056,
      "grad_norm": 0.1033332315090373,
      "learning_rate": 9.348055294308074e-06,
      "loss": 1.6493,
      "step": 180
    },
    {
      "epoch": 2.8689138576779025,
      "grad_norm": 0.10863505508600654,
      "learning_rate": 8.351448853289448e-06,
      "loss": 1.6523,
      "step": 190
    },
    {
      "epoch": 3.0299625468164795,
      "grad_norm": 0.11011780389030625,
      "learning_rate": 7.371436327516854e-06,
      "loss": 1.8007,
      "step": 200
    },
    {
      "epoch": 3.1797752808988764,
      "grad_norm": 0.11069082588928542,
      "learning_rate": 6.417882284932373e-06,
      "loss": 1.5238,
      "step": 210
    },
    {
      "epoch": 3.3295880149812733,
      "grad_norm": 0.12073113842302774,
      "learning_rate": 5.5003849688157075e-06,
      "loss": 1.5296,
      "step": 220
    },
    {
      "epoch": 3.4794007490636703,
      "grad_norm": 0.11345698404737706,
      "learning_rate": 4.628179684199685e-06,
      "loss": 1.5378,
      "step": 230
    },
    {
      "epoch": 3.629213483146067,
      "grad_norm": 0.12200859514126239,
      "learning_rate": 3.81004583753399e-06,
      "loss": 1.534,
      "step": 240
    },
    {
      "epoch": 3.7790262172284645,
      "grad_norm": 0.11587613626094642,
      "learning_rate": 3.0542185653132216e-06,
      "loss": 1.5323,
      "step": 250
    },
    {
      "epoch": 3.9288389513108615,
      "grad_norm": 0.11334084939433413,
      "learning_rate": 2.3683058411940563e-06,
      "loss": 1.5183,
      "step": 260
    },
    {
      "epoch": 4.089887640449438,
      "grad_norm": 0.11608541820756209,
      "learning_rate": 1.75921189598118e-06,
      "loss": 1.652,
      "step": 270
    },
    {
      "epoch": 4.239700374531835,
      "grad_norm": 0.11284395726345454,
      "learning_rate": 1.2330677213177034e-06,
      "loss": 1.4885,
      "step": 280
    },
    {
      "epoch": 4.389513108614232,
      "grad_norm": 0.11997412903993453,
      "learning_rate": 7.951693566131325e-07,
      "loss": 1.467,
      "step": 290
    },
    {
      "epoch": 4.539325842696629,
      "grad_norm": 0.11946622289642324,
      "learning_rate": 4.499245803975927e-07,
      "loss": 1.4361,
      "step": 300
    },
    {
      "epoch": 4.689138576779026,
      "grad_norm": 0.12489155725139654,
      "learning_rate": 2.00808542694233e-07,
      "loss": 1.4571,
      "step": 310
    },
    {
      "epoch": 4.8389513108614235,
      "grad_norm": 0.11948986877619222,
      "learning_rate": 5.032878500355498e-08,
      "loss": 1.48,
      "step": 320
    },
    {
      "epoch": 4.98876404494382,
      "grad_norm": 0.12128900926884226,
      "learning_rate": 0.0,
      "loss": 1.4623,
      "step": 330
    },
    {
      "epoch": 4.98876404494382,
      "step": 330,
      "total_flos": 2146936553472.0,
      "train_loss": 1.7175929474108147,
      "train_runtime": 1171.7731,
      "train_samples_per_second": 36.402,
      "train_steps_per_second": 0.282
    }
  ],
  "logging_steps": 10,
  "max_steps": 330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2146936553472.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}