{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9935483870967743,
  "eval_steps": 500,
  "global_step": 348,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08602150537634409,
      "grad_norm": 0.8645952939987183,
      "learning_rate": 2.9938918800982563e-05,
      "loss": 0.1833,
      "step": 10
    },
    {
      "epoch": 0.17204301075268819,
      "grad_norm": 0.5983677506446838,
      "learning_rate": 2.975617265898004e-05,
      "loss": 0.0724,
      "step": 20
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 0.7896360158920288,
      "learning_rate": 2.9453249887788343e-05,
      "loss": 0.0594,
      "step": 30
    },
    {
      "epoch": 0.34408602150537637,
      "grad_norm": 0.6655340790748596,
      "learning_rate": 2.9032617538884018e-05,
      "loss": 0.0547,
      "step": 40
    },
    {
      "epoch": 0.43010752688172044,
      "grad_norm": 0.9506097435951233,
      "learning_rate": 2.84977013093626e-05,
      "loss": 0.0509,
      "step": 50
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 0.5851807594299316,
      "learning_rate": 2.7852857642513838e-05,
      "loss": 0.053,
      "step": 60
    },
    {
      "epoch": 0.6021505376344086,
      "grad_norm": 0.7461451888084412,
      "learning_rate": 2.7103338248251055e-05,
      "loss": 0.0493,
      "step": 70
    },
    {
      "epoch": 0.6881720430107527,
      "grad_norm": 0.7790912389755249,
      "learning_rate": 2.6255247332346036e-05,
      "loss": 0.0471,
      "step": 80
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 0.8489375114440918,
      "learning_rate": 2.531549188280135e-05,
      "loss": 0.0477,
      "step": 90
    },
    {
      "epoch": 0.8602150537634409,
      "grad_norm": 0.504687488079071,
      "learning_rate": 2.4291725418235848e-05,
      "loss": 0.04,
      "step": 100
    },
    {
      "epoch": 0.946236559139785,
      "grad_norm": 0.6806123852729797,
      "learning_rate": 2.3192285656405456e-05,
      "loss": 0.0358,
      "step": 110
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": 0.8986548185348511,
      "learning_rate": 2.2026126610496852e-05,
      "loss": 0.0426,
      "step": 120
    },
    {
      "epoch": 1.118279569892473,
      "grad_norm": 0.6983468532562256,
      "learning_rate": 2.0802745666212592e-05,
      "loss": 0.0329,
      "step": 130
    },
    {
      "epoch": 1.2043010752688172,
      "grad_norm": 0.6994673609733582,
      "learning_rate": 1.953210623354359e-05,
      "loss": 0.0346,
      "step": 140
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 0.6783556342124939,
      "learning_rate": 1.8224556603165363e-05,
      "loss": 0.0353,
      "step": 150
    },
    {
      "epoch": 1.3763440860215055,
      "grad_norm": 0.6973330974578857,
      "learning_rate": 1.689074566830434e-05,
      "loss": 0.0371,
      "step": 160
    },
    {
      "epoch": 1.4623655913978495,
      "grad_norm": 0.9516863822937012,
      "learning_rate": 1.5541536198449044e-05,
      "loss": 0.0339,
      "step": 170
    },
    {
      "epoch": 1.5483870967741935,
      "grad_norm": 0.551609218120575,
      "learning_rate": 1.4187916371218739e-05,
      "loss": 0.0327,
      "step": 180
    },
    {
      "epoch": 1.6344086021505375,
      "grad_norm": 0.5641576647758484,
      "learning_rate": 1.2840910282888211e-05,
      "loss": 0.031,
      "step": 190
    },
    {
      "epoch": 1.7204301075268817,
      "grad_norm": 0.7011380195617676,
      "learning_rate": 1.1511488166385349e-05,
      "loss": 0.0329,
      "step": 200
    },
    {
      "epoch": 1.8064516129032258,
      "grad_norm": 0.7577546238899231,
      "learning_rate": 1.0210477047960303e-05,
      "loss": 0.0329,
      "step": 210
    },
    {
      "epoch": 1.89247311827957,
      "grad_norm": 0.5536512136459351,
      "learning_rate": 8.948472570152874e-06,
      "loss": 0.0331,
      "step": 220
    },
    {
      "epoch": 1.978494623655914,
      "grad_norm": 0.9683991074562073,
      "learning_rate": 7.735752699185711e-06,
      "loss": 0.0324,
      "step": 230
    },
    {
      "epoch": 2.064516129032258,
      "grad_norm": 0.4118397831916809,
      "learning_rate": 6.582194019564266e-06,
      "loss": 0.0246,
      "step": 240
    },
    {
      "epoch": 2.150537634408602,
      "grad_norm": 0.7641584277153015,
      "learning_rate": 5.497191297593647e-06,
      "loss": 0.0276,
      "step": 250
    },
    {
      "epoch": 2.236559139784946,
      "grad_norm": 0.796150803565979,
      "learning_rate": 4.4895809688998655e-06,
      "loss": 0.0258,
      "step": 260
    },
    {
      "epoch": 2.3225806451612905,
      "grad_norm": 0.4853476583957672,
      "learning_rate": 3.567569173085455e-06,
      "loss": 0.0221,
      "step": 270
    },
    {
      "epoch": 2.4086021505376345,
      "grad_norm": 1.066999912261963,
      "learning_rate": 2.7386649216166233e-06,
      "loss": 0.0232,
      "step": 280
    },
    {
      "epoch": 2.4946236559139785,
      "grad_norm": 1.0369054079055786,
      "learning_rate": 2.0096189432334194e-06,
      "loss": 0.0254,
      "step": 290
    },
    {
      "epoch": 2.5806451612903225,
      "grad_norm": 0.5320150852203369,
      "learning_rate": 1.3863687049356465e-06,
      "loss": 0.0249,
      "step": 300
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.8379970192909241,
      "learning_rate": 8.7399005630238e-07,
      "loss": 0.0261,
      "step": 310
    },
    {
      "epoch": 2.752688172043011,
      "grad_norm": 0.660368800163269,
      "learning_rate": 4.766558909615504e-07,
      "loss": 0.0222,
      "step": 320
    },
    {
      "epoch": 2.838709677419355,
      "grad_norm": 0.7505407929420471,
      "learning_rate": 1.9760216187710788e-07,
      "loss": 0.027,
      "step": 330
    },
    {
      "epoch": 2.924731182795699,
      "grad_norm": 0.6225216388702393,
      "learning_rate": 3.910152723075322e-08,
      "loss": 0.0248,
      "step": 340
    },
    {
      "epoch": 2.9935483870967743,
      "step": 348,
      "total_flos": 1.642592412987556e+17,
      "train_loss": 0.04012600602260951,
      "train_runtime": 3577.9913,
      "train_samples_per_second": 3.116,
      "train_steps_per_second": 0.097
    }
  ],
  "logging_steps": 10,
  "max_steps": 348,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 1.642592412987556e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}