{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.982857142857143,
  "eval_steps": 500,
  "global_step": 215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 1.4335445165634155,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.2099,
      "step": 10
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": 1.0458570718765259,
      "learning_rate": 4.0909090909090915e-05,
      "loss": 0.0488,
      "step": 20
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 2.0838749408721924,
      "learning_rate": 4.988086142592657e-05,
      "loss": 0.0793,
      "step": 30
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": 0.2897286117076874,
      "learning_rate": 4.9156900467474784e-05,
      "loss": 0.0443,
      "step": 40
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.42701688408851624,
      "learning_rate": 4.779428322078716e-05,
      "loss": 0.0483,
      "step": 50
    },
    {
      "epoch": 1.3885714285714286,
      "grad_norm": 1.3219645023345947,
      "learning_rate": 4.582903434367222e-05,
      "loss": 0.0234,
      "step": 60
    },
    {
      "epoch": 1.617142857142857,
      "grad_norm": 0.7189111113548279,
      "learning_rate": 4.3313110773031186e-05,
      "loss": 0.0351,
      "step": 70
    },
    {
      "epoch": 1.8457142857142856,
      "grad_norm": 0.19501705467700958,
      "learning_rate": 4.031302809563292e-05,
      "loss": 0.0282,
      "step": 80
    },
    {
      "epoch": 2.0914285714285716,
      "grad_norm": 0.47736552357673645,
      "learning_rate": 3.6908102019621666e-05,
      "loss": 0.0241,
      "step": 90
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.5043835043907166,
      "learning_rate": 3.3188351438453996e-05,
      "loss": 0.0127,
      "step": 100
    },
    {
      "epoch": 2.5485714285714285,
      "grad_norm": 0.4290105402469635,
      "learning_rate": 2.925211852572667e-05,
      "loss": 0.0146,
      "step": 110
    },
    {
      "epoch": 2.777142857142857,
      "grad_norm": 0.4446091055870056,
      "learning_rate": 2.5203468780449323e-05,
      "loss": 0.0115,
      "step": 120
    },
    {
      "epoch": 3.0228571428571427,
      "grad_norm": 0.5306875109672546,
      "learning_rate": 2.1149439759951277e-05,
      "loss": 0.0113,
      "step": 130
    },
    {
      "epoch": 3.2514285714285713,
      "grad_norm": 0.09367158263921738,
      "learning_rate": 1.719721123798362e-05,
      "loss": 0.008,
      "step": 140
    },
    {
      "epoch": 3.48,
      "grad_norm": 0.40400221943855286,
      "learning_rate": 1.3451271602926246e-05,
      "loss": 0.003,
      "step": 150
    },
    {
      "epoch": 3.7085714285714286,
      "grad_norm": 0.9837874174118042,
      "learning_rate": 1.0010655410412744e-05,
      "loss": 0.0042,
      "step": 160
    },
    {
      "epoch": 3.9371428571428573,
      "grad_norm": 1.6841741800308228,
      "learning_rate": 6.966325123517109e-06,
      "loss": 0.0098,
      "step": 170
    },
    {
      "epoch": 4.182857142857143,
      "grad_norm": 1.109780192375183,
      "learning_rate": 4.398766261638271e-06,
      "loss": 0.0042,
      "step": 180
    },
    {
      "epoch": 4.411428571428571,
      "grad_norm": 0.17733371257781982,
      "learning_rate": 2.375859537153302e-06,
      "loss": 0.0036,
      "step": 190
    },
    {
      "epoch": 4.64,
      "grad_norm": 0.039348188787698746,
      "learning_rate": 9.510862359517814e-07,
      "loss": 0.0007,
      "step": 200
    },
    {
      "epoch": 4.868571428571428,
      "grad_norm": 0.06708058714866638,
      "learning_rate": 1.6211428771484295e-07,
      "loss": 0.0005,
      "step": 210
    },
    {
      "epoch": 4.982857142857143,
      "step": 215,
      "total_flos": 6.16643394722857e+16,
      "train_loss": 0.029113658708195354,
      "train_runtime": 1637.6537,
      "train_samples_per_second": 1.069,
      "train_steps_per_second": 0.131
    }
  ],
  "logging_steps": 10,
  "max_steps": 215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.16643394722857e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}