{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9988851727982163,
  "eval_steps": 500,
  "global_step": 224,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044593088071348944,
      "grad_norm": 1.3298993879930503,
      "learning_rate": 4.347826086956522e-06,
      "loss": 0.8838,
      "step": 10
    },
    {
      "epoch": 0.08918617614269789,
      "grad_norm": 0.7761384469317142,
      "learning_rate": 8.695652173913044e-06,
      "loss": 0.5643,
      "step": 20
    },
    {
      "epoch": 0.13377926421404682,
      "grad_norm": 0.7388880857506953,
      "learning_rate": 9.970104180843881e-06,
      "loss": 0.5064,
      "step": 30
    },
    {
      "epoch": 0.17837235228539577,
      "grad_norm": 0.724653222623146,
      "learning_rate": 9.8245356575224e-06,
      "loss": 0.4889,
      "step": 40
    },
    {
      "epoch": 0.2229654403567447,
      "grad_norm": 0.5993960298183308,
      "learning_rate": 9.561347763324484e-06,
      "loss": 0.4955,
      "step": 50
    },
    {
      "epoch": 0.26755852842809363,
      "grad_norm": 0.6058266855598197,
      "learning_rate": 9.186956865904004e-06,
      "loss": 0.4677,
      "step": 60
    },
    {
      "epoch": 0.31215161649944256,
      "grad_norm": 0.5660093789707933,
      "learning_rate": 8.710490397400007e-06,
      "loss": 0.4661,
      "step": 70
    },
    {
      "epoch": 0.35674470457079155,
      "grad_norm": 0.5427662696911218,
      "learning_rate": 8.143564332954426e-06,
      "loss": 0.4699,
      "step": 80
    },
    {
      "epoch": 0.4013377926421405,
      "grad_norm": 0.664420778167954,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.4601,
      "step": 90
    },
    {
      "epoch": 0.4459308807134894,
      "grad_norm": 0.5927500300049297,
      "learning_rate": 6.795487122343124e-06,
      "loss": 0.4591,
      "step": 100
    },
    {
      "epoch": 0.49052396878483834,
      "grad_norm": 0.49071930107510425,
      "learning_rate": 6.047201313830724e-06,
      "loss": 0.4568,
      "step": 110
    },
    {
      "epoch": 0.5351170568561873,
      "grad_norm": 0.5210863039113355,
      "learning_rate": 5.2733853468829295e-06,
      "loss": 0.4436,
      "step": 120
    },
    {
      "epoch": 0.5797101449275363,
      "grad_norm": 0.5959809226999278,
      "learning_rate": 4.492904404320942e-06,
      "loss": 0.4535,
      "step": 130
    },
    {
      "epoch": 0.6243032329988851,
      "grad_norm": 0.5211561870266984,
      "learning_rate": 3.7247861571916183e-06,
      "loss": 0.46,
      "step": 140
    },
    {
      "epoch": 0.6688963210702341,
      "grad_norm": 0.5179371520272593,
      "learning_rate": 2.9877568812237325e-06,
      "loss": 0.4489,
      "step": 150
    },
    {
      "epoch": 0.7134894091415831,
      "grad_norm": 0.5537839499631814,
      "learning_rate": 2.299784921126622e-06,
      "loss": 0.4638,
      "step": 160
    },
    {
      "epoch": 0.758082497212932,
      "grad_norm": 0.46909498015980716,
      "learning_rate": 1.677642632805892e-06,
      "loss": 0.4537,
      "step": 170
    },
    {
      "epoch": 0.802675585284281,
      "grad_norm": 0.4665216166420411,
      "learning_rate": 1.1364974830899438e-06,
      "loss": 0.4411,
      "step": 180
    },
    {
      "epoch": 0.8472686733556298,
      "grad_norm": 0.5078988510841556,
      "learning_rate": 6.895422757179682e-07,
      "loss": 0.4475,
      "step": 190
    },
    {
      "epoch": 0.8918617614269788,
      "grad_norm": 0.5090664794586085,
      "learning_rate": 3.4767351846456744e-07,
      "loss": 0.4483,
      "step": 200
    },
    {
      "epoch": 0.9364548494983278,
      "grad_norm": 0.46716721186961896,
      "learning_rate": 1.1922577262327374e-07,
      "loss": 0.459,
      "step": 210
    },
    {
      "epoch": 0.9810479375696767,
      "grad_norm": 0.47165862326587277,
      "learning_rate": 9.768461253920614e-09,
      "loss": 0.4392,
      "step": 220
    },
    {
      "epoch": 0.9988851727982163,
      "step": 224,
      "total_flos": 43988224573440.0,
      "train_loss": 0.4852701084954398,
      "train_runtime": 6118.0115,
      "train_samples_per_second": 3.518,
      "train_steps_per_second": 0.037
    }
  ],
  "logging_steps": 10,
  "max_steps": 224,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 43988224573440.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}