{
  "best_global_step": 150,
  "best_metric": 0.34326156973838806,
  "best_model_checkpoint": "/content/output/checkpoint-150",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.9156391620635986,
      "learning_rate": 1.7543859649122806e-05,
      "loss": 1.2171,
      "mean_token_accuracy": 0.7375583708286285,
      "num_tokens": 32413.0,
      "step": 10
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.815642774105072,
      "learning_rate": 3.508771929824561e-05,
      "loss": 0.9632,
      "mean_token_accuracy": 0.7655525088310242,
      "num_tokens": 64714.0,
      "step": 20
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.39404281973838806,
      "learning_rate": 5.2631578947368424e-05,
      "loss": 0.5951,
      "mean_token_accuracy": 0.8334747165441513,
      "num_tokens": 96352.0,
      "step": 30
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.41063451766967773,
      "learning_rate": 7.017543859649122e-05,
      "loss": 0.4305,
      "mean_token_accuracy": 0.8707121074199676,
      "num_tokens": 125717.0,
      "step": 40
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.3393928110599518,
      "learning_rate": 8.771929824561403e-05,
      "loss": 0.3874,
      "mean_token_accuracy": 0.8828857451677322,
      "num_tokens": 157446.0,
      "step": 50
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.2939395606517792,
      "learning_rate": 9.905660377358492e-05,
      "loss": 0.3613,
      "mean_token_accuracy": 0.8902347713708878,
      "num_tokens": 187947.0,
      "step": 60
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.30780646204948425,
      "learning_rate": 9.59119496855346e-05,
      "loss": 0.3545,
      "mean_token_accuracy": 0.8908359378576278,
      "num_tokens": 219528.0,
      "step": 70
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.35836032032966614,
      "eval_mean_token_accuracy": 0.8900894594192504,
      "eval_num_tokens": 234547.0,
      "eval_runtime": 47.5564,
      "eval_samples_per_second": 2.103,
      "eval_steps_per_second": 0.526,
      "step": 75
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.29364290833473206,
      "learning_rate": 9.276729559748428e-05,
      "loss": 0.3282,
      "mean_token_accuracy": 0.8956525355577469,
      "num_tokens": 249942.0,
      "step": 80
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.3256814479827881,
      "learning_rate": 8.962264150943397e-05,
      "loss": 0.3033,
      "mean_token_accuracy": 0.9027387470006942,
      "num_tokens": 280660.0,
      "step": 90
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.3860395848751068,
      "learning_rate": 8.647798742138365e-05,
      "loss": 0.3139,
      "mean_token_accuracy": 0.9029639422893524,
      "num_tokens": 312269.0,
      "step": 100
    },
    {
      "epoch": 1.4666666666666668,
      "grad_norm": 0.35767263174057007,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.3188,
      "mean_token_accuracy": 0.9010519236326218,
      "num_tokens": 343451.0,
      "step": 110
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.37099793553352356,
      "learning_rate": 8.018867924528302e-05,
      "loss": 0.3053,
      "mean_token_accuracy": 0.9043950855731964,
      "num_tokens": 375605.0,
      "step": 120
    },
    {
      "epoch": 1.7333333333333334,
      "grad_norm": 0.42942672967910767,
      "learning_rate": 7.704402515723272e-05,
      "loss": 0.2819,
      "mean_token_accuracy": 0.9102458357810974,
      "num_tokens": 407072.0,
      "step": 130
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 0.43511271476745605,
      "learning_rate": 7.389937106918238e-05,
      "loss": 0.2928,
      "mean_token_accuracy": 0.9080147057771683,
      "num_tokens": 439028.0,
      "step": 140
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4053526818752289,
      "learning_rate": 7.075471698113208e-05,
      "loss": 0.2847,
      "mean_token_accuracy": 0.9118992000818252,
      "num_tokens": 469094.0,
      "step": 150
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.34326156973838806,
      "eval_mean_token_accuracy": 0.8937170529365539,
      "eval_num_tokens": 469094.0,
      "eval_runtime": 47.6074,
      "eval_samples_per_second": 2.101,
      "eval_steps_per_second": 0.525,
      "step": 150
    }
  ],
  "logging_steps": 10,
  "max_steps": 375,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6303037473857536e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}