{
  "best_metric": 0.19941402971744537,
  "best_model_checkpoint": "/kaggle/working/trainer/checkpoint-590",
  "epoch": 15.0,
  "eval_steps": 500,
  "global_step": 1770,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.8408871745419484e-05,
      "loss": 2.902,
      "step": 118
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.314755380153656,
      "eval_runtime": 19.7216,
      "eval_samples_per_second": 1.318,
      "eval_steps_per_second": 0.659,
      "step": 118
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.563645130183221e-05,
      "loss": 0.3101,
      "step": 236
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8408044576644897,
      "eval_runtime": 19.716,
      "eval_samples_per_second": 1.319,
      "eval_steps_per_second": 0.659,
      "step": 236
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.2960462873674064e-05,
      "loss": 1.0237,
      "step": 354
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.23988741636276245,
      "eval_runtime": 19.7335,
      "eval_samples_per_second": 1.318,
      "eval_steps_per_second": 0.659,
      "step": 354
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.011571841851495e-05,
      "loss": 0.3245,
      "step": 472
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.20902396738529205,
      "eval_runtime": 19.6909,
      "eval_samples_per_second": 1.32,
      "eval_steps_per_second": 0.66,
      "step": 472
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.7270973963355835e-05,
      "loss": 0.1679,
      "step": 590
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.19941402971744537,
      "eval_runtime": 19.7266,
      "eval_samples_per_second": 1.318,
      "eval_steps_per_second": 0.659,
      "step": 590
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.442622950819672e-05,
      "loss": 0.1973,
      "step": 708
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.21409890055656433,
      "eval_runtime": 19.7603,
      "eval_samples_per_second": 1.316,
      "eval_steps_per_second": 0.658,
      "step": 708
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.158148505303761e-05,
      "loss": 0.2323,
      "step": 826
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.2766213119029999,
      "eval_runtime": 19.7249,
      "eval_samples_per_second": 1.318,
      "eval_steps_per_second": 0.659,
      "step": 826
    },
    {
      "epoch": 8.0,
      "learning_rate": 2.87367405978785e-05,
      "loss": 0.2064,
      "step": 944
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.20961548388004303,
      "eval_runtime": 19.7074,
      "eval_samples_per_second": 1.319,
      "eval_steps_per_second": 0.66,
      "step": 944
    },
    {
      "epoch": 9.0,
      "learning_rate": 2.589199614271938e-05,
      "loss": 0.1943,
      "step": 1062
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.2783980965614319,
      "eval_runtime": 19.7328,
      "eval_samples_per_second": 1.318,
      "eval_steps_per_second": 0.659,
      "step": 1062
    },
    {
      "epoch": 10.0,
      "learning_rate": 2.304725168756027e-05,
      "loss": 0.2605,
      "step": 1180
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.28063008189201355,
      "eval_runtime": 19.721,
      "eval_samples_per_second": 1.318,
      "eval_steps_per_second": 0.659,
      "step": 1180
    },
    {
      "epoch": 11.0,
      "learning_rate": 2.020250723240116e-05,
      "loss": 0.2797,
      "step": 1298
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.7226824164390564,
      "eval_runtime": 19.7144,
      "eval_samples_per_second": 1.319,
      "eval_steps_per_second": 0.659,
      "step": 1298
    },
    {
      "epoch": 12.0,
      "learning_rate": 1.7357762777242045e-05,
      "loss": 0.5877,
      "step": 1416
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.3170361816883087,
      "eval_runtime": 19.7302,
      "eval_samples_per_second": 1.318,
      "eval_steps_per_second": 0.659,
      "step": 1416
    },
    {
      "epoch": 13.0,
      "learning_rate": 1.4513018322082934e-05,
      "loss": 0.3059,
      "step": 1534
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.24836881458759308,
      "eval_runtime": 19.6883,
      "eval_samples_per_second": 1.321,
      "eval_steps_per_second": 0.66,
      "step": 1534
    },
    {
      "epoch": 14.0,
      "learning_rate": 1.166827386692382e-05,
      "loss": 0.1948,
      "step": 1652
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.25250551104545593,
      "eval_runtime": 19.7516,
      "eval_samples_per_second": 1.316,
      "eval_steps_per_second": 0.658,
      "step": 1652
    },
    {
      "epoch": 15.0,
      "learning_rate": 8.823529411764707e-06,
      "loss": 0.1966,
      "step": 1770
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.21671946346759796,
      "eval_runtime": 19.7256,
      "eval_samples_per_second": 1.318,
      "eval_steps_per_second": 0.659,
      "step": 1770
    }
  ],
  "logging_steps": 500,
  "max_steps": 2124,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 18,
  "save_steps": 500,
  "total_flos": 3.242923135598592e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}