{
  "best_metric": 19.45676397235889,
  "best_model_checkpoint": "./routed_longformer_docmt/checkpoint-786",
  "epoch": 0.9993642720915448,
  "eval_steps": 500,
  "global_step": 786,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12714558169103624,
      "grad_norm": 2.7216010093688965,
      "learning_rate": 2.875318066157761e-05,
      "loss": 3.5051,
      "step": 100
    },
    {
      "epoch": 0.25429116338207247,
      "grad_norm": 2.2804791927337646,
      "learning_rate": 2.7480916030534352e-05,
      "loss": 2.6407,
      "step": 200
    },
    {
      "epoch": 0.3814367450731087,
      "grad_norm": 2.807426691055298,
      "learning_rate": 2.6208651399491097e-05,
      "loss": 2.3397,
      "step": 300
    },
    {
      "epoch": 0.5085823267641449,
      "grad_norm": 1.993668556213379,
      "learning_rate": 2.4936386768447838e-05,
      "loss": 2.1398,
      "step": 400
    },
    {
      "epoch": 0.6357279084551812,
      "grad_norm": 2.3265788555145264,
      "learning_rate": 2.3664122137404583e-05,
      "loss": 2.0065,
      "step": 500
    },
    {
      "epoch": 0.7628734901462174,
      "grad_norm": 1.7298423051834106,
      "learning_rate": 2.2391857506361324e-05,
      "loss": 1.8887,
      "step": 600
    },
    {
      "epoch": 0.8900190718372537,
      "grad_norm": 2.18813419342041,
      "learning_rate": 2.1119592875318066e-05,
      "loss": 1.8264,
      "step": 700
    },
    {
      "epoch": 0.9993642720915448,
      "eval_bleu": 19.45676397235889,
      "eval_chrf": 53.07001767638457,
      "eval_comet": 0.4521310674039932,
      "eval_loss": 1.5774508714675903,
      "eval_runtime": 710.5738,
      "eval_samples_per_second": 1.967,
      "eval_steps_per_second": 0.246,
      "step": 786
    }
  ],
  "logging_steps": 100,
  "max_steps": 2358,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}