trainer_state.json

{
  "best_metric": 0.8141798973083496,
  "best_model_checkpoint": "./results/run-7a00201a/checkpoint-1275",
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 2550,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000784313725490196,
      "grad_norm": 0.6707581281661987,
      "learning_rate": 1.1116381679112563e-07,
      "loss": 1.0997,
      "step": 1
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 2.603963613510132,
      "learning_rate": 1.8728686524591818e-05,
      "loss": 0.8879,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_f1": 0.5636810375356157,
      "eval_loss": 0.8141798973083496,
      "eval_runtime": 19.9525,
      "eval_samples_per_second": 340.71,
      "eval_steps_per_second": 42.601,
      "step": 1275
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 5.432121276855469,
      "learning_rate": 6.645662960339033e-06,
      "loss": 0.7432,
      "step": 2000
    },
    {
      "epoch": 2.0,
      "eval_f1": 0.585795322825296,
      "eval_loss": 0.8491290807723999,
      "eval_runtime": 19.9821,
      "eval_samples_per_second": 340.205,
      "eval_steps_per_second": 42.538,
      "step": 2550
    }
  ],
  "logging_steps": 1000,
  "max_steps": 2550,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 6987202920860400.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 2.7790954197781407e-05,
    "num_train_epochs": 2,
    "per_device_train_batch_size": 16,
    "warmup_steps": 250,
    "weight_decay": 0.27440436845088456
  }
}