trainer_state.json

{
  "best_global_step": 716,
  "best_metric": 0.20679529011249542,
  "best_model_checkpoint": "./sentiment_model/checkpoint-716",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1790,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.934301958307012,
      "eval_f1": 0.9310534001387455,
      "eval_loss": 0.2211858481168747,
      "eval_runtime": 12.4736,
      "eval_samples_per_second": 126.908,
      "eval_steps_per_second": 4.008,
      "step": 358
    },
    {
      "epoch": 1.3966480446927374,
      "grad_norm": 7.75230598449707,
      "learning_rate": 1.4424581005586593e-05,
      "loss": 0.2821,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9418825015792799,
      "eval_f1": 0.940750568688658,
      "eval_loss": 0.20679529011249542,
      "eval_runtime": 12.5058,
      "eval_samples_per_second": 126.581,
      "eval_steps_per_second": 3.998,
      "step": 716
    },
    {
      "epoch": 2.793296089385475,
      "grad_norm": 3.6269500255584717,
      "learning_rate": 8.837988826815643e-06,
      "loss": 0.1522,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9444093493367025,
      "eval_f1": 0.9414769686480463,
      "eval_loss": 0.21175681054592133,
      "eval_runtime": 12.5136,
      "eval_samples_per_second": 126.502,
      "eval_steps_per_second": 3.996,
      "step": 1074
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9456727732154138,
      "eval_f1": 0.943473191123415,
      "eval_loss": 0.23586392402648926,
      "eval_runtime": 12.4727,
      "eval_samples_per_second": 126.917,
      "eval_steps_per_second": 4.009,
      "step": 1432
    },
    {
      "epoch": 4.189944134078212,
      "grad_norm": 6.93758487701416,
      "learning_rate": 3.251396648044693e-06,
      "loss": 0.1029,
      "step": 1500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9456727732154138,
      "eval_f1": 0.9431961768989716,
      "eval_loss": 0.2388758659362793,
      "eval_runtime": 12.517,
      "eval_samples_per_second": 126.468,
      "eval_steps_per_second": 3.995,
      "step": 1790
    }
  ],
  "logging_steps": 500,
  "max_steps": 1790,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7515834777400320.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}