checkpoint-495/trainer_state.json

{
  "best_metric": NaN,
  "best_model_checkpoint": "autotrain-uug06-oi4rk/checkpoint-495",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 495,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.048484848484848485,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.09696969696969697,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 48
    },
    {
      "epoch": 0.14545454545454545,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 72
    },
    {
      "epoch": 0.19393939393939394,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 96
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 120
    },
    {
      "epoch": 0.2909090909090909,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 144
    },
    {
      "epoch": 0.3393939393939394,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 168
    },
    {
      "epoch": 0.3878787878787879,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 192
    },
    {
      "epoch": 0.43636363636363634,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 216
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 240
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 264
    },
    {
      "epoch": 0.5818181818181818,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 288
    },
    {
      "epoch": 0.6303030303030303,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 312
    },
    {
      "epoch": 0.6787878787878788,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 336
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 360
    },
    {
      "epoch": 0.7757575757575758,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 384
    },
    {
      "epoch": 0.8242424242424242,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 408
    },
    {
      "epoch": 0.8727272727272727,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 432
    },
    {
      "epoch": 0.9212121212121213,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 456
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 480
    },
    {
      "epoch": 1.0,
      "eval_gen_len": 18.9939,
      "eval_loss": NaN,
      "eval_rouge1": 29.1474,
      "eval_rouge2": 9.4486,
      "eval_rougeL": 28.7519,
      "eval_rougeLsum": 28.735,
      "eval_runtime": 54.8909,
      "eval_samples_per_second": 18.036,
      "eval_steps_per_second": 1.13,
      "step": 495
    }
  ],
  "logging_steps": 24,
  "max_steps": 2475,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3008962942451712.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}