trainer_state.json

{
  "best_metric": 2.3808858394622803,
  "best_model_checkpoint": "./drive/MyDrive/Models/LazDEF_ESM/checkpoint-2441",
  "epoch": 0.999795207864018,
  "eval_steps": 500,
  "global_step": 2441,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2047921359819783,
      "grad_norm": 0.6516537070274353,
      "learning_rate": 2.385497746825072e-06,
      "loss": 2.4431,
      "step": 500
    },
    {
      "epoch": 0.4095842719639566,
      "grad_norm": 0.6351372599601746,
      "learning_rate": 1.7709954936501437e-06,
      "loss": 2.3986,
      "step": 1000
    },
    {
      "epoch": 0.6143764079459348,
      "grad_norm": 0.7128742337226868,
      "learning_rate": 1.1564932404752152e-06,
      "loss": 2.3949,
      "step": 1500
    },
    {
      "epoch": 0.8191685439279132,
      "grad_norm": 0.5619348287582397,
      "learning_rate": 5.419909873002868e-07,
      "loss": 2.3908,
      "step": 2000
    },
    {
      "epoch": 0.999795207864018,
      "eval_loss": 2.3808858394622803,
      "eval_runtime": 53.5019,
      "eval_samples_per_second": 934.547,
      "eval_steps_per_second": 3.663,
      "step": 2441
    }
  ],
  "logging_steps": 500,
  "max_steps": 2441,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 7.322542733601792e+16,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}