trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 6365,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3927729772191673,
      "grad_norm": 2.493880033493042,
      "learning_rate": 4.6072270227808326e-05,
      "loss": 0.7773,
      "step": 500
    },
    {
      "epoch": 0.7855459544383346,
      "grad_norm": 3.362963914871216,
      "learning_rate": 4.2144540455616656e-05,
      "loss": 0.6407,
      "step": 1000
    },
    {
      "epoch": 1.178318931657502,
      "grad_norm": 3.4124033451080322,
      "learning_rate": 3.821681068342498e-05,
      "loss": 0.5413,
      "step": 1500
    },
    {
      "epoch": 1.5710919088766693,
      "grad_norm": 5.418175220489502,
      "learning_rate": 3.42890809112333e-05,
      "loss": 0.4516,
      "step": 2000
    },
    {
      "epoch": 1.9638648860958368,
      "grad_norm": 4.3173418045043945,
      "learning_rate": 3.0361351139041634e-05,
      "loss": 0.442,
      "step": 2500
    },
    {
      "epoch": 2.356637863315004,
      "grad_norm": 4.252607345581055,
      "learning_rate": 2.6433621366849964e-05,
      "loss": 0.3087,
      "step": 3000
    },
    {
      "epoch": 2.7494108405341713,
      "grad_norm": 4.939857482910156,
      "learning_rate": 2.2505891594658287e-05,
      "loss": 0.2938,
      "step": 3500
    },
    {
      "epoch": 3.1421838177533385,
      "grad_norm": 3.5636911392211914,
      "learning_rate": 1.8578161822466618e-05,
      "loss": 0.2533,
      "step": 4000
    },
    {
      "epoch": 3.534956794972506,
      "grad_norm": 4.615169048309326,
      "learning_rate": 1.4650432050274943e-05,
      "loss": 0.1909,
      "step": 4500
    },
    {
      "epoch": 3.927729772191673,
      "grad_norm": 4.99422025680542,
      "learning_rate": 1.0722702278083268e-05,
      "loss": 0.1856,
      "step": 5000
    },
    {
      "epoch": 4.32050274941084,
      "grad_norm": 4.294362545013428,
      "learning_rate": 6.794972505891594e-06,
      "loss": 0.1385,
      "step": 5500
    },
    {
      "epoch": 4.713275726630008,
      "grad_norm": 5.682995319366455,
      "learning_rate": 2.8672427336999217e-06,
      "loss": 0.1274,
      "step": 6000
    }
  ],
  "logging_steps": 500,
  "max_steps": 6365,
  "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": 2.69683595364672e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}