trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.4210526315789473,
  "eval_steps": 500,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 100.67807006835938,
      "learning_rate": 0.0003,
      "loss": 93.814,
      "step": 1
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 52.641910552978516,
      "learning_rate": 0.0003,
      "loss": 57.6198,
      "step": 2
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 43.552066802978516,
      "learning_rate": 0.0003,
      "loss": 43.7589,
      "step": 3
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 21.531784057617188,
      "learning_rate": 0.0003,
      "loss": 35.7938,
      "step": 4
    },
    {
      "epoch": 1.0,
      "grad_norm": 12.112222671508789,
      "learning_rate": 0.0003,
      "loss": 24.003,
      "step": 5
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 16.41153907775879,
      "learning_rate": 0.0003,
      "loss": 28.6775,
      "step": 6
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 8.535775184631348,
      "learning_rate": 0.0003,
      "loss": 26.4559,
      "step": 7
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 10.890907287597656,
      "learning_rate": 0.0003,
      "loss": 25.4337,
      "step": 8
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 9.562114715576172,
      "learning_rate": 0.0003,
      "loss": 24.6052,
      "step": 9
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.177497386932373,
      "learning_rate": 0.0003,
      "loss": 17.8112,
      "step": 10
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 12.433683395385742,
      "learning_rate": 0.0003,
      "loss": 22.2664,
      "step": 11
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 7.592349052429199,
      "learning_rate": 0.0003,
      "loss": 21.7592,
      "step": 12
    },
    {
      "epoch": 2.4210526315789473,
      "step": 12,
      "total_flos": 0.0,
      "train_loss": 35.166557470957436,
      "train_runtime": 114.9604,
      "train_samples_per_second": 3.914,
      "train_steps_per_second": 0.104
    }
  ],
  "logging_steps": 1,
  "max_steps": 12,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}