checkpoint-2000/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.8461538461538463,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 55.766353607177734,
      "learning_rate": 7.600961538461539e-06,
      "loss": -103.214,
      "step": 500
    },
    {
      "epoch": 1.9230769230769231,
      "grad_norm": 112.92929077148438,
      "learning_rate": 5.197115384615385e-06,
      "loss": -151.8486,
      "step": 1000
    },
    {
      "epoch": 2.8846153846153846,
      "grad_norm": 88.40676879882812,
      "learning_rate": 2.7932692307692313e-06,
      "loss": -155.1752,
      "step": 1500
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 71.34072875976562,
      "learning_rate": 3.8942307692307696e-07,
      "loss": -157.0243,
      "step": 2000
    }
  ],
  "logging_steps": 500,
  "max_steps": 2080,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}