last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0005176988287064001,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 5.1769882870640004e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 5.1769882870640004e-05,
      "eval_loss": NaN,
      "eval_runtime": 350.3903,
      "eval_samples_per_second": 23.214,
      "eval_steps_per_second": 11.607,
      "step": 1
    },
    {
      "epoch": 0.00010353976574128001,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00015530964861192002,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00015530964861192002,
      "eval_loss": NaN,
      "eval_runtime": 348.998,
      "eval_samples_per_second": 23.307,
      "eval_steps_per_second": 11.653,
      "step": 3
    },
    {
      "epoch": 0.00020707953148256002,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00025884941435320004,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00031061929722384004,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00031061929722384004,
      "eval_loss": NaN,
      "eval_runtime": 348.953,
      "eval_samples_per_second": 23.31,
      "eval_steps_per_second": 11.655,
      "step": 6
    },
    {
      "epoch": 0.00036238918009448004,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00041415906296512003,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00046592894583576003,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00046592894583576003,
      "eval_loss": NaN,
      "eval_runtime": 348.8967,
      "eval_samples_per_second": 23.313,
      "eval_steps_per_second": 11.657,
      "step": 9
    },
    {
      "epoch": 0.0005176988287064001,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2923396784455680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}