last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011841326228537596,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011841326228537595,
      "grad_norm": 1.1621721982955933,
      "learning_rate": 2e-05,
      "loss": 2.1562,
      "step": 1
    },
    {
      "epoch": 0.002368265245707519,
      "grad_norm": 0.7399325966835022,
      "learning_rate": 4e-05,
      "loss": 0.7487,
      "step": 2
    },
    {
      "epoch": 0.003552397868561279,
      "grad_norm": 0.8471466302871704,
      "learning_rate": 6e-05,
      "loss": 1.6955,
      "step": 3
    },
    {
      "epoch": 0.003552397868561279,
      "eval_loss": 1.656009316444397,
      "eval_runtime": 25.1689,
      "eval_samples_per_second": 14.144,
      "eval_steps_per_second": 7.072,
      "step": 3
    },
    {
      "epoch": 0.004736530491415038,
      "grad_norm": 1.1407734155654907,
      "learning_rate": 8e-05,
      "loss": 1.7198,
      "step": 4
    },
    {
      "epoch": 0.005920663114268798,
      "grad_norm": 0.7835360169410706,
      "learning_rate": 0.0001,
      "loss": 1.534,
      "step": 5
    },
    {
      "epoch": 0.007104795737122558,
      "grad_norm": 1.132032871246338,
      "learning_rate": 0.00012,
      "loss": 1.2132,
      "step": 6
    },
    {
      "epoch": 0.007104795737122558,
      "eval_loss": 1.630635142326355,
      "eval_runtime": 25.7592,
      "eval_samples_per_second": 13.82,
      "eval_steps_per_second": 6.91,
      "step": 6
    },
    {
      "epoch": 0.008288928359976317,
      "grad_norm": 0.8722746968269348,
      "learning_rate": 0.00014,
      "loss": 1.8956,
      "step": 7
    },
    {
      "epoch": 0.009473060982830076,
      "grad_norm": 0.738004207611084,
      "learning_rate": 0.00016,
      "loss": 1.8152,
      "step": 8
    },
    {
      "epoch": 0.010657193605683837,
      "grad_norm": 0.803749144077301,
      "learning_rate": 0.00018,
      "loss": 1.7991,
      "step": 9
    },
    {
      "epoch": 0.010657193605683837,
      "eval_loss": 1.57768714427948,
      "eval_runtime": 25.2018,
      "eval_samples_per_second": 14.126,
      "eval_steps_per_second": 7.063,
      "step": 9
    },
    {
      "epoch": 0.011841326228537596,
      "grad_norm": 1.021946668624878,
      "learning_rate": 0.0002,
      "loss": 2.0315,
      "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": 133557245706240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}