last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10526315789473684,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010526315789473684,
      "grad_norm": 0.4161433279514313,
      "learning_rate": 2e-05,
      "loss": 1.1861,
      "step": 1
    },
    {
      "epoch": 0.021052631578947368,
      "grad_norm": 0.5023602247238159,
      "learning_rate": 4e-05,
      "loss": 1.4012,
      "step": 2
    },
    {
      "epoch": 0.031578947368421054,
      "grad_norm": 0.4932239353656769,
      "learning_rate": 6e-05,
      "loss": 1.1922,
      "step": 3
    },
    {
      "epoch": 0.031578947368421054,
      "eval_loss": 1.2776458263397217,
      "eval_runtime": 2.4957,
      "eval_samples_per_second": 16.028,
      "eval_steps_per_second": 8.014,
      "step": 3
    },
    {
      "epoch": 0.042105263157894736,
      "grad_norm": 0.4685695171356201,
      "learning_rate": 8e-05,
      "loss": 1.4126,
      "step": 4
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.7175632119178772,
      "learning_rate": 0.0001,
      "loss": 1.482,
      "step": 5
    },
    {
      "epoch": 0.06315789473684211,
      "grad_norm": 0.43501541018486023,
      "learning_rate": 0.00012,
      "loss": 1.1629,
      "step": 6
    },
    {
      "epoch": 0.06315789473684211,
      "eval_loss": 1.2478293180465698,
      "eval_runtime": 4.4978,
      "eval_samples_per_second": 8.893,
      "eval_steps_per_second": 4.447,
      "step": 6
    },
    {
      "epoch": 0.07368421052631578,
      "grad_norm": 0.5722425580024719,
      "learning_rate": 0.00014,
      "loss": 1.2619,
      "step": 7
    },
    {
      "epoch": 0.08421052631578947,
      "grad_norm": 0.6308000087738037,
      "learning_rate": 0.00016,
      "loss": 1.3727,
      "step": 8
    },
    {
      "epoch": 0.09473684210526316,
      "grad_norm": 0.6886353492736816,
      "learning_rate": 0.00018,
      "loss": 1.1993,
      "step": 9
    },
    {
      "epoch": 0.09473684210526316,
      "eval_loss": 1.1333757638931274,
      "eval_runtime": 4.5992,
      "eval_samples_per_second": 8.697,
      "eval_steps_per_second": 4.349,
      "step": 9
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.4539870321750641,
      "learning_rate": 0.0002,
      "loss": 1.0458,
      "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": 2972437973041152.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}