trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06688963210702341,
      "grad_norm": 1.140625,
      "learning_rate": 9.4e-06,
      "loss": 2.2013,
      "step": 10
    },
    {
      "epoch": 0.13377926421404682,
      "grad_norm": 1.0546875,
      "learning_rate": 8.733333333333333e-06,
      "loss": 1.9781,
      "step": 20
    },
    {
      "epoch": 0.20066889632107024,
      "grad_norm": 1.015625,
      "learning_rate": 8.066666666666667e-06,
      "loss": 1.8603,
      "step": 30
    },
    {
      "epoch": 0.26755852842809363,
      "grad_norm": 0.921875,
      "learning_rate": 7.4e-06,
      "loss": 1.8597,
      "step": 40
    },
    {
      "epoch": 0.33444816053511706,
      "grad_norm": 0.91796875,
      "learning_rate": 6.733333333333334e-06,
      "loss": 1.806,
      "step": 50
    },
    {
      "epoch": 0.4013377926421405,
      "grad_norm": 0.87109375,
      "learning_rate": 6.066666666666667e-06,
      "loss": 1.784,
      "step": 60
    },
    {
      "epoch": 0.4682274247491639,
      "grad_norm": 0.953125,
      "learning_rate": 5.400000000000001e-06,
      "loss": 1.7707,
      "step": 70
    },
    {
      "epoch": 0.5351170568561873,
      "grad_norm": 0.94140625,
      "learning_rate": 4.7333333333333335e-06,
      "loss": 1.7625,
      "step": 80
    },
    {
      "epoch": 0.6020066889632107,
      "grad_norm": 0.86328125,
      "learning_rate": 4.066666666666667e-06,
      "loss": 1.7817,
      "step": 90
    },
    {
      "epoch": 0.6688963210702341,
      "grad_norm": 0.953125,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 1.7621,
      "step": 100
    },
    {
      "epoch": 0.7357859531772575,
      "grad_norm": 1.0,
      "learning_rate": 2.7333333333333336e-06,
      "loss": 1.7484,
      "step": 110
    },
    {
      "epoch": 0.802675585284281,
      "grad_norm": 0.9453125,
      "learning_rate": 2.0666666666666666e-06,
      "loss": 1.7617,
      "step": 120
    },
    {
      "epoch": 0.8695652173913043,
      "grad_norm": 0.95703125,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 1.7377,
      "step": 130
    },
    {
      "epoch": 0.9364548494983278,
      "grad_norm": 0.92578125,
      "learning_rate": 7.333333333333334e-07,
      "loss": 1.7298,
      "step": 140
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.73828125,
      "learning_rate": 6.666666666666668e-08,
      "loss": 1.6729,
      "step": 150
    },
    {
      "epoch": 1.0,
      "step": 150,
      "total_flos": 1.1045760817771315e+17,
      "train_loss": 1.8144684982299806,
      "train_runtime": 664.7859,
      "train_samples_per_second": 1.798,
      "train_steps_per_second": 0.226
    }
  ],
  "logging_steps": 10,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.1045760817771315e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}