last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003884136216657118,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.8841362166571184e-05,
      "grad_norm": 1337.6612548828125,
      "learning_rate": 2e-05,
      "loss": 48.3903,
      "step": 1
    },
    {
      "epoch": 7.768272433314237e-05,
      "grad_norm": 1237.1090087890625,
      "learning_rate": 4e-05,
      "loss": 82.2165,
      "step": 2
    },
    {
      "epoch": 0.00011652408649971354,
      "grad_norm": 867.312744140625,
      "learning_rate": 6e-05,
      "loss": 31.9198,
      "step": 3
    },
    {
      "epoch": 0.00011652408649971354,
      "eval_loss": 11.575413703918457,
      "eval_runtime": 261.1845,
      "eval_samples_per_second": 41.507,
      "eval_steps_per_second": 20.755,
      "step": 3
    },
    {
      "epoch": 0.00015536544866628474,
      "grad_norm": 1267.2216796875,
      "learning_rate": 8e-05,
      "loss": 43.4303,
      "step": 4
    },
    {
      "epoch": 0.0001942068108328559,
      "grad_norm": 1062.40234375,
      "learning_rate": 0.0001,
      "loss": 33.3487,
      "step": 5
    },
    {
      "epoch": 0.0002330481729994271,
      "grad_norm": 1249.7735595703125,
      "learning_rate": 0.00012,
      "loss": 41.8347,
      "step": 6
    },
    {
      "epoch": 0.0002330481729994271,
      "eval_loss": 11.542579650878906,
      "eval_runtime": 259.9141,
      "eval_samples_per_second": 41.71,
      "eval_steps_per_second": 20.857,
      "step": 6
    },
    {
      "epoch": 0.00027188953516599825,
      "grad_norm": 1034.145263671875,
      "learning_rate": 0.00014,
      "loss": 48.4583,
      "step": 7
    },
    {
      "epoch": 0.00031073089733256947,
      "grad_norm": 1013.7915649414062,
      "learning_rate": 0.00016,
      "loss": 32.965,
      "step": 8
    },
    {
      "epoch": 0.00034957225949914063,
      "grad_norm": 1290.4112548828125,
      "learning_rate": 0.00018,
      "loss": 63.7696,
      "step": 9
    },
    {
      "epoch": 0.00034957225949914063,
      "eval_loss": 11.457053184509277,
      "eval_runtime": 264.0088,
      "eval_samples_per_second": 41.063,
      "eval_steps_per_second": 20.533,
      "step": 9
    },
    {
      "epoch": 0.0003884136216657118,
      "grad_norm": 929.0032958984375,
      "learning_rate": 0.0002,
      "loss": 43.6878,
      "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": 17996835717120.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}