last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0006903574325607083,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.903574325607083e-05,
      "grad_norm": 1.649429202079773,
      "learning_rate": 2e-05,
      "loss": 0.9717,
      "step": 1
    },
    {
      "epoch": 6.903574325607083e-05,
      "eval_loss": 1.402584433555603,
      "eval_runtime": 225.675,
      "eval_samples_per_second": 27.026,
      "eval_steps_per_second": 13.515,
      "step": 1
    },
    {
      "epoch": 0.00013807148651214166,
      "grad_norm": 0.5260131359100342,
      "learning_rate": 4e-05,
      "loss": 0.3297,
      "step": 2
    },
    {
      "epoch": 0.00020710722976821248,
      "grad_norm": 1.48221755027771,
      "learning_rate": 6e-05,
      "loss": 1.0116,
      "step": 3
    },
    {
      "epoch": 0.00020710722976821248,
      "eval_loss": 1.3901009559631348,
      "eval_runtime": 222.6708,
      "eval_samples_per_second": 27.39,
      "eval_steps_per_second": 13.697,
      "step": 3
    },
    {
      "epoch": 0.0002761429730242833,
      "grad_norm": 1.0205483436584473,
      "learning_rate": 8e-05,
      "loss": 0.6226,
      "step": 4
    },
    {
      "epoch": 0.00034517871628035417,
      "grad_norm": 0.9916964769363403,
      "learning_rate": 0.0001,
      "loss": 0.6296,
      "step": 5
    },
    {
      "epoch": 0.00041421445953642496,
      "grad_norm": 1.6199209690093994,
      "learning_rate": 0.00012,
      "loss": 0.8327,
      "step": 6
    },
    {
      "epoch": 0.00041421445953642496,
      "eval_loss": 1.1207962036132812,
      "eval_runtime": 222.9444,
      "eval_samples_per_second": 27.357,
      "eval_steps_per_second": 13.681,
      "step": 6
    },
    {
      "epoch": 0.0004832502027924958,
      "grad_norm": 3.845686197280884,
      "learning_rate": 0.00014,
      "loss": 1.6431,
      "step": 7
    },
    {
      "epoch": 0.0005522859460485666,
      "grad_norm": 1.3479456901550293,
      "learning_rate": 0.00016,
      "loss": 0.3864,
      "step": 8
    },
    {
      "epoch": 0.0006213216893046374,
      "grad_norm": 2.227390766143799,
      "learning_rate": 0.00018,
      "loss": 0.4494,
      "step": 9
    },
    {
      "epoch": 0.0006213216893046374,
      "eval_loss": 0.3269291818141937,
      "eval_runtime": 222.7301,
      "eval_samples_per_second": 27.383,
      "eval_steps_per_second": 13.694,
      "step": 9
    },
    {
      "epoch": 0.0006903574325607083,
      "grad_norm": 0.48034343123435974,
      "learning_rate": 0.0002,
      "loss": 0.1047,
      "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": 2265755663990784.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}