last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0015535790577543014,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015535790577543015,
      "grad_norm": 1.815487265586853,
      "learning_rate": 2e-05,
      "loss": 0.9445,
      "step": 1
    },
    {
      "epoch": 0.00015535790577543015,
      "eval_loss": 2.0217957496643066,
      "eval_runtime": 154.1175,
      "eval_samples_per_second": 17.59,
      "eval_steps_per_second": 8.798,
      "step": 1
    },
    {
      "epoch": 0.0003107158115508603,
      "grad_norm": 0.9126102328300476,
      "learning_rate": 4e-05,
      "loss": 0.4973,
      "step": 2
    },
    {
      "epoch": 0.00046607371732629044,
      "grad_norm": 4.327394485473633,
      "learning_rate": 6e-05,
      "loss": 2.0792,
      "step": 3
    },
    {
      "epoch": 0.00046607371732629044,
      "eval_loss": 2.0084359645843506,
      "eval_runtime": 152.9264,
      "eval_samples_per_second": 17.727,
      "eval_steps_per_second": 8.867,
      "step": 3
    },
    {
      "epoch": 0.0006214316231017206,
      "grad_norm": 2.028557777404785,
      "learning_rate": 8e-05,
      "loss": 1.1813,
      "step": 4
    },
    {
      "epoch": 0.0007767895288771507,
      "grad_norm": 1.389418363571167,
      "learning_rate": 0.0001,
      "loss": 0.8467,
      "step": 5
    },
    {
      "epoch": 0.0009321474346525809,
      "grad_norm": 1.6109280586242676,
      "learning_rate": 0.00012,
      "loss": 0.8758,
      "step": 6
    },
    {
      "epoch": 0.0009321474346525809,
      "eval_loss": 1.7915416955947876,
      "eval_runtime": 152.8435,
      "eval_samples_per_second": 17.737,
      "eval_steps_per_second": 8.872,
      "step": 6
    },
    {
      "epoch": 0.001087505340428011,
      "grad_norm": 1.7988044023513794,
      "learning_rate": 0.00014,
      "loss": 0.7795,
      "step": 7
    },
    {
      "epoch": 0.0012428632462034412,
      "grad_norm": 1.4882478713989258,
      "learning_rate": 0.00016,
      "loss": 0.6938,
      "step": 8
    },
    {
      "epoch": 0.0013982211519788714,
      "grad_norm": 3.2228457927703857,
      "learning_rate": 0.00018,
      "loss": 1.0042,
      "step": 9
    },
    {
      "epoch": 0.0013982211519788714,
      "eval_loss": 1.0252125263214111,
      "eval_runtime": 152.8871,
      "eval_samples_per_second": 17.732,
      "eval_steps_per_second": 8.869,
      "step": 9
    },
    {
      "epoch": 0.0015535790577543014,
      "grad_norm": 2.2106058597564697,
      "learning_rate": 0.0002,
      "loss": 1.0226,
      "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": 3560473186271232.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}