last-checkpoint/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14464534075104313,
  "eval_steps": 13,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011126564673157162,
      "grad_norm": 0.45852020382881165,
      "learning_rate": 1e-05,
      "loss": 0.7788,
      "step": 1
    },
    {
      "epoch": 0.011126564673157162,
      "eval_loss": 0.8189165592193604,
      "eval_runtime": 32.0686,
      "eval_samples_per_second": 4.74,
      "eval_steps_per_second": 2.37,
      "step": 1
    },
    {
      "epoch": 0.022253129346314324,
      "grad_norm": 0.3102879822254181,
      "learning_rate": 2e-05,
      "loss": 0.7235,
      "step": 2
    },
    {
      "epoch": 0.03337969401947149,
      "grad_norm": 0.4298129081726074,
      "learning_rate": 3e-05,
      "loss": 0.6954,
      "step": 3
    },
    {
      "epoch": 0.04450625869262865,
      "grad_norm": 0.4370204508304596,
      "learning_rate": 4e-05,
      "loss": 0.7928,
      "step": 4
    },
    {
      "epoch": 0.055632823365785816,
      "grad_norm": 0.34161755442619324,
      "learning_rate": 5e-05,
      "loss": 0.8569,
      "step": 5
    },
    {
      "epoch": 0.06675938803894298,
      "grad_norm": 0.2788660228252411,
      "learning_rate": 6e-05,
      "loss": 0.7285,
      "step": 6
    },
    {
      "epoch": 0.07788595271210014,
      "grad_norm": 0.31495457887649536,
      "learning_rate": 7e-05,
      "loss": 0.7721,
      "step": 7
    },
    {
      "epoch": 0.0890125173852573,
      "grad_norm": 0.24107243120670319,
      "learning_rate": 8e-05,
      "loss": 0.7058,
      "step": 8
    },
    {
      "epoch": 0.10013908205841446,
      "grad_norm": 0.2623262107372284,
      "learning_rate": 9e-05,
      "loss": 0.7499,
      "step": 9
    },
    {
      "epoch": 0.11126564673157163,
      "grad_norm": 0.30620405077934265,
      "learning_rate": 0.0001,
      "loss": 0.6713,
      "step": 10
    },
    {
      "epoch": 0.12239221140472879,
      "grad_norm": 0.9073506593704224,
      "learning_rate": 9.98458666866564e-05,
      "loss": 0.748,
      "step": 11
    },
    {
      "epoch": 0.13351877607788595,
      "grad_norm": 0.3162141740322113,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.8322,
      "step": 12
    },
    {
      "epoch": 0.14464534075104313,
      "grad_norm": 0.2846090793609619,
      "learning_rate": 9.861849601988383e-05,
      "loss": 0.7256,
      "step": 13
    },
    {
      "epoch": 0.14464534075104313,
      "eval_loss": 0.7517489194869995,
      "eval_runtime": 21.8923,
      "eval_samples_per_second": 6.943,
      "eval_steps_per_second": 3.472,
      "step": 13
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.71562774902866e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}