checkpoint-100/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10504201680672269,
  "eval_steps": 50,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01050420168067227,
      "grad_norm": 2.5582146644592285,
      "learning_rate": 4.98249299719888e-05,
      "loss": 1.6787,
      "step": 10
    },
    {
      "epoch": 0.02100840336134454,
      "grad_norm": 0.9345070719718933,
      "learning_rate": 4.96498599439776e-05,
      "loss": 0.518,
      "step": 20
    },
    {
      "epoch": 0.031512605042016806,
      "grad_norm": 1.6358414888381958,
      "learning_rate": 4.947478991596639e-05,
      "loss": 0.4604,
      "step": 30
    },
    {
      "epoch": 0.04201680672268908,
      "grad_norm": 0.7778844237327576,
      "learning_rate": 4.9299719887955186e-05,
      "loss": 0.3771,
      "step": 40
    },
    {
      "epoch": 0.052521008403361345,
      "grad_norm": 0.7006077766418457,
      "learning_rate": 4.912464985994398e-05,
      "loss": 0.3842,
      "step": 50
    },
    {
      "epoch": 0.052521008403361345,
      "eval_loss": 0.42603224515914917,
      "eval_runtime": 13.5673,
      "eval_samples_per_second": 35.379,
      "eval_steps_per_second": 2.211,
      "step": 50
    },
    {
      "epoch": 0.06302521008403361,
      "grad_norm": 0.6415153741836548,
      "learning_rate": 4.8949579831932775e-05,
      "loss": 0.3399,
      "step": 60
    },
    {
      "epoch": 0.07352941176470588,
      "grad_norm": 0.6030780076980591,
      "learning_rate": 4.877450980392157e-05,
      "loss": 0.3447,
      "step": 70
    },
    {
      "epoch": 0.08403361344537816,
      "grad_norm": 0.688852071762085,
      "learning_rate": 4.859943977591036e-05,
      "loss": 0.3219,
      "step": 80
    },
    {
      "epoch": 0.09453781512605042,
      "grad_norm": 0.6371557712554932,
      "learning_rate": 4.8424369747899164e-05,
      "loss": 0.3379,
      "step": 90
    },
    {
      "epoch": 0.10504201680672269,
      "grad_norm": 0.7739270329475403,
      "learning_rate": 4.824929971988796e-05,
      "loss": 0.3177,
      "step": 100
    },
    {
      "epoch": 0.10504201680672269,
      "eval_loss": 0.3801896274089813,
      "eval_runtime": 13.6107,
      "eval_samples_per_second": 35.266,
      "eval_steps_per_second": 2.204,
      "step": 100
    }
  ],
  "logging_steps": 10,
  "max_steps": 2856,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1886860020875264e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}