trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9957805907172996,
  "eval_steps": 500,
  "global_step": 118,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08438818565400844,
      "grad_norm": 6.15625,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.2054,
      "step": 10
    },
    {
      "epoch": 0.16877637130801687,
      "grad_norm": 2.546875,
      "learning_rate": 1.9720229140804108e-06,
      "loss": 1.1272,
      "step": 20
    },
    {
      "epoch": 0.25316455696202533,
      "grad_norm": 1.484375,
      "learning_rate": 1.8610436117673553e-06,
      "loss": 1.0603,
      "step": 30
    },
    {
      "epoch": 0.33755274261603374,
      "grad_norm": 1.109375,
      "learning_rate": 1.6749830015182104e-06,
      "loss": 1.0228,
      "step": 40
    },
    {
      "epoch": 0.4219409282700422,
      "grad_norm": 0.96875,
      "learning_rate": 1.4300652022765205e-06,
      "loss": 1.0089,
      "step": 50
    },
    {
      "epoch": 0.5063291139240507,
      "grad_norm": 0.9296875,
      "learning_rate": 1.1476465640024813e-06,
      "loss": 1.0109,
      "step": 60
    },
    {
      "epoch": 0.5907172995780591,
      "grad_norm": 0.890625,
      "learning_rate": 8.523534359975189e-07,
      "loss": 1.0062,
      "step": 70
    },
    {
      "epoch": 0.6751054852320675,
      "grad_norm": 0.8984375,
      "learning_rate": 5.699347977234798e-07,
      "loss": 0.9945,
      "step": 80
    },
    {
      "epoch": 0.759493670886076,
      "grad_norm": 0.8671875,
      "learning_rate": 3.2501699848178964e-07,
      "loss": 0.9971,
      "step": 90
    },
    {
      "epoch": 0.8438818565400844,
      "grad_norm": 0.875,
      "learning_rate": 1.3895638823264445e-07,
      "loss": 1.0152,
      "step": 100
    },
    {
      "epoch": 0.9282700421940928,
      "grad_norm": 0.8515625,
      "learning_rate": 2.797708591958925e-08,
      "loss": 0.9995,
      "step": 110
    },
    {
      "epoch": 0.9957805907172996,
      "step": 118,
      "total_flos": 1.3120143844945428e+18,
      "train_loss": 1.0387564513642908,
      "train_runtime": 4852.3718,
      "train_samples_per_second": 3.125,
      "train_steps_per_second": 0.024
    }
  ],
  "logging_steps": 10,
  "max_steps": 118,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3120143844945428e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}