trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.791208791208791,
  "eval_steps": 500,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 2.0971016883850098,
      "learning_rate": 1.6363636363636365e-06,
      "loss": 0.7587,
      "step": 10
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 0.8449636101722717,
      "learning_rate": 1.967948701396356e-06,
      "loss": 0.691,
      "step": 20
    },
    {
      "epoch": 1.3076923076923077,
      "grad_norm": 0.6521225571632385,
      "learning_rate": 1.8412535328311812e-06,
      "loss": 0.627,
      "step": 30
    },
    {
      "epoch": 1.7472527472527473,
      "grad_norm": 0.580456554889679,
      "learning_rate": 1.6305526670845225e-06,
      "loss": 0.6099,
      "step": 40
    },
    {
      "epoch": 2.1758241758241756,
      "grad_norm": 0.6621115207672119,
      "learning_rate": 1.3568862215918717e-06,
      "loss": 0.5569,
      "step": 50
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.4708077311515808,
      "learning_rate": 1.0475819158237424e-06,
      "loss": 0.5164,
      "step": 60
    },
    {
      "epoch": 3.043956043956044,
      "grad_norm": 0.6353986859321594,
      "learning_rate": 7.335261863099651e-07,
      "loss": 0.4935,
      "step": 70
    },
    {
      "epoch": 3.4835164835164836,
      "grad_norm": 0.653141975402832,
      "learning_rate": 4.460799361338897e-07,
      "loss": 0.4535,
      "step": 80
    },
    {
      "epoch": 3.9230769230769234,
      "grad_norm": 0.6834583878517151,
      "learning_rate": 2.139469052572127e-07,
      "loss": 0.4811,
      "step": 90
    },
    {
      "epoch": 4.351648351648351,
      "grad_norm": 0.584416925907135,
      "learning_rate": 6.030737921409168e-08,
      "loss": 0.4414,
      "step": 100
    },
    {
      "epoch": 4.791208791208791,
      "grad_norm": 0.6029403805732727,
      "learning_rate": 5.034576168149174e-10,
      "loss": 0.4517,
      "step": 110
    },
    {
      "epoch": 4.791208791208791,
      "step": 110,
      "total_flos": 1.8378852146977178e+17,
      "train_loss": 0.552842664718628,
      "train_runtime": 1381.2939,
      "train_samples_per_second": 5.267,
      "train_steps_per_second": 0.08
    }
  ],
  "logging_steps": 10,
  "max_steps": 110,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 250,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8378852146977178e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}