trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 15.4,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8,
      "grad_norm": 1.7011343240737915,
      "learning_rate": 0.00018,
      "loss": 0.5995,
      "step": 10
    },
    {
      "epoch": 1.56,
      "grad_norm": 0.22524015605449677,
      "learning_rate": 0.0001905263157894737,
      "loss": 0.0139,
      "step": 20
    },
    {
      "epoch": 2.32,
      "grad_norm": 0.04040924832224846,
      "learning_rate": 0.00018,
      "loss": 0.0052,
      "step": 30
    },
    {
      "epoch": 3.08,
      "grad_norm": 0.014496985822916031,
      "learning_rate": 0.00016947368421052633,
      "loss": 0.0044,
      "step": 40
    },
    {
      "epoch": 3.88,
      "grad_norm": 0.04556073993444443,
      "learning_rate": 0.00015894736842105264,
      "loss": 0.0043,
      "step": 50
    },
    {
      "epoch": 4.64,
      "grad_norm": 0.08168065547943115,
      "learning_rate": 0.00014842105263157895,
      "loss": 0.0053,
      "step": 60
    },
    {
      "epoch": 5.4,
      "grad_norm": 0.036317914724349976,
      "learning_rate": 0.00013789473684210527,
      "loss": 0.0046,
      "step": 70
    },
    {
      "epoch": 6.16,
      "grad_norm": 0.0234612375497818,
      "learning_rate": 0.00012736842105263158,
      "loss": 0.0045,
      "step": 80
    },
    {
      "epoch": 6.96,
      "grad_norm": 0.023044303059577942,
      "learning_rate": 0.00011684210526315791,
      "loss": 0.0047,
      "step": 90
    },
    {
      "epoch": 7.72,
      "grad_norm": 0.0161167923361063,
      "learning_rate": 0.00010631578947368421,
      "loss": 0.004,
      "step": 100
    },
    {
      "epoch": 8.48,
      "grad_norm": 0.00939767062664032,
      "learning_rate": 9.578947368421052e-05,
      "loss": 0.0044,
      "step": 110
    },
    {
      "epoch": 9.24,
      "grad_norm": 0.03683692589402199,
      "learning_rate": 8.526315789473685e-05,
      "loss": 0.004,
      "step": 120
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.02535077929496765,
      "learning_rate": 7.473684210526316e-05,
      "loss": 0.0042,
      "step": 130
    },
    {
      "epoch": 10.8,
      "grad_norm": 0.024098610505461693,
      "learning_rate": 6.421052631578948e-05,
      "loss": 0.004,
      "step": 140
    },
    {
      "epoch": 11.56,
      "grad_norm": 0.016196303069591522,
      "learning_rate": 5.368421052631579e-05,
      "loss": 0.0038,
      "step": 150
    },
    {
      "epoch": 12.32,
      "grad_norm": 0.020965227857232094,
      "learning_rate": 4.3157894736842105e-05,
      "loss": 0.004,
      "step": 160
    },
    {
      "epoch": 13.08,
      "grad_norm": 0.017107339575886726,
      "learning_rate": 3.2631578947368426e-05,
      "loss": 0.004,
      "step": 170
    },
    {
      "epoch": 13.88,
      "grad_norm": 0.03667628765106201,
      "learning_rate": 2.2105263157894736e-05,
      "loss": 0.004,
      "step": 180
    },
    {
      "epoch": 14.64,
      "grad_norm": 0.0402102991938591,
      "learning_rate": 1.1578947368421053e-05,
      "loss": 0.0038,
      "step": 190
    },
    {
      "epoch": 15.4,
      "grad_norm": 0.04898475855588913,
      "learning_rate": 1.0526315789473685e-06,
      "loss": 0.004,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 17,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3105837514930176.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}