checkpoint-13/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 161.63536071777344,
      "learning_rate": 2e-05,
      "loss": 6.492,
      "step": 1
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 159.5704345703125,
      "learning_rate": 4e-05,
      "loss": 6.4968,
      "step": 2
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 142.9398193359375,
      "learning_rate": 6e-05,
      "loss": 5.6031,
      "step": 3
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 171.34854125976562,
      "learning_rate": 8e-05,
      "loss": 4.0835,
      "step": 4
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 124.95561218261719,
      "learning_rate": 0.0001,
      "loss": 2.2652,
      "step": 5
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 202.09657287597656,
      "learning_rate": 0.00012,
      "loss": 1.3066,
      "step": 6
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 89.74258422851562,
      "learning_rate": 0.00014,
      "loss": 0.6958,
      "step": 7
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 20.369661331176758,
      "learning_rate": 0.00016,
      "loss": 0.336,
      "step": 8
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 4.07184362411499,
      "learning_rate": 0.00018,
      "loss": 0.173,
      "step": 9
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 0.5548842549324036,
      "learning_rate": 0.0002,
      "loss": 0.1229,
      "step": 10
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 0.37989184260368347,
      "learning_rate": 0.00019230769230769233,
      "loss": 0.1154,
      "step": 11
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 10.629559516906738,
      "learning_rate": 0.00018461538461538463,
      "loss": 0.1451,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.5450623631477356,
      "learning_rate": 0.00017692307692307693,
      "loss": 0.124,
      "step": 13
    }
  ],
  "logging_steps": 1,
  "max_steps": 36,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2208272127885312.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}