checkpoint-14/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 14,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 0.0,
      "learning_rate": 0,
      "loss": 3.1568,
      "step": 1
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.0,
      "learning_rate": 0,
      "loss": 2.0929,
      "step": 2
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.0,
      "learning_rate": 0,
      "loss": 1.8548,
      "step": 3
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.0,
      "learning_rate": 0,
      "loss": 1.9561,
      "step": 4
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 31.57492020476853,
      "learning_rate": 0.0,
      "loss": 2.158,
      "step": 5
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 31.153859925878365,
      "learning_rate": 1e-05,
      "loss": 2.1095,
      "step": 6
    },
    {
      "epoch": 1.0,
      "grad_norm": 27.11565016529603,
      "learning_rate": 1e-05,
      "loss": 1.9969,
      "step": 7
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 13.454490530290899,
      "learning_rate": 9.166666666666666e-06,
      "loss": 1.9251,
      "step": 8
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 11.618148917850199,
      "learning_rate": 8.333333333333334e-06,
      "loss": 2.3126,
      "step": 9
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 15.134253327445556,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.937,
      "step": 10
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 15.062018295753115,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.8163,
      "step": 11
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 14.2866003252187,
      "learning_rate": 5.833333333333334e-06,
      "loss": 1.98,
      "step": 12
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 13.311110732967121,
      "learning_rate": 5e-06,
      "loss": 1.9709,
      "step": 13
    },
    {
      "epoch": 2.0,
      "grad_norm": 13.689697089288877,
      "learning_rate": 4.166666666666667e-06,
      "loss": 1.9649,
      "step": 14
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 14,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}