trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 14.492753623188406,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7246376811594203,
      "grad_norm": 0.024382874369621277,
      "learning_rate": 2.45e-05,
      "loss": 0.1151,
      "step": 50
    },
    {
      "epoch": 1.4492753623188406,
      "grad_norm": 0.005299532786011696,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 0.0004,
      "step": 100
    },
    {
      "epoch": 2.1739130434782608,
      "grad_norm": 0.0024427291937172413,
      "learning_rate": 4.727777777777778e-05,
      "loss": 0.0001,
      "step": 150
    },
    {
      "epoch": 2.898550724637681,
      "grad_norm": 0.0012963886838406324,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 0.0001,
      "step": 200
    },
    {
      "epoch": 3.6231884057971016,
      "grad_norm": 0.0011170754441991448,
      "learning_rate": 4.172222222222222e-05,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 4.3478260869565215,
      "grad_norm": 0.0009609300759620965,
      "learning_rate": 3.894444444444444e-05,
      "loss": 0.0,
      "step": 300
    },
    {
      "epoch": 5.072463768115942,
      "grad_norm": 0.0007455663289874792,
      "learning_rate": 3.6166666666666674e-05,
      "loss": 0.0,
      "step": 350
    },
    {
      "epoch": 5.797101449275362,
      "grad_norm": 0.0007628346793353558,
      "learning_rate": 3.338888888888889e-05,
      "loss": 0.0,
      "step": 400
    },
    {
      "epoch": 6.521739130434782,
      "grad_norm": 0.0006400482379831374,
      "learning_rate": 3.061111111111111e-05,
      "loss": 0.0,
      "step": 450
    },
    {
      "epoch": 7.246376811594203,
      "grad_norm": 0.0006571674603037536,
      "learning_rate": 2.7833333333333333e-05,
      "loss": 0.0,
      "step": 500
    },
    {
      "epoch": 7.971014492753623,
      "grad_norm": 0.0004984458209946752,
      "learning_rate": 2.5055555555555555e-05,
      "loss": 0.0,
      "step": 550
    },
    {
      "epoch": 8.695652173913043,
      "grad_norm": 0.0005247824592515826,
      "learning_rate": 2.2277777777777778e-05,
      "loss": 0.0,
      "step": 600
    },
    {
      "epoch": 9.420289855072463,
      "grad_norm": 0.0005136411054991186,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 0.0,
      "step": 650
    },
    {
      "epoch": 10.144927536231885,
      "grad_norm": 0.00042652638512663543,
      "learning_rate": 1.6722222222222222e-05,
      "loss": 0.0,
      "step": 700
    },
    {
      "epoch": 10.869565217391305,
      "grad_norm": 0.0003991111880168319,
      "learning_rate": 1.3944444444444446e-05,
      "loss": 0.0,
      "step": 750
    },
    {
      "epoch": 11.594202898550725,
      "grad_norm": 0.00043558661127462983,
      "learning_rate": 1.1166666666666668e-05,
      "loss": 0.0,
      "step": 800
    },
    {
      "epoch": 12.318840579710145,
      "grad_norm": 0.00038388941902667284,
      "learning_rate": 8.38888888888889e-06,
      "loss": 0.0,
      "step": 850
    },
    {
      "epoch": 13.043478260869565,
      "grad_norm": 0.00033727928530424833,
      "learning_rate": 5.611111111111112e-06,
      "loss": 0.0,
      "step": 900
    },
    {
      "epoch": 13.768115942028986,
      "grad_norm": 0.00039866630686447024,
      "learning_rate": 2.8333333333333335e-06,
      "loss": 0.0,
      "step": 950
    },
    {
      "epoch": 14.492753623188406,
      "grad_norm": 0.0003358957765158266,
      "learning_rate": 5.555555555555556e-08,
      "loss": 0.0,
      "step": 1000
    },
    {
      "epoch": 14.492753623188406,
      "step": 1000,
      "total_flos": 2082787114229760.0,
      "train_loss": 0.005802426487207413,
      "train_runtime": 92.609,
      "train_samples_per_second": 86.385,
      "train_steps_per_second": 10.798
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2082787114229760.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}