model/trainer_state.json

{
  "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": 0.08,
      "grad_norm": 130.75577214745246,
      "learning_rate": 2e-05,
      "loss": 1.2648,
      "step": 1
    },
    {
      "epoch": 0.15,
      "grad_norm": 126.67616596972118,
      "learning_rate": 1.9659258262890683e-05,
      "loss": 1.2283,
      "step": 2
    },
    {
      "epoch": 0.23,
      "grad_norm": 56.84219933724937,
      "learning_rate": 1.866025403784439e-05,
      "loss": 0.4188,
      "step": 3
    },
    {
      "epoch": 0.31,
      "grad_norm": 89.42666319016989,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 2.4789,
      "step": 4
    },
    {
      "epoch": 0.38,
      "grad_norm": 72.41844398977439,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.7853,
      "step": 5
    },
    {
      "epoch": 0.46,
      "grad_norm": 799.0148731599335,
      "learning_rate": 1.2588190451025209e-05,
      "loss": 8.2197,
      "step": 6
    },
    {
      "epoch": 0.54,
      "grad_norm": 34.525610403243014,
      "learning_rate": 1e-05,
      "loss": 0.3008,
      "step": 7
    },
    {
      "epoch": 0.62,
      "grad_norm": 64.98250527603693,
      "learning_rate": 7.411809548974792e-06,
      "loss": 0.3999,
      "step": 8
    },
    {
      "epoch": 0.69,
      "grad_norm": 11.46902235575636,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.2575,
      "step": 9
    },
    {
      "epoch": 0.77,
      "grad_norm": 42.63293180170212,
      "learning_rate": 2.9289321881345257e-06,
      "loss": 0.3174,
      "step": 10
    },
    {
      "epoch": 0.85,
      "grad_norm": 40.64988981794197,
      "learning_rate": 1.339745962155613e-06,
      "loss": 0.3054,
      "step": 11
    },
    {
      "epoch": 0.92,
      "grad_norm": 27.588182133457394,
      "learning_rate": 3.4074173710931804e-07,
      "loss": 0.2827,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 17.48926557604337,
      "learning_rate": 0.0,
      "loss": 0.2751,
      "step": 13
    },
    {
      "epoch": 1.0,
      "step": 13,
      "total_flos": 0.0,
      "train_loss": 1.2718768601234143,
      "train_runtime": 323.0635,
      "train_samples_per_second": 41.206,
      "train_steps_per_second": 0.04
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 13,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}