trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 13,
  "global_step": 13,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 0.65625,
      "learning_rate": 1e-05,
      "loss": 2.3096,
      "step": 1
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.6875,
      "learning_rate": 9.230769230769232e-06,
      "loss": 2.3782,
      "step": 2
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.640625,
      "learning_rate": 8.461538461538462e-06,
      "loss": 2.3575,
      "step": 3
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.64453125,
      "learning_rate": 7.692307692307694e-06,
      "loss": 2.3558,
      "step": 4
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 0.56640625,
      "learning_rate": 6.923076923076923e-06,
      "loss": 2.2811,
      "step": 5
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.55078125,
      "learning_rate": 6.153846153846155e-06,
      "loss": 2.2474,
      "step": 6
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 0.54296875,
      "learning_rate": 5.384615384615385e-06,
      "loss": 2.3761,
      "step": 7
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.53515625,
      "learning_rate": 4.615384615384616e-06,
      "loss": 2.274,
      "step": 8
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.515625,
      "learning_rate": 3.846153846153847e-06,
      "loss": 2.2458,
      "step": 9
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.52734375,
      "learning_rate": 3.0769230769230774e-06,
      "loss": 2.281,
      "step": 10
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 0.5078125,
      "learning_rate": 2.307692307692308e-06,
      "loss": 2.3008,
      "step": 11
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.5078125,
      "learning_rate": 1.5384615384615387e-06,
      "loss": 2.2986,
      "step": 12
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.48046875,
      "learning_rate": 7.692307692307694e-07,
      "loss": 2.2631,
      "step": 13
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.275115728378296,
      "eval_runtime": 12.3652,
      "eval_samples_per_second": 2.831,
      "eval_steps_per_second": 0.404,
      "step": 13
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 13,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.444361076192051e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}