trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.903225806451613,
  "eval_steps": 100,
  "global_step": 14,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 8.196986198425293,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.0394,
      "step": 1
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 7.987215995788574,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 1.9977,
      "step": 2
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 5.537262439727783,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.8627,
      "step": 3
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 9.710270881652832,
      "learning_rate": 0.00011999999999999999,
      "loss": 1.7279,
      "step": 4
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 2.6102840900421143,
      "learning_rate": 0.00015,
      "loss": 1.5248,
      "step": 5
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 3.099637985229492,
      "learning_rate": 0.00017999999999999998,
      "loss": 1.407,
      "step": 6
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 2.4216651916503906,
      "learning_rate": 0.00020999999999999998,
      "loss": 1.2938,
      "step": 7
    },
    {
      "epoch": 1.129032258064516,
      "grad_norm": 4.433651447296143,
      "learning_rate": 0.00023999999999999998,
      "loss": 2.3081,
      "step": 8
    },
    {
      "epoch": 1.2580645161290323,
      "grad_norm": 2.2491350173950195,
      "learning_rate": 0.00027,
      "loss": 1.0445,
      "step": 9
    },
    {
      "epoch": 1.3870967741935485,
      "grad_norm": 2.2750585079193115,
      "learning_rate": 0.0003,
      "loss": 0.9604,
      "step": 10
    },
    {
      "epoch": 1.5161290322580645,
      "grad_norm": 2.2191295623779297,
      "learning_rate": 0.000225,
      "loss": 0.8531,
      "step": 11
    },
    {
      "epoch": 1.6451612903225805,
      "grad_norm": 2.1309051513671875,
      "learning_rate": 0.00015,
      "loss": 0.7651,
      "step": 12
    },
    {
      "epoch": 1.7741935483870968,
      "grad_norm": 1.9368622303009033,
      "learning_rate": 7.5e-05,
      "loss": 0.7049,
      "step": 13
    },
    {
      "epoch": 1.903225806451613,
      "grad_norm": 1.6794031858444214,
      "learning_rate": 0.0,
      "loss": 0.6562,
      "step": 14
    }
  ],
  "logging_steps": 1,
  "max_steps": 14,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2696330040311808.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}