trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9952,
  "eval_steps": 500,
  "global_step": 468,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.192,
      "grad_norm": 1.4319641974590682,
      "learning_rate": 4.94947663010567e-06,
      "loss": 1.2723,
      "step": 30
    },
    {
      "epoch": 0.384,
      "grad_norm": 1.4181330588366226,
      "learning_rate": 4.799948609147061e-06,
      "loss": 1.1224,
      "step": 60
    },
    {
      "epoch": 0.576,
      "grad_norm": 1.3827748693618769,
      "learning_rate": 4.5574596647341414e-06,
      "loss": 1.0991,
      "step": 90
    },
    {
      "epoch": 0.768,
      "grad_norm": 1.380851549330067,
      "learning_rate": 4.231810883773999e-06,
      "loss": 1.1043,
      "step": 120
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.4453919991748538,
      "learning_rate": 3.836164565319503e-06,
      "loss": 1.0811,
      "step": 150
    },
    {
      "epoch": 1.152,
      "grad_norm": 1.324571711000525,
      "learning_rate": 3.386512217606339e-06,
      "loss": 0.979,
      "step": 180
    },
    {
      "epoch": 1.3439999999999999,
      "grad_norm": 1.2804196573941362,
      "learning_rate": 2.9010282021444008e-06,
      "loss": 0.9475,
      "step": 210
    },
    {
      "epoch": 1.536,
      "grad_norm": 1.4317291029384576,
      "learning_rate": 2.399335149726463e-06,
      "loss": 0.9448,
      "step": 240
    },
    {
      "epoch": 1.728,
      "grad_norm": 1.3007829385541925,
      "learning_rate": 1.9017108392811065e-06,
      "loss": 0.948,
      "step": 270
    },
    {
      "epoch": 1.92,
      "grad_norm": 1.3074797323905452,
      "learning_rate": 1.4282685964923643e-06,
      "loss": 0.9441,
      "step": 300
    },
    {
      "epoch": 2.112,
      "grad_norm": 1.3722511438236185,
      "learning_rate": 9.981443394050525e-07,
      "loss": 0.8881,
      "step": 330
    },
    {
      "epoch": 2.304,
      "grad_norm": 1.3473061104065585,
      "learning_rate": 6.28723129572247e-07,
      "loss": 0.8517,
      "step": 360
    },
    {
      "epoch": 2.496,
      "grad_norm": 1.4273254376199542,
      "learning_rate": 3.3493649053890325e-07,
      "loss": 0.8528,
      "step": 390
    },
    {
      "epoch": 2.6879999999999997,
      "grad_norm": 1.3593903671680356,
      "learning_rate": 1.286588951321363e-07,
      "loss": 0.85,
      "step": 420
    },
    {
      "epoch": 2.88,
      "grad_norm": 1.372755113165561,
      "learning_rate": 1.822781475486507e-08,
      "loss": 0.8456,
      "step": 450
    },
    {
      "epoch": 2.9952,
      "step": 468,
      "total_flos": 80591486713856.0,
      "train_loss": 0.9765883449815277,
      "train_runtime": 2615.9926,
      "train_samples_per_second": 22.936,
      "train_steps_per_second": 0.179
    }
  ],
  "logging_steps": 30,
  "max_steps": 468,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 80591486713856.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}