checkpoint-60/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9968847352024922,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08307372793354102,
      "grad_norm": 0.5125107169151306,
      "learning_rate": 2.0833333333333334e-06,
      "loss": 3.5515,
      "step": 5
    },
    {
      "epoch": 0.16614745586708204,
      "grad_norm": 0.4532736539840698,
      "learning_rate": 4.166666666666667e-06,
      "loss": 3.6807,
      "step": 10
    },
    {
      "epoch": 0.24922118380062305,
      "grad_norm": 0.4483909606933594,
      "learning_rate": 6.25e-06,
      "loss": 3.5357,
      "step": 15
    },
    {
      "epoch": 0.3322949117341641,
      "grad_norm": 0.5020395517349243,
      "learning_rate": 8.333333333333334e-06,
      "loss": 3.645,
      "step": 20
    },
    {
      "epoch": 0.4153686396677051,
      "grad_norm": 0.8230155110359192,
      "learning_rate": 1.0416666666666668e-05,
      "loss": 3.5682,
      "step": 25
    },
    {
      "epoch": 0.4984423676012461,
      "grad_norm": 1.3333394527435303,
      "learning_rate": 1.25e-05,
      "loss": 3.5155,
      "step": 30
    },
    {
      "epoch": 0.5815160955347871,
      "grad_norm": 0.7118450999259949,
      "learning_rate": 1.4583333333333335e-05,
      "loss": 3.4724,
      "step": 35
    },
    {
      "epoch": 0.6645898234683282,
      "grad_norm": 1.0282073020935059,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 3.4205,
      "step": 40
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 1.0468826293945312,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 3.3295,
      "step": 45
    },
    {
      "epoch": 0.8307372793354102,
      "grad_norm": 0.8730693459510803,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 3.0831,
      "step": 50
    },
    {
      "epoch": 0.9138110072689511,
      "grad_norm": 0.9377574324607849,
      "learning_rate": 2.2916666666666667e-05,
      "loss": 2.8412,
      "step": 55
    },
    {
      "epoch": 0.9968847352024922,
      "grad_norm": 1.0129190683364868,
      "learning_rate": 2.5e-05,
      "loss": 2.3229,
      "step": 60
    }
  ],
  "logging_steps": 5,
  "max_steps": 1200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 60,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2621395037061120.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}