trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 8842,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0565482922415743,
      "grad_norm": 6.099003791809082,
      "learning_rate": 4.7172585387921285e-05,
      "loss": 5.2788,
      "step": 500
    },
    {
      "epoch": 0.1130965844831486,
      "grad_norm": 4.438333988189697,
      "learning_rate": 4.434517077584257e-05,
      "loss": 4.8237,
      "step": 1000
    },
    {
      "epoch": 0.16964487672472292,
      "grad_norm": 5.307681083679199,
      "learning_rate": 4.1517756163763856e-05,
      "loss": 4.737,
      "step": 1500
    },
    {
      "epoch": 0.2261931689662972,
      "grad_norm": 5.611371040344238,
      "learning_rate": 3.869034155168514e-05,
      "loss": 4.6918,
      "step": 2000
    },
    {
      "epoch": 0.2827414612078715,
      "grad_norm": 5.551920413970947,
      "learning_rate": 3.586292693960643e-05,
      "loss": 4.6628,
      "step": 2500
    },
    {
      "epoch": 0.33928975344944584,
      "grad_norm": 5.272426605224609,
      "learning_rate": 3.303551232752771e-05,
      "loss": 4.6474,
      "step": 3000
    },
    {
      "epoch": 0.39583804569102016,
      "grad_norm": 5.137388229370117,
      "learning_rate": 3.0208097715448996e-05,
      "loss": 4.6272,
      "step": 3500
    },
    {
      "epoch": 0.4523863379325944,
      "grad_norm": 6.018069744110107,
      "learning_rate": 2.7380683103370282e-05,
      "loss": 4.6025,
      "step": 4000
    },
    {
      "epoch": 0.5089346301741687,
      "grad_norm": 5.987523555755615,
      "learning_rate": 2.4553268491291564e-05,
      "loss": 4.5791,
      "step": 4500
    },
    {
      "epoch": 0.565482922415743,
      "grad_norm": 5.519354820251465,
      "learning_rate": 2.172585387921285e-05,
      "loss": 4.5844,
      "step": 5000
    },
    {
      "epoch": 0.6220312146573174,
      "grad_norm": 5.536919593811035,
      "learning_rate": 1.8898439267134132e-05,
      "loss": 4.5647,
      "step": 5500
    },
    {
      "epoch": 0.6785795068988917,
      "grad_norm": 5.017457962036133,
      "learning_rate": 1.6071024655055418e-05,
      "loss": 4.5574,
      "step": 6000
    },
    {
      "epoch": 0.735127799140466,
      "grad_norm": 5.590214252471924,
      "learning_rate": 1.3243610042976704e-05,
      "loss": 4.548,
      "step": 6500
    },
    {
      "epoch": 0.7916760913820403,
      "grad_norm": 4.2981181144714355,
      "learning_rate": 1.0416195430897988e-05,
      "loss": 4.5641,
      "step": 7000
    },
    {
      "epoch": 0.8482243836236145,
      "grad_norm": 5.723196983337402,
      "learning_rate": 7.588780818819271e-06,
      "loss": 4.5633,
      "step": 7500
    },
    {
      "epoch": 0.9047726758651888,
      "grad_norm": 5.700985431671143,
      "learning_rate": 4.761366206740556e-06,
      "loss": 4.5486,
      "step": 8000
    },
    {
      "epoch": 0.9613209681067632,
      "grad_norm": 5.034333229064941,
      "learning_rate": 1.9339515946618415e-06,
      "loss": 4.5307,
      "step": 8500
    }
  ],
  "logging_steps": 500,
  "max_steps": 8842,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3333874049690624e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}