trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9999347982004303,
  "eval_steps": 500,
  "global_step": 1917,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0521614396557345,
      "grad_norm": 6.860655307769775,
      "learning_rate": 9.895833333333334e-06,
      "loss": 0.2352,
      "step": 100
    },
    {
      "epoch": 0.104322879311469,
      "grad_norm": 0.910341203212738,
      "learning_rate": 1.996521739130435e-05,
      "loss": 0.0854,
      "step": 200
    },
    {
      "epoch": 0.1564843189672035,
      "grad_norm": 15.565857887268066,
      "learning_rate": 1.8817391304347828e-05,
      "loss": 0.0579,
      "step": 300
    },
    {
      "epoch": 0.208645758622938,
      "grad_norm": 8.692508697509766,
      "learning_rate": 1.7657971014492754e-05,
      "loss": 0.0662,
      "step": 400
    },
    {
      "epoch": 0.2608071982786725,
      "grad_norm": 0.031041253358125687,
      "learning_rate": 1.6510144927536233e-05,
      "loss": 0.0784,
      "step": 500
    },
    {
      "epoch": 0.312968637934407,
      "grad_norm": 3.0286190509796143,
      "learning_rate": 1.535072463768116e-05,
      "loss": 0.0975,
      "step": 600
    },
    {
      "epoch": 0.3651300775901415,
      "grad_norm": 17.107019424438477,
      "learning_rate": 1.4191304347826087e-05,
      "loss": 0.1162,
      "step": 700
    },
    {
      "epoch": 0.417291517245876,
      "grad_norm": 0.3376404047012329,
      "learning_rate": 1.3031884057971015e-05,
      "loss": 0.1132,
      "step": 800
    },
    {
      "epoch": 0.4694529569016105,
      "grad_norm": 0.49836966395378113,
      "learning_rate": 1.1872463768115942e-05,
      "loss": 0.192,
      "step": 900
    },
    {
      "epoch": 0.521614396557345,
      "grad_norm": 0.1673300564289093,
      "learning_rate": 1.071304347826087e-05,
      "loss": 0.1107,
      "step": 1000
    },
    {
      "epoch": 0.5737758362130795,
      "grad_norm": 1.4948456287384033,
      "learning_rate": 9.553623188405798e-06,
      "loss": 0.1355,
      "step": 1100
    },
    {
      "epoch": 0.625937275868814,
      "grad_norm": 2.7801311016082764,
      "learning_rate": 8.394202898550725e-06,
      "loss": 0.1275,
      "step": 1200
    },
    {
      "epoch": 0.6780987155245485,
      "grad_norm": 5.762394428253174,
      "learning_rate": 7.234782608695653e-06,
      "loss": 0.1514,
      "step": 1300
    },
    {
      "epoch": 0.730260155180283,
      "grad_norm": 3.5544540882110596,
      "learning_rate": 6.07536231884058e-06,
      "loss": 0.165,
      "step": 1400
    },
    {
      "epoch": 0.7824215948360175,
      "grad_norm": 15.184954643249512,
      "learning_rate": 4.915942028985508e-06,
      "loss": 0.1568,
      "step": 1500
    },
    {
      "epoch": 0.834583034491752,
      "grad_norm": 0.3603503108024597,
      "learning_rate": 3.7565217391304347e-06,
      "loss": 0.2338,
      "step": 1600
    },
    {
      "epoch": 0.8867444741474865,
      "grad_norm": 21.175050735473633,
      "learning_rate": 2.5971014492753625e-06,
      "loss": 0.2064,
      "step": 1700
    },
    {
      "epoch": 0.938905913803221,
      "grad_norm": 4.581367015838623,
      "learning_rate": 1.4376811594202899e-06,
      "loss": 0.3337,
      "step": 1800
    },
    {
      "epoch": 0.9910673534589555,
      "grad_norm": 627.7379760742188,
      "learning_rate": 2.7826086956521744e-07,
      "loss": 0.6769,
      "step": 1900
    }
  ],
  "logging_steps": 100,
  "max_steps": 1917,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}