checkpoint-197/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 197,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10152284263959391,
      "grad_norm": 0.2823072373867035,
      "learning_rate": 3.9948625730435075e-05,
      "loss": 2.8273,
      "step": 10
    },
    {
      "epoch": 0.20304568527918782,
      "grad_norm": 0.2618003189563751,
      "learning_rate": 3.969770236712935e-05,
      "loss": 2.6708,
      "step": 20
    },
    {
      "epoch": 0.30456852791878175,
      "grad_norm": 0.24902400374412537,
      "learning_rate": 3.9240711835383766e-05,
      "loss": 2.495,
      "step": 30
    },
    {
      "epoch": 0.40609137055837563,
      "grad_norm": 0.21406474709510803,
      "learning_rate": 3.858297520699212e-05,
      "loss": 2.3206,
      "step": 40
    },
    {
      "epoch": 0.5076142131979695,
      "grad_norm": 0.24804013967514038,
      "learning_rate": 3.7732150985966965e-05,
      "loss": 2.1775,
      "step": 50
    },
    {
      "epoch": 0.6091370558375635,
      "grad_norm": 0.28641432523727417,
      "learning_rate": 3.6698145935029794e-05,
      "loss": 1.9521,
      "step": 60
    },
    {
      "epoch": 0.7106598984771574,
      "grad_norm": 0.3936513066291809,
      "learning_rate": 3.5492999723996456e-05,
      "loss": 1.7139,
      "step": 70
    },
    {
      "epoch": 0.8121827411167513,
      "grad_norm": 0.2143162190914154,
      "learning_rate": 3.41307447431802e-05,
      "loss": 1.4854,
      "step": 80
    },
    {
      "epoch": 0.9137055837563451,
      "grad_norm": 0.08941923081874847,
      "learning_rate": 3.262724271410661e-05,
      "loss": 1.3727,
      "step": 90
    },
    {
      "epoch": 1.015228426395939,
      "grad_norm": 0.08629459887742996,
      "learning_rate": 3.1e-05,
      "loss": 1.3856,
      "step": 100
    },
    {
      "epoch": 1.116751269035533,
      "grad_norm": 0.07598450779914856,
      "learning_rate": 2.9267963766515236e-05,
      "loss": 1.3676,
      "step": 110
    },
    {
      "epoch": 1.218274111675127,
      "grad_norm": 0.08433938026428223,
      "learning_rate": 2.7451301366163116e-05,
      "loss": 1.3437,
      "step": 120
    },
    {
      "epoch": 1.3197969543147208,
      "grad_norm": 0.06350907683372498,
      "learning_rate": 2.557116551521642e-05,
      "loss": 1.3879,
      "step": 130
    },
    {
      "epoch": 1.4213197969543148,
      "grad_norm": 0.07121391594409943,
      "learning_rate": 2.364944799731179e-05,
      "loss": 1.3591,
      "step": 140
    },
    {
      "epoch": 1.5228426395939088,
      "grad_norm": 0.0733482763171196,
      "learning_rate": 2.1708524761554973e-05,
      "loss": 1.3315,
      "step": 150
    },
    {
      "epoch": 1.6243654822335025,
      "grad_norm": 0.08874043822288513,
      "learning_rate": 1.9770995383136862e-05,
      "loss": 1.3264,
      "step": 160
    },
    {
      "epoch": 1.7258883248730963,
      "grad_norm": 0.07142503559589386,
      "learning_rate": 1.7859419920108888e-05,
      "loss": 1.3342,
      "step": 170
    },
    {
      "epoch": 1.8274111675126905,
      "grad_norm": 0.07405081391334534,
      "learning_rate": 1.5996056230285237e-05,
      "loss": 1.325,
      "step": 180
    },
    {
      "epoch": 1.9289340101522843,
      "grad_norm": 0.07454005628824234,
      "learning_rate": 1.420260080688125e-05,
      "loss": 1.3448,
      "step": 190
    }
  ],
  "logging_steps": 10,
  "max_steps": 294,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.326952425476096e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}