checkpoint-121/trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 121,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08307372793354102,
      "grad_norm": 1.962915062904358,
      "learning_rate": 0.0001950413223140496,
      "loss": 2.3273,
      "step": 10
    },
    {
      "epoch": 0.16614745586708204,
      "grad_norm": 1.6449666023254395,
      "learning_rate": 0.00018953168044077135,
      "loss": 1.7616,
      "step": 20
    },
    {
      "epoch": 0.24922118380062305,
      "grad_norm": 1.6963361501693726,
      "learning_rate": 0.0001840220385674931,
      "loss": 1.6516,
      "step": 30
    },
    {
      "epoch": 0.3322949117341641,
      "grad_norm": 1.6359336376190186,
      "learning_rate": 0.00017851239669421489,
      "loss": 1.7249,
      "step": 40
    },
    {
      "epoch": 0.4153686396677051,
      "grad_norm": 1.0282535552978516,
      "learning_rate": 0.00017300275482093664,
      "loss": 1.4954,
      "step": 50
    },
    {
      "epoch": 0.4984423676012461,
      "grad_norm": 1.546828031539917,
      "learning_rate": 0.00016749311294765842,
      "loss": 1.5683,
      "step": 60
    },
    {
      "epoch": 0.5815160955347871,
      "grad_norm": 1.2639796733856201,
      "learning_rate": 0.00016198347107438017,
      "loss": 1.5565,
      "step": 70
    },
    {
      "epoch": 0.6645898234683282,
      "grad_norm": 1.4530669450759888,
      "learning_rate": 0.00015647382920110195,
      "loss": 1.5476,
      "step": 80
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 1.5613621473312378,
      "learning_rate": 0.0001509641873278237,
      "loss": 1.6268,
      "step": 90
    },
    {
      "epoch": 0.8307372793354102,
      "grad_norm": 1.1224900484085083,
      "learning_rate": 0.00014545454545454546,
      "loss": 1.4214,
      "step": 100
    },
    {
      "epoch": 0.9138110072689511,
      "grad_norm": 1.2382973432540894,
      "learning_rate": 0.0001399449035812672,
      "loss": 1.5272,
      "step": 110
    },
    {
      "epoch": 0.9968847352024922,
      "grad_norm": 1.1352381706237793,
      "learning_rate": 0.000134435261707989,
      "loss": 1.5175,
      "step": 120
    }
  ],
  "logging_steps": 10,
  "max_steps": 363,
  "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": 961341358153728.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}