trainer_state.json

{
  "best_metric": 0.9295774647887324,
  "best_model_checkpoint": "test\\checkpoint-500",
  "epoch": 90.9090909090909,
  "eval_steps": 100,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.090909090909092,
      "eval_accuracy": 0.9558011049723757,
      "eval_f1": 0.9382022471910112,
      "eval_loss": 0.29965895414352417,
      "eval_precision": 0.9542857142857143,
      "eval_recall": 0.9226519337016574,
      "eval_runtime": 1.1706,
      "eval_samples_per_second": 18.793,
      "eval_steps_per_second": 2.563,
      "step": 100
    },
    {
      "epoch": 18.181818181818183,
      "eval_accuracy": 0.9447513812154696,
      "eval_f1": 0.923943661971831,
      "eval_loss": 0.372881144285202,
      "eval_precision": 0.9425287356321839,
      "eval_recall": 0.9060773480662984,
      "eval_runtime": 1.142,
      "eval_samples_per_second": 19.265,
      "eval_steps_per_second": 2.627,
      "step": 200
    },
    {
      "epoch": 27.272727272727273,
      "eval_accuracy": 0.9558011049723757,
      "eval_f1": 0.9382022471910112,
      "eval_loss": 0.34077441692352295,
      "eval_precision": 0.9542857142857143,
      "eval_recall": 0.9226519337016574,
      "eval_runtime": 1.1531,
      "eval_samples_per_second": 19.078,
      "eval_steps_per_second": 2.602,
      "step": 300
    },
    {
      "epoch": 36.36363636363637,
      "eval_accuracy": 0.9502762430939227,
      "eval_f1": 0.9295774647887324,
      "eval_loss": 0.3566364049911499,
      "eval_precision": 0.9482758620689655,
      "eval_recall": 0.9116022099447514,
      "eval_runtime": 1.1486,
      "eval_samples_per_second": 19.153,
      "eval_steps_per_second": 2.612,
      "step": 400
    },
    {
      "epoch": 45.45454545454545,
      "grad_norm": 0.019077150151133537,
      "learning_rate": 5e-06,
      "loss": 0.0997,
      "step": 500
    },
    {
      "epoch": 45.45454545454545,
      "eval_accuracy": 0.9502762430939227,
      "eval_f1": 0.9295774647887324,
      "eval_loss": 0.36847400665283203,
      "eval_precision": 0.9482758620689655,
      "eval_recall": 0.9116022099447514,
      "eval_runtime": 1.1347,
      "eval_samples_per_second": 19.388,
      "eval_steps_per_second": 2.644,
      "step": 500
    },
    {
      "epoch": 54.54545454545455,
      "eval_accuracy": 0.9502762430939227,
      "eval_f1": 0.9295774647887324,
      "eval_loss": 0.373576819896698,
      "eval_precision": 0.9482758620689655,
      "eval_recall": 0.9116022099447514,
      "eval_runtime": 1.1846,
      "eval_samples_per_second": 18.571,
      "eval_steps_per_second": 2.532,
      "step": 600
    },
    {
      "epoch": 63.63636363636363,
      "eval_accuracy": 0.9502762430939227,
      "eval_f1": 0.9295774647887324,
      "eval_loss": 0.3865794837474823,
      "eval_precision": 0.9482758620689655,
      "eval_recall": 0.9116022099447514,
      "eval_runtime": 1.1816,
      "eval_samples_per_second": 18.619,
      "eval_steps_per_second": 2.539,
      "step": 700
    },
    {
      "epoch": 72.72727272727273,
      "eval_accuracy": 0.9502762430939227,
      "eval_f1": 0.9295774647887324,
      "eval_loss": 0.398957759141922,
      "eval_precision": 0.9482758620689655,
      "eval_recall": 0.9116022099447514,
      "eval_runtime": 1.1845,
      "eval_samples_per_second": 18.574,
      "eval_steps_per_second": 2.533,
      "step": 800
    },
    {
      "epoch": 81.81818181818181,
      "eval_accuracy": 0.9502762430939227,
      "eval_f1": 0.9295774647887324,
      "eval_loss": 0.401752769947052,
      "eval_precision": 0.9482758620689655,
      "eval_recall": 0.9116022099447514,
      "eval_runtime": 1.1859,
      "eval_samples_per_second": 18.551,
      "eval_steps_per_second": 2.53,
      "step": 900
    },
    {
      "epoch": 90.9090909090909,
      "grad_norm": 0.01136627048254013,
      "learning_rate": 0.0,
      "loss": 0.001,
      "step": 1000
    },
    {
      "epoch": 90.9090909090909,
      "eval_accuracy": 0.9502762430939227,
      "eval_f1": 0.9295774647887324,
      "eval_loss": 0.39788535237312317,
      "eval_precision": 0.9482758620689655,
      "eval_recall": 0.9116022099447514,
      "eval_runtime": 1.1728,
      "eval_samples_per_second": 18.759,
      "eval_steps_per_second": 2.558,
      "step": 1000
    },
    {
      "epoch": 90.9090909090909,
      "step": 1000,
      "total_flos": 2061430731509760.0,
      "train_loss": 0.05030770355463028,
      "train_runtime": 605.6405,
      "train_samples_per_second": 13.209,
      "train_steps_per_second": 1.651
    }
  ],
  "logging_steps": 500,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 91,
  "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": 2061430731509760.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}