trainer_state.json

{
  "best_metric": 0.46181365847587585,
  "best_model_checkpoint": "/content/drive/MyDrive/Medical_notes/./checkpoints/Baichuan2-7B-Chat-finetuned-Eng_Instruction/checkpoint-1200",
  "epoch": 0.8,
  "eval_steps": 200,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 9.339559706470981e-06,
      "loss": 0.8721,
      "step": 100
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.67244829886591e-06,
      "loss": 0.6735,
      "step": 200
    },
    {
      "epoch": 0.13,
      "eval_loss": 0.6549514532089233,
      "eval_runtime": 96.5113,
      "eval_samples_per_second": 5.502,
      "eval_steps_per_second": 5.502,
      "step": 200
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.005336891260842e-06,
      "loss": 0.6019,
      "step": 300
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.338225483655771e-06,
      "loss": 0.5629,
      "step": 400
    },
    {
      "epoch": 0.27,
      "eval_loss": 0.5494726300239563,
      "eval_runtime": 96.4513,
      "eval_samples_per_second": 5.505,
      "eval_steps_per_second": 5.505,
      "step": 400
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.671114076050701e-06,
      "loss": 0.5096,
      "step": 500
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.004002668445631e-06,
      "loss": 0.5106,
      "step": 600
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.5072886347770691,
      "eval_runtime": 96.4115,
      "eval_samples_per_second": 5.508,
      "eval_steps_per_second": 5.508,
      "step": 600
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.336891260840561e-06,
      "loss": 0.4815,
      "step": 700
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.669779853235491e-06,
      "loss": 0.4649,
      "step": 800
    },
    {
      "epoch": 0.53,
      "eval_loss": 0.4842279851436615,
      "eval_runtime": 96.3738,
      "eval_samples_per_second": 5.51,
      "eval_steps_per_second": 5.51,
      "step": 800
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.002668445630421e-06,
      "loss": 0.5184,
      "step": 900
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.3355570380253505e-06,
      "loss": 0.4491,
      "step": 1000
    },
    {
      "epoch": 0.67,
      "eval_loss": 0.47028857469558716,
      "eval_runtime": 96.4169,
      "eval_samples_per_second": 5.507,
      "eval_steps_per_second": 5.507,
      "step": 1000
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.6684456304202807e-06,
      "loss": 0.4948,
      "step": 1100
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0013342228152104e-06,
      "loss": 0.4322,
      "step": 1200
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.46181365847587585,
      "eval_runtime": 96.4069,
      "eval_samples_per_second": 5.508,
      "eval_steps_per_second": 5.508,
      "step": 1200
    }
  ],
  "logging_steps": 100,
  "max_steps": 1500,
  "num_train_epochs": 1,
  "save_steps": 200,
  "total_flos": 1.8825566908022784e+16,
  "trial_name": null,
  "trial_params": null
}