{
  "best_metric": 1.814998745918274,
  "best_model_checkpoint": "/home/ubuntu/workplace/NER_simi/output/LLM_05_13/checkpoint-1000",
  "epoch": 0.5675368898978433,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 3.147441434337073e-05,
      "loss": 2.3247,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.705117131325856e-05,
      "loss": 1.9413,
      "step": 100
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.031336501627827e-05,
      "loss": 1.8845,
      "step": 150
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.262792828314637e-05,
      "loss": 1.8492,
      "step": 200
    },
    {
      "epoch": 0.11,
      "eval_loss": 1.9344485998153687,
      "eval_runtime": 336.1736,
      "eval_samples_per_second": 95.918,
      "eval_steps_per_second": 0.75,
      "step": 200
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.442324303011218e-05,
      "loss": 1.8316,
      "step": 250
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.589012198616609e-05,
      "loss": 1.8137,
      "step": 300
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.713035047190436e-05,
      "loss": 1.7988,
      "step": 350
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.82046852530342e-05,
      "loss": 1.7873,
      "step": 400
    },
    {
      "epoch": 0.23,
      "eval_loss": 1.8653844594955444,
      "eval_runtime": 336.5787,
      "eval_samples_per_second": 95.802,
      "eval_steps_per_second": 0.749,
      "step": 400
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.915231568918581e-05,
      "loss": 1.7599,
      "step": 450
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-05,
      "loss": 1.7658,
      "step": 500
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 1.7534,
      "step": 550
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 1.7399,
      "step": 600
    },
    {
      "epoch": 0.34,
      "eval_loss": 1.8613653182983398,
      "eval_runtime": 336.3899,
      "eval_samples_per_second": 95.856,
      "eval_steps_per_second": 0.749,
      "step": 600
    },
    {
      "epoch": 0.37,
      "learning_rate": 5e-05,
      "loss": 1.7327,
      "step": 650
    },
    {
      "epoch": 0.4,
      "learning_rate": 5e-05,
      "loss": 1.7445,
      "step": 700
    },
    {
      "epoch": 0.43,
      "learning_rate": 5e-05,
      "loss": 1.7255,
      "step": 750
    },
    {
      "epoch": 0.45,
      "learning_rate": 5e-05,
      "loss": 1.7249,
      "step": 800
    },
    {
      "epoch": 0.45,
      "eval_loss": 1.8731602430343628,
      "eval_runtime": 336.4325,
      "eval_samples_per_second": 95.844,
      "eval_steps_per_second": 0.749,
      "step": 800
    },
    {
      "epoch": 0.48,
      "learning_rate": 5e-05,
      "loss": 1.7257,
      "step": 850
    },
    {
      "epoch": 0.51,
      "learning_rate": 5e-05,
      "loss": 1.7176,
      "step": 900
    },
    {
      "epoch": 0.54,
      "learning_rate": 5e-05,
      "loss": 1.708,
      "step": 950
    },
    {
      "epoch": 0.57,
      "learning_rate": 5e-05,
      "loss": 1.7116,
      "step": 1000
    },
    {
      "epoch": 0.57,
      "eval_loss": 1.814998745918274,
      "eval_runtime": 336.1286,
      "eval_samples_per_second": 95.931,
      "eval_steps_per_second": 0.75,
      "step": 1000
    }
  ],
  "max_steps": 1762,
  "num_train_epochs": 1,
  "total_flos": 196298259038208.0,
  "trial_name": null,
  "trial_params": null
}