checkpoint-1000/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4911591355599214,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 8.999464304375242e-06,
      "loss": 0.7019,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.997857345043108e-06,
      "loss": 0.6739,
      "step": 100
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.99517950459963e-06,
      "loss": 0.6677,
      "step": 150
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.99143142060366e-06,
      "loss": 0.6625,
      "step": 200
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.98661398542506e-06,
      "loss": 0.6649,
      "step": 250
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.980728346032255e-06,
      "loss": 0.6528,
      "step": 300
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.973775903719142e-06,
      "loss": 0.6442,
      "step": 350
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.965758313771466e-06,
      "loss": 0.6375,
      "step": 400
    },
    {
      "epoch": 0.22,
      "learning_rate": 8.956677485072722e-06,
      "loss": 0.6303,
      "step": 450
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.946535579649664e-06,
      "loss": 0.634,
      "step": 500
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.0,
      "eval_loss": 0.6457224488258362,
      "eval_runtime": 154.2695,
      "eval_samples_per_second": 87.989,
      "eval_steps_per_second": 14.669,
      "step": 500
    },
    {
      "epoch": 0.27,
      "learning_rate": 8.935335012157564e-06,
      "loss": 0.6236,
      "step": 550
    },
    {
      "epoch": 0.29,
      "learning_rate": 8.92307844930531e-06,
      "loss": 0.6235,
      "step": 600
    },
    {
      "epoch": 0.32,
      "learning_rate": 8.909768809220503e-06,
      "loss": 0.6301,
      "step": 650
    },
    {
      "epoch": 0.34,
      "learning_rate": 8.895409260754679e-06,
      "loss": 0.6227,
      "step": 700
    },
    {
      "epoch": 0.37,
      "learning_rate": 8.880003222728855e-06,
      "loss": 0.6187,
      "step": 750
    },
    {
      "epoch": 0.39,
      "learning_rate": 8.863554363119547e-06,
      "loss": 0.6201,
      "step": 800
    },
    {
      "epoch": 0.42,
      "learning_rate": 8.846066598185479e-06,
      "loss": 0.614,
      "step": 850
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.827544091535166e-06,
      "loss": 0.607,
      "step": 900
    },
    {
      "epoch": 0.47,
      "learning_rate": 8.80799125313562e-06,
      "loss": 0.6176,
      "step": 950
    },
    {
      "epoch": 0.49,
      "learning_rate": 8.787412738262386e-06,
      "loss": 0.5999,
      "step": 1000
    },
    {
      "epoch": 0.49,
      "eval_accuracy": 0.0,
      "eval_loss": 0.6475000977516174,
      "eval_runtime": 154.4877,
      "eval_samples_per_second": 87.865,
      "eval_steps_per_second": 14.648,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 10180,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}