redpj7B-lora-cnn-dailymail-results_6000_samples/checkpoint-600/trainer_state.json

{
  "best_metric": 1.9635850191116333,
  "best_model_checkpoint": "./results/redpj7B-lora-cnn-dailymail-results_fine_tune_test/checkpoint-600",
  "epoch": 0.19900497512437812,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.00027082228116710874,
      "loss": 1.8654,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0002681697612732095,
      "loss": 1.8124,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0002655172413793103,
      "loss": 1.8231,
      "step": 60
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002628647214854111,
      "loss": 1.7818,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00026021220159151194,
      "loss": 1.8446,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002575596816976127,
      "loss": 1.9001,
      "step": 120
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002549071618037135,
      "loss": 1.8073,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0002522546419098143,
      "loss": 1.8506,
      "step": 160
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002496021220159151,
      "loss": 1.8471,
      "step": 180
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002469496021220159,
      "loss": 1.8647,
      "step": 200
    },
    {
      "epoch": 0.07,
      "eval_loss": 1.966022253036499,
      "eval_runtime": 12002.3952,
      "eval_samples_per_second": 1.114,
      "eval_steps_per_second": 0.139,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00024429708222811666,
      "loss": 1.8578,
      "step": 220
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002416445623342175,
      "loss": 1.8329,
      "step": 240
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002389920424403183,
      "loss": 1.8119,
      "step": 260
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002363395225464191,
      "loss": 1.8884,
      "step": 280
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00023368700265251986,
      "loss": 1.9077,
      "step": 300
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00023103448275862065,
      "loss": 1.8092,
      "step": 320
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00022838196286472146,
      "loss": 1.9237,
      "step": 340
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00022572944297082225,
      "loss": 1.8701,
      "step": 360
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00022307692307692306,
      "loss": 1.8933,
      "step": 380
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00022042440318302385,
      "loss": 1.8453,
      "step": 400
    },
    {
      "epoch": 0.13,
      "eval_loss": 1.9667036533355713,
      "eval_runtime": 11991.8036,
      "eval_samples_per_second": 1.115,
      "eval_steps_per_second": 0.139,
      "step": 400
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00021777188328912466,
      "loss": 1.8272,
      "step": 420
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00021511936339522545,
      "loss": 1.8149,
      "step": 440
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00021246684350132626,
      "loss": 1.8565,
      "step": 460
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00020981432360742705,
      "loss": 1.8139,
      "step": 480
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0002071618037135278,
      "loss": 1.802,
      "step": 500
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00020450928381962862,
      "loss": 1.8795,
      "step": 520
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002018567639257294,
      "loss": 1.8621,
      "step": 540
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019920424403183022,
      "loss": 1.8363,
      "step": 560
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000196551724137931,
      "loss": 1.8746,
      "step": 580
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019389920424403182,
      "loss": 1.7763,
      "step": 600
    },
    {
      "epoch": 0.2,
      "eval_loss": 1.9635850191116333,
      "eval_runtime": 11976.5234,
      "eval_samples_per_second": 1.116,
      "eval_steps_per_second": 0.14,
      "step": 600
    }
  ],
  "max_steps": 9045,
  "num_train_epochs": 3,
  "total_flos": 3.74219846516736e+16,
  "trial_name": null,
  "trial_params": null
}