checkpoint-1300/trainer_state.json

{
  "best_metric": 2.561117649078369,
  "best_model_checkpoint": "./gpt2_dolly_lite/checkpoint-1300",
  "epoch": 0.9998077292828302,
  "eval_steps": 500,
  "global_step": 1300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "learning_rate": 0.0009871794871794872,
      "loss": 3.3078,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0009743589743589744,
      "loss": 3.1249,
      "step": 100
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0009615384615384616,
      "loss": 3.1026,
      "step": 150
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0009487179487179487,
      "loss": 3.0496,
      "step": 200
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000935897435897436,
      "loss": 2.9706,
      "step": 250
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0009230769230769232,
      "loss": 3.0195,
      "step": 300
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0009102564102564102,
      "loss": 2.9747,
      "step": 350
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0008974358974358974,
      "loss": 2.9205,
      "step": 400
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0008846153846153846,
      "loss": 2.9495,
      "step": 450
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0008717948717948718,
      "loss": 2.8866,
      "step": 500
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0008589743589743589,
      "loss": 2.892,
      "step": 550
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0008461538461538462,
      "loss": 2.8849,
      "step": 600
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0008333333333333334,
      "loss": 2.8819,
      "step": 650
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0008205128205128205,
      "loss": 2.8561,
      "step": 700
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0008076923076923078,
      "loss": 2.8311,
      "step": 750
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0007948717948717948,
      "loss": 2.8176,
      "step": 800
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.000782051282051282,
      "loss": 2.7782,
      "step": 850
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0007692307692307693,
      "loss": 2.7273,
      "step": 900
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0007564102564102564,
      "loss": 2.7686,
      "step": 950
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0007435897435897436,
      "loss": 2.7274,
      "step": 1000
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0007307692307692307,
      "loss": 2.7514,
      "step": 1050
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.000717948717948718,
      "loss": 2.7232,
      "step": 1100
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0007051282051282052,
      "loss": 2.6937,
      "step": 1150
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0006923076923076923,
      "loss": 2.7209,
      "step": 1200
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0006794871794871796,
      "loss": 2.6832,
      "step": 1250
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0006666666666666666,
      "loss": 2.708,
      "step": 1300
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.561117649078369,
      "eval_runtime": 41.0726,
      "eval_samples_per_second": 253.235,
      "eval_steps_per_second": 7.937,
      "step": 1300
    }
  ],
  "logging_steps": 50,
  "max_steps": 3900,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2217745708572672.0,
  "trial_name": null,
  "trial_params": null
}