trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.99660441426146,
  "eval_steps": 50,
  "global_step": 294,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 3e-05,
      "loss": 1.2025,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 3e-05,
      "loss": 1.1367,
      "step": 20
    },
    {
      "epoch": 0.2,
      "learning_rate": 3e-05,
      "loss": 1.1325,
      "step": 30
    },
    {
      "epoch": 0.27,
      "learning_rate": 3e-05,
      "loss": 1.1111,
      "step": 40
    },
    {
      "epoch": 0.34,
      "learning_rate": 3e-05,
      "loss": 1.1008,
      "step": 50
    },
    {
      "epoch": 0.34,
      "eval_loss": 1.1499062776565552,
      "eval_runtime": 15.0698,
      "eval_samples_per_second": 17.386,
      "eval_steps_per_second": 4.38,
      "step": 50
    },
    {
      "epoch": 0.41,
      "learning_rate": 3e-05,
      "loss": 1.0935,
      "step": 60
    },
    {
      "epoch": 0.48,
      "learning_rate": 3e-05,
      "loss": 1.0925,
      "step": 70
    },
    {
      "epoch": 0.54,
      "learning_rate": 3e-05,
      "loss": 1.1389,
      "step": 80
    },
    {
      "epoch": 0.61,
      "learning_rate": 3e-05,
      "loss": 1.1186,
      "step": 90
    },
    {
      "epoch": 0.68,
      "learning_rate": 3e-05,
      "loss": 1.0663,
      "step": 100
    },
    {
      "epoch": 0.68,
      "eval_loss": 1.1313854455947876,
      "eval_runtime": 15.0724,
      "eval_samples_per_second": 17.383,
      "eval_steps_per_second": 4.379,
      "step": 100
    },
    {
      "epoch": 0.75,
      "learning_rate": 3e-05,
      "loss": 1.0572,
      "step": 110
    },
    {
      "epoch": 0.81,
      "learning_rate": 3e-05,
      "loss": 1.1099,
      "step": 120
    },
    {
      "epoch": 0.88,
      "learning_rate": 3e-05,
      "loss": 1.094,
      "step": 130
    },
    {
      "epoch": 0.95,
      "learning_rate": 3e-05,
      "loss": 1.074,
      "step": 140
    },
    {
      "epoch": 1.02,
      "learning_rate": 3e-05,
      "loss": 1.04,
      "step": 150
    },
    {
      "epoch": 1.02,
      "eval_loss": 1.1262978315353394,
      "eval_runtime": 15.1147,
      "eval_samples_per_second": 17.334,
      "eval_steps_per_second": 4.367,
      "step": 150
    },
    {
      "epoch": 1.09,
      "learning_rate": 3e-05,
      "loss": 0.9901,
      "step": 160
    },
    {
      "epoch": 1.15,
      "learning_rate": 3e-05,
      "loss": 1.0634,
      "step": 170
    },
    {
      "epoch": 1.22,
      "learning_rate": 3e-05,
      "loss": 0.9784,
      "step": 180
    },
    {
      "epoch": 1.29,
      "learning_rate": 3e-05,
      "loss": 0.9506,
      "step": 190
    },
    {
      "epoch": 1.36,
      "learning_rate": 3e-05,
      "loss": 1.0182,
      "step": 200
    },
    {
      "epoch": 1.36,
      "eval_loss": 1.1319481134414673,
      "eval_runtime": 15.0625,
      "eval_samples_per_second": 17.394,
      "eval_steps_per_second": 4.382,
      "step": 200
    },
    {
      "epoch": 1.43,
      "learning_rate": 3e-05,
      "loss": 0.9876,
      "step": 210
    },
    {
      "epoch": 1.49,
      "learning_rate": 3e-05,
      "loss": 0.9059,
      "step": 220
    },
    {
      "epoch": 1.56,
      "learning_rate": 3e-05,
      "loss": 0.997,
      "step": 230
    },
    {
      "epoch": 1.63,
      "learning_rate": 3e-05,
      "loss": 0.9893,
      "step": 240
    },
    {
      "epoch": 1.7,
      "learning_rate": 3e-05,
      "loss": 1.0291,
      "step": 250
    },
    {
      "epoch": 1.7,
      "eval_loss": 1.1290254592895508,
      "eval_runtime": 15.0498,
      "eval_samples_per_second": 17.409,
      "eval_steps_per_second": 4.385,
      "step": 250
    },
    {
      "epoch": 1.77,
      "learning_rate": 3e-05,
      "loss": 0.966,
      "step": 260
    },
    {
      "epoch": 1.83,
      "learning_rate": 3e-05,
      "loss": 1.0419,
      "step": 270
    },
    {
      "epoch": 1.9,
      "learning_rate": 3e-05,
      "loss": 0.9625,
      "step": 280
    },
    {
      "epoch": 1.97,
      "learning_rate": 3e-05,
      "loss": 0.9313,
      "step": 290
    },
    {
      "epoch": 2.0,
      "step": 294,
      "total_flos": 7.119009482145792e+16,
      "train_loss": 1.0449795049874961,
      "train_runtime": 831.3165,
      "train_samples_per_second": 5.668,
      "train_steps_per_second": 0.354
    }
  ],
  "logging_steps": 10,
  "max_steps": 294,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 250,
  "total_flos": 7.119009482145792e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}