checkpoint-900/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 34.013333333333335,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 11.1254,
      "step": 1
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00025,
      "loss": 8.9373,
      "step": 50
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.0005,
      "loss": 7.7501,
      "step": 100
    },
    {
      "epoch": 5.02,
      "learning_rate": 0.0005833333333333333,
      "loss": 7.5554,
      "step": 150
    },
    {
      "epoch": 7.01,
      "learning_rate": 0.0005555555555555556,
      "loss": 7.3707,
      "step": 200
    },
    {
      "epoch": 9.01,
      "learning_rate": 0.0005277777777777777,
      "loss": 7.1995,
      "step": 250
    },
    {
      "epoch": 11.01,
      "learning_rate": 0.0005,
      "loss": 7.0101,
      "step": 300
    },
    {
      "epoch": 13.01,
      "learning_rate": 0.00047222222222222224,
      "loss": 6.7643,
      "step": 350
    },
    {
      "epoch": 15.01,
      "learning_rate": 0.00044444444444444436,
      "loss": 6.5143,
      "step": 400
    },
    {
      "epoch": 17.01,
      "learning_rate": 0.00041666666666666664,
      "loss": 6.2988,
      "step": 450
    },
    {
      "epoch": 19.0,
      "learning_rate": 0.00038888888888888887,
      "loss": 6.0872,
      "step": 500
    },
    {
      "epoch": 21.0,
      "learning_rate": 0.0003611111111111111,
      "loss": 5.8851,
      "step": 550
    },
    {
      "epoch": 23.0,
      "learning_rate": 0.0003333333333333333,
      "loss": 5.7103,
      "step": 600
    },
    {
      "epoch": 24.02,
      "learning_rate": 0.00030555555555555555,
      "loss": 5.4879,
      "step": 650
    },
    {
      "epoch": 26.02,
      "learning_rate": 0.0002777777777777778,
      "loss": 5.4167,
      "step": 700
    },
    {
      "epoch": 28.02,
      "learning_rate": 0.00025,
      "loss": 5.289,
      "step": 750
    },
    {
      "epoch": 30.02,
      "learning_rate": 0.00022222222222222218,
      "loss": 5.1692,
      "step": 800
    },
    {
      "epoch": 32.02,
      "learning_rate": 0.00019444444444444443,
      "loss": 5.0667,
      "step": 850
    },
    {
      "epoch": 34.01,
      "learning_rate": 0.00016666666666666666,
      "loss": 4.974,
      "step": 900
    }
  ],
  "max_steps": 1200,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 2.46385844158464e+17,
  "trial_name": null,
  "trial_params": null
}