checkpoint-2850/trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.0,
  "global_step": 2850,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21,
      "learning_rate": 1e-05,
      "loss": 0.65,
      "step": 100
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 0.4943,
      "step": 200
    },
    {
      "epoch": 0.63,
      "learning_rate": 3e-05,
      "loss": 0.4019,
      "step": 300
    },
    {
      "epoch": 0.84,
      "learning_rate": 4e-05,
      "loss": 0.4193,
      "step": 400
    },
    {
      "epoch": 1.05,
      "learning_rate": 5e-05,
      "loss": 0.3961,
      "step": 500
    },
    {
      "epoch": 1.26,
      "learning_rate": 4.787234042553192e-05,
      "loss": 0.324,
      "step": 600
    },
    {
      "epoch": 1.47,
      "learning_rate": 4.574468085106383e-05,
      "loss": 0.3471,
      "step": 700
    },
    {
      "epoch": 1.68,
      "learning_rate": 4.3617021276595746e-05,
      "loss": 0.287,
      "step": 800
    },
    {
      "epoch": 1.89,
      "learning_rate": 4.148936170212766e-05,
      "loss": 0.2373,
      "step": 900
    },
    {
      "epoch": 2.11,
      "learning_rate": 3.936170212765958e-05,
      "loss": 0.2729,
      "step": 1000
    },
    {
      "epoch": 2.32,
      "learning_rate": 3.723404255319149e-05,
      "loss": 0.1955,
      "step": 1100
    },
    {
      "epoch": 2.53,
      "learning_rate": 3.5106382978723407e-05,
      "loss": 0.1929,
      "step": 1200
    },
    {
      "epoch": 2.74,
      "learning_rate": 3.2978723404255317e-05,
      "loss": 0.1849,
      "step": 1300
    },
    {
      "epoch": 2.95,
      "learning_rate": 3.085106382978723e-05,
      "loss": 0.2012,
      "step": 1400
    },
    {
      "epoch": 3.16,
      "learning_rate": 2.8723404255319154e-05,
      "loss": 0.152,
      "step": 1500
    },
    {
      "epoch": 3.37,
      "learning_rate": 2.6595744680851064e-05,
      "loss": 0.1388,
      "step": 1600
    },
    {
      "epoch": 3.58,
      "learning_rate": 2.446808510638298e-05,
      "loss": 0.1337,
      "step": 1700
    },
    {
      "epoch": 3.79,
      "learning_rate": 2.2340425531914894e-05,
      "loss": 0.1571,
      "step": 1800
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.0212765957446807e-05,
      "loss": 0.1088,
      "step": 1900
    },
    {
      "epoch": 4.21,
      "learning_rate": 1.8085106382978724e-05,
      "loss": 0.0701,
      "step": 2000
    },
    {
      "epoch": 4.42,
      "learning_rate": 1.595744680851064e-05,
      "loss": 0.0853,
      "step": 2100
    },
    {
      "epoch": 4.63,
      "learning_rate": 1.3829787234042554e-05,
      "loss": 0.0923,
      "step": 2200
    },
    {
      "epoch": 4.84,
      "learning_rate": 1.170212765957447e-05,
      "loss": 0.0695,
      "step": 2300
    },
    {
      "epoch": 5.05,
      "learning_rate": 9.574468085106383e-06,
      "loss": 0.0867,
      "step": 2400
    },
    {
      "epoch": 5.26,
      "learning_rate": 7.446808510638298e-06,
      "loss": 0.0371,
      "step": 2500
    },
    {
      "epoch": 5.47,
      "learning_rate": 5.319148936170213e-06,
      "loss": 0.0201,
      "step": 2600
    },
    {
      "epoch": 5.68,
      "learning_rate": 3.1914893617021277e-06,
      "loss": 0.0141,
      "step": 2700
    },
    {
      "epoch": 5.89,
      "learning_rate": 1.0638297872340427e-06,
      "loss": 0.1063,
      "step": 2800
    }
  ],
  "max_steps": 2850,
  "num_train_epochs": 6,
  "total_flos": 5994196063211520.0,
  "trial_name": null,
  "trial_params": null
}