trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.935064935064935,
  "eval_steps": 500,
  "global_step": 190,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 0.0001,
      "loss": 2.0038,
      "step": 5
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001,
      "loss": 1.9796,
      "step": 10
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001,
      "loss": 1.9617,
      "step": 15
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0001,
      "loss": 2.0267,
      "step": 20
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0001,
      "loss": 1.9767,
      "step": 25
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0001,
      "loss": 1.9649,
      "step": 30
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0001,
      "loss": 2.0785,
      "step": 35
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.0001,
      "loss": 1.8929,
      "step": 40
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0001,
      "loss": 1.9942,
      "step": 45
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001,
      "loss": 1.8956,
      "step": 50
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001,
      "loss": 1.8971,
      "step": 55
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001,
      "loss": 1.8397,
      "step": 60
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0001,
      "loss": 1.9135,
      "step": 65
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.0001,
      "loss": 1.8782,
      "step": 70
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0001,
      "loss": 1.8756,
      "step": 75
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.0001,
      "loss": 1.887,
      "step": 80
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0001,
      "loss": 1.8408,
      "step": 85
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.0001,
      "loss": 1.8352,
      "step": 90
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0001,
      "loss": 1.8403,
      "step": 95
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.0001,
      "loss": 1.8519,
      "step": 100
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.0001,
      "loss": 1.8683,
      "step": 105
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0001,
      "loss": 1.8082,
      "step": 110
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.0001,
      "loss": 1.811,
      "step": 115
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.0001,
      "loss": 1.8451,
      "step": 120
    },
    {
      "epoch": 3.25,
      "learning_rate": 0.0001,
      "loss": 1.7562,
      "step": 125
    },
    {
      "epoch": 3.38,
      "learning_rate": 0.0001,
      "loss": 1.8435,
      "step": 130
    },
    {
      "epoch": 3.51,
      "learning_rate": 0.0001,
      "loss": 1.7416,
      "step": 135
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.0001,
      "loss": 1.8242,
      "step": 140
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.0001,
      "loss": 1.7191,
      "step": 145
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.0001,
      "loss": 1.8372,
      "step": 150
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.0001,
      "loss": 1.6897,
      "step": 155
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.0001,
      "loss": 1.7764,
      "step": 160
    },
    {
      "epoch": 4.29,
      "learning_rate": 0.0001,
      "loss": 1.7044,
      "step": 165
    },
    {
      "epoch": 4.42,
      "learning_rate": 0.0001,
      "loss": 1.6948,
      "step": 170
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.0001,
      "loss": 1.7268,
      "step": 175
    },
    {
      "epoch": 4.68,
      "learning_rate": 0.0001,
      "loss": 1.7703,
      "step": 180
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.0001,
      "loss": 1.7836,
      "step": 185
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.0001,
      "loss": 1.7871,
      "step": 190
    },
    {
      "epoch": 4.94,
      "step": 190,
      "total_flos": 697572311040000.0,
      "train_loss": 1.8531885046707957,
      "train_runtime": 316.8119,
      "train_samples_per_second": 4.861,
      "train_steps_per_second": 0.6
    }
  ],
  "logging_steps": 5,
  "max_steps": 190,
  "num_train_epochs": 5,
  "save_steps": 1000,
  "total_flos": 697572311040000.0,
  "trial_name": null,
  "trial_params": null
}