trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9943289224952743,
  "global_step": 198,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0,
      "loss": 1.0585,
      "step": 1
    },
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 0.6923,
      "step": 8
    },
    {
      "epoch": 0.24,
      "learning_rate": 2e-05,
      "loss": 0.5149,
      "step": 16
    },
    {
      "epoch": 0.36,
      "learning_rate": 2e-05,
      "loss": 0.3899,
      "step": 24
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 0.3511,
      "step": 32
    },
    {
      "epoch": 0.6,
      "learning_rate": 2e-05,
      "loss": 0.3321,
      "step": 40
    },
    {
      "epoch": 0.73,
      "learning_rate": 2e-05,
      "loss": 0.3254,
      "step": 48
    },
    {
      "epoch": 0.85,
      "learning_rate": 2e-05,
      "loss": 0.3104,
      "step": 56
    },
    {
      "epoch": 0.97,
      "learning_rate": 2e-05,
      "loss": 0.3007,
      "step": 64
    },
    {
      "epoch": 1.09,
      "learning_rate": 2e-05,
      "loss": 0.2617,
      "step": 72
    },
    {
      "epoch": 1.21,
      "learning_rate": 2e-05,
      "loss": 0.2454,
      "step": 80
    },
    {
      "epoch": 1.33,
      "learning_rate": 2e-05,
      "loss": 0.2362,
      "step": 88
    },
    {
      "epoch": 1.45,
      "learning_rate": 2e-05,
      "loss": 0.2334,
      "step": 96
    },
    {
      "epoch": 1.57,
      "learning_rate": 2e-05,
      "loss": 0.2275,
      "step": 104
    },
    {
      "epoch": 1.69,
      "learning_rate": 2e-05,
      "loss": 0.23,
      "step": 112
    },
    {
      "epoch": 1.81,
      "learning_rate": 2e-05,
      "loss": 0.217,
      "step": 120
    },
    {
      "epoch": 1.94,
      "learning_rate": 2e-05,
      "loss": 0.2205,
      "step": 128
    },
    {
      "epoch": 2.06,
      "learning_rate": 2e-05,
      "loss": 0.2031,
      "step": 136
    },
    {
      "epoch": 2.18,
      "learning_rate": 2e-05,
      "loss": 0.1629,
      "step": 144
    },
    {
      "epoch": 2.3,
      "learning_rate": 2e-05,
      "loss": 0.167,
      "step": 152
    },
    {
      "epoch": 2.42,
      "learning_rate": 2e-05,
      "loss": 0.1627,
      "step": 160
    },
    {
      "epoch": 2.54,
      "learning_rate": 2e-05,
      "loss": 0.1594,
      "step": 168
    },
    {
      "epoch": 2.66,
      "learning_rate": 2e-05,
      "loss": 0.1553,
      "step": 176
    },
    {
      "epoch": 2.78,
      "learning_rate": 2e-05,
      "loss": 0.1623,
      "step": 184
    },
    {
      "epoch": 2.9,
      "learning_rate": 2e-05,
      "loss": 0.1576,
      "step": 192
    },
    {
      "epoch": 2.99,
      "step": 198,
      "total_flos": 424189693526016.0,
      "train_loss": 0.2658990031540996,
      "train_runtime": 7827.5947,
      "train_samples_per_second": 3.244,
      "train_steps_per_second": 0.025
    }
  ],
  "max_steps": 198,
  "num_train_epochs": 3,
  "total_flos": 424189693526016.0,
  "trial_name": null,
  "trial_params": null
}