trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9962577962577963,
  "global_step": 1200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 1.662757831681574e-05,
      "loss": 0.6867,
      "step": 50
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.9777236052888476e-05,
      "loss": 0.6579,
      "step": 100
    },
    {
      "epoch": 0.25,
      "learning_rate": 2e-05,
      "loss": 0.6459,
      "step": 150
    },
    {
      "epoch": 0.33,
      "learning_rate": 2e-05,
      "loss": 0.6523,
      "step": 200
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 0.6483,
      "step": 250
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 0.6507,
      "step": 300
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 0.6488,
      "step": 350
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 0.6447,
      "step": 400
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 0.6504,
      "step": 450
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 0.65,
      "step": 500
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-05,
      "loss": 0.6383,
      "step": 550
    },
    {
      "epoch": 1.0,
      "learning_rate": 2e-05,
      "loss": 0.6451,
      "step": 600
    },
    {
      "epoch": 1.08,
      "learning_rate": 2e-05,
      "loss": 0.6484,
      "step": 650
    },
    {
      "epoch": 1.16,
      "learning_rate": 2e-05,
      "loss": 0.6495,
      "step": 700
    },
    {
      "epoch": 1.25,
      "learning_rate": 2e-05,
      "loss": 0.6392,
      "step": 750
    },
    {
      "epoch": 1.33,
      "learning_rate": 2e-05,
      "loss": 0.6445,
      "step": 800
    },
    {
      "epoch": 1.41,
      "learning_rate": 2e-05,
      "loss": 0.6474,
      "step": 850
    },
    {
      "epoch": 1.5,
      "learning_rate": 2e-05,
      "loss": 0.6491,
      "step": 900
    },
    {
      "epoch": 1.58,
      "learning_rate": 2e-05,
      "loss": 0.6496,
      "step": 950
    },
    {
      "epoch": 1.66,
      "learning_rate": 2e-05,
      "loss": 0.6438,
      "step": 1000
    },
    {
      "epoch": 1.75,
      "learning_rate": 2e-05,
      "loss": 0.6482,
      "step": 1050
    },
    {
      "epoch": 1.83,
      "learning_rate": 2e-05,
      "loss": 0.6489,
      "step": 1100
    },
    {
      "epoch": 1.91,
      "learning_rate": 2e-05,
      "loss": 0.6483,
      "step": 1150
    },
    {
      "epoch": 2.0,
      "learning_rate": 2e-05,
      "loss": 0.652,
      "step": 1200
    }
  ],
  "max_steps": 1803,
  "num_train_epochs": 3,
  "total_flos": 1.7536187092579647e+19,
  "trial_name": null,
  "trial_params": null
}