trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07918701332981391,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.3109243697478994e-05,
      "loss": 1.3971,
      "step": 50
    },
    {
      "epoch": 0.03,
      "learning_rate": 2.100840336134454e-05,
      "loss": 0.4632,
      "step": 100
    },
    {
      "epoch": 0.03,
      "eval_loss": 0.4099404215812683,
      "eval_runtime": 1367.0833,
      "eval_samples_per_second": 1.167,
      "eval_steps_per_second": 0.146,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.8907563025210083e-05,
      "loss": 0.382,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.6806722689075634e-05,
      "loss": 0.3659,
      "step": 200
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.36828184127807617,
      "eval_runtime": 1367.1443,
      "eval_samples_per_second": 1.167,
      "eval_steps_per_second": 0.146,
      "step": 200
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.4705882352941177e-05,
      "loss": 0.3167,
      "step": 250
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.2605042016806723e-05,
      "loss": 0.344,
      "step": 300
    },
    {
      "epoch": 0.08,
      "eval_loss": 0.3531185984611511,
      "eval_runtime": 1367.1817,
      "eval_samples_per_second": 1.167,
      "eval_steps_per_second": 0.146,
      "step": 300
    }
  ],
  "logging_steps": 50,
  "max_steps": 600,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 3.576361434218496e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}