trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9473684210526314,
  "eval_steps": 500,
  "global_step": 126,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.23391812865497075,
      "grad_norm": 0.3421129584312439,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.8206,
      "step": 10
    },
    {
      "epoch": 0.4678362573099415,
      "grad_norm": 0.2985590398311615,
      "learning_rate": 4.952806974561518e-05,
      "loss": 1.704,
      "step": 20
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 0.2648092210292816,
      "learning_rate": 4.7259364450857096e-05,
      "loss": 1.6412,
      "step": 30
    },
    {
      "epoch": 0.935672514619883,
      "grad_norm": 0.27310284972190857,
      "learning_rate": 4.374817961675553e-05,
      "loss": 1.6007,
      "step": 40
    },
    {
      "epoch": 1.1695906432748537,
      "grad_norm": 0.3133543133735657,
      "learning_rate": 3.848943205739711e-05,
      "loss": 1.4302,
      "step": 50
    },
    {
      "epoch": 1.4035087719298245,
      "grad_norm": 0.2750793397426605,
      "learning_rate": 3.219473788427984e-05,
      "loss": 1.3741,
      "step": 60
    },
    {
      "epoch": 1.6374269005847952,
      "grad_norm": 0.41151949763298035,
      "learning_rate": 2.5347510119207878e-05,
      "loss": 1.4629,
      "step": 70
    },
    {
      "epoch": 1.871345029239766,
      "grad_norm": 0.3097662925720215,
      "learning_rate": 1.847359465300006e-05,
      "loss": 1.3836,
      "step": 80
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 0.3223315477371216,
      "learning_rate": 1.2100886909287478e-05,
      "loss": 1.377,
      "step": 90
    },
    {
      "epoch": 2.3391812865497075,
      "grad_norm": 0.27889469265937805,
      "learning_rate": 6.718791110537287e-06,
      "loss": 1.2488,
      "step": 100
    },
    {
      "epoch": 2.573099415204678,
      "grad_norm": 0.3442135155200958,
      "learning_rate": 2.7406355491429086e-06,
      "loss": 1.2359,
      "step": 110
    },
    {
      "epoch": 2.807017543859649,
      "grad_norm": 0.28369471430778503,
      "learning_rate": 4.719302543848225e-07,
      "loss": 1.2869,
      "step": 120
    },
    {
      "epoch": 2.9473684210526314,
      "step": 126,
      "total_flos": 1.8634359800070144e+17,
      "train_loss": 1.452950118080018,
      "train_runtime": 1472.8252,
      "train_samples_per_second": 2.784,
      "train_steps_per_second": 0.086
    }
  ],
  "logging_steps": 10,
  "max_steps": 126,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8634359800070144e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}