trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 0.36308756470680237,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 1.3855,
      "step": 20
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 0.3340895473957062,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 1.3679,
      "step": 40
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 0.3473477363586426,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 1.3813,
      "step": 60
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 0.35594913363456726,
      "learning_rate": 4.965385884295467e-06,
      "loss": 1.2987,
      "step": 80
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 0.39734789729118347,
      "learning_rate": 4.798150758954164e-06,
      "loss": 1.237,
      "step": 100
    },
    {
      "epoch": 0.36363636363636365,
      "grad_norm": 0.42136889696121216,
      "learning_rate": 4.501353102310901e-06,
      "loss": 1.1311,
      "step": 120
    },
    {
      "epoch": 0.42424242424242425,
      "grad_norm": 0.557064414024353,
      "learning_rate": 4.091725435297721e-06,
      "loss": 1.0763,
      "step": 140
    },
    {
      "epoch": 0.48484848484848486,
      "grad_norm": 0.5050609707832336,
      "learning_rate": 3.5923612809233987e-06,
      "loss": 0.9135,
      "step": 160
    },
    {
      "epoch": 0.5454545454545454,
      "grad_norm": 0.43929287791252136,
      "learning_rate": 3.0314132238824416e-06,
      "loss": 0.7968,
      "step": 180
    },
    {
      "epoch": 0.6060606060606061,
      "grad_norm": 0.39808526635169983,
      "learning_rate": 2.440505756134732e-06,
      "loss": 0.74,
      "step": 200
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.45625489950180054,
      "learning_rate": 1.852952387243698e-06,
      "loss": 0.7124,
      "step": 220
    },
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.4360494017601013,
      "learning_rate": 1.301877533199859e-06,
      "loss": 0.6832,
      "step": 240
    },
    {
      "epoch": 0.7878787878787878,
      "grad_norm": 0.38371819257736206,
      "learning_rate": 8.183490657468687e-07,
      "loss": 0.6885,
      "step": 260
    },
    {
      "epoch": 0.8484848484848485,
      "grad_norm": 0.36575645208358765,
      "learning_rate": 4.2962680322157335e-07,
      "loss": 0.6905,
      "step": 280
    },
    {
      "epoch": 0.9090909090909091,
      "grad_norm": 0.5191577672958374,
      "learning_rate": 1.5762568750059604e-07,
      "loss": 0.6939,
      "step": 300
    },
    {
      "epoch": 0.9696969696969697,
      "grad_norm": 0.42232680320739746,
      "learning_rate": 1.768028831677926e-08,
      "loss": 0.6645,
      "step": 320
    },
    {
      "epoch": 1.0,
      "step": 330,
      "total_flos": 1.519725494403072e+16,
      "train_loss": 0.958257312485666,
      "train_runtime": 404.051,
      "train_samples_per_second": 3.267,
      "train_steps_per_second": 0.817
    }
  ],
  "logging_steps": 20,
  "max_steps": 330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.519725494403072e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}