trainer_state.json

{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05116561670557385,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025582808352786926,
      "grad_norm": 0.41173064708709717,
      "learning_rate": 0.00018,
      "loss": 2.2691,
      "step": 10
    },
    {
      "epoch": 0.005116561670557385,
      "grad_norm": 0.35278061032295227,
      "learning_rate": 0.00019889478706014687,
      "loss": 2.2137,
      "step": 20
    },
    {
      "epoch": 0.007674842505836078,
      "grad_norm": 0.32279932498931885,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.2253,
      "step": 30
    },
    {
      "epoch": 0.01023312334111477,
      "grad_norm": 0.32902857661247253,
      "learning_rate": 0.0001887222819443612,
      "loss": 2.2422,
      "step": 40
    },
    {
      "epoch": 0.012791404176393463,
      "grad_norm": 0.4015531539916992,
      "learning_rate": 0.0001799187996894925,
      "loss": 2.1889,
      "step": 50
    },
    {
      "epoch": 0.015349685011672156,
      "grad_norm": 0.3013351857662201,
      "learning_rate": 0.0001689353409118566,
      "loss": 2.2778,
      "step": 60
    },
    {
      "epoch": 0.017907965846950848,
      "grad_norm": 0.2108200341463089,
      "learning_rate": 0.0001560715057351673,
      "loss": 2.1985,
      "step": 70
    },
    {
      "epoch": 0.02046624668222954,
      "grad_norm": 0.44372543692588806,
      "learning_rate": 0.00014167818604952906,
      "loss": 1.9972,
      "step": 80
    },
    {
      "epoch": 0.023024527517508234,
      "grad_norm": 0.36838993430137634,
      "learning_rate": 0.00012614799409538198,
      "loss": 2.17,
      "step": 90
    },
    {
      "epoch": 0.025582808352786927,
      "grad_norm": 0.33015120029449463,
      "learning_rate": 0.0001099045530250463,
      "loss": 2.2036,
      "step": 100
    },
    {
      "epoch": 0.02814108918806562,
      "grad_norm": 0.22048693895339966,
      "learning_rate": 9.339094156743007e-05,
      "loss": 2.2489,
      "step": 110
    },
    {
      "epoch": 0.030699370023344313,
      "grad_norm": 0.23766057193279266,
      "learning_rate": 7.705760799532485e-05,
      "loss": 1.8966,
      "step": 120
    },
    {
      "epoch": 0.033257650858623006,
      "grad_norm": 0.24646614491939545,
      "learning_rate": 6.135008307075481e-05,
      "loss": 1.9245,
      "step": 130
    },
    {
      "epoch": 0.035815931693901695,
      "grad_norm": 0.393329918384552,
      "learning_rate": 4.669682712720065e-05,
      "loss": 2.2395,
      "step": 140
    },
    {
      "epoch": 0.03837421252918039,
      "grad_norm": 0.23788638412952423,
      "learning_rate": 3.349754278861517e-05,
      "loss": 2.0628,
      "step": 150
    },
    {
      "epoch": 0.04093249336445908,
      "grad_norm": 0.5308476686477661,
      "learning_rate": 2.2112272123788768e-05,
      "loss": 2.2382,
      "step": 160
    },
    {
      "epoch": 0.04349077419973778,
      "grad_norm": 0.30160173773765564,
      "learning_rate": 1.2851575637272262e-05,
      "loss": 2.0997,
      "step": 170
    },
    {
      "epoch": 0.04604905503501647,
      "grad_norm": 0.418215274810791,
      "learning_rate": 5.968060988383883e-06,
      "loss": 2.0202,
      "step": 180
    },
    {
      "epoch": 0.048607335870295164,
      "grad_norm": 0.37242060899734497,
      "learning_rate": 1.6494925127617634e-06,
      "loss": 2.2179,
      "step": 190
    },
    {
      "epoch": 0.05116561670557385,
      "grad_norm": 0.3666183352470398,
      "learning_rate": 1.3669500753099585e-08,
      "loss": 2.0904,
      "step": 200
    },
    {
      "epoch": 0.05116561670557385,
      "step": 200,
      "total_flos": 1.3791695468878234e+17,
      "train_loss": 2.1512529373168947,
      "train_runtime": 30852.7311,
      "train_samples_per_second": 0.052,
      "train_steps_per_second": 0.006
    }
  ],
  "logging_steps": 10,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3791695468878234e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}