trainer_state.json

{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.026763013515321826,
  "eval_steps": 999999,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013381506757660913,
      "grad_norm": 43.25,
      "learning_rate": 6.684491978609625e-09,
      "loss": -1.2338,
      "step": 10
    },
    {
      "epoch": 0.0026763013515321826,
      "grad_norm": 66.0,
      "learning_rate": 1.336898395721925e-08,
      "loss": -0.96,
      "step": 20
    },
    {
      "epoch": 0.004014452027298274,
      "grad_norm": 77.5,
      "learning_rate": 2.0053475935828877e-08,
      "loss": -0.7695,
      "step": 30
    },
    {
      "epoch": 0.005352602703064365,
      "grad_norm": 156.0,
      "learning_rate": 2.67379679144385e-08,
      "loss": -0.5852,
      "step": 40
    },
    {
      "epoch": 0.006690753378830456,
      "grad_norm": 49.25,
      "learning_rate": 3.342245989304813e-08,
      "loss": -1.3508,
      "step": 50
    },
    {
      "epoch": 0.008028904054596548,
      "grad_norm": 145.0,
      "learning_rate": 4.0106951871657754e-08,
      "loss": -0.7302,
      "step": 60
    },
    {
      "epoch": 0.009367054730362638,
      "grad_norm": 4.96875,
      "learning_rate": 4.679144385026738e-08,
      "loss": -0.5402,
      "step": 70
    },
    {
      "epoch": 0.01070520540612873,
      "grad_norm": 56.5,
      "learning_rate": 5.3475935828877e-08,
      "loss": -1.5851,
      "step": 80
    },
    {
      "epoch": 0.01204335608189482,
      "grad_norm": 97.0,
      "learning_rate": 6.016042780748662e-08,
      "loss": -1.9164,
      "step": 90
    },
    {
      "epoch": 0.013381506757660913,
      "grad_norm": 157.0,
      "learning_rate": 6.684491978609626e-08,
      "loss": -1.0399,
      "step": 100
    },
    {
      "epoch": 0.014719657433427003,
      "grad_norm": 346.0,
      "learning_rate": 7.352941176470588e-08,
      "loss": -0.788,
      "step": 110
    },
    {
      "epoch": 0.016057808109193095,
      "grad_norm": 416.0,
      "learning_rate": 8.021390374331551e-08,
      "loss": -1.6681,
      "step": 120
    },
    {
      "epoch": 0.017395958784959187,
      "grad_norm": 58.0,
      "learning_rate": 8.689839572192513e-08,
      "loss": -0.9137,
      "step": 130
    },
    {
      "epoch": 0.018734109460725276,
      "grad_norm": 7.03125,
      "learning_rate": 9.358288770053476e-08,
      "loss": -0.8646,
      "step": 140
    },
    {
      "epoch": 0.02007226013649137,
      "grad_norm": 63.0,
      "learning_rate": 1.0026737967914438e-07,
      "loss": -0.5643,
      "step": 150
    },
    {
      "epoch": 0.02141041081225746,
      "grad_norm": 46.0,
      "learning_rate": 1.06951871657754e-07,
      "loss": -0.8626,
      "step": 160
    },
    {
      "epoch": 0.022748561488023553,
      "grad_norm": 91.0,
      "learning_rate": 1.1363636363636363e-07,
      "loss": -0.9937,
      "step": 170
    },
    {
      "epoch": 0.02408671216378964,
      "grad_norm": 45.75,
      "learning_rate": 1.2032085561497325e-07,
      "loss": -1.1182,
      "step": 180
    },
    {
      "epoch": 0.025424862839555733,
      "grad_norm": 69.5,
      "learning_rate": 1.2700534759358288e-07,
      "loss": -1.2665,
      "step": 190
    },
    {
      "epoch": 0.026763013515321826,
      "grad_norm": 15.1875,
      "learning_rate": 1.3368983957219251e-07,
      "loss": -0.4304,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 7473,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}