{
  "best_global_step": 200,
  "best_metric": 1.0,
  "best_model_checkpoint": "./models/punctuation/encoder_model/checkpoint-200",
  "epoch": 1.8752941176470588,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 0.36188849806785583,
      "learning_rate": 8.181818181818183e-05,
      "loss": 1.1219,
      "step": 10
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 0.2508435845375061,
      "learning_rate": 0.00017272727272727275,
      "loss": 0.9281,
      "step": 20
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 0.2157556265592575,
      "learning_rate": 0.00019934477790194445,
      "loss": 0.852,
      "step": 30
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 0.25683870911598206,
      "learning_rate": 0.0001961561797682962,
      "loss": 0.844,
      "step": 40
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.26627957820892334,
      "learning_rate": 0.00019039892931234435,
      "loss": 0.8168,
      "step": 50
    },
    {
      "epoch": 0.47058823529411764,
      "eval_loss": 0.8057724237442017,
      "eval_model_preparation_time": 0.0129,
      "eval_runtime": 3.824,
      "eval_samples_per_second": 26.15,
      "eval_steps_per_second": 13.075,
      "step": 50
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 0.228170707821846,
      "learning_rate": 0.00018222682189897752,
      "loss": 0.8023,
      "step": 60
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 0.26517826318740845,
      "learning_rate": 0.0001718581617779698,
      "loss": 0.7858,
      "step": 70
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 0.22760385274887085,
      "learning_rate": 0.00015956993044924334,
      "loss": 0.7632,
      "step": 80
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 0.2228352576494217,
      "learning_rate": 0.00014569038756304207,
      "loss": 0.7788,
      "step": 90
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.25218382477760315,
      "learning_rate": 0.00013059030200965536,
      "loss": 0.7637,
      "step": 100
    },
    {
      "epoch": 0.9411764705882353,
      "eval_loss": 0.753893256187439,
      "eval_model_preparation_time": 0.0129,
      "eval_runtime": 3.8121,
      "eval_samples_per_second": 26.232,
      "eval_steps_per_second": 13.116,
      "step": 100
    },
    {
      "epoch": 1.0282352941176471,
      "grad_norm": 0.23036813735961914,
      "learning_rate": 0.00011467304744553618,
      "loss": 0.7508,
      "step": 110
    },
    {
      "epoch": 1.1223529411764706,
      "grad_norm": 0.25190669298171997,
      "learning_rate": 9.836382683735132e-05,
      "loss": 0.6933,
      "step": 120
    },
    {
      "epoch": 1.2164705882352942,
      "grad_norm": 0.27167296409606934,
      "learning_rate": 8.209831387233676e-05,
      "loss": 0.6799,
      "step": 130
    },
    {
      "epoch": 1.3105882352941176,
      "grad_norm": 0.29528751969337463,
      "learning_rate": 6.6311014660778e-05,
      "loss": 0.6377,
      "step": 140
    },
    {
      "epoch": 1.4047058823529412,
      "grad_norm": 0.2657102346420288,
      "learning_rate": 5.142366062836599e-05,
      "loss": 0.6636,
      "step": 150
    },
    {
      "epoch": 1.4047058823529412,
      "eval_loss": 0.7372229099273682,
      "eval_model_preparation_time": 0.0129,
      "eval_runtime": 3.8052,
      "eval_samples_per_second": 26.28,
      "eval_steps_per_second": 13.14,
      "step": 150
    },
    {
      "epoch": 1.4988235294117647,
      "grad_norm": 0.27975210547447205,
      "learning_rate": 3.783394266299228e-05,
      "loss": 0.6498,
      "step": 160
    },
    {
      "epoch": 1.592941176470588,
      "grad_norm": 0.2573317587375641,
      "learning_rate": 2.5904887464504114e-05,
      "loss": 0.6343,
      "step": 170
    },
    {
      "epoch": 1.6870588235294117,
      "grad_norm": 0.2996138036251068,
      "learning_rate": 1.595515989055618e-05,
      "loss": 0.6505,
      "step": 180
    },
    {
      "epoch": 1.7811764705882354,
      "grad_norm": 0.2739143669605255,
      "learning_rate": 8.250550355250875e-06,
      "loss": 0.6494,
      "step": 190
    },
    {
      "epoch": 1.8752941176470588,
      "grad_norm": 0.3023104965686798,
      "learning_rate": 2.996874680545603e-06,
      "loss": 0.6241,
      "step": 200
    },
    {
      "epoch": 1.8752941176470588,
      "eval_loss": 0.7298660278320312,
      "eval_model_preparation_time": 0.0129,
      "eval_runtime": 3.8044,
      "eval_samples_per_second": 26.286,
      "eval_steps_per_second": 13.143,
      "step": 200
    }
  ],
  "logging_steps": 10,
  "max_steps": 214,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2.9025710777769984e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}