punctuation/encoder_model/checkpoint-150/trainer_state.json

{
  "best_global_step": 50,
  "best_metric": 0.5,
  "best_model_checkpoint": "./models/punctuation/encoder_model/checkpoint-50",
  "epoch": 1.4047058823529412,
  "eval_steps": 50,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09411764705882353,
      "grad_norm": 0.2591496407985687,
      "learning_rate": 0.0001,
      "loss": 1.0255,
      "step": 10
    },
    {
      "epoch": 0.18823529411764706,
      "grad_norm": 0.23840643465518951,
      "learning_rate": 0.0001,
      "loss": 0.8799,
      "step": 20
    },
    {
      "epoch": 0.2823529411764706,
      "grad_norm": 0.2382705807685852,
      "learning_rate": 0.0001,
      "loss": 0.8393,
      "step": 30
    },
    {
      "epoch": 0.3764705882352941,
      "grad_norm": 0.26509279012680054,
      "learning_rate": 0.0001,
      "loss": 0.8444,
      "step": 40
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.26330241560935974,
      "learning_rate": 0.0001,
      "loss": 0.8232,
      "step": 50
    },
    {
      "epoch": 0.47058823529411764,
      "eval_loss": 0.8152285814285278,
      "eval_model_preparation_time": 0.0135,
      "eval_runtime": 4.0525,
      "eval_samples_per_second": 24.676,
      "eval_steps_per_second": 12.338,
      "step": 50
    },
    {
      "epoch": 0.5647058823529412,
      "grad_norm": 0.2532142400741577,
      "learning_rate": 0.0001,
      "loss": 0.8123,
      "step": 60
    },
    {
      "epoch": 0.6588235294117647,
      "grad_norm": 0.2938081622123718,
      "learning_rate": 0.0001,
      "loss": 0.7956,
      "step": 70
    },
    {
      "epoch": 0.7529411764705882,
      "grad_norm": 0.2652847170829773,
      "learning_rate": 0.0001,
      "loss": 0.7741,
      "step": 80
    },
    {
      "epoch": 0.8470588235294118,
      "grad_norm": 0.257866770029068,
      "learning_rate": 0.0001,
      "loss": 0.7907,
      "step": 90
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.29850393533706665,
      "learning_rate": 0.0001,
      "loss": 0.7763,
      "step": 100
    },
    {
      "epoch": 0.9411764705882353,
      "eval_loss": 0.7670149207115173,
      "eval_model_preparation_time": 0.0135,
      "eval_runtime": 4.0483,
      "eval_samples_per_second": 24.702,
      "eval_steps_per_second": 12.351,
      "step": 100
    },
    {
      "epoch": 1.0282352941176471,
      "grad_norm": 0.277658611536026,
      "learning_rate": 0.0001,
      "loss": 0.7689,
      "step": 110
    },
    {
      "epoch": 1.1223529411764706,
      "grad_norm": 0.30186522006988525,
      "learning_rate": 0.0001,
      "loss": 0.7235,
      "step": 120
    },
    {
      "epoch": 1.2164705882352942,
      "grad_norm": 0.32689717411994934,
      "learning_rate": 0.0001,
      "loss": 0.7106,
      "step": 130
    },
    {
      "epoch": 1.3105882352941176,
      "grad_norm": 0.3532510995864868,
      "learning_rate": 0.0001,
      "loss": 0.6671,
      "step": 140
    },
    {
      "epoch": 1.4047058823529412,
      "grad_norm": 0.3470897376537323,
      "learning_rate": 0.0001,
      "loss": 0.6976,
      "step": 150
    },
    {
      "epoch": 1.4047058823529412,
      "eval_loss": 0.7519224286079407,
      "eval_model_preparation_time": 0.0135,
      "eval_runtime": 4.0317,
      "eval_samples_per_second": 24.804,
      "eval_steps_per_second": 12.402,
      "step": 150
    }
  ],
  "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": 2.171126396147712e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}