trainer_state.json

{
  "best_metric": 0.6206879019737244,
  "best_model_checkpoint": "mobilebert_add_GLUE_Experiment_mrpc_256/checkpoint-174",
  "epoch": 11.0,
  "global_step": 319,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.9e-05,
      "loss": 0.6419,
      "step": 29
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6266346573829651,
      "eval_runtime": 0.7408,
      "eval_samples_per_second": 550.789,
      "eval_steps_per_second": 5.4,
      "step": 29
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8e-05,
      "loss": 0.6297,
      "step": 58
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6235790848731995,
      "eval_runtime": 0.7584,
      "eval_samples_per_second": 537.948,
      "eval_steps_per_second": 5.274,
      "step": 58
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.7e-05,
      "loss": 0.6307,
      "step": 87
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6241391897201538,
      "eval_runtime": 0.7543,
      "eval_samples_per_second": 540.934,
      "eval_steps_per_second": 5.303,
      "step": 87
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.63,
      "step": 116
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6243211627006531,
      "eval_runtime": 0.7353,
      "eval_samples_per_second": 554.855,
      "eval_steps_per_second": 5.44,
      "step": 116
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.5e-05,
      "loss": 0.6283,
      "step": 145
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6218860745429993,
      "eval_runtime": 0.7846,
      "eval_samples_per_second": 520.041,
      "eval_steps_per_second": 5.098,
      "step": 145
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6243,
      "step": 174
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6206879019737244,
      "eval_runtime": 0.7596,
      "eval_samples_per_second": 537.127,
      "eval_steps_per_second": 5.266,
      "step": 174
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.3e-05,
      "loss": 0.6206,
      "step": 203
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6346157193183899,
      "eval_runtime": 0.7532,
      "eval_samples_per_second": 541.682,
      "eval_steps_per_second": 5.311,
      "step": 203
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.2e-05,
      "loss": 0.6034,
      "step": 232
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6348039215686274,
      "eval_combined_score": 0.6946671996640501,
      "eval_f1": 0.7545304777594728,
      "eval_loss": 0.6519109606742859,
      "eval_runtime": 0.7382,
      "eval_samples_per_second": 552.685,
      "eval_steps_per_second": 5.418,
      "step": 232
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.1e-05,
      "loss": 0.5877,
      "step": 261
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6374713778495789,
      "eval_runtime": 0.7444,
      "eval_samples_per_second": 548.103,
      "eval_steps_per_second": 5.374,
      "step": 261
    },
    {
      "epoch": 10.0,
      "learning_rate": 4e-05,
      "loss": 0.5722,
      "step": 290
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.6299019607843137,
      "eval_combined_score": 0.6901575919624048,
      "eval_f1": 0.7504132231404959,
      "eval_loss": 0.6445620656013489,
      "eval_runtime": 0.7628,
      "eval_samples_per_second": 534.84,
      "eval_steps_per_second": 5.244,
      "step": 290
    },
    {
      "epoch": 11.0,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.5619,
      "step": 319
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.6813725490196079,
      "eval_combined_score": 0.7459340879208827,
      "eval_f1": 0.8104956268221574,
      "eval_loss": 0.6732954382896423,
      "eval_runtime": 0.7445,
      "eval_samples_per_second": 548.034,
      "eval_steps_per_second": 5.373,
      "step": 319
    },
    {
      "epoch": 11.0,
      "step": 319,
      "total_flos": 1039978272391168.0,
      "train_loss": 0.611870960008388,
      "train_runtime": 307.3617,
      "train_samples_per_second": 596.691,
      "train_steps_per_second": 4.718
    }
  ],
  "max_steps": 1450,
  "num_train_epochs": 50,
  "total_flos": 1039978272391168.0,
  "trial_name": null,
  "trial_params": null
}