trainer_state.json

{
  "best_metric": 0.39622641509433965,
  "best_model_checkpoint": "./Validated_Balanced_Raw_Data_model_boost8_outputs/checkpoint-80",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.625,
      "grad_norm": 1.026680588722229,
      "learning_rate": 2.9541003989089956e-05,
      "loss": 1.3729,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.39622641509433965,
      "eval_loss": 1.3302552700042725,
      "eval_runtime": 1.4024,
      "eval_samples_per_second": 151.165,
      "eval_steps_per_second": 9.983,
      "step": 80
    },
    {
      "epoch": 1.25,
      "grad_norm": 1.0671523809432983,
      "learning_rate": 2.6837107640945904e-05,
      "loss": 1.3422,
      "step": 100
    },
    {
      "epoch": 1.875,
      "grad_norm": 1.1258270740509033,
      "learning_rate": 2.2139210895556104e-05,
      "loss": 1.3243,
      "step": 150
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.38207547169811323,
      "eval_loss": 1.3050692081451416,
      "eval_runtime": 1.3895,
      "eval_samples_per_second": 152.569,
      "eval_steps_per_second": 10.075,
      "step": 160
    },
    {
      "epoch": 2.5,
      "grad_norm": 1.1245783567428589,
      "learning_rate": 1.623869018208499e-05,
      "loss": 1.3093,
      "step": 200
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.37735849056603776,
      "eval_loss": 1.2962387800216675,
      "eval_runtime": 1.3825,
      "eval_samples_per_second": 153.341,
      "eval_steps_per_second": 10.126,
      "step": 240
    },
    {
      "epoch": 3.125,
      "grad_norm": 0.9223591685295105,
      "learning_rate": 1.0129507961929749e-05,
      "loss": 1.3138,
      "step": 250
    },
    {
      "epoch": 3.75,
      "grad_norm": 1.2660913467407227,
      "learning_rate": 4.840776425613887e-06,
      "loss": 1.2908,
      "step": 300
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.38207547169811323,
      "eval_loss": 1.2940889596939087,
      "eval_runtime": 1.3786,
      "eval_samples_per_second": 153.781,
      "eval_steps_per_second": 10.155,
      "step": 320
    },
    {
      "epoch": 4.375,
      "grad_norm": 1.12974214553833,
      "learning_rate": 1.2634001001741375e-06,
      "loss": 1.3193,
      "step": 350
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.500447392463684,
      "learning_rate": 0.0,
      "loss": 1.2836,
      "step": 400
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.37735849056603776,
      "eval_loss": 1.2936153411865234,
      "eval_runtime": 1.4054,
      "eval_samples_per_second": 150.848,
      "eval_steps_per_second": 9.962,
      "step": 400
    },
    {
      "epoch": 5.0,
      "step": 400,
      "total_flos": 4.2409746528731136e+17,
      "train_loss": 1.319512176513672,
      "train_runtime": 85.175,
      "train_samples_per_second": 37.335,
      "train_steps_per_second": 4.696
    }
  ],
  "logging_steps": 50,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.2409746528731136e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}