fine-tuned-model-16/checkpoint-413/trainer_state.json

{
  "best_global_step": 413,
  "best_metric": 0.1363692432641983,
  "best_model_checkpoint": "./fine-tuned-model-16\\checkpoint-413",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 413,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8519701810436635,
      "grad_norm": 0.2258640080690384,
      "learning_rate": 4.5689655172413794e-05,
      "loss": 0.5163,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.17305970191955566,
      "eval_runtime": 188.3457,
      "eval_samples_per_second": 0.557,
      "eval_steps_per_second": 0.557,
      "step": 59
    },
    {
      "epoch": 1.698615548455804,
      "grad_norm": 0.16990907490253448,
      "learning_rate": 4.1379310344827587e-05,
      "loss": 0.1656,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.15038533508777618,
      "eval_runtime": 188.0181,
      "eval_samples_per_second": 0.558,
      "eval_steps_per_second": 0.558,
      "step": 118
    },
    {
      "epoch": 2.545260915867945,
      "grad_norm": 0.28422054648399353,
      "learning_rate": 3.7068965517241385e-05,
      "loss": 0.133,
      "step": 150
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.14531958103179932,
      "eval_runtime": 187.6033,
      "eval_samples_per_second": 0.56,
      "eval_steps_per_second": 0.56,
      "step": 177
    },
    {
      "epoch": 3.3919062832800853,
      "grad_norm": 0.25157108902931213,
      "learning_rate": 3.275862068965517e-05,
      "loss": 0.1179,
      "step": 200
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.14057818055152893,
      "eval_runtime": 188.9752,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.556,
      "step": 236
    },
    {
      "epoch": 4.238551650692226,
      "grad_norm": 0.224246546626091,
      "learning_rate": 2.844827586206897e-05,
      "loss": 0.1041,
      "step": 250
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.1371779888868332,
      "eval_runtime": 187.9394,
      "eval_samples_per_second": 0.559,
      "eval_steps_per_second": 0.559,
      "step": 295
    },
    {
      "epoch": 5.085197018104366,
      "grad_norm": 0.23708942532539368,
      "learning_rate": 2.413793103448276e-05,
      "loss": 0.0963,
      "step": 300
    },
    {
      "epoch": 5.93716719914803,
      "grad_norm": 0.3290882408618927,
      "learning_rate": 1.9827586206896554e-05,
      "loss": 0.0877,
      "step": 350
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.13712403178215027,
      "eval_runtime": 188.2543,
      "eval_samples_per_second": 0.558,
      "eval_steps_per_second": 0.558,
      "step": 354
    },
    {
      "epoch": 6.7838125665601705,
      "grad_norm": 0.21974337100982666,
      "learning_rate": 1.5517241379310346e-05,
      "loss": 0.0787,
      "step": 400
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.1363692432641983,
      "eval_runtime": 188.8614,
      "eval_samples_per_second": 0.556,
      "eval_steps_per_second": 0.556,
      "step": 413
    }
  ],
  "logging_steps": 50,
  "max_steps": 580,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6117466234565427e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}