fine-tuned-model-8-diff/checkpoint-290/trainer_state.json

{
  "best_global_step": 290,
  "best_metric": 0.1572711169719696,
  "best_model_checkpoint": "./fine-tuned-model-8-diff\\checkpoint-290",
  "epoch": 4.920127795527156,
  "eval_steps": 500,
  "global_step": 290,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8519701810436635,
      "grad_norm": 0.3280849754810333,
      "learning_rate": 3.310344827586207e-05,
      "loss": 0.7606,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.24083571135997772,
      "eval_runtime": 209.8235,
      "eval_samples_per_second": 0.5,
      "eval_steps_per_second": 0.5,
      "step": 59
    },
    {
      "epoch": 1.698615548455804,
      "grad_norm": 0.17877578735351562,
      "learning_rate": 2.620689655172414e-05,
      "loss": 0.2316,
      "step": 100
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.16867588460445404,
      "eval_runtime": 210.4202,
      "eval_samples_per_second": 0.499,
      "eval_steps_per_second": 0.499,
      "step": 118
    },
    {
      "epoch": 2.545260915867945,
      "grad_norm": 0.27560967206954956,
      "learning_rate": 1.931034482758621e-05,
      "loss": 0.1695,
      "step": 150
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.16012603044509888,
      "eval_runtime": 209.4479,
      "eval_samples_per_second": 0.501,
      "eval_steps_per_second": 0.501,
      "step": 177
    },
    {
      "epoch": 3.3919062832800853,
      "grad_norm": 0.21748089790344238,
      "learning_rate": 1.2413793103448277e-05,
      "loss": 0.1571,
      "step": 200
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.15796616673469543,
      "eval_runtime": 210.9531,
      "eval_samples_per_second": 0.498,
      "eval_steps_per_second": 0.498,
      "step": 236
    },
    {
      "epoch": 4.238551650692226,
      "grad_norm": 0.20169177651405334,
      "learning_rate": 5.517241379310345e-06,
      "loss": 0.1471,
      "step": 250
    },
    {
      "epoch": 4.920127795527156,
      "eval_loss": 0.1572711169719696,
      "eval_runtime": 215.9464,
      "eval_samples_per_second": 0.486,
      "eval_steps_per_second": 0.486,
      "step": 290
    }
  ],
  "logging_steps": 50,
  "max_steps": 290,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1262995069534208e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}