trainer_state.json

{
  "best_metric": 0.11598550528287888,
  "best_model_checkpoint": "./HFTB-SmolLM2-135M-Instruct-OTCMedicinePHv2\\checkpoint-250",
  "epoch": 9.70873786407767,
  "eval_steps": 50,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.941747572815534,
      "grad_norm": 0.35462793707847595,
      "learning_rate": 0.0005,
      "loss": 0.8189,
      "step": 50
    },
    {
      "epoch": 1.941747572815534,
      "eval_loss": 0.16038869321346283,
      "eval_runtime": 13.1355,
      "eval_samples_per_second": 40.349,
      "eval_steps_per_second": 5.101,
      "step": 50
    },
    {
      "epoch": 3.883495145631068,
      "grad_norm": 0.2993379235267639,
      "learning_rate": 0.0005,
      "loss": 0.1464,
      "step": 100
    },
    {
      "epoch": 3.883495145631068,
      "eval_loss": 0.12895184755325317,
      "eval_runtime": 12.8791,
      "eval_samples_per_second": 41.152,
      "eval_steps_per_second": 5.202,
      "step": 100
    },
    {
      "epoch": 5.825242718446602,
      "grad_norm": 0.14636453986167908,
      "learning_rate": 0.0005,
      "loss": 0.127,
      "step": 150
    },
    {
      "epoch": 5.825242718446602,
      "eval_loss": 0.12111850827932358,
      "eval_runtime": 12.7129,
      "eval_samples_per_second": 41.69,
      "eval_steps_per_second": 5.27,
      "step": 150
    },
    {
      "epoch": 7.766990291262136,
      "grad_norm": 0.1845141053199768,
      "learning_rate": 0.0005,
      "loss": 0.1212,
      "step": 200
    },
    {
      "epoch": 7.766990291262136,
      "eval_loss": 0.11958930641412735,
      "eval_runtime": 14.1475,
      "eval_samples_per_second": 37.463,
      "eval_steps_per_second": 4.736,
      "step": 200
    },
    {
      "epoch": 9.70873786407767,
      "grad_norm": 0.14870111644268036,
      "learning_rate": 0.0005,
      "loss": 0.1183,
      "step": 250
    },
    {
      "epoch": 9.70873786407767,
      "eval_loss": 0.11598550528287888,
      "eval_runtime": 13.0644,
      "eval_samples_per_second": 40.568,
      "eval_steps_per_second": 5.128,
      "step": 250
    },
    {
      "epoch": 9.70873786407767,
      "step": 250,
      "total_flos": 634548176930304.0,
      "train_loss": 0.2663491096496582,
      "train_runtime": 2216.0805,
      "train_samples_per_second": 21.66,
      "train_steps_per_second": 0.451
    }
  ],
  "logging_steps": 50,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 634548176930304.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}