{
  "best_metric": 0.7480754124116261,
  "best_model_checkpoint": "trained/hebban-reviews5/robbert-v2-dutch-base/checkpoint-3000",
  "epoch": 4.382997370727432,
  "global_step": 5001,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.44,
      "learning_rate": 4.501099780043991e-05,
      "loss": 1.0492,
      "step": 500
    },
    {
      "epoch": 0.44,
      "eval_accuracy": 0.5691568047337278,
      "eval_f1": 0.5636413822079555,
      "eval_loss": 0.9223524332046509,
      "eval_precision": 0.5918143879920826,
      "eval_qwk": 0.7063098801003743,
      "eval_recall": 0.5691568047337278,
      "eval_runtime": 23.2899,
      "eval_samples_per_second": 696.61,
      "eval_steps_per_second": 5.453,
      "step": 500
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.0011997600479906e-05,
      "loss": 0.9178,
      "step": 1000
    },
    {
      "epoch": 0.88,
      "eval_accuracy": 0.5837031558185405,
      "eval_f1": 0.5793159803831781,
      "eval_loss": 0.9023029208183289,
      "eval_precision": 0.6074918212756761,
      "eval_qwk": 0.7007746526525567,
      "eval_recall": 0.5837031558185405,
      "eval_runtime": 23.0813,
      "eval_samples_per_second": 702.906,
      "eval_steps_per_second": 5.502,
      "step": 1000
    },
    {
      "epoch": 1.31,
      "learning_rate": 3.5022995400919816e-05,
      "loss": 0.8109,
      "step": 1500
    },
    {
      "epoch": 1.31,
      "eval_accuracy": 0.5977564102564102,
      "eval_f1": 0.5928304451541198,
      "eval_loss": 0.9542309641838074,
      "eval_precision": 0.61219538907447,
      "eval_qwk": 0.7336756182944968,
      "eval_recall": 0.5977564102564102,
      "eval_runtime": 22.9709,
      "eval_samples_per_second": 706.285,
      "eval_steps_per_second": 5.529,
      "step": 1500
    },
    {
      "epoch": 1.75,
      "learning_rate": 3.0033993201359727e-05,
      "loss": 0.7808,
      "step": 2000
    },
    {
      "epoch": 1.75,
      "eval_accuracy": 0.6158777120315582,
      "eval_f1": 0.6160589696416037,
      "eval_loss": 0.9172691106796265,
      "eval_precision": 0.6237298170154965,
      "eval_qwk": 0.7443852226981237,
      "eval_recall": 0.6158777120315582,
      "eval_runtime": 22.9508,
      "eval_samples_per_second": 706.903,
      "eval_steps_per_second": 5.534,
      "step": 2000
    },
    {
      "epoch": 2.19,
      "learning_rate": 2.503499300139972e-05,
      "loss": 0.704,
      "step": 2500
    },
    {
      "epoch": 2.19,
      "eval_accuracy": 0.6121794871794872,
      "eval_f1": 0.6079206553629232,
      "eval_loss": 1.1115827560424805,
      "eval_precision": 0.6233537730211096,
      "eval_qwk": 0.7381725383149609,
      "eval_recall": 0.6121794871794872,
      "eval_runtime": 23.189,
      "eval_samples_per_second": 699.641,
      "eval_steps_per_second": 5.477,
      "step": 2500
    },
    {
      "epoch": 2.63,
      "learning_rate": 2.0045990801839633e-05,
      "loss": 0.6401,
      "step": 3000
    },
    {
      "epoch": 2.63,
      "eval_accuracy": 0.6272805719921104,
      "eval_f1": 0.6283777941836641,
      "eval_loss": 1.1353460550308228,
      "eval_precision": 0.6325852588723305,
      "eval_qwk": 0.7480754124116261,
      "eval_recall": 0.6272805719921104,
      "eval_runtime": 23.0847,
      "eval_samples_per_second": 702.804,
      "eval_steps_per_second": 5.501,
      "step": 3000
    },
    {
      "epoch": 3.07,
      "learning_rate": 1.5046990601879624e-05,
      "loss": 0.612,
      "step": 3500
    },
    {
      "epoch": 3.07,
      "eval_accuracy": 0.624198717948718,
      "eval_f1": 0.6228264241003357,
      "eval_loss": 1.2358475923538208,
      "eval_precision": 0.6296279459229124,
      "eval_qwk": 0.7443813858149255,
      "eval_recall": 0.624198717948718,
      "eval_runtime": 23.07,
      "eval_samples_per_second": 703.252,
      "eval_steps_per_second": 5.505,
      "step": 3500
    },
    {
      "epoch": 3.51,
      "learning_rate": 1.0047990401919617e-05,
      "loss": 0.536,
      "step": 4000
    },
    {
      "epoch": 3.51,
      "eval_accuracy": 0.6244452662721893,
      "eval_f1": 0.623840669755937,
      "eval_loss": 1.2645397186279297,
      "eval_precision": 0.6306447854320058,
      "eval_qwk": 0.743683140105029,
      "eval_recall": 0.6244452662721893,
      "eval_runtime": 22.815,
      "eval_samples_per_second": 711.112,
      "eval_steps_per_second": 5.567,
      "step": 4000
    },
    {
      "epoch": 3.94,
      "learning_rate": 5.048990201959608e-06,
      "loss": 0.5326,
      "step": 4500
    },
    {
      "epoch": 3.94,
      "eval_accuracy": 0.6256780078895463,
      "eval_f1": 0.625250776842927,
      "eval_loss": 1.2848360538482666,
      "eval_precision": 0.6314145408376363,
      "eval_qwk": 0.7451057727705823,
      "eval_recall": 0.6256780078895463,
      "eval_runtime": 23.0764,
      "eval_samples_per_second": 703.056,
      "eval_steps_per_second": 5.503,
      "step": 4500
    },
    {
      "epoch": 4.38,
      "learning_rate": 4.999000199960008e-08,
      "loss": 0.4802,
      "step": 5000
    },
    {
      "epoch": 4.38,
      "eval_accuracy": 0.6283900394477318,
      "eval_f1": 0.6282900923952147,
      "eval_loss": 1.3624160289764404,
      "eval_precision": 0.6318538074407878,
      "eval_qwk": 0.7462804704035614,
      "eval_recall": 0.6283900394477318,
      "eval_runtime": 23.1033,
      "eval_samples_per_second": 702.237,
      "eval_steps_per_second": 5.497,
      "step": 5000
    },
    {
      "epoch": 4.38,
      "step": 5001,
      "total_flos": 1.6839139993111757e+17,
      "train_loss": 0.7063156554363318,
      "train_runtime": 2589.1522,
      "train_samples_per_second": 247.235,
      "train_steps_per_second": 1.932
    }
  ],
  "max_steps": 5001,
  "num_train_epochs": 5,
  "total_flos": 1.6839139993111757e+17,
  "trial_name": null,
  "trial_params": null
}