training_history.json

[
  {
    "loss": 0.8685,
    "grad_norm": 3.481233835220337,
    "learning_rate": 9.900000000000002e-06,
    "epoch": 0.7092198581560284,
    "step": 100
  },
  {
    "eval_loss": 0.2325897216796875,
    "eval_accuracy": 0.9201523930470672,
    "eval_f1": 0.717974180734856,
    "eval_runtime": 3.2063,
    "eval_samples_per_second": 174.345,
    "eval_steps_per_second": 5.614,
    "epoch": 1.0,
    "step": 141
  },
  {
    "loss": 0.2274,
    "grad_norm": 1.5385990142822266,
    "learning_rate": 1.9900000000000003e-05,
    "epoch": 1.4184397163120568,
    "step": 200
  },
  {
    "eval_loss": 0.14628532528877258,
    "eval_accuracy": 0.9490435748868958,
    "eval_f1": 0.8258811152025249,
    "eval_runtime": 3.1326,
    "eval_samples_per_second": 178.447,
    "eval_steps_per_second": 5.746,
    "epoch": 2.0,
    "step": 282
  },
  {
    "loss": 0.1409,
    "grad_norm": 1.131034016609192,
    "learning_rate": 2.9900000000000002e-05,
    "epoch": 2.127659574468085,
    "step": 300
  },
  {
    "loss": 0.1162,
    "grad_norm": 1.4681241512298584,
    "learning_rate": 3.99e-05,
    "epoch": 2.8368794326241136,
    "step": 400
  },
  {
    "eval_loss": 0.16565711796283722,
    "eval_accuracy": 0.9450750059528534,
    "eval_f1": 0.8205513784461153,
    "eval_runtime": 3.1398,
    "eval_samples_per_second": 178.04,
    "eval_steps_per_second": 5.733,
    "epoch": 3.0,
    "step": 423
  },
  {
    "train_runtime": 218.6651,
    "train_samples_per_second": 61.491,
    "train_steps_per_second": 1.934,
    "total_flos": 878380812168192.0,
    "train_loss": 0.3254874164049225,
    "epoch": 3.0,
    "step": 423
  },
  {
    "eval_loss": 0.12958413362503052,
    "eval_accuracy": 0.9540563620836892,
    "eval_f1": 0.8495117748420448,
    "eval_runtime": 3.1102,
    "eval_samples_per_second": 179.087,
    "eval_steps_per_second": 5.787,
    "epoch": 3.0,
    "step": 423
  }
]