{
 "base": "Qwen/Qwen3.5-2B",
 "dataset": "cagataydev/loopl-train",
 "dataset_revision": "47d27b4415f8f9e35d352fdfecc02f551103366a",
 "split": "train",
 "families": null,
 "format": "both",
 "rows": 13704,
 "tokens": 37226229,
 "max_length": 4096,
 "lora": null,
 "epochs": 2.0,
 "max_steps": -1,
 "lr": 1.5e-05,
 "batch": 2,
 "grad_accum": 8,
 "oversample": "c=2",
 "best_checkpoint": "/tmp/loopl-sft/ckpt/checkpoint-857",
 "best_eval_loss": 1.6541149616241455,
 "eval_history": [
  {
   "eval_loss": 1.6541149616241455,
   "epoch": 1.0
  },
  {
   "eval_loss": 1.7137993574142456,
   "epoch": 2.0
  },
  {
   "eval_loss": 1.6541149616241455,
   "epoch": 2.0
  }
 ],
 "metrics": {
  "train_runtime": 12636.3554,
  "train_samples_per_second": 2.169,
  "train_steps_per_second": 0.136,
  "total_flos": 9.425559306021765e+17,
  "train_loss": 1.0968182736544794,
  "epoch": 2.0,
  "eval_loss": 1.6541149616241455,
  "eval_runtime": 151.4762,
  "eval_samples_per_second": 9.124,
  "eval_steps_per_second": 1.142,
  "eval_entropy": 1.548327516613668,
  "eval_num_tokens": 74452458.0,
  "eval_mean_token_accuracy": 0.6377897055851931
 },
 "data_stats": {
  "read": 8676,
  "rendered": 13704,
  "no_assistant": 1802,
  "render_error": 0,
  "truncated_hint": 1000,
  "tools_injected": 2778
 },
 "wall_s": 13010,
 "versions": {
  "transformers": "5.19.0",
  "trl": "1.14.2",
  "peft": "0.21.2",
  "torch": "2.14.1+cu130"
 },
 "job_id": "6ac5e6ec404719ba37665446"
}