{
 "args": {
  "model": "Qwen/Qwen3.5-4B",
  "out": "C:\\ft\\qwen35-rocket-cap60-s42",
  "train": "C:\\ft\\data_qwen\\sft_v2_cap60.jsonl",
  "test": "new_results/sft_test_v2.jsonl",
  "epochs": 3,
  "lr": 0.0002,
  "rank": 16,
  "alpha": 16,
  "batch": 1,
  "accum": 8,
  "max_len": 6400,
  "seed": 42,
  "keep_thought": true,
  "smoke": 0,
  "no_export": false,
  "export_only": false,
  "gguf": "q4_k_m",
  "name": null
 },
 "lowest_test_loss_checkpoint": "C:\\ft\\qwen35-rocket-cap60-s42\\checkpoints\\checkpoint-57",
 "lowest_test_loss": 0.4498031437397003,
 "log_history": [
  {
   "loss": 1.1940197944641113,
   "grad_norm": 0.5686907768249512,
   "learning_rate": 0.0,
   "epoch": 0.052980132450331126,
   "step": 1
  },
  {
   "loss": 1.1503667831420898,
   "grad_norm": 0.5759090781211853,
   "learning_rate": 4e-05,
   "epoch": 0.10596026490066225,
   "step": 2
  },
  {
   "loss": 1.097617745399475,
   "grad_norm": 0.4405198097229004,
   "learning_rate": 8e-05,
   "epoch": 0.15894039735099338,
   "step": 3
  },
  {
   "loss": 1.2405256032943726,
   "grad_norm": 0.5403232574462891,
   "learning_rate": 0.00012,
   "epoch": 0.2119205298013245,
   "step": 4
  },
  {
   "loss": 1.0477312803268433,
   "grad_norm": 0.422463059425354,
   "learning_rate": 0.00016,
   "epoch": 0.26490066225165565,
   "step": 5
  },
  {
   "loss": 1.0621228218078613,
   "grad_norm": 0.42640793323516846,
   "learning_rate": 0.0002,
   "epoch": 0.31788079470198677,
   "step": 6
  },
  {
   "loss": 0.8830090761184692,
   "grad_norm": 0.3740926682949066,
   "learning_rate": 0.00019615384615384615,
   "epoch": 0.3708609271523179,
   "step": 7
  },
  {
   "loss": 0.8500662446022034,
   "grad_norm": 0.6125431060791016,
   "learning_rate": 0.00019230769230769233,
   "epoch": 0.423841059602649,
   "step": 8
  },
  {
   "loss": 0.7644960284233093,
   "grad_norm": 1.4327044486999512,
   "learning_rate": 0.00018846153846153847,
   "epoch": 0.4768211920529801,
   "step": 9
  },
  {
   "loss": 0.6838762164115906,
   "grad_norm": 0.5240151882171631,
   "learning_rate": 0.00018461538461538463,
   "epoch": 0.5298013245033113,
   "step": 10
  },
  {
   "loss": 0.631365954875946,
   "grad_norm": 0.548250675201416,
   "learning_rate": 0.00018076923076923077,
   "epoch": 0.5827814569536424,
   "step": 11
  },
  {
   "loss": 0.544463574886322,
   "grad_norm": 0.4309953451156616,
   "learning_rate": 0.00017692307692307693,
   "epoch": 0.6357615894039735,
   "step": 12
  },
  {
   "loss": 0.5192594528198242,
   "grad_norm": 0.5269620418548584,
   "learning_rate": 0.0001730769230769231,
   "epoch": 0.6887417218543046,
   "step": 13
  },
  {
   "loss": 0.5038818120956421,
   "grad_norm": 0.4541371464729309,
   "learning_rate": 0.00016923076923076923,
   "epoch": 0.7417218543046358,
   "step": 14
  },
  {
   "loss": 0.4713430404663086,
   "grad_norm": 0.2787449061870575,
   "learning_rate": 0.0001653846153846154,
   "epoch": 0.7947019867549668,
   "step": 15
  },
  {
   "loss": 0.45822674036026,
   "grad_norm": 0.42266541719436646,
   "learning_rate": 0.00016153846153846155,
   "epoch": 0.847682119205298,
   "step": 16
  },
  {
   "loss": 0.42965811491012573,
   "grad_norm": 0.3698597252368927,
   "learning_rate": 0.0001576923076923077,
   "epoch": 0.9006622516556292,
   "step": 17
  },
  {
   "loss": 0.4353315532207489,
   "grad_norm": 0.27575576305389404,
   "learning_rate": 0.00015384615384615385,
   "epoch": 0.9536423841059603,
   "step": 18
  },
  {
   "loss": 0.5523375868797302,
   "grad_norm": 0.4252977967262268,
   "learning_rate": 0.00015000000000000001,
   "epoch": 1.0,
   "step": 19
  },
  {
   "eval_loss": 0.49851980805397034,
   "eval_runtime": 5.9076,
   "eval_samples_per_second": 6.432,
   "eval_steps_per_second": 6.432,
   "epoch": 1.0,
   "step": 19
  },
  {
   "loss": 0.38191357254981995,
   "grad_norm": 0.2684159278869629,
   "learning_rate": 0.00014615384615384615,
   "epoch": 1.0529801324503312,
   "step": 20
  },
  {
   "loss": 0.46314921975135803,
   "grad_norm": 0.27592435479164124,
   "learning_rate": 0.0001423076923076923,
   "epoch": 1.1059602649006623,
   "step": 21
  },
  {
   "loss": 0.36137470602989197,
   "grad_norm": 0.25687986612319946,
   "learning_rate": 0.00013846153846153847,
   "epoch": 1.1589403973509933,
   "step": 22
  },
  {
   "loss": 0.4026918113231659,
   "grad_norm": 0.25701817870140076,
   "learning_rate": 0.00013461538461538464,
   "epoch": 1.2119205298013245,
   "step": 23
  },
  {
   "loss": 0.3442859351634979,
   "grad_norm": 0.32386720180511475,
   "learning_rate": 0.00013076923076923077,
   "epoch": 1.2649006622516556,
   "step": 24
  },
  {
   "loss": 0.33980318903923035,
   "grad_norm": 0.23817896842956543,
   "learning_rate": 0.00012692307692307693,
   "epoch": 1.3178807947019868,
   "step": 25
  },
  {
   "loss": 0.3924781084060669,
   "grad_norm": 0.2661411762237549,
   "learning_rate": 0.0001230769230769231,
   "epoch": 1.370860927152318,
   "step": 26
  },
  {
   "loss": 0.3287935256958008,
   "grad_norm": 0.2644951343536377,
   "learning_rate": 0.00011923076923076923,
   "epoch": 1.423841059602649,
   "step": 27
  },
  {
   "loss": 0.38360974192619324,
   "grad_norm": 0.2365025132894516,
   "learning_rate": 0.00011538461538461538,
   "epoch": 1.4768211920529801,
   "step": 28
  },
  {
   "loss": 0.34624168276786804,
   "grad_norm": 0.22081725299358368,
   "learning_rate": 0.00011153846153846154,
   "epoch": 1.5298013245033113,
   "step": 29
  },
  {
   "loss": 0.3713926374912262,
   "grad_norm": 0.30055052042007446,
   "learning_rate": 0.0001076923076923077,
   "epoch": 1.5827814569536423,
   "step": 30
  },
  {
   "loss": 0.341941773891449,
   "grad_norm": 0.2464168816804886,
   "learning_rate": 0.00010384615384615386,
   "epoch": 1.6357615894039736,
   "step": 31
  },
  {
   "loss": 0.3046576678752899,
   "grad_norm": 0.26711592078208923,
   "learning_rate": 0.0001,
   "epoch": 1.6887417218543046,
   "step": 32
  },
  {
   "loss": 0.3337293267250061,
   "grad_norm": 0.2371147722005844,
   "learning_rate": 9.615384615384617e-05,
   "epoch": 1.7417218543046358,
   "step": 33
  },
  {
   "loss": 0.3232137858867645,
   "grad_norm": 0.28805726766586304,
   "learning_rate": 9.230769230769232e-05,
   "epoch": 1.794701986754967,
   "step": 34
  },
  {
   "loss": 0.3332085609436035,
   "grad_norm": 0.2506534159183502,
   "learning_rate": 8.846153846153847e-05,
   "epoch": 1.847682119205298,
   "step": 35
  },
  {
   "loss": 0.32374894618988037,
   "grad_norm": 0.2647243142127991,
   "learning_rate": 8.461538461538461e-05,
   "epoch": 1.9006622516556293,
   "step": 36
  },
  {
   "loss": 0.3772493898868561,
   "grad_norm": 0.23724476993083954,
   "learning_rate": 8.076923076923078e-05,
   "epoch": 1.9536423841059603,
   "step": 37
  },
  {
   "loss": 0.32642272114753723,
   "grad_norm": 0.25431814789772034,
   "learning_rate": 7.692307692307693e-05,
   "epoch": 2.0,
   "step": 38
  },
  {
   "eval_loss": 0.4524935185909271,
   "eval_runtime": 4.617,
   "eval_samples_per_second": 8.23,
   "eval_steps_per_second": 8.23,
   "epoch": 2.0,
   "step": 38
  },
  {
   "loss": 0.32388836145401,
   "grad_norm": 0.242446631193161,
   "learning_rate": 7.307692307692307e-05,
   "epoch": 2.052980132450331,
   "step": 39
  },
  {
   "loss": 0.3339792490005493,
   "grad_norm": 0.24037185311317444,
   "learning_rate": 6.923076923076924e-05,
   "epoch": 2.1059602649006623,
   "step": 40
  },
  {
   "loss": 0.2732575237751007,
   "grad_norm": 0.29293331503868103,
   "learning_rate": 6.538461538461539e-05,
   "epoch": 2.1589403973509933,
   "step": 41
  },
  {
   "loss": 0.3503388464450836,
   "grad_norm": 0.2509494423866272,
   "learning_rate": 6.153846153846155e-05,
   "epoch": 2.2119205298013247,
   "step": 42
  },
  {
   "loss": 0.32519522309303284,
   "grad_norm": 0.2634280323982239,
   "learning_rate": 5.769230769230769e-05,
   "epoch": 2.2649006622516556,
   "step": 43
  },
  {
   "loss": 0.25674334168434143,
   "grad_norm": 0.2411653846502304,
   "learning_rate": 5.384615384615385e-05,
   "epoch": 2.3178807947019866,
   "step": 44
  },
  {
   "loss": 0.3119312524795532,
   "grad_norm": 0.21579930186271667,
   "learning_rate": 5e-05,
   "epoch": 2.370860927152318,
   "step": 45
  },
  {
   "loss": 0.294747918844223,
   "grad_norm": 0.25472205877304077,
   "learning_rate": 4.615384615384616e-05,
   "epoch": 2.423841059602649,
   "step": 46
  },
  {
   "loss": 0.2929841876029968,
   "grad_norm": 0.2879176139831543,
   "learning_rate": 4.230769230769231e-05,
   "epoch": 2.47682119205298,
   "step": 47
  },
  {
   "loss": 0.30371516942977905,
   "grad_norm": 0.28370824456214905,
   "learning_rate": 3.846153846153846e-05,
   "epoch": 2.5298013245033113,
   "step": 48
  },
  {
   "loss": 0.28118428587913513,
   "grad_norm": 0.2666170597076416,
   "learning_rate": 3.461538461538462e-05,
   "epoch": 2.5827814569536423,
   "step": 49
  },
  {
   "loss": 0.26528528332710266,
   "grad_norm": 0.281615287065506,
   "learning_rate": 3.0769230769230774e-05,
   "epoch": 2.6357615894039736,
   "step": 50
  },
  {
   "loss": 0.32126152515411377,
   "grad_norm": 0.24899466335773468,
   "learning_rate": 2.6923076923076923e-05,
   "epoch": 2.6887417218543046,
   "step": 51
  },
  {
   "loss": 0.2957591414451599,
   "grad_norm": 0.25963354110717773,
   "learning_rate": 2.307692307692308e-05,
   "epoch": 2.741721854304636,
   "step": 52
  },
  {
   "loss": 0.2610109746456146,
   "grad_norm": 0.3147188723087311,
   "learning_rate": 1.923076923076923e-05,
   "epoch": 2.794701986754967,
   "step": 53
  },
  {
   "loss": 0.3080472946166992,
   "grad_norm": 0.22268587350845337,
   "learning_rate": 1.5384615384615387e-05,
   "epoch": 2.847682119205298,
   "step": 54
  },
  {
   "loss": 0.291984498500824,
   "grad_norm": 0.28291916847229004,
   "learning_rate": 1.153846153846154e-05,
   "epoch": 2.9006622516556293,
   "step": 55
  },
  {
   "loss": 0.29318422079086304,
   "grad_norm": 0.22744245827198029,
   "learning_rate": 7.692307692307694e-06,
   "epoch": 2.9536423841059603,
   "step": 56
  },
  {
   "loss": 0.26727962493896484,
   "grad_norm": 0.2928221821784973,
   "learning_rate": 3.846153846153847e-06,
   "epoch": 3.0,
   "step": 57
  },
  {
   "eval_loss": 0.4498031437397003,
   "eval_runtime": 4.2761,
   "eval_samples_per_second": 8.887,
   "eval_steps_per_second": 8.887,
   "epoch": 3.0,
   "step": 57
  },
  {
   "train_runtime": 225.952,
   "train_samples_per_second": 2.005,
   "train_steps_per_second": 0.252,
   "total_flos": 1.1110113536504832e+16,
   "train_loss": 0.47283129211057695,
   "epoch": 3.0,
   "step": 57
  }
 ]
}