Training in progress, epoch 1, checkpoint

checkpoint-555/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73390260de79e2c8629bcd13a704a7b0a9571a7b60fb682f4a2233bfce71939b
+oid sha256:8149a3fa6dc63e6cfa5e7d3784b20b3374fe33d5c7e5a330a26eabf4b1653ea7
 size 1629432864

checkpoint-555/trainer_state.json

@@ -8,411 +8,418 @@
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0,
+      "eval_f1": 0.45686228664952067,
+      "eval_loss": 0.701814591884613,
+      "eval_precision": 0.4909547738693467,
+      "eval_recall": 0.42719720157411456,
+      "eval_runtime": 72.3647,
+      "eval_samples_per_second": 64.576,
+      "eval_steps_per_second": 8.084,
+      "step": 0
+    },
     {
       "epoch": 0.018026137899954935,
-      "grad_norm": 37.54188919067383,
-      "learning_rate": 4.981949458483755e-05,
-      "loss": 0.8911,
+      "grad_norm": 37.129154205322266,
+      "learning_rate": 4.9548736462093865e-05,
+      "loss": 0.8401,
       "step": 10
     },
     {
       "epoch": 0.03605227579990987,
-      "grad_norm": 15.440231323242188,
-      "learning_rate": 4.963898916967509e-05,
-      "loss": 0.6165,
+      "grad_norm": 32.83527374267578,
+      "learning_rate": 4.909747292418773e-05,
+      "loss": 0.6093,
       "step": 20
     },
     {
       "epoch": 0.054078413699864804,
-      "grad_norm": 226.8269500732422,
-      "learning_rate": 4.945848375451264e-05,
-      "loss": 0.5151,
+      "grad_norm": 48.55173873901367,
+      "learning_rate": 4.864620938628159e-05,
+      "loss": 0.5201,
       "step": 30
     },
     {
       "epoch": 0.07210455159981974,
-      "grad_norm": 21.70491600036621,
-      "learning_rate": 4.927797833935018e-05,
-      "loss": 0.5669,
+      "grad_norm": 24.419078826904297,
+      "learning_rate": 4.819494584837546e-05,
+      "loss": 0.5847,
       "step": 40
     },
     {
       "epoch": 0.09013068949977468,
-      "grad_norm": 79.27781677246094,
-      "learning_rate": 4.909747292418773e-05,
-      "loss": 0.5119,
+      "grad_norm": 27.96658706665039,
+      "learning_rate": 4.7743682310469314e-05,
+      "loss": 0.4958,
       "step": 50
     },
     {
       "epoch": 0.10815682739972961,
-      "grad_norm": 15.314950942993164,
-      "learning_rate": 4.891696750902527e-05,
-      "loss": 0.474,
+      "grad_norm": 28.15681266784668,
+      "learning_rate": 4.7292418772563177e-05,
+      "loss": 0.4754,
       "step": 60
     },
     {
       "epoch": 0.12618296529968454,
-      "grad_norm": 25.575763702392578,
-      "learning_rate": 4.873646209386282e-05,
-      "loss": 0.478,
+      "grad_norm": 27.729917526245117,
+      "learning_rate": 4.684115523465704e-05,
+      "loss": 0.4621,
       "step": 70
     },
     {
       "epoch": 0.14420910319963948,
-      "grad_norm": 27.453636169433594,
-      "learning_rate": 4.855595667870036e-05,
-      "loss": 0.4285,
+      "grad_norm": 24.70597267150879,
+      "learning_rate": 4.63898916967509e-05,
+      "loss": 0.4333,
       "step": 80
     },
     {
       "epoch": 0.16223524109959442,
-      "grad_norm": 34.88062286376953,
-      "learning_rate": 4.837545126353791e-05,
-      "loss": 0.4317,
+      "grad_norm": 30.800254821777344,
+      "learning_rate": 4.5938628158844764e-05,
+      "loss": 0.4425,
       "step": 90
     },
     {
       "epoch": 0.18026137899954936,
-      "grad_norm": 46.823577880859375,
-      "learning_rate": 4.819494584837546e-05,
-      "loss": 0.4899,
+      "grad_norm": 37.59977340698242,
+      "learning_rate": 4.548736462093863e-05,
+      "loss": 0.4774,
       "step": 100
     },
     {
       "epoch": 0.19828751689950427,
-      "grad_norm": 36.73914337158203,
-      "learning_rate": 4.8014440433213e-05,
-      "loss": 0.4839,
+      "grad_norm": 36.29924392700195,
+      "learning_rate": 4.5036101083032495e-05,
+      "loss": 0.4853,
       "step": 110
     },
     {
       "epoch": 0.21631365479945922,
-      "grad_norm": 102.61051940917969,
-      "learning_rate": 4.783393501805055e-05,
-      "loss": 0.4795,
+      "grad_norm": 22.9832763671875,
+      "learning_rate": 4.458483754512636e-05,
+      "loss": 0.4419,
       "step": 120
     },
     {
       "epoch": 0.23433979269941416,
-      "grad_norm": 24.9108829498291,
-      "learning_rate": 4.765342960288809e-05,
-      "loss": 0.4332,
+      "grad_norm": 35.384368896484375,
+      "learning_rate": 4.413357400722022e-05,
+      "loss": 0.4376,
       "step": 130
     },
     {
       "epoch": 0.25236593059936907,
-      "grad_norm": 14.366719245910645,
-      "learning_rate": 4.747292418772563e-05,
-      "loss": 0.4811,
+      "grad_norm": 16.165664672851562,
+      "learning_rate": 4.368231046931408e-05,
+      "loss": 0.4557,
       "step": 140
     },
     {
       "epoch": 0.270392068499324,
-      "grad_norm": 19.95521354675293,
-      "learning_rate": 4.7292418772563177e-05,
-      "loss": 0.4544,
+      "grad_norm": 13.965127944946289,
+      "learning_rate": 4.3231046931407945e-05,
+      "loss": 0.4723,
       "step": 150
     },
     {
       "epoch": 0.28841820639927895,
-      "grad_norm": 20.914020538330078,
-      "learning_rate": 4.711191335740072e-05,
-      "loss": 0.4646,
+      "grad_norm": 30.59395980834961,
+      "learning_rate": 4.277978339350181e-05,
+      "loss": 0.4656,
       "step": 160
     },
     {
       "epoch": 0.3064443442992339,
-      "grad_norm": 154.6277313232422,
-      "learning_rate": 4.693140794223827e-05,
-      "loss": 0.47,
+      "grad_norm": 27.32846450805664,
+      "learning_rate": 4.232851985559567e-05,
+      "loss": 0.4858,
       "step": 170
     },
     {
       "epoch": 0.32447048219918884,
-      "grad_norm": 30.73076820373535,
-      "learning_rate": 4.675090252707581e-05,
-      "loss": 0.4341,
+      "grad_norm": 14.389259338378906,
+      "learning_rate": 4.187725631768953e-05,
+      "loss": 0.4604,
       "step": 180
     },
     {
       "epoch": 0.3424966200991438,
-      "grad_norm": 14.621489524841309,
-      "learning_rate": 4.657039711191336e-05,
-      "loss": 0.5163,
+      "grad_norm": 17.084495544433594,
+      "learning_rate": 4.1425992779783394e-05,
+      "loss": 0.504,
       "step": 190
     },
     {
       "epoch": 0.3605227579990987,
-      "grad_norm": 25.546030044555664,
-      "learning_rate": 4.63898916967509e-05,
-      "loss": 0.4601,
+      "grad_norm": 27.83977508544922,
+      "learning_rate": 4.0974729241877256e-05,
+      "loss": 0.4581,
       "step": 200
     },
     {
       "epoch": 0.3785488958990536,
-      "grad_norm": 18.222177505493164,
-      "learning_rate": 4.620938628158845e-05,
-      "loss": 0.4398,
+      "grad_norm": 27.089218139648438,
+      "learning_rate": 4.052346570397112e-05,
+      "loss": 0.4239,
       "step": 210
     },
     {
       "epoch": 0.39657503379900855,
-      "grad_norm": 20.1109676361084,
-      "learning_rate": 4.602888086642599e-05,
-      "loss": 0.432,
+      "grad_norm": 22.199338912963867,
+      "learning_rate": 4.007220216606498e-05,
+      "loss": 0.4356,
       "step": 220
     },
     {
       "epoch": 0.4146011716989635,
-      "grad_norm": 13.729535102844238,
-      "learning_rate": 4.584837545126354e-05,
-      "loss": 0.4327,
+      "grad_norm": 13.628811836242676,
+      "learning_rate": 3.962093862815885e-05,
+      "loss": 0.4363,
       "step": 230
     },
     {
       "epoch": 0.43262730959891843,
-      "grad_norm": 32.50856018066406,
-      "learning_rate": 4.566787003610109e-05,
-      "loss": 0.4208,
+      "grad_norm": 27.136962890625,
+      "learning_rate": 3.916967509025271e-05,
+      "loss": 0.4419,
       "step": 240
     },
     {
       "epoch": 0.45065344749887337,
-      "grad_norm": 15.05933666229248,
-      "learning_rate": 4.548736462093863e-05,
-      "loss": 0.4451,
+      "grad_norm": 21.228151321411133,
+      "learning_rate": 3.8718411552346575e-05,
+      "loss": 0.4258,
       "step": 250
     },
     {
       "epoch": 0.4686795853988283,
-      "grad_norm": 31.787078857421875,
-      "learning_rate": 4.530685920577618e-05,
-      "loss": 0.4376,
+      "grad_norm": 21.63435935974121,
+      "learning_rate": 3.826714801444044e-05,
+      "loss": 0.4232,
       "step": 260
     },
     {
       "epoch": 0.48670572329878325,
-      "grad_norm": 25.446210861206055,
-      "learning_rate": 4.5126353790613716e-05,
-      "loss": 0.4131,
+      "grad_norm": 23.011816024780273,
+      "learning_rate": 3.78158844765343e-05,
+      "loss": 0.417,
       "step": 270
     },
     {
       "epoch": 0.5047318611987381,
-      "grad_norm": 31.328969955444336,
-      "learning_rate": 4.494584837545127e-05,
-      "loss": 0.4194,
+      "grad_norm": 22.028409957885742,
+      "learning_rate": 3.7364620938628155e-05,
+      "loss": 0.3913,
       "step": 280
     },
     {
       "epoch": 0.5227579990986931,
-      "grad_norm": 255.53672790527344,
-      "learning_rate": 4.4765342960288806e-05,
-      "loss": 0.4984,
+      "grad_norm": 13.293946266174316,
+      "learning_rate": 3.6913357400722025e-05,
+      "loss": 0.4443,
       "step": 290
     },
     {
       "epoch": 0.540784136998648,
-      "grad_norm": 14.31953239440918,
-      "learning_rate": 4.458483754512636e-05,
-      "loss": 0.4417,
+      "grad_norm": 16.026897430419922,
+      "learning_rate": 3.646209386281589e-05,
+      "loss": 0.4243,
       "step": 300
     },
     {
       "epoch": 0.558810274898603,
-      "grad_norm": 26.942129135131836,
-      "learning_rate": 4.44043321299639e-05,
-      "loss": 0.4527,
+      "grad_norm": 22.489286422729492,
+      "learning_rate": 3.601083032490975e-05,
+      "loss": 0.4157,
       "step": 310
     },
     {
       "epoch": 0.5768364127985579,
-      "grad_norm": 36.217586517333984,
-      "learning_rate": 4.422382671480145e-05,
-      "loss": 0.4485,
+      "grad_norm": 34.415470123291016,
+      "learning_rate": 3.555956678700361e-05,
+      "loss": 0.4159,
       "step": 320
     },
     {
       "epoch": 0.5948625506985128,
-      "grad_norm": 38.54646682739258,
-      "learning_rate": 4.404332129963899e-05,
-      "loss": 0.4579,
+      "grad_norm": 28.348594665527344,
+      "learning_rate": 3.5108303249097474e-05,
+      "loss": 0.4409,
       "step": 330
     },
     {
       "epoch": 0.6128886885984678,
-      "grad_norm": 21.504106521606445,
-      "learning_rate": 4.386281588447654e-05,
-      "loss": 0.4117,
+      "grad_norm": 16.92120933532715,
+      "learning_rate": 3.4657039711191336e-05,
+      "loss": 0.4034,
       "step": 340
     },
     {
       "epoch": 0.6309148264984227,
-      "grad_norm": 16.283788681030273,
-      "learning_rate": 4.368231046931408e-05,
-      "loss": 0.438,
+      "grad_norm": 15.073827743530273,
+      "learning_rate": 3.42057761732852e-05,
+      "loss": 0.4164,
       "step": 350
     },
     {
       "epoch": 0.6489409643983777,
-      "grad_norm": 33.57164001464844,
-      "learning_rate": 4.350180505415163e-05,
-      "loss": 0.4043,
+      "grad_norm": 23.035175323486328,
+      "learning_rate": 3.375451263537907e-05,
+      "loss": 0.3952,
       "step": 360
     },
     {
       "epoch": 0.6669671022983326,
-      "grad_norm": 12.821700096130371,
-      "learning_rate": 4.332129963898917e-05,
-      "loss": 0.4119,
+      "grad_norm": 19.5601806640625,
+      "learning_rate": 3.330324909747293e-05,
+      "loss": 0.3883,
       "step": 370
     },
     {
       "epoch": 0.6849932401982876,
-      "grad_norm": 23.477996826171875,
-      "learning_rate": 4.314079422382672e-05,
-      "loss": 0.3783,
+      "grad_norm": 20.22748565673828,
+      "learning_rate": 3.2851985559566786e-05,
+      "loss": 0.3869,
       "step": 380
     },
     {
       "epoch": 0.7030193780982424,
-      "grad_norm": 18.2862548828125,
-      "learning_rate": 4.296028880866426e-05,
-      "loss": 0.4023,
+      "grad_norm": 19.998939514160156,
+      "learning_rate": 3.240072202166065e-05,
+      "loss": 0.3889,
       "step": 390
     },
     {
       "epoch": 0.7210455159981974,
-      "grad_norm": 19.799530029296875,
-      "learning_rate": 4.277978339350181e-05,
-      "loss": 0.419,
+      "grad_norm": 27.682971954345703,
+      "learning_rate": 3.194945848375451e-05,
+      "loss": 0.4554,
       "step": 400
     },
     {
       "epoch": 0.7390716538981523,
-      "grad_norm": 17.081830978393555,
-      "learning_rate": 4.259927797833935e-05,
-      "loss": 0.467,
+      "grad_norm": 16.14117431640625,
+      "learning_rate": 3.149819494584837e-05,
+      "loss": 0.4202,
       "step": 410
     },
     {
       "epoch": 0.7570977917981072,
-      "grad_norm": 24.008344650268555,
-      "learning_rate": 4.24187725631769e-05,
-      "loss": 0.4302,
+      "grad_norm": 30.020023345947266,
+      "learning_rate": 3.104693140794224e-05,
+      "loss": 0.4067,
       "step": 420
     },
     {
       "epoch": 0.7751239296980622,
-      "grad_norm": 40.07936477661133,
-      "learning_rate": 4.223826714801444e-05,
-      "loss": 0.3622,
+      "grad_norm": 33.89706039428711,
+      "learning_rate": 3.0595667870036104e-05,
+      "loss": 0.3647,
       "step": 430
     },
     {
       "epoch": 0.7931500675980171,
-      "grad_norm": 19.614171981811523,
-      "learning_rate": 4.205776173285199e-05,
-      "loss": 0.4645,
+      "grad_norm": 15.263274192810059,
+      "learning_rate": 3.0144404332129967e-05,
+      "loss": 0.4292,
       "step": 440
     },
     {
       "epoch": 0.8111762054979721,
-      "grad_norm": 32.0594596862793,
-      "learning_rate": 4.187725631768953e-05,
-      "loss": 0.3755,
+      "grad_norm": 20.31402587890625,
+      "learning_rate": 2.969314079422383e-05,
+      "loss": 0.3802,
       "step": 450
     },
     {
       "epoch": 0.829202343397927,
-      "grad_norm": 15.177023887634277,
-      "learning_rate": 4.169675090252708e-05,
-      "loss": 0.4275,
+      "grad_norm": 18.45032501220703,
+      "learning_rate": 2.924187725631769e-05,
+      "loss": 0.39,
       "step": 460
     },
     {
       "epoch": 0.847228481297882,
-      "grad_norm": 11.258400917053223,
-      "learning_rate": 4.151624548736462e-05,
-      "loss": 0.4137,
+      "grad_norm": 13.733787536621094,
+      "learning_rate": 2.879061371841155e-05,
+      "loss": 0.3903,
       "step": 470
     },
     {
       "epoch": 0.8652546191978369,
-      "grad_norm": 13.211421012878418,
-      "learning_rate": 4.1335740072202167e-05,
-      "loss": 0.4337,
+      "grad_norm": 18.276058197021484,
+      "learning_rate": 2.8339350180505413e-05,
+      "loss": 0.4174,
       "step": 480
     },
     {
       "epoch": 0.8832807570977917,
-      "grad_norm": 14.50296401977539,
-      "learning_rate": 4.115523465703972e-05,
-      "loss": 0.4318,
+      "grad_norm": 14.345264434814453,
+      "learning_rate": 2.7888086642599282e-05,
+      "loss": 0.4075,
       "step": 490
     },
     {
       "epoch": 0.9013068949977467,
-      "grad_norm": 21.239362716674805,
-      "learning_rate": 4.0974729241877256e-05,
-      "loss": 0.3939,
+      "grad_norm": 18.126863479614258,
+      "learning_rate": 2.7436823104693144e-05,
+      "loss": 0.3761,
       "step": 500
     },
     {
       "epoch": 0.9193330328977016,
-      "grad_norm": 18.6204891204834,
-      "learning_rate": 4.079422382671481e-05,
-      "loss": 0.3838,
+      "grad_norm": 27.871076583862305,
+      "learning_rate": 2.6985559566787007e-05,
+      "loss": 0.3941,
       "step": 510
     },
     {
       "epoch": 0.9373591707976566,
-      "grad_norm": 21.722551345825195,
-      "learning_rate": 4.0613718411552346e-05,
-      "loss": 0.4236,
+      "grad_norm": 17.600557327270508,
+      "learning_rate": 2.6534296028880866e-05,
+      "loss": 0.3836,
       "step": 520
     },
     {
       "epoch": 0.9553853086976115,
-      "grad_norm": 23.824357986450195,
-      "learning_rate": 4.043321299638989e-05,
-      "loss": 0.4062,
+      "grad_norm": 23.826416015625,
+      "learning_rate": 2.6083032490974728e-05,
+      "loss": 0.3882,
       "step": 530
     },
     {
       "epoch": 0.9734114465975665,
-      "grad_norm": 18.93727684020996,
-      "learning_rate": 4.0252707581227436e-05,
-      "loss": 0.4412,
+      "grad_norm": 17.19468116760254,
+      "learning_rate": 2.563176895306859e-05,
+      "loss": 0.4026,
       "step": 540
     },
     {
       "epoch": 0.9914375844975214,
-      "grad_norm": 16.050817489624023,
-      "learning_rate": 4.007220216606498e-05,
-      "loss": 0.4142,
+      "grad_norm": 14.197047233581543,
+      "learning_rate": 2.518050541516246e-05,
+      "loss": 0.3874,
       "step": 550
     },
     {
       "epoch": 1.0,
-      "eval_f1": 0.8390086641144469,
-      "eval_fn": 205,
-      "eval_fp": 594,
-      "eval_loss": 0.3744712173938751,
-      "eval_precision": 0.7780269058295964,
-      "eval_recall": 0.910362920857018,
-      "eval_runtime": 73.1391,
-      "eval_samples_per_second": 63.892,
-      "eval_steps_per_second": 7.998,
-      "eval_tn": 1792,
-      "eval_tp": 2082,
+      "eval_f1": 0.8447773616312942,
+      "eval_loss": 0.35632607340812683,
+      "eval_precision": 0.8058753473600635,
+      "eval_recall": 0.8876257105378225,
+      "eval_runtime": 83.9871,
+      "eval_samples_per_second": 55.639,
+      "eval_steps_per_second": 6.965,
       "step": 555
     }
   ],
   "logging_steps": 10,
-  "max_steps": 2770,
+  "max_steps": 1108,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {

checkpoint-555/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:810629f6569bf22bd4122bdaa88d9cc0d6cea1b331667027a3cd4891b919dd14
+oid sha256:863b542ed1120790af07a52bd3cabdf15b7f39057e82c90e137fcc5e7061f2a0
 size 5432