Training in progress, epoch 1, checkpoint

checkpoint-555/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91b0eaf62f6feb29f8e6c91e27f4c943c7c5cb4f86aeb4b64c72f034a0e92bdd
+oid sha256:4925590b4fcc049337dd052850da563e4659200d9b37fc4bd1edc4cc27cbc07d
 size 437958648

checkpoint-555/trainer_state.json

@@ -10,409 +10,409 @@
   "log_history": [
     {
       "epoch": 0.018026137899954935,
-      "grad_norm": 13.032843589782715,
-      "learning_rate": 4.981949458483755e-05,
-      "loss": 0.6633,
+      "grad_norm": 16.059541702270508,
+      "learning_rate": 4.9548736462093865e-05,
+      "loss": 0.6728,
       "step": 10
     },
     {
       "epoch": 0.03605227579990987,
-      "grad_norm": 35.63669204711914,
-      "learning_rate": 4.963898916967509e-05,
-      "loss": 0.5651,
+      "grad_norm": 22.368194580078125,
+      "learning_rate": 4.909747292418773e-05,
+      "loss": 0.5752,
       "step": 20
     },
     {
       "epoch": 0.054078413699864804,
-      "grad_norm": 16.95796012878418,
-      "learning_rate": 4.945848375451264e-05,
-      "loss": 0.5359,
+      "grad_norm": 21.088069915771484,
+      "learning_rate": 4.864620938628159e-05,
+      "loss": 0.5414,
       "step": 30
     },
     {
       "epoch": 0.07210455159981974,
-      "grad_norm": 14.045697212219238,
-      "learning_rate": 4.927797833935018e-05,
-      "loss": 0.5421,
+      "grad_norm": 17.759164810180664,
+      "learning_rate": 4.819494584837546e-05,
+      "loss": 0.5483,
       "step": 40
     },
     {
       "epoch": 0.09013068949977468,
-      "grad_norm": 43.34794235229492,
-      "learning_rate": 4.909747292418773e-05,
-      "loss": 0.5222,
+      "grad_norm": 35.45125961303711,
+      "learning_rate": 4.7743682310469314e-05,
+      "loss": 0.5284,
       "step": 50
     },
     {
       "epoch": 0.10815682739972961,
-      "grad_norm": 32.69561767578125,
-      "learning_rate": 4.891696750902527e-05,
-      "loss": 0.4589,
+      "grad_norm": 34.69957733154297,
+      "learning_rate": 4.7292418772563177e-05,
+      "loss": 0.4792,
       "step": 60
     },
     {
       "epoch": 0.12618296529968454,
-      "grad_norm": 29.39051055908203,
-      "learning_rate": 4.873646209386282e-05,
-      "loss": 0.4858,
+      "grad_norm": 31.315162658691406,
+      "learning_rate": 4.684115523465704e-05,
+      "loss": 0.505,
       "step": 70
     },
     {
       "epoch": 0.14420910319963948,
-      "grad_norm": 30.52906608581543,
-      "learning_rate": 4.855595667870036e-05,
-      "loss": 0.4418,
+      "grad_norm": 28.01712417602539,
+      "learning_rate": 4.63898916967509e-05,
+      "loss": 0.4575,
       "step": 80
     },
     {
       "epoch": 0.16223524109959442,
-      "grad_norm": 15.103797912597656,
-      "learning_rate": 4.837545126353791e-05,
-      "loss": 0.4713,
+      "grad_norm": 22.80365562438965,
+      "learning_rate": 4.5938628158844764e-05,
+      "loss": 0.4678,
       "step": 90
     },
     {
       "epoch": 0.18026137899954936,
-      "grad_norm": 40.57420349121094,
-      "learning_rate": 4.819494584837546e-05,
-      "loss": 0.468,
+      "grad_norm": 38.55846405029297,
+      "learning_rate": 4.548736462093863e-05,
+      "loss": 0.4724,
       "step": 100
     },
     {
       "epoch": 0.19828751689950427,
-      "grad_norm": 37.67963409423828,
-      "learning_rate": 4.8014440433213e-05,
-      "loss": 0.492,
+      "grad_norm": 29.91495704650879,
+      "learning_rate": 4.5036101083032495e-05,
+      "loss": 0.4891,
       "step": 110
     },
     {
       "epoch": 0.21631365479945922,
-      "grad_norm": 30.945823669433594,
-      "learning_rate": 4.783393501805055e-05,
-      "loss": 0.4633,
+      "grad_norm": 26.530668258666992,
+      "learning_rate": 4.458483754512636e-05,
+      "loss": 0.4578,
       "step": 120
     },
     {
       "epoch": 0.23433979269941416,
-      "grad_norm": 40.709590911865234,
-      "learning_rate": 4.765342960288809e-05,
-      "loss": 0.4392,
+      "grad_norm": 53.58538055419922,
+      "learning_rate": 4.413357400722022e-05,
+      "loss": 0.4735,
       "step": 130
     },
     {
       "epoch": 0.25236593059936907,
-      "grad_norm": 19.698150634765625,
-      "learning_rate": 4.747292418772563e-05,
-      "loss": 0.4707,
+      "grad_norm": 22.026208877563477,
+      "learning_rate": 4.368231046931408e-05,
+      "loss": 0.4743,
       "step": 140
     },
     {
       "epoch": 0.270392068499324,
-      "grad_norm": 21.289947509765625,
-      "learning_rate": 4.7292418772563177e-05,
-      "loss": 0.4576,
+      "grad_norm": 28.057222366333008,
+      "learning_rate": 4.3231046931407945e-05,
+      "loss": 0.4559,
       "step": 150
     },
     {
       "epoch": 0.28841820639927895,
-      "grad_norm": 26.911935806274414,
-      "learning_rate": 4.711191335740072e-05,
-      "loss": 0.4583,
+      "grad_norm": 22.690412521362305,
+      "learning_rate": 4.277978339350181e-05,
+      "loss": 0.4638,
       "step": 160
     },
     {
       "epoch": 0.3064443442992339,
-      "grad_norm": 19.308853149414062,
-      "learning_rate": 4.693140794223827e-05,
-      "loss": 0.4937,
+      "grad_norm": 21.292953491210938,
+      "learning_rate": 4.232851985559567e-05,
+      "loss": 0.4877,
       "step": 170
     },
     {
       "epoch": 0.32447048219918884,
-      "grad_norm": 34.61503219604492,
-      "learning_rate": 4.675090252707581e-05,
-      "loss": 0.4836,
+      "grad_norm": 36.56389236450195,
+      "learning_rate": 4.187725631768953e-05,
+      "loss": 0.4927,
       "step": 180
     },
     {
       "epoch": 0.3424966200991438,
-      "grad_norm": 16.551424026489258,
-      "learning_rate": 4.657039711191336e-05,
-      "loss": 0.4919,
+      "grad_norm": 17.6762752532959,
+      "learning_rate": 4.1425992779783394e-05,
+      "loss": 0.491,
       "step": 190
     },
     {
       "epoch": 0.3605227579990987,
-      "grad_norm": 16.011377334594727,
-      "learning_rate": 4.63898916967509e-05,
-      "loss": 0.4518,
+      "grad_norm": 19.962385177612305,
+      "learning_rate": 4.0974729241877256e-05,
+      "loss": 0.4428,
       "step": 200
     },
     {
       "epoch": 0.3785488958990536,
-      "grad_norm": 22.71525764465332,
-      "learning_rate": 4.620938628158845e-05,
-      "loss": 0.4221,
+      "grad_norm": 23.71368408203125,
+      "learning_rate": 4.052346570397112e-05,
+      "loss": 0.4318,
       "step": 210
     },
     {
       "epoch": 0.39657503379900855,
-      "grad_norm": 22.2515811920166,
-      "learning_rate": 4.602888086642599e-05,
-      "loss": 0.4286,
+      "grad_norm": 24.030736923217773,
+      "learning_rate": 4.007220216606498e-05,
+      "loss": 0.4532,
       "step": 220
     },
     {
       "epoch": 0.4146011716989635,
-      "grad_norm": 18.233482360839844,
-      "learning_rate": 4.584837545126354e-05,
-      "loss": 0.4442,
+      "grad_norm": 23.85675811767578,
+      "learning_rate": 3.962093862815885e-05,
+      "loss": 0.4427,
       "step": 230
     },
     {
       "epoch": 0.43262730959891843,
-      "grad_norm": 33.190948486328125,
-      "learning_rate": 4.566787003610109e-05,
-      "loss": 0.4584,
+      "grad_norm": 32.091190338134766,
+      "learning_rate": 3.916967509025271e-05,
+      "loss": 0.4432,
       "step": 240
     },
     {
       "epoch": 0.45065344749887337,
-      "grad_norm": 29.945205688476562,
-      "learning_rate": 4.548736462093863e-05,
-      "loss": 0.4339,
+      "grad_norm": 32.51976776123047,
+      "learning_rate": 3.8718411552346575e-05,
+      "loss": 0.4289,
       "step": 250
     },
     {
       "epoch": 0.4686795853988283,
-      "grad_norm": 17.004419326782227,
-      "learning_rate": 4.530685920577618e-05,
-      "loss": 0.4504,
+      "grad_norm": 17.93523406982422,
+      "learning_rate": 3.826714801444044e-05,
+      "loss": 0.4485,
       "step": 260
     },
     {
       "epoch": 0.48670572329878325,
-      "grad_norm": 23.36432647705078,
-      "learning_rate": 4.5126353790613716e-05,
-      "loss": 0.4405,
+      "grad_norm": 34.29135513305664,
+      "learning_rate": 3.78158844765343e-05,
+      "loss": 0.4373,
       "step": 270
     },
     {
       "epoch": 0.5047318611987381,
-      "grad_norm": 29.156505584716797,
-      "learning_rate": 4.494584837545127e-05,
-      "loss": 0.4319,
+      "grad_norm": 21.879440307617188,
+      "learning_rate": 3.7364620938628155e-05,
+      "loss": 0.4367,
       "step": 280
     },
     {
       "epoch": 0.5227579990986931,
-      "grad_norm": 16.330259323120117,
-      "learning_rate": 4.4765342960288806e-05,
-      "loss": 0.453,
+      "grad_norm": 16.587345123291016,
+      "learning_rate": 3.6913357400722025e-05,
+      "loss": 0.4476,
       "step": 290
     },
     {
       "epoch": 0.540784136998648,
-      "grad_norm": 21.66246223449707,
-      "learning_rate": 4.458483754512636e-05,
-      "loss": 0.416,
+      "grad_norm": 21.923376083374023,
+      "learning_rate": 3.646209386281589e-05,
+      "loss": 0.4186,
       "step": 300
     },
     {
       "epoch": 0.558810274898603,
-      "grad_norm": 22.177268981933594,
-      "learning_rate": 4.44043321299639e-05,
-      "loss": 0.4456,
+      "grad_norm": 25.472400665283203,
+      "learning_rate": 3.601083032490975e-05,
+      "loss": 0.4317,
       "step": 310
     },
     {
       "epoch": 0.5768364127985579,
-      "grad_norm": 38.450069427490234,
-      "learning_rate": 4.422382671480145e-05,
-      "loss": 0.4216,
+      "grad_norm": 36.07789611816406,
+      "learning_rate": 3.555956678700361e-05,
+      "loss": 0.4281,
       "step": 320
     },
     {
       "epoch": 0.5948625506985128,
-      "grad_norm": 28.213655471801758,
-      "learning_rate": 4.404332129963899e-05,
-      "loss": 0.4392,
+      "grad_norm": 32.51295852661133,
+      "learning_rate": 3.5108303249097474e-05,
+      "loss": 0.4391,
       "step": 330
     },
     {
       "epoch": 0.6128886885984678,
-      "grad_norm": 19.354459762573242,
-      "learning_rate": 4.386281588447654e-05,
-      "loss": 0.4303,
+      "grad_norm": 19.069826126098633,
+      "learning_rate": 3.4657039711191336e-05,
+      "loss": 0.4249,
       "step": 340
     },
     {
       "epoch": 0.6309148264984227,
-      "grad_norm": 20.212663650512695,
-      "learning_rate": 4.368231046931408e-05,
-      "loss": 0.4426,
+      "grad_norm": 22.865673065185547,
+      "learning_rate": 3.42057761732852e-05,
+      "loss": 0.4394,
       "step": 350
     },
     {
       "epoch": 0.6489409643983777,
-      "grad_norm": 34.96459197998047,
-      "learning_rate": 4.350180505415163e-05,
-      "loss": 0.4146,
+      "grad_norm": 35.98612594604492,
+      "learning_rate": 3.375451263537907e-05,
+      "loss": 0.407,
       "step": 360
     },
     {
       "epoch": 0.6669671022983326,
-      "grad_norm": 17.65025520324707,
-      "learning_rate": 4.332129963898917e-05,
-      "loss": 0.4506,
+      "grad_norm": 19.89366340637207,
+      "learning_rate": 3.330324909747293e-05,
+      "loss": 0.434,
       "step": 370
     },
     {
       "epoch": 0.6849932401982876,
-      "grad_norm": 18.796554565429688,
-      "learning_rate": 4.314079422382672e-05,
-      "loss": 0.3765,
+      "grad_norm": 20.73752212524414,
+      "learning_rate": 3.2851985559566786e-05,
+      "loss": 0.3815,
       "step": 380
     },
     {
       "epoch": 0.7030193780982424,
-      "grad_norm": 21.690357208251953,
-      "learning_rate": 4.296028880866426e-05,
-      "loss": 0.4158,
+      "grad_norm": 20.23769187927246,
+      "learning_rate": 3.240072202166065e-05,
+      "loss": 0.4159,
       "step": 390
     },
     {
       "epoch": 0.7210455159981974,
-      "grad_norm": 39.8782844543457,
-      "learning_rate": 4.277978339350181e-05,
-      "loss": 0.4602,
+      "grad_norm": 40.59239196777344,
+      "learning_rate": 3.194945848375451e-05,
+      "loss": 0.4582,
       "step": 400
     },
     {
       "epoch": 0.7390716538981523,
-      "grad_norm": 26.3798885345459,
-      "learning_rate": 4.259927797833935e-05,
-      "loss": 0.4512,
+      "grad_norm": 22.728296279907227,
+      "learning_rate": 3.149819494584837e-05,
+      "loss": 0.4387,
       "step": 410
     },
     {
       "epoch": 0.7570977917981072,
-      "grad_norm": 18.073617935180664,
-      "learning_rate": 4.24187725631769e-05,
-      "loss": 0.4347,
+      "grad_norm": 20.43068504333496,
+      "learning_rate": 3.104693140794224e-05,
+      "loss": 0.4302,
       "step": 420
     },
     {
       "epoch": 0.7751239296980622,
-      "grad_norm": 30.09633445739746,
-      "learning_rate": 4.223826714801444e-05,
+      "grad_norm": 30.140209197998047,
+      "learning_rate": 3.0595667870036104e-05,
       "loss": 0.3858,
       "step": 430
     },
     {
       "epoch": 0.7931500675980171,
-      "grad_norm": 17.02672576904297,
-      "learning_rate": 4.205776173285199e-05,
-      "loss": 0.4815,
+      "grad_norm": 15.338220596313477,
+      "learning_rate": 3.0144404332129967e-05,
+      "loss": 0.4634,
       "step": 440
     },
     {
       "epoch": 0.8111762054979721,
-      "grad_norm": 19.149808883666992,
-      "learning_rate": 4.187725631768953e-05,
-      "loss": 0.4196,
+      "grad_norm": 24.517107009887695,
+      "learning_rate": 2.969314079422383e-05,
+      "loss": 0.4079,
       "step": 450
     },
     {
       "epoch": 0.829202343397927,
-      "grad_norm": 28.140705108642578,
-      "learning_rate": 4.169675090252708e-05,
-      "loss": 0.4085,
+      "grad_norm": 25.604442596435547,
+      "learning_rate": 2.924187725631769e-05,
+      "loss": 0.3903,
       "step": 460
     },
     {
       "epoch": 0.847228481297882,
-      "grad_norm": 21.819814682006836,
-      "learning_rate": 4.151624548736462e-05,
-      "loss": 0.3986,
+      "grad_norm": 26.43514060974121,
+      "learning_rate": 2.879061371841155e-05,
+      "loss": 0.4037,
       "step": 470
     },
     {
       "epoch": 0.8652546191978369,
-      "grad_norm": 15.050581932067871,
-      "learning_rate": 4.1335740072202167e-05,
-      "loss": 0.4267,
+      "grad_norm": 18.30228042602539,
+      "learning_rate": 2.8339350180505413e-05,
+      "loss": 0.4374,
       "step": 480
     },
     {
       "epoch": 0.8832807570977917,
-      "grad_norm": 14.929478645324707,
-      "learning_rate": 4.115523465703972e-05,
-      "loss": 0.4315,
+      "grad_norm": 16.212318420410156,
+      "learning_rate": 2.7888086642599282e-05,
+      "loss": 0.4219,
       "step": 490
     },
     {
       "epoch": 0.9013068949977467,
-      "grad_norm": 20.087432861328125,
-      "learning_rate": 4.0974729241877256e-05,
-      "loss": 0.3886,
+      "grad_norm": 23.251705169677734,
+      "learning_rate": 2.7436823104693144e-05,
+      "loss": 0.3784,
       "step": 500
     },
     {
       "epoch": 0.9193330328977016,
-      "grad_norm": 32.96128463745117,
-      "learning_rate": 4.079422382671481e-05,
-      "loss": 0.4046,
+      "grad_norm": 37.26618194580078,
+      "learning_rate": 2.6985559566787007e-05,
+      "loss": 0.4144,
       "step": 510
     },
     {
       "epoch": 0.9373591707976566,
-      "grad_norm": 19.673940658569336,
-      "learning_rate": 4.0613718411552346e-05,
-      "loss": 0.4127,
+      "grad_norm": 22.583784103393555,
+      "learning_rate": 2.6534296028880866e-05,
+      "loss": 0.4123,
       "step": 520
     },
     {
       "epoch": 0.9553853086976115,
-      "grad_norm": 16.12790298461914,
-      "learning_rate": 4.043321299638989e-05,
-      "loss": 0.4227,
+      "grad_norm": 18.812397003173828,
+      "learning_rate": 2.6083032490974728e-05,
+      "loss": 0.422,
       "step": 530
     },
     {
       "epoch": 0.9734114465975665,
-      "grad_norm": 20.4881649017334,
-      "learning_rate": 4.0252707581227436e-05,
-      "loss": 0.4223,
+      "grad_norm": 20.292518615722656,
+      "learning_rate": 2.563176895306859e-05,
+      "loss": 0.4346,
       "step": 540
     },
     {
       "epoch": 0.9914375844975214,
-      "grad_norm": 17.96915054321289,
-      "learning_rate": 4.007220216606498e-05,
-      "loss": 0.395,
+      "grad_norm": 25.314495086669922,
+      "learning_rate": 2.518050541516246e-05,
+      "loss": 0.393,
       "step": 550
     },
     {
       "epoch": 1.0,
-      "eval_f1": 0.8363481591828048,
-      "eval_fn": 322,
-      "eval_fp": 447,
-      "eval_loss": 0.372616171836853,
-      "eval_precision": 0.8146766169154229,
-      "eval_recall": 0.8592041976388282,
-      "eval_runtime": 12.0589,
-      "eval_samples_per_second": 387.513,
-      "eval_steps_per_second": 48.512,
-      "eval_tn": 1939,
-      "eval_tp": 1965,
+      "eval_f1": 0.8425531914893617,
+      "eval_fn": 307,
+      "eval_fp": 433,
+      "eval_loss": 0.36401602625846863,
+      "eval_precision": 0.8205553253211769,
+      "eval_recall": 0.8657630083078268,
+      "eval_runtime": 13.0048,
+      "eval_samples_per_second": 359.329,
+      "eval_steps_per_second": 44.983,
+      "eval_tn": 1953,
+      "eval_tp": 1980,
       "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 sha256:7e924750e5e12e6bb9372df333907b4d7f42d9dd2da839a2407f8f861ab40940
+oid sha256:1b4fc31351a02f492c40017a3c0ee23cf1c98a7172c96374c9e2c9f12affd1d3
 size 5432