Training in progress, epoch 1

all_results.json

@@ -38,10 +38,10 @@
     "eval_ne_word_err_precision": 0.9970827762246263,
     "eval_ne_word_err_recall": 0.9946647265672366,
     "eval_overall_accuracy": 0.9993957202777317,
-    "eval_runtime": 11.3466,
+    "eval_runtime": 11.4329,
     "eval_samples": 18388,
-    "eval_samples_per_second": 1620.567,
-    "eval_steps_per_second": 101.352,
+    "eval_samples_per_second": 1608.342,
+    "eval_steps_per_second": 100.587,
     "eval_unc_insert_err_f1": 0.9961218836565098,
     "eval_unc_insert_err_number": 902,
     "eval_unc_insert_err_precision": 0.9955703211517165,
@@ -51,8 +51,8 @@
     "eval_weighted_avg_precision": 0.9936401344515604,
     "eval_weighted_avg_recall": 0.9931156910287495,
     "train_loss": 0.06519987745561462,
-    "train_runtime": 1743.5904,
+    "train_runtime": 1743.8633,
     "train_samples": 18388,
-    "train_samples_per_second": 316.382,
-    "train_steps_per_second": 9.893
+    "train_samples_per_second": 316.332,
+    "train_steps_per_second": 9.892
 }

eval_results.json

@@ -38,10 +38,10 @@
     "eval_ne_word_err_precision": 0.9970827762246263,
     "eval_ne_word_err_recall": 0.9946647265672366,
     "eval_overall_accuracy": 0.9993957202777317,
-    "eval_runtime": 11.3466,
+    "eval_runtime": 11.4329,
     "eval_samples": 18388,
-    "eval_samples_per_second": 1620.567,
-    "eval_steps_per_second": 101.352,
+    "eval_samples_per_second": 1608.342,
+    "eval_steps_per_second": 100.587,
     "eval_unc_insert_err_f1": 0.9961218836565098,
     "eval_unc_insert_err_number": 902,
     "eval_unc_insert_err_precision": 0.9955703211517165,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb8de0288b5a6e76feea0bd3fc8fd584ac1e2b3cae7999f2b363d2d1f1869015
+oid sha256:782a74d01c2012b5d99332313c0794974e8965c7c8027eb0901f5118df32f7f3
 size 440204333

runs/Mar03_01-20-39_home-3090/events.out.tfevents.1677786630.home-3090.52004.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39373ce231698dc357cc544e011a293aa1868f277921b0565725b850385cdef0
+size 2994

runs/Mar03_15-28-56_home-3090/1677835755.4833965/events.out.tfevents.1677835755.home-3090.22403.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e69d61ff4a983ba335c65dc90e26811b6900344b603bb5126edff8dd4be54f
+size 5523

runs/Mar03_15-28-56_home-3090/events.out.tfevents.1677835755.home-3090.22403.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b8e1128585d66a929bdb76df7bdece7d52108c15b5b3897af64bde3d519505
+size 7325

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 30.0,
     "train_loss": 0.06519987745561462,
-    "train_runtime": 1743.5904,
+    "train_runtime": 1743.8633,
     "train_samples": 18388,
-    "train_samples_per_second": 316.382,
-    "train_steps_per_second": 9.893
+    "train_samples_per_second": 316.332,
+    "train_steps_per_second": 9.892
 }

trainer_state.json

@@ -53,9 +53,9 @@
       "eval_ne_word_err_precision": 0.6340406114533425,
       "eval_ne_word_err_recall": 0.33697101976476296,
       "eval_overall_accuracy": 0.9313016896134979,
-      "eval_runtime": 11.4511,
-      "eval_samples_per_second": 1605.79,
-      "eval_steps_per_second": 100.427,
+      "eval_runtime": 11.367,
+      "eval_samples_per_second": 1617.671,
+      "eval_steps_per_second": 101.17,
       "eval_unc_insert_err_f1": 0.0,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.0,
@@ -112,9 +112,9 @@
       "eval_ne_word_err_precision": 0.7050460865489767,
       "eval_ne_word_err_recall": 0.5472292955013944,
       "eval_overall_accuracy": 0.9455378089528188,
-      "eval_runtime": 12.2219,
-      "eval_samples_per_second": 1504.512,
-      "eval_steps_per_second": 94.093,
+      "eval_runtime": 11.0987,
+      "eval_samples_per_second": 1656.776,
+      "eval_steps_per_second": 103.616,
       "eval_unc_insert_err_f1": 0.0022148394241417496,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 1.0,
@@ -171,9 +171,9 @@
       "eval_ne_word_err_precision": 0.7622462787550744,
       "eval_ne_word_err_recall": 0.6830362556080999,
       "eval_overall_accuracy": 0.9567288324367876,
-      "eval_runtime": 11.5134,
-      "eval_samples_per_second": 1597.097,
-      "eval_steps_per_second": 99.884,
+      "eval_runtime": 11.1567,
+      "eval_samples_per_second": 1648.155,
+      "eval_steps_per_second": 103.077,
       "eval_unc_insert_err_f1": 0.3054662379421222,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.5555555555555556,
@@ -230,9 +230,9 @@
       "eval_ne_word_err_precision": 0.8228239366963402,
       "eval_ne_word_err_recall": 0.8069601067054687,
       "eval_overall_accuracy": 0.9701177753027322,
-      "eval_runtime": 11.6132,
-      "eval_samples_per_second": 1583.375,
-      "eval_steps_per_second": 99.026,
+      "eval_runtime": 11.5543,
+      "eval_samples_per_second": 1591.447,
+      "eval_steps_per_second": 99.53,
       "eval_unc_insert_err_f1": 0.37326813365933176,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.7046153846153846,
@@ -289,9 +289,9 @@
       "eval_ne_word_err_precision": 0.887815750371471,
       "eval_ne_word_err_recall": 0.869407057111677,
       "eval_overall_accuracy": 0.9797270077489988,
-      "eval_runtime": 11.582,
-      "eval_samples_per_second": 1587.637,
-      "eval_steps_per_second": 99.292,
+      "eval_runtime": 11.5559,
+      "eval_samples_per_second": 1591.224,
+      "eval_steps_per_second": 99.516,
       "eval_unc_insert_err_f1": 0.5340674466620785,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.7041742286751361,
@@ -348,9 +348,9 @@
       "eval_ne_word_err_precision": 0.918532634587899,
       "eval_ne_word_err_recall": 0.935127925306172,
       "eval_overall_accuracy": 0.9874049148084078,
-      "eval_runtime": 11.5539,
-      "eval_samples_per_second": 1591.493,
-      "eval_steps_per_second": 99.533,
+      "eval_runtime": 11.4906,
+      "eval_samples_per_second": 1600.268,
+      "eval_steps_per_second": 100.082,
       "eval_unc_insert_err_f1": 0.7559591373439274,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.7744186046511627,
@@ -407,9 +407,9 @@
       "eval_ne_word_err_precision": 0.9517692680562287,
       "eval_ne_word_err_recall": 0.9523463077482721,
       "eval_overall_accuracy": 0.9913860518021754,
-      "eval_runtime": 11.6281,
-      "eval_samples_per_second": 1581.339,
-      "eval_steps_per_second": 98.898,
+      "eval_runtime": 11.5809,
+      "eval_samples_per_second": 1587.783,
+      "eval_steps_per_second": 99.301,
       "eval_unc_insert_err_f1": 0.8407367280606717,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.8220338983050848,
@@ -466,9 +466,9 @@
       "eval_ne_word_err_precision": 0.9697043435941112,
       "eval_ne_word_err_recall": 0.9664120286164666,
       "eval_overall_accuracy": 0.9938387165572644,
-      "eval_runtime": 11.5399,
-      "eval_samples_per_second": 1593.424,
-      "eval_steps_per_second": 99.654,
+      "eval_runtime": 11.5948,
+      "eval_samples_per_second": 1585.884,
+      "eval_steps_per_second": 99.182,
       "eval_unc_insert_err_f1": 0.897196261682243,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.8898582333696837,
@@ -525,9 +525,9 @@
       "eval_ne_word_err_precision": 0.9782503037667072,
       "eval_ne_word_err_recall": 0.9762337819813266,
       "eval_overall_accuracy": 0.9954619777719851,
-      "eval_runtime": 11.5934,
-      "eval_samples_per_second": 1586.069,
-      "eval_steps_per_second": 99.194,
+      "eval_runtime": 11.4901,
+      "eval_samples_per_second": 1600.333,
+      "eval_steps_per_second": 100.086,
       "eval_unc_insert_err_f1": 0.934559221200649,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9123548046462513,
@@ -584,9 +584,9 @@
       "eval_ne_word_err_precision": 0.9809141745684415,
       "eval_ne_word_err_recall": 0.9784163938401843,
       "eval_overall_accuracy": 0.9963387758003744,
-      "eval_runtime": 11.5919,
-      "eval_samples_per_second": 1586.275,
-      "eval_steps_per_second": 99.207,
+      "eval_runtime": 11.5603,
+      "eval_samples_per_second": 1590.617,
+      "eval_steps_per_second": 99.478,
       "eval_unc_insert_err_f1": 0.9537289058247141,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9368983957219251,
@@ -643,9 +643,9 @@
       "eval_ne_word_err_precision": 0.989462075726014,
       "eval_ne_word_err_recall": 0.9791439311264702,
       "eval_overall_accuracy": 0.9968541908576033,
-      "eval_runtime": 11.5138,
-      "eval_samples_per_second": 1597.044,
-      "eval_steps_per_second": 99.88,
+      "eval_runtime": 11.4621,
+      "eval_samples_per_second": 1604.24,
+      "eval_steps_per_second": 100.33,
       "eval_unc_insert_err_f1": 0.9379310344827587,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.8992878942014242,
@@ -702,9 +702,9 @@
       "eval_ne_word_err_precision": 0.9917153996101364,
       "eval_ne_word_err_recall": 0.9870255850612344,
       "eval_overall_accuracy": 0.9976184269769426,
-      "eval_runtime": 11.5829,
-      "eval_samples_per_second": 1587.51,
-      "eval_steps_per_second": 99.284,
+      "eval_runtime": 11.7351,
+      "eval_samples_per_second": 1566.929,
+      "eval_steps_per_second": 97.997,
       "eval_unc_insert_err_f1": 0.9763866007688083,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9673558215451578,
@@ -761,9 +761,9 @@
       "eval_ne_word_err_precision": 0.991969826012897,
       "eval_ne_word_err_recall": 0.9886019158481872,
       "eval_overall_accuracy": 0.9980627503021399,
-      "eval_runtime": 11.6079,
-      "eval_samples_per_second": 1584.097,
-      "eval_steps_per_second": 99.071,
+      "eval_runtime": 11.5718,
+      "eval_samples_per_second": 1589.041,
+      "eval_steps_per_second": 99.38,
       "eval_unc_insert_err_f1": 0.9796367638965328,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9726775956284153,
@@ -820,9 +820,9 @@
       "eval_ne_word_err_precision": 0.9943957115009746,
       "eval_ne_word_err_recall": 0.9896932217776161,
       "eval_overall_accuracy": 0.9983589658522714,
-      "eval_runtime": 11.6047,
-      "eval_samples_per_second": 1584.53,
-      "eval_steps_per_second": 99.098,
+      "eval_runtime": 11.4901,
+      "eval_samples_per_second": 1600.34,
+      "eval_steps_per_second": 100.087,
       "eval_unc_insert_err_f1": 0.9839513004980631,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9823204419889503,
@@ -879,9 +879,9 @@
       "eval_ne_word_err_precision": 0.9951290793960058,
       "eval_ne_word_err_recall": 0.9909057839214259,
       "eval_overall_accuracy": 0.9986137112253844,
-      "eval_runtime": 11.5772,
-      "eval_samples_per_second": 1588.3,
-      "eval_steps_per_second": 99.334,
+      "eval_runtime": 11.4842,
+      "eval_samples_per_second": 1601.155,
+      "eval_steps_per_second": 100.137,
       "eval_unc_insert_err_f1": 0.991111111111111,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9933184855233853,
@@ -938,9 +938,9 @@
       "eval_ne_word_err_precision": 0.9948998178506375,
       "eval_ne_word_err_recall": 0.9934521644234267,
       "eval_overall_accuracy": 0.998862532287495,
-      "eval_runtime": 12.719,
-      "eval_samples_per_second": 1445.712,
-      "eval_steps_per_second": 90.416,
+      "eval_runtime": 11.5461,
+      "eval_samples_per_second": 1592.57,
+      "eval_steps_per_second": 99.601,
       "eval_unc_insert_err_f1": 0.9900662251655629,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9857142857142858,
@@ -997,9 +997,9 @@
       "eval_ne_word_err_precision": 0.9945454545454545,
       "eval_ne_word_err_recall": 0.9949072389959985,
       "eval_overall_accuracy": 0.9990106400625607,
-      "eval_runtime": 11.5897,
-      "eval_samples_per_second": 1586.578,
-      "eval_steps_per_second": 99.226,
+      "eval_runtime": 11.5275,
+      "eval_samples_per_second": 1595.144,
+      "eval_steps_per_second": 99.762,
       "eval_unc_insert_err_f1": 0.9927897947864671,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9933407325194229,
@@ -1056,9 +1056,9 @@
       "eval_ne_word_err_precision": 0.9949097079141922,
       "eval_ne_word_err_recall": 0.9953922638535225,
       "eval_overall_accuracy": 0.9991054290386028,
-      "eval_runtime": 11.5456,
-      "eval_samples_per_second": 1592.643,
-      "eval_steps_per_second": 99.605,
+      "eval_runtime": 11.4848,
+      "eval_samples_per_second": 1601.066,
+      "eval_steps_per_second": 100.132,
       "eval_unc_insert_err_f1": 0.9927897947864671,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9933407325194229,
@@ -1115,9 +1115,9 @@
       "eval_ne_word_err_precision": 0.9956300072833212,
       "eval_ne_word_err_recall": 0.9945434703528556,
       "eval_overall_accuracy": 0.9992179909476527,
-      "eval_runtime": 11.6822,
-      "eval_samples_per_second": 1574.022,
-      "eval_steps_per_second": 98.441,
+      "eval_runtime": 11.5451,
+      "eval_samples_per_second": 1592.714,
+      "eval_steps_per_second": 99.61,
       "eval_unc_insert_err_f1": 0.9933701657458565,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9900881057268722,
@@ -1174,9 +1174,9 @@
       "eval_ne_word_err_precision": 0.9959941733430444,
       "eval_ne_word_err_recall": 0.9949072389959985,
       "eval_overall_accuracy": 0.9992594611246712,
-      "eval_runtime": 11.3322,
-      "eval_samples_per_second": 1622.634,
-      "eval_steps_per_second": 101.481,
+      "eval_runtime": 11.5037,
+      "eval_samples_per_second": 1598.447,
+      "eval_steps_per_second": 99.968,
       "eval_unc_insert_err_f1": 0.9944444444444444,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9966592427616926,
@@ -1233,9 +1233,9 @@
       "eval_ne_word_err_precision": 0.9953922638535225,
       "eval_ne_word_err_recall": 0.9953922638535225,
       "eval_overall_accuracy": 0.999295006990687,
-      "eval_runtime": 11.5781,
-      "eval_samples_per_second": 1588.177,
-      "eval_steps_per_second": 99.326,
+      "eval_runtime": 11.4631,
+      "eval_samples_per_second": 1604.101,
+      "eval_steps_per_second": 100.322,
       "eval_unc_insert_err_f1": 0.9944506104328523,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9955555555555555,
@@ -1292,9 +1292,9 @@
       "eval_ne_word_err_precision": 0.996719319562576,
       "eval_ne_word_err_recall": 0.9946647265672366,
       "eval_overall_accuracy": 0.9993127799236948,
-      "eval_runtime": 11.7025,
-      "eval_samples_per_second": 1571.285,
-      "eval_steps_per_second": 98.269,
+      "eval_runtime": 11.5654,
+      "eval_samples_per_second": 1589.911,
+      "eval_steps_per_second": 99.434,
       "eval_unc_insert_err_f1": 0.9939125622578859,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9922651933701657,
@@ -1351,9 +1351,9 @@
       "eval_ne_word_err_precision": 0.9975666139433021,
       "eval_ne_word_err_recall": 0.9941797017097126,
       "eval_overall_accuracy": 0.9993601744117159,
-      "eval_runtime": 11.5685,
-      "eval_samples_per_second": 1589.49,
-      "eval_steps_per_second": 99.408,
+      "eval_runtime": 11.5142,
+      "eval_samples_per_second": 1596.978,
+      "eval_steps_per_second": 99.876,
       "eval_unc_insert_err_f1": 0.9950193691200886,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9933701657458563,
@@ -1410,9 +1410,9 @@
       "eval_ne_word_err_precision": 0.9959966031784544,
       "eval_ne_word_err_recall": 0.9955135200679035,
       "eval_overall_accuracy": 0.9993720230337212,
-      "eval_runtime": 11.5823,
-      "eval_samples_per_second": 1587.59,
-      "eval_steps_per_second": 99.289,
+      "eval_runtime": 11.4924,
+      "eval_samples_per_second": 1600.014,
+      "eval_steps_per_second": 100.066,
       "eval_unc_insert_err_f1": 0.9950138504155125,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9944629014396457,
@@ -1469,9 +1469,9 @@
       "eval_ne_word_err_precision": 0.9968412100595311,
       "eval_ne_word_err_recall": 0.9949072389959985,
       "eval_overall_accuracy": 0.9993720230337212,
-      "eval_runtime": 11.6443,
-      "eval_samples_per_second": 1579.141,
-      "eval_steps_per_second": 98.761,
+      "eval_runtime": 11.6279,
+      "eval_samples_per_second": 1581.368,
+      "eval_steps_per_second": 98.9,
       "eval_unc_insert_err_f1": 0.9955654101995566,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9955654101995566,
@@ -1528,9 +1528,9 @@
       "eval_ne_word_err_precision": 0.9957565470417071,
       "eval_ne_word_err_recall": 0.9958772887110464,
       "eval_overall_accuracy": 0.9993779473447238,
-      "eval_runtime": 11.6017,
-      "eval_samples_per_second": 1584.944,
-      "eval_steps_per_second": 99.124,
+      "eval_runtime": 11.5517,
+      "eval_samples_per_second": 1591.803,
+      "eval_steps_per_second": 99.553,
       "eval_unc_insert_err_f1": 0.995575221238938,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9933774834437086,
@@ -1587,9 +1587,9 @@
       "eval_ne_word_err_precision": 0.9964784456587735,
       "eval_ne_word_err_recall": 0.9950284952103795,
       "eval_overall_accuracy": 0.9993720230337212,
-      "eval_runtime": 11.6586,
-      "eval_samples_per_second": 1577.202,
-      "eval_steps_per_second": 98.639,
+      "eval_runtime": 11.5195,
+      "eval_samples_per_second": 1596.249,
+      "eval_steps_per_second": 99.831,
       "eval_unc_insert_err_f1": 0.9955703211517165,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9944690265486725,
@@ -1646,9 +1646,9 @@
       "eval_ne_word_err_precision": 0.9963578972927036,
       "eval_ne_word_err_recall": 0.9951497514247605,
       "eval_overall_accuracy": 0.9993838716557264,
-      "eval_runtime": 11.7106,
-      "eval_samples_per_second": 1570.205,
-      "eval_steps_per_second": 98.202,
+      "eval_runtime": 11.5765,
+      "eval_samples_per_second": 1588.392,
+      "eval_steps_per_second": 99.339,
       "eval_unc_insert_err_f1": 0.9955703211517165,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9944690265486725,
@@ -1705,9 +1705,9 @@
       "eval_ne_word_err_precision": 0.9962374074523607,
       "eval_ne_word_err_recall": 0.9952710076391416,
       "eval_overall_accuracy": 0.9993957202777317,
-      "eval_runtime": 11.6052,
-      "eval_samples_per_second": 1584.462,
-      "eval_steps_per_second": 99.094,
+      "eval_runtime": 11.5017,
+      "eval_samples_per_second": 1598.724,
+      "eval_steps_per_second": 99.985,
       "eval_unc_insert_err_f1": 0.9961175818080976,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9966703662597114,
@@ -1764,9 +1764,9 @@
       "eval_ne_word_err_precision": 0.9970827762246263,
       "eval_ne_word_err_recall": 0.9946647265672366,
       "eval_overall_accuracy": 0.9993957202777317,
-      "eval_runtime": 11.623,
-      "eval_samples_per_second": 1582.033,
-      "eval_steps_per_second": 98.942,
+      "eval_runtime": 11.5014,
+      "eval_samples_per_second": 1598.761,
+      "eval_steps_per_second": 99.988,
       "eval_unc_insert_err_f1": 0.9961218836565098,
       "eval_unc_insert_err_number": 902,
       "eval_unc_insert_err_precision": 0.9955703211517165,
@@ -1782,9 +1782,9 @@
       "step": 17250,
       "total_flos": 7911429330344064.0,
       "train_loss": 0.06519987745561462,
-      "train_runtime": 1743.5904,
-      "train_samples_per_second": 316.382,
-      "train_steps_per_second": 9.893
+      "train_runtime": 1743.8633,
+      "train_samples_per_second": 316.332,
+      "train_steps_per_second": 9.892
     }
   ],
   "max_steps": 17250,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c6b5e11b5bd25aac69af9ca386e301fbfbec9996b7dd5cb1ba740476d0951a
+oid sha256:735e977a5aabe6e9dacf785770cbcf801ab51c2533de47ea8a4cedd007b5807f
 size 3387