Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52516cfe6f6005fef145743ed7429f2aa6539626d4de6b81b29e4638e55944ae
+oid sha256:196f0ec635e698bf3dd473c9d3c6b5326a1e64ddaf8c97fcb3a34e3e68a134ba
 size 393799132

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286cf499d0dcbf9a15a6582865c78f4b1a165dafb11a7b184e5faa5b576bec45
+oid sha256:d25b483c4c9ebc2b09cdfd9b9dc2ff7f3400985c3c30fc3c7f66893548c477db
 size 112281209

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d291cee2d93195736fcf3b4639627b7f20896c3352f7062cb763bb6ff6bf17d8
+oid sha256:6c7c2c6889489e88d23048787444b150bfd24d0342706104cf2a0e3719fcc7d3
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec7dd949d35f48dc8fb27535e4827834a15e6e3a364a22af8ae0bcf2b10765e
+oid sha256:d23290f09d2127ca8198403a77e319b783a12d8fcf81756f51ef5695c491adbd
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37315ef08bfa8057ff315cea8e5349272ef9591e350519ec1b303f17a237220b
+oid sha256:b911940bdf86ae7e1f217f9bf9f400780319e842159e75db8115406aa532903a
 size 1465

last-checkpoint/trainer_state.json

@@ -2,152 +2,292 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001168613381791835,
+  "epoch": 0.00233722676358367,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 5.8430669089591743e-05,
-      "grad_norm": 11.07726764678955,
+      "grad_norm": 9.783331871032715,
       "learning_rate": 6e-06,
-      "loss": 36.76383972167969,
+      "loss": 36.68600158691406,
       "step": 10
     },
     {
       "epoch": 0.00011686133817918349,
-      "grad_norm": 11.017424583435059,
+      "grad_norm": 11.469252586364746,
       "learning_rate": 1.2666666666666668e-05,
-      "loss": 36.636288452148435,
+      "loss": 36.55324096679688,
       "step": 20
     },
     {
       "epoch": 0.00017529200726877522,
-      "grad_norm": 12.144283294677734,
+      "grad_norm": 12.40107250213623,
       "learning_rate": 1.9333333333333333e-05,
-      "loss": 36.379736328125,
+      "loss": 36.35345458984375,
       "step": 30
     },
     {
       "epoch": 0.00023372267635836697,
-      "grad_norm": 11.435462951660156,
+      "grad_norm": 11.716872215270996,
       "learning_rate": 2.6000000000000002e-05,
-      "loss": 36.049258422851565,
+      "loss": 36.08180236816406,
       "step": 40
     },
     {
       "epoch": 0.0002921533454479587,
-      "grad_norm": 13.229930877685547,
+      "grad_norm": 14.445358276367188,
       "learning_rate": 3.266666666666667e-05,
-      "loss": 35.619537353515625,
+      "loss": 35.567361450195314,
       "step": 50
     },
     {
       "epoch": 0.00035058401453755045,
-      "grad_norm": 13.213104248046875,
+      "grad_norm": 12.091419219970703,
       "learning_rate": 3.933333333333333e-05,
-      "loss": 35.00741271972656,
+      "loss": 35.10403137207031,
       "step": 60
     },
     {
       "epoch": 0.0004090146836271422,
-      "grad_norm": 13.932770729064941,
+      "grad_norm": 13.730995178222656,
       "learning_rate": 4.600000000000001e-05,
-      "loss": 34.09678649902344,
+      "loss": 33.99032287597656,
       "step": 70
     },
     {
       "epoch": 0.00046744535271673395,
-      "grad_norm": 15.470704078674316,
+      "grad_norm": 14.165889739990234,
       "learning_rate": 5.266666666666666e-05,
-      "loss": 33.10928955078125,
+      "loss": 33.32759094238281,
       "step": 80
     },
     {
       "epoch": 0.0005258760218063257,
-      "grad_norm": 17.481962203979492,
+      "grad_norm": 17.01044273376465,
       "learning_rate": 5.9333333333333343e-05,
-      "loss": 31.9614013671875,
+      "loss": 31.982687377929686,
       "step": 90
     },
     {
       "epoch": 0.0005843066908959174,
-      "grad_norm": 22.919269561767578,
+      "grad_norm": 20.539939880371094,
       "learning_rate": 6.6e-05,
-      "loss": 30.236492919921876,
+      "loss": 30.40308532714844,
       "step": 100
     },
     {
       "epoch": 0.0006427373599855092,
-      "grad_norm": 25.20511245727539,
+      "grad_norm": 20.50539207458496,
       "learning_rate": 7.266666666666667e-05,
-      "loss": 28.413812255859376,
+      "loss": 28.605145263671876,
       "step": 110
     },
     {
       "epoch": 0.0007011680290751009,
-      "grad_norm": 37.575218200683594,
+      "grad_norm": 35.68551254272461,
       "learning_rate": 7.933333333333334e-05,
-      "loss": 26.530050659179686,
+      "loss": 26.790576171875,
       "step": 120
     },
     {
       "epoch": 0.0007595986981646927,
-      "grad_norm": 29.32003402709961,
+      "grad_norm": 22.74065589904785,
       "learning_rate": 8.6e-05,
-      "loss": 24.708087158203124,
+      "loss": 24.934747314453126,
       "step": 130
     },
     {
       "epoch": 0.0008180293672542844,
-      "grad_norm": 94.21218872070312,
+      "grad_norm": 59.207008361816406,
       "learning_rate": 9.266666666666666e-05,
-      "loss": 23.144088745117188,
+      "loss": 23.048512268066407,
       "step": 140
     },
     {
       "epoch": 0.0008764600363438762,
-      "grad_norm": 50.958736419677734,
+      "grad_norm": 46.39744186401367,
       "learning_rate": 9.933333333333334e-05,
-      "loss": 22.03218994140625,
+      "loss": 21.81122589111328,
       "step": 150
     },
     {
       "epoch": 0.0009348907054334679,
-      "grad_norm": 41.21607971191406,
+      "grad_norm": 46.57512283325195,
       "learning_rate": 0.00010600000000000002,
-      "loss": 21.708474731445314,
+      "loss": 21.49383087158203,
       "step": 160
     },
     {
       "epoch": 0.0009933213745230596,
-      "grad_norm": 45.95130920410156,
+      "grad_norm": 20.875106811523438,
       "learning_rate": 0.00011266666666666668,
-      "loss": 20.753807067871094,
+      "loss": 20.477175903320312,
       "step": 170
     },
     {
       "epoch": 0.0010517520436126514,
-      "grad_norm": 44.12228775024414,
+      "grad_norm": 31.581335067749023,
       "learning_rate": 0.00011933333333333334,
-      "loss": 19.997039794921875,
+      "loss": 19.832745361328126,
       "step": 180
     },
     {
       "epoch": 0.001110182712702243,
-      "grad_norm": 59.23231887817383,
+      "grad_norm": 56.4605712890625,
       "learning_rate": 0.000126,
-      "loss": 19.628582763671876,
+      "loss": 19.4491943359375,
       "step": 190
     },
     {
       "epoch": 0.001168613381791835,
-      "grad_norm": NaN,
+      "grad_norm": 162.9219512939453,
       "learning_rate": 0.00013266666666666667,
-      "loss": 19.711293029785157,
+      "loss": 19.48320617675781,
       "step": 200
+    },
+    {
+      "epoch": 0.0012270440508814267,
+      "grad_norm": 220.9387664794922,
+      "learning_rate": 0.00013933333333333335,
+      "loss": 38.3218017578125,
+      "step": 210
+    },
+    {
+      "epoch": 0.0012854747199710183,
+      "grad_norm": 820.2343139648438,
+      "learning_rate": 0.000146,
+      "loss": 38.626034545898435,
+      "step": 220
+    },
+    {
+      "epoch": 0.0013439053890606102,
+      "grad_norm": 368.6383056640625,
+      "learning_rate": 0.00015266666666666667,
+      "loss": 39.935272216796875,
+      "step": 230
+    },
+    {
+      "epoch": 0.0014023360581502018,
+      "grad_norm": 38955.70703125,
+      "learning_rate": 0.00015933333333333332,
+      "loss": 38.100244140625,
+      "step": 240
+    },
+    {
+      "epoch": 0.0014607667272397936,
+      "grad_norm": 5041.26904296875,
+      "learning_rate": 0.000166,
+      "loss": 37.66072082519531,
+      "step": 250
+    },
+    {
+      "epoch": 0.0015191973963293855,
+      "grad_norm": 37627.18359375,
+      "learning_rate": 0.00017266666666666667,
+      "loss": 39.782492065429686,
+      "step": 260
+    },
+    {
+      "epoch": 0.001577628065418977,
+      "grad_norm": 177714.9375,
+      "learning_rate": 0.00017933333333333332,
+      "loss": 39.62332458496094,
+      "step": 270
+    },
+    {
+      "epoch": 0.001636058734508569,
+      "grad_norm": 8465394.0,
+      "learning_rate": 0.00018600000000000002,
+      "loss": 39.9508544921875,
+      "step": 280
+    },
+    {
+      "epoch": 0.0016944894035981605,
+      "grad_norm": 498348.375,
+      "learning_rate": 0.0001926666666666667,
+      "loss": 40.279449462890625,
+      "step": 290
+    },
+    {
+      "epoch": 0.0017529200726877523,
+      "grad_norm": 5466723.0,
+      "learning_rate": 0.00019933333333333334,
+      "loss": 40.805364990234374,
+      "step": 300
+    },
+    {
+      "epoch": 0.0018113507417773442,
+      "grad_norm": 1285695.125,
+      "learning_rate": 0.00019999999996000412,
+      "loss": 41.477255249023436,
+      "step": 310
+    },
+    {
+      "epoch": 0.0018697814108669358,
+      "grad_norm": 15952.0712890625,
+      "learning_rate": 0.00019999999982174674,
+      "loss": 41.24312133789063,
+      "step": 320
+    },
+    {
+      "epoch": 0.0019282120799565276,
+      "grad_norm": 14303.1611328125,
+      "learning_rate": 0.00019999999958473402,
+      "loss": 41.04373779296875,
+      "step": 330
+    },
+    {
+      "epoch": 0.0019866427490461192,
+      "grad_norm": 2404.072509765625,
+      "learning_rate": 0.00019999999924896604,
+      "loss": 41.058935546875,
+      "step": 340
+    },
+    {
+      "epoch": 0.002045073418135711,
+      "grad_norm": 4675.54296875,
+      "learning_rate": 0.00019999999881444277,
+      "loss": 42.03901977539063,
+      "step": 350
+    },
+    {
+      "epoch": 0.002103504087225303,
+      "grad_norm": 4408.5849609375,
+      "learning_rate": 0.00019999999828116422,
+      "loss": 44.66916198730469,
+      "step": 360
+    },
+    {
+      "epoch": 0.0021619347563148947,
+      "grad_norm": 19542.03515625,
+      "learning_rate": 0.00019999999764913037,
+      "loss": 40.449554443359375,
+      "step": 370
+    },
+    {
+      "epoch": 0.002220365425404486,
+      "grad_norm": 4808.32470703125,
+      "learning_rate": 0.00019999999691834125,
+      "loss": 41.15361022949219,
+      "step": 380
+    },
+    {
+      "epoch": 0.002278796094494078,
+      "grad_norm": 2390296.5,
+      "learning_rate": 0.00019999999608879683,
+      "loss": 40.7291259765625,
+      "step": 390
+    },
+    {
+      "epoch": 0.00233722676358367,
+      "grad_norm": 232325.234375,
+      "learning_rate": 0.00019999999516049713,
+      "loss": 41.33089599609375,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -167,7 +307,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1598220482291712.0,
+  "total_flos": 3201536247736320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70c232850a4dbee80edbe61b74faebfee8c9657ad64122625f20b6dc9d16b315
+oid sha256:8d048205bd016dcc3f50c370d419a863d908222158184c67e022cf413d298307
 size 5329