Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96c58e4260bfcc3a43fdc809034b30790dfbc567c316c9bcf8d6c1eea25d8d4d
+oid sha256:52516cfe6f6005fef145743ed7429f2aa6539626d4de6b81b29e4638e55944ae
 size 393799132

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d4518d62a67ac697059d4fc7f592151f627d1c9020a58df554eb897a246e350
+oid sha256:286cf499d0dcbf9a15a6582865c78f4b1a165dafb11a7b184e5faa5b576bec45
 size 112281209

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e3e00ac45983e3f3b18b0a35bc5f49bfdc14b5a98eb9031c068377ea5a38632
+oid sha256:d291cee2d93195736fcf3b4639627b7f20896c3352f7062cb763bb6ff6bf17d8
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e16c200580b7602b0b15f8ef887984614d32d1cb9f81496bb019539a5f882ad5
+oid sha256:0ec7dd949d35f48dc8fb27535e4827834a15e6e3a364a22af8ae0bcf2b10765e
 size 1383

last-checkpoint/scheduler.pt

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

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00233722676358367,
+  "epoch": 0.001168613381791835,
   "eval_steps": 500,
-  "global_step": 400,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,276 +18,136 @@
     },
     {
       "epoch": 0.00011686133817918349,
-      "grad_norm": 11.017434120178223,
+      "grad_norm": 11.017424583435059,
       "learning_rate": 1.2666666666666668e-05,
       "loss": 36.636288452148435,
       "step": 20
     },
     {
       "epoch": 0.00017529200726877522,
-      "grad_norm": 12.14416790008545,
+      "grad_norm": 12.144283294677734,
       "learning_rate": 1.9333333333333333e-05,
-      "loss": 36.379754638671876,
+      "loss": 36.379736328125,
       "step": 30
     },
     {
       "epoch": 0.00023372267635836697,
-      "grad_norm": 11.435386657714844,
+      "grad_norm": 11.435462951660156,
       "learning_rate": 2.6000000000000002e-05,
-      "loss": 36.049191284179685,
+      "loss": 36.049258422851565,
       "step": 40
     },
     {
       "epoch": 0.0002921533454479587,
-      "grad_norm": 13.229822158813477,
+      "grad_norm": 13.229930877685547,
       "learning_rate": 3.266666666666667e-05,
-      "loss": 35.61943054199219,
+      "loss": 35.619537353515625,
       "step": 50
     },
     {
       "epoch": 0.00035058401453755045,
-      "grad_norm": 13.212897300720215,
+      "grad_norm": 13.213104248046875,
       "learning_rate": 3.933333333333333e-05,
-      "loss": 35.00739440917969,
+      "loss": 35.00741271972656,
       "step": 60
     },
     {
       "epoch": 0.0004090146836271422,
-      "grad_norm": 13.932629585266113,
+      "grad_norm": 13.932770729064941,
       "learning_rate": 4.600000000000001e-05,
-      "loss": 34.096868896484374,
+      "loss": 34.09678649902344,
       "step": 70
     },
     {
       "epoch": 0.00046744535271673395,
-      "grad_norm": 15.47088623046875,
+      "grad_norm": 15.470704078674316,
       "learning_rate": 5.266666666666666e-05,
-      "loss": 33.10926208496094,
+      "loss": 33.10928955078125,
       "step": 80
     },
     {
       "epoch": 0.0005258760218063257,
-      "grad_norm": 17.481712341308594,
+      "grad_norm": 17.481962203979492,
       "learning_rate": 5.9333333333333343e-05,
-      "loss": 31.961520385742187,
+      "loss": 31.9614013671875,
       "step": 90
     },
     {
       "epoch": 0.0005843066908959174,
-      "grad_norm": 22.917377471923828,
+      "grad_norm": 22.919269561767578,
       "learning_rate": 6.6e-05,
-      "loss": 30.23651123046875,
+      "loss": 30.236492919921876,
       "step": 100
     },
     {
       "epoch": 0.0006427373599855092,
-      "grad_norm": 25.20553207397461,
+      "grad_norm": 25.20511245727539,
       "learning_rate": 7.266666666666667e-05,
-      "loss": 28.413836669921874,
+      "loss": 28.413812255859376,
       "step": 110
     },
     {
       "epoch": 0.0007011680290751009,
-      "grad_norm": 37.58531951904297,
+      "grad_norm": 37.575218200683594,
       "learning_rate": 7.933333333333334e-05,
-      "loss": 26.530044555664062,
+      "loss": 26.530050659179686,
       "step": 120
     },
     {
       "epoch": 0.0007595986981646927,
-      "grad_norm": 29.315284729003906,
+      "grad_norm": 29.32003402709961,
       "learning_rate": 8.6e-05,
-      "loss": 24.70811309814453,
+      "loss": 24.708087158203124,
       "step": 130
     },
     {
       "epoch": 0.0008180293672542844,
-      "grad_norm": 94.33854675292969,
+      "grad_norm": 94.21218872070312,
       "learning_rate": 9.266666666666666e-05,
-      "loss": 23.1440673828125,
+      "loss": 23.144088745117188,
       "step": 140
     },
     {
       "epoch": 0.0008764600363438762,
-      "grad_norm": 50.9583625793457,
+      "grad_norm": 50.958736419677734,
       "learning_rate": 9.933333333333334e-05,
-      "loss": 22.032106018066408,
+      "loss": 22.03218994140625,
       "step": 150
     },
     {
       "epoch": 0.0009348907054334679,
-      "grad_norm": 41.25766372680664,
+      "grad_norm": 41.21607971191406,
       "learning_rate": 0.00010600000000000002,
-      "loss": 21.708222961425783,
+      "loss": 21.708474731445314,
       "step": 160
     },
     {
       "epoch": 0.0009933213745230596,
-      "grad_norm": 46.097476959228516,
+      "grad_norm": 45.95130920410156,
       "learning_rate": 0.00011266666666666668,
-      "loss": 20.753759765625,
+      "loss": 20.753807067871094,
       "step": 170
     },
     {
       "epoch": 0.0010517520436126514,
-      "grad_norm": 44.175113677978516,
+      "grad_norm": 44.12228775024414,
       "learning_rate": 0.00011933333333333334,
-      "loss": 19.99718475341797,
+      "loss": 19.997039794921875,
       "step": 180
     },
     {
       "epoch": 0.001110182712702243,
-      "grad_norm": 59.265438079833984,
+      "grad_norm": 59.23231887817383,
       "learning_rate": 0.000126,
-      "loss": 19.62855224609375,
+      "loss": 19.628582763671876,
       "step": 190
     },
     {
       "epoch": 0.001168613381791835,
       "grad_norm": NaN,
       "learning_rate": 0.00013266666666666667,
-      "loss": 19.71117401123047,
+      "loss": 19.711293029785157,
       "step": 200
-    },
-    {
-      "epoch": 0.0012270440508814267,
-      "grad_norm": 264.33056640625,
-      "learning_rate": 0.00013933333333333335,
-      "loss": 19.4333984375,
-      "step": 210
-    },
-    {
-      "epoch": 0.0012854747199710183,
-      "grad_norm": 667.041259765625,
-      "learning_rate": 0.000146,
-      "loss": 19.633015441894532,
-      "step": 220
-    },
-    {
-      "epoch": 0.0013439053890606102,
-      "grad_norm": 269.3677673339844,
-      "learning_rate": 0.00015266666666666667,
-      "loss": 20.40240020751953,
-      "step": 230
-    },
-    {
-      "epoch": 0.0014023360581502018,
-      "grad_norm": NaN,
-      "learning_rate": 0.00015933333333333332,
-      "loss": 19.42903289794922,
-      "step": 240
-    },
-    {
-      "epoch": 0.0014607667272397936,
-      "grad_norm": 34716.453125,
-      "learning_rate": 0.000166,
-      "loss": 19.334349060058592,
-      "step": 250
-    },
-    {
-      "epoch": 0.0015191973963293855,
-      "grad_norm": 64080.4921875,
-      "learning_rate": 0.00017266666666666667,
-      "loss": 20.815042114257814,
-      "step": 260
-    },
-    {
-      "epoch": 0.001577628065418977,
-      "grad_norm": 6061549.5,
-      "learning_rate": 0.00017933333333333332,
-      "loss": 21.26500701904297,
-      "step": 270
-    },
-    {
-      "epoch": 0.001636058734508569,
-      "grad_norm": 886888.875,
-      "learning_rate": 0.00018600000000000002,
-      "loss": 21.720132446289064,
-      "step": 280
-    },
-    {
-      "epoch": 0.0016944894035981605,
-      "grad_norm": 4256860.0,
-      "learning_rate": 0.0001926666666666667,
-      "loss": 22.704322814941406,
-      "step": 290
-    },
-    {
-      "epoch": 0.0017529200726877523,
-      "grad_norm": 7430499.0,
-      "learning_rate": 0.00019933333333333334,
-      "loss": 23.518629455566405,
-      "step": 300
-    },
-    {
-      "epoch": 0.0018113507417773442,
-      "grad_norm": 894349.75,
-      "learning_rate": 0.00019999999996000412,
-      "loss": 23.982521057128906,
-      "step": 310
-    },
-    {
-      "epoch": 0.0018697814108669358,
-      "grad_norm": 2417416.0,
-      "learning_rate": 0.00019999999982174674,
-      "loss": 24.528610229492188,
-      "step": 320
-    },
-    {
-      "epoch": 0.0019282120799565276,
-      "grad_norm": 3199948.5,
-      "learning_rate": 0.00019999999958473402,
-      "loss": 24.749864196777345,
-      "step": 330
-    },
-    {
-      "epoch": 0.0019866427490461192,
-      "grad_norm": 444.504150390625,
-      "learning_rate": 0.00019999999924896604,
-      "loss": 23.710609436035156,
-      "step": 340
-    },
-    {
-      "epoch": 0.002045073418135711,
-      "grad_norm": 70555.0390625,
-      "learning_rate": 0.00019999999881444277,
-      "loss": 22.891081237792967,
-      "step": 350
-    },
-    {
-      "epoch": 0.002103504087225303,
-      "grad_norm": 284.5023193359375,
-      "learning_rate": 0.00019999999828116422,
-      "loss": 22.034759521484375,
-      "step": 360
-    },
-    {
-      "epoch": 0.0021619347563148947,
-      "grad_norm": 1010.1900024414062,
-      "learning_rate": 0.00019999999764913037,
-      "loss": 21.432949829101563,
-      "step": 370
-    },
-    {
-      "epoch": 0.002220365425404486,
-      "grad_norm": 4254.8564453125,
-      "learning_rate": 0.00019999999691834125,
-      "loss": 21.196998596191406,
-      "step": 380
-    },
-    {
-      "epoch": 0.002278796094494078,
-      "grad_norm": 17355.26171875,
-      "learning_rate": 0.00019999999608879683,
-      "loss": 20.504833984375,
-      "step": 390
-    },
-    {
-      "epoch": 0.00233722676358367,
-      "grad_norm": 2989.653564453125,
-      "learning_rate": 0.00019999999516049713,
-      "loss": 20.668417358398436,
-      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -307,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3201253176450048.0,
+  "total_flos": 1598220482291712.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null