End of training

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 0.9991111111111111,
-    "eval_accuracy": 0.62025,
-    "eval_loss": 1.2218776941299438,
-    "eval_runtime": 57.2683,
-    "eval_samples_per_second": 69.847,
-    "eval_steps_per_second": 2.183,
-    "total_flos": 8.943699469318226e+17,
-    "train_loss": 1.6086162854768202,
-    "train_runtime": 797.2781,
-    "train_samples_per_second": 45.149,
-    "train_steps_per_second": 0.352
+    "epoch": 2.997333333333333,
+    "eval_accuracy": 0.714,
+    "eval_loss": 0.9282281398773193,
+    "eval_runtime": 57.5051,
+    "eval_samples_per_second": 69.559,
+    "eval_steps_per_second": 2.174,
+    "total_flos": 2.6829109150955274e+18,
+    "train_loss": 1.3250810132756352,
+    "train_runtime": 2481.2668,
+    "train_samples_per_second": 43.521,
+    "train_steps_per_second": 0.34
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.9991111111111111,
-    "eval_accuracy": 0.62025,
-    "eval_loss": 1.2218776941299438,
-    "eval_runtime": 57.2683,
-    "eval_samples_per_second": 69.847,
-    "eval_steps_per_second": 2.183
+    "epoch": 2.997333333333333,
+    "eval_accuracy": 0.714,
+    "eval_loss": 0.9282281398773193,
+    "eval_runtime": 57.5051,
+    "eval_samples_per_second": 69.559,
+    "eval_steps_per_second": 2.174
 }

runs/Jun19_08-47-26_4b348fdd3627/events.out.tfevents.1718789393.4b348fdd3627.1278.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d0be1cc3c5f54bb699ba392b3c667e21dfbb20a4f104b77d7027f2484c6830
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.9991111111111111,
-    "total_flos": 8.943699469318226e+17,
-    "train_loss": 1.6086162854768202,
-    "train_runtime": 797.2781,
-    "train_samples_per_second": 45.149,
-    "train_steps_per_second": 0.352
+    "epoch": 2.997333333333333,
+    "total_flos": 2.6829109150955274e+18,
+    "train_loss": 1.3250810132756352,
+    "train_runtime": 2481.2668,
+    "train_samples_per_second": 43.521,
+    "train_steps_per_second": 0.34
 }

trainer_state.json

@@ -1,232 +1,642 @@
 {
-  "best_metric": 0.62025,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-281",
-  "epoch": 0.9991111111111111,
+  "best_metric": 0.714,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-finetuned-eurosat/checkpoint-843",
+  "epoch": 2.997333333333333,
   "eval_steps": 500,
-  "global_step": 281,
+  "global_step": 843,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.035555555555555556,
-      "grad_norm": 7.3984904289245605,
-      "learning_rate": 1.7241379310344828e-05,
-      "loss": 2.7474,
+      "grad_norm": 7.188250541687012,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 2.7793,
       "step": 10
     },
     {
       "epoch": 0.07111111111111111,
-      "grad_norm": 7.859865188598633,
-      "learning_rate": 3.4482758620689657e-05,
-      "loss": 2.6199,
+      "grad_norm": 15.252310752868652,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 2.7235,
       "step": 20
     },
     {
       "epoch": 0.10666666666666667,
-      "grad_norm": 21.349201202392578,
-      "learning_rate": 4.9801587301587306e-05,
-      "loss": 2.2658,
+      "grad_norm": 20.026681900024414,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 2.6203,
       "step": 30
     },
     {
       "epoch": 0.14222222222222222,
-      "grad_norm": 23.123310089111328,
-      "learning_rate": 4.781746031746032e-05,
-      "loss": 2.0242,
+      "grad_norm": 12.86706829071045,
+      "learning_rate": 2.3529411764705884e-05,
+      "loss": 2.4325,
       "step": 40
     },
     {
       "epoch": 0.17777777777777778,
-      "grad_norm": 10.755074501037598,
-      "learning_rate": 4.5833333333333334e-05,
-      "loss": 1.866,
+      "grad_norm": 22.171051025390625,
+      "learning_rate": 2.9411764705882354e-05,
+      "loss": 2.1824,
       "step": 50
     },
     {
       "epoch": 0.21333333333333335,
-      "grad_norm": 9.822580337524414,
-      "learning_rate": 4.384920634920635e-05,
-      "loss": 1.7276,
+      "grad_norm": 16.04732894897461,
+      "learning_rate": 3.529411764705883e-05,
+      "loss": 1.977,
       "step": 60
     },
     {
       "epoch": 0.24888888888888888,
-      "grad_norm": 11.387887001037598,
-      "learning_rate": 4.186507936507937e-05,
-      "loss": 1.6602,
+      "grad_norm": 11.828266143798828,
+      "learning_rate": 4.11764705882353e-05,
+      "loss": 1.8274,
       "step": 70
     },
     {
       "epoch": 0.28444444444444444,
-      "grad_norm": 11.359118461608887,
-      "learning_rate": 3.9880952380952386e-05,
-      "loss": 1.6713,
+      "grad_norm": 21.65501594543457,
+      "learning_rate": 4.705882352941177e-05,
+      "loss": 1.7634,
       "step": 80
     },
     {
       "epoch": 0.32,
-      "grad_norm": 10.438748359680176,
-      "learning_rate": 3.7896825396825396e-05,
-      "loss": 1.6469,
+      "grad_norm": 9.372465133666992,
+      "learning_rate": 4.967018469656992e-05,
+      "loss": 1.7128,
       "step": 90
     },
     {
       "epoch": 0.35555555555555557,
-      "grad_norm": 10.260947227478027,
-      "learning_rate": 3.591269841269841e-05,
-      "loss": 1.5134,
+      "grad_norm": 8.170567512512207,
+      "learning_rate": 4.901055408970976e-05,
+      "loss": 1.5845,
       "step": 100
     },
     {
       "epoch": 0.39111111111111113,
-      "grad_norm": 8.524605751037598,
-      "learning_rate": 3.392857142857143e-05,
-      "loss": 1.5694,
+      "grad_norm": 8.884113311767578,
+      "learning_rate": 4.835092348284961e-05,
+      "loss": 1.5652,
       "step": 110
     },
     {
       "epoch": 0.4266666666666667,
-      "grad_norm": 10.703609466552734,
-      "learning_rate": 3.194444444444444e-05,
-      "loss": 1.597,
+      "grad_norm": 9.709837913513184,
+      "learning_rate": 4.7691292875989446e-05,
+      "loss": 1.6439,
       "step": 120
     },
     {
       "epoch": 0.4622222222222222,
-      "grad_norm": 10.19986629486084,
-      "learning_rate": 2.996031746031746e-05,
-      "loss": 1.4785,
+      "grad_norm": 12.577466011047363,
+      "learning_rate": 4.703166226912929e-05,
+      "loss": 1.6118,
       "step": 130
     },
     {
       "epoch": 0.49777777777777776,
-      "grad_norm": 9.872143745422363,
-      "learning_rate": 2.797619047619048e-05,
-      "loss": 1.4853,
+      "grad_norm": 8.617718696594238,
+      "learning_rate": 4.6372031662269136e-05,
+      "loss": 1.4722,
       "step": 140
     },
     {
       "epoch": 0.5333333333333333,
-      "grad_norm": 8.166397094726562,
-      "learning_rate": 2.5992063492063496e-05,
-      "loss": 1.4354,
+      "grad_norm": 11.635614395141602,
+      "learning_rate": 4.5712401055408974e-05,
+      "loss": 1.4748,
       "step": 150
     },
     {
       "epoch": 0.5688888888888889,
-      "grad_norm": 12.244831085205078,
-      "learning_rate": 2.400793650793651e-05,
-      "loss": 1.5286,
+      "grad_norm": 10.609350204467773,
+      "learning_rate": 4.505277044854881e-05,
+      "loss": 1.4546,
       "step": 160
     },
     {
       "epoch": 0.6044444444444445,
-      "grad_norm": 9.033407211303711,
-      "learning_rate": 2.2023809523809524e-05,
-      "loss": 1.3584,
+      "grad_norm": 9.702072143554688,
+      "learning_rate": 4.439313984168866e-05,
+      "loss": 1.4868,
       "step": 170
     },
     {
       "epoch": 0.64,
-      "grad_norm": 7.281382083892822,
-      "learning_rate": 2.003968253968254e-05,
-      "loss": 1.4626,
+      "grad_norm": 8.165207862854004,
+      "learning_rate": 4.3733509234828496e-05,
+      "loss": 1.4197,
       "step": 180
     },
     {
       "epoch": 0.6755555555555556,
-      "grad_norm": 7.3251519203186035,
-      "learning_rate": 1.8055555555555555e-05,
-      "loss": 1.3453,
+      "grad_norm": 8.345643043518066,
+      "learning_rate": 4.307387862796834e-05,
+      "loss": 1.4298,
       "step": 190
     },
     {
       "epoch": 0.7111111111111111,
-      "grad_norm": 9.071359634399414,
-      "learning_rate": 1.6071428571428572e-05,
-      "loss": 1.3493,
+      "grad_norm": 9.1146821975708,
+      "learning_rate": 4.2414248021108186e-05,
+      "loss": 1.437,
       "step": 200
     },
     {
       "epoch": 0.7466666666666667,
-      "grad_norm": 11.566309928894043,
-      "learning_rate": 1.4087301587301587e-05,
-      "loss": 1.3759,
+      "grad_norm": 10.016292572021484,
+      "learning_rate": 4.1754617414248024e-05,
+      "loss": 1.3961,
       "step": 210
     },
     {
       "epoch": 0.7822222222222223,
-      "grad_norm": 9.21988582611084,
-      "learning_rate": 1.2103174603174603e-05,
-      "loss": 1.365,
+      "grad_norm": 6.980156421661377,
+      "learning_rate": 4.109498680738786e-05,
+      "loss": 1.3571,
       "step": 220
     },
     {
       "epoch": 0.8177777777777778,
-      "grad_norm": 8.32099437713623,
-      "learning_rate": 1.011904761904762e-05,
-      "loss": 1.3049,
+      "grad_norm": 9.158329010009766,
+      "learning_rate": 4.043535620052771e-05,
+      "loss": 1.3691,
       "step": 230
     },
     {
       "epoch": 0.8533333333333334,
-      "grad_norm": 10.410431861877441,
-      "learning_rate": 8.134920634920636e-06,
-      "loss": 1.3583,
+      "grad_norm": 8.437979698181152,
+      "learning_rate": 3.9775725593667545e-05,
+      "loss": 1.2722,
       "step": 240
     },
     {
       "epoch": 0.8888888888888888,
-      "grad_norm": 7.7621073722839355,
-      "learning_rate": 6.1507936507936505e-06,
-      "loss": 1.3066,
+      "grad_norm": 7.31761360168457,
+      "learning_rate": 3.911609498680739e-05,
+      "loss": 1.3382,
       "step": 250
     },
     {
       "epoch": 0.9244444444444444,
-      "grad_norm": 9.822245597839355,
-      "learning_rate": 4.166666666666667e-06,
-      "loss": 1.3564,
+      "grad_norm": 10.811269760131836,
+      "learning_rate": 3.8456464379947235e-05,
+      "loss": 1.3005,
       "step": 260
     },
     {
       "epoch": 0.96,
-      "grad_norm": 11.113300323486328,
-      "learning_rate": 2.1825396825396824e-06,
-      "loss": 1.2959,
+      "grad_norm": 7.826028823852539,
+      "learning_rate": 3.779683377308707e-05,
+      "loss": 1.2971,
       "step": 270
     },
     {
       "epoch": 0.9955555555555555,
-      "grad_norm": 8.999974250793457,
-      "learning_rate": 1.9841269841269841e-07,
-      "loss": 1.3575,
+      "grad_norm": 8.89599609375,
+      "learning_rate": 3.713720316622691e-05,
+      "loss": 1.3142,
       "step": 280
     },
     {
       "epoch": 0.9991111111111111,
-      "eval_accuracy": 0.62025,
-      "eval_loss": 1.2218776941299438,
-      "eval_runtime": 59.4645,
-      "eval_samples_per_second": 67.267,
-      "eval_steps_per_second": 2.102,
+      "eval_accuracy": 0.629,
+      "eval_loss": 1.176965594291687,
+      "eval_runtime": 61.7496,
+      "eval_samples_per_second": 64.778,
+      "eval_steps_per_second": 2.024,
       "step": 281
     },
     {
-      "epoch": 0.9991111111111111,
-      "step": 281,
-      "total_flos": 8.943699469318226e+17,
-      "train_loss": 1.6086162854768202,
-      "train_runtime": 797.2781,
-      "train_samples_per_second": 45.149,
-      "train_steps_per_second": 0.352
+      "epoch": 1.031111111111111,
+      "grad_norm": 8.035099029541016,
+      "learning_rate": 3.6477572559366756e-05,
+      "loss": 1.2879,
+      "step": 290
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 10.644525527954102,
+      "learning_rate": 3.58179419525066e-05,
+      "loss": 1.2803,
+      "step": 300
+    },
+    {
+      "epoch": 1.1022222222222222,
+      "grad_norm": 12.751725196838379,
+      "learning_rate": 3.515831134564644e-05,
+      "loss": 1.2765,
+      "step": 310
+    },
+    {
+      "epoch": 1.1377777777777778,
+      "grad_norm": 9.897214889526367,
+      "learning_rate": 3.4498680738786285e-05,
+      "loss": 1.234,
+      "step": 320
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 6.898780822753906,
+      "learning_rate": 3.383905013192612e-05,
+      "loss": 1.2247,
+      "step": 330
+    },
+    {
+      "epoch": 1.208888888888889,
+      "grad_norm": 9.826775550842285,
+      "learning_rate": 3.317941952506596e-05,
+      "loss": 1.302,
+      "step": 340
+    },
+    {
+      "epoch": 1.2444444444444445,
+      "grad_norm": 7.03531551361084,
+      "learning_rate": 3.2519788918205806e-05,
+      "loss": 1.2956,
+      "step": 350
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 7.564468860626221,
+      "learning_rate": 3.186015831134565e-05,
+      "loss": 1.2087,
+      "step": 360
+    },
+    {
+      "epoch": 1.3155555555555556,
+      "grad_norm": 9.157870292663574,
+      "learning_rate": 3.120052770448549e-05,
+      "loss": 1.2794,
+      "step": 370
+    },
+    {
+      "epoch": 1.3511111111111112,
+      "grad_norm": 6.955115795135498,
+      "learning_rate": 3.0540897097625334e-05,
+      "loss": 1.2916,
+      "step": 380
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 8.055458068847656,
+      "learning_rate": 2.9881266490765176e-05,
+      "loss": 1.2643,
+      "step": 390
+    },
+    {
+      "epoch": 1.4222222222222223,
+      "grad_norm": 8.577414512634277,
+      "learning_rate": 2.9221635883905014e-05,
+      "loss": 1.2435,
+      "step": 400
+    },
+    {
+      "epoch": 1.4577777777777778,
+      "grad_norm": 8.334266662597656,
+      "learning_rate": 2.8562005277044855e-05,
+      "loss": 1.1744,
+      "step": 410
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 7.725725173950195,
+      "learning_rate": 2.79023746701847e-05,
+      "loss": 1.1909,
+      "step": 420
+    },
+    {
+      "epoch": 1.528888888888889,
+      "grad_norm": 10.035604476928711,
+      "learning_rate": 2.724274406332454e-05,
+      "loss": 1.1839,
+      "step": 430
+    },
+    {
+      "epoch": 1.5644444444444443,
+      "grad_norm": 8.928838729858398,
+      "learning_rate": 2.658311345646438e-05,
+      "loss": 1.2524,
+      "step": 440
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 10.327030181884766,
+      "learning_rate": 2.5923482849604225e-05,
+      "loss": 1.2254,
+      "step": 450
+    },
+    {
+      "epoch": 1.6355555555555554,
+      "grad_norm": 7.943435192108154,
+      "learning_rate": 2.5263852242744063e-05,
+      "loss": 1.1067,
+      "step": 460
+    },
+    {
+      "epoch": 1.6711111111111112,
+      "grad_norm": 9.097575187683105,
+      "learning_rate": 2.4604221635883905e-05,
+      "loss": 1.1412,
+      "step": 470
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 8.329163551330566,
+      "learning_rate": 2.3944591029023746e-05,
+      "loss": 1.1277,
+      "step": 480
+    },
+    {
+      "epoch": 1.7422222222222223,
+      "grad_norm": 9.431710243225098,
+      "learning_rate": 2.328496042216359e-05,
+      "loss": 1.1697,
+      "step": 490
+    },
+    {
+      "epoch": 1.7777777777777777,
+      "grad_norm": 7.484973907470703,
+      "learning_rate": 2.262532981530343e-05,
+      "loss": 1.1522,
+      "step": 500
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 8.600388526916504,
+      "learning_rate": 2.196569920844327e-05,
+      "loss": 1.1673,
+      "step": 510
+    },
+    {
+      "epoch": 1.8488888888888888,
+      "grad_norm": 7.894708156585693,
+      "learning_rate": 2.1306068601583116e-05,
+      "loss": 1.1206,
+      "step": 520
+    },
+    {
+      "epoch": 1.8844444444444446,
+      "grad_norm": 9.636763572692871,
+      "learning_rate": 2.0646437994722954e-05,
+      "loss": 1.2176,
+      "step": 530
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 9.740330696105957,
+      "learning_rate": 1.9986807387862796e-05,
+      "loss": 1.2078,
+      "step": 540
+    },
+    {
+      "epoch": 1.9555555555555557,
+      "grad_norm": 7.4491353034973145,
+      "learning_rate": 1.932717678100264e-05,
+      "loss": 1.1472,
+      "step": 550
+    },
+    {
+      "epoch": 1.991111111111111,
+      "grad_norm": 10.187119483947754,
+      "learning_rate": 1.866754617414248e-05,
+      "loss": 1.0761,
+      "step": 560
+    },
+    {
+      "epoch": 1.9982222222222221,
+      "eval_accuracy": 0.69825,
+      "eval_loss": 1.0089702606201172,
+      "eval_runtime": 60.6333,
+      "eval_samples_per_second": 65.97,
+      "eval_steps_per_second": 2.062,
+      "step": 562
+    },
+    {
+      "epoch": 2.026666666666667,
+      "grad_norm": 10.728060722351074,
+      "learning_rate": 1.8007915567282324e-05,
+      "loss": 1.1074,
+      "step": 570
+    },
+    {
+      "epoch": 2.062222222222222,
+      "grad_norm": 6.846221923828125,
+      "learning_rate": 1.7348284960422166e-05,
+      "loss": 1.1202,
+      "step": 580
+    },
+    {
+      "epoch": 2.097777777777778,
+      "grad_norm": 7.134582996368408,
+      "learning_rate": 1.6688654353562007e-05,
+      "loss": 1.1013,
+      "step": 590
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 6.4924397468566895,
+      "learning_rate": 1.602902374670185e-05,
+      "loss": 1.1429,
+      "step": 600
+    },
+    {
+      "epoch": 2.168888888888889,
+      "grad_norm": 7.079750061035156,
+      "learning_rate": 1.536939313984169e-05,
+      "loss": 1.1282,
+      "step": 610
+    },
+    {
+      "epoch": 2.2044444444444444,
+      "grad_norm": 11.857382774353027,
+      "learning_rate": 1.470976253298153e-05,
+      "loss": 1.0689,
+      "step": 620
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 7.431779861450195,
+      "learning_rate": 1.4050131926121373e-05,
+      "loss": 1.1116,
+      "step": 630
+    },
+    {
+      "epoch": 2.2755555555555556,
+      "grad_norm": 8.456690788269043,
+      "learning_rate": 1.3390501319261215e-05,
+      "loss": 1.0721,
+      "step": 640
+    },
+    {
+      "epoch": 2.311111111111111,
+      "grad_norm": 10.243916511535645,
+      "learning_rate": 1.2730870712401055e-05,
+      "loss": 1.1046,
+      "step": 650
+    },
+    {
+      "epoch": 2.3466666666666667,
+      "grad_norm": 9.12217903137207,
+      "learning_rate": 1.2071240105540896e-05,
+      "loss": 1.1231,
+      "step": 660
+    },
+    {
+      "epoch": 2.3822222222222225,
+      "grad_norm": 6.960771560668945,
+      "learning_rate": 1.141160949868074e-05,
+      "loss": 1.0449,
+      "step": 670
+    },
+    {
+      "epoch": 2.417777777777778,
+      "grad_norm": 6.853394031524658,
+      "learning_rate": 1.0751978891820581e-05,
+      "loss": 1.0166,
+      "step": 680
+    },
+    {
+      "epoch": 2.453333333333333,
+      "grad_norm": 6.347965717315674,
+      "learning_rate": 1.0092348284960421e-05,
+      "loss": 1.0753,
+      "step": 690
+    },
+    {
+      "epoch": 2.488888888888889,
+      "grad_norm": 7.328911304473877,
+      "learning_rate": 9.432717678100264e-06,
+      "loss": 1.0528,
+      "step": 700
+    },
+    {
+      "epoch": 2.5244444444444447,
+      "grad_norm": 7.785583019256592,
+      "learning_rate": 8.773087071240106e-06,
+      "loss": 1.1255,
+      "step": 710
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 8.781428337097168,
+      "learning_rate": 8.113456464379948e-06,
+      "loss": 1.0989,
+      "step": 720
+    },
+    {
+      "epoch": 2.5955555555555554,
+      "grad_norm": 6.994375228881836,
+      "learning_rate": 7.453825857519789e-06,
+      "loss": 1.0473,
+      "step": 730
+    },
+    {
+      "epoch": 2.631111111111111,
+      "grad_norm": 8.248795509338379,
+      "learning_rate": 6.794195250659631e-06,
+      "loss": 1.0968,
+      "step": 740
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 7.137526035308838,
+      "learning_rate": 6.134564643799472e-06,
+      "loss": 1.0421,
+      "step": 750
+    },
+    {
+      "epoch": 2.7022222222222223,
+      "grad_norm": 10.059906959533691,
+      "learning_rate": 5.474934036939315e-06,
+      "loss": 1.0794,
+      "step": 760
+    },
+    {
+      "epoch": 2.7377777777777776,
+      "grad_norm": 7.585984230041504,
+      "learning_rate": 4.8153034300791555e-06,
+      "loss": 1.0677,
+      "step": 770
+    },
+    {
+      "epoch": 2.7733333333333334,
+      "grad_norm": 7.5168137550354,
+      "learning_rate": 4.155672823218998e-06,
+      "loss": 0.9899,
+      "step": 780
+    },
+    {
+      "epoch": 2.8088888888888888,
+      "grad_norm": 8.242053985595703,
+      "learning_rate": 3.496042216358839e-06,
+      "loss": 1.1027,
+      "step": 790
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": 7.243769645690918,
+      "learning_rate": 2.836411609498681e-06,
+      "loss": 1.1244,
+      "step": 800
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 9.468960762023926,
+      "learning_rate": 2.1767810026385226e-06,
+      "loss": 1.076,
+      "step": 810
+    },
+    {
+      "epoch": 2.9155555555555557,
+      "grad_norm": 9.269329071044922,
+      "learning_rate": 1.5171503957783642e-06,
+      "loss": 1.0397,
+      "step": 820
+    },
+    {
+      "epoch": 2.951111111111111,
+      "grad_norm": 8.011164665222168,
+      "learning_rate": 8.575197889182058e-07,
+      "loss": 1.0792,
+      "step": 830
+    },
+    {
+      "epoch": 2.986666666666667,
+      "grad_norm": 7.399364471435547,
+      "learning_rate": 1.9788918205804752e-07,
+      "loss": 1.0439,
+      "step": 840
+    },
+    {
+      "epoch": 2.997333333333333,
+      "eval_accuracy": 0.714,
+      "eval_loss": 0.9282281398773193,
+      "eval_runtime": 56.4403,
+      "eval_samples_per_second": 70.871,
+      "eval_steps_per_second": 2.215,
+      "step": 843
+    },
+    {
+      "epoch": 2.997333333333333,
+      "step": 843,
+      "total_flos": 2.6829109150955274e+18,
+      "train_loss": 1.3250810132756352,
+      "train_runtime": 2481.2668,
+      "train_samples_per_second": 43.521,
+      "train_steps_per_second": 0.34
     }
   ],
   "logging_steps": 10,
-  "max_steps": 281,
+  "max_steps": 843,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -240,7 +650,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.943699469318226e+17,
+  "total_flos": 2.6829109150955274e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null