End of training

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 datasets:
 - imagefolder
@@ -22,7 +24,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7538461538461538
+      value: 0.7615384615384615
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3683
-- Accuracy: 0.7538
+- Loss: 1.3440
+- Accuracy: 0.7615
 
 ## Model description
 

all_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 200.0,
-    "eval_accuracy": 0.7769230769230769,
-    "eval_loss": 1.6097954511642456,
-    "eval_runtime": 2.2046,
-    "eval_samples_per_second": 58.968,
-    "eval_steps_per_second": 0.907,
-    "train_loss": 0.39147548845836094,
-    "train_runtime": 3403.5317,
-    "train_samples_per_second": 30.556,
-    "train_steps_per_second": 0.411
+    "epoch": 250.0,
+    "eval_accuracy": 0.7615384615384615,
+    "eval_loss": 1.3439607620239258,
+    "eval_runtime": 2.1945,
+    "eval_samples_per_second": 59.239,
+    "eval_steps_per_second": 0.911,
+    "train_loss": 0.09994067628043038,
+    "train_runtime": 2169.5998,
+    "train_samples_per_second": 59.919,
+    "train_steps_per_second": 0.807
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 200.0,
-    "eval_accuracy": 0.7769230769230769,
-    "eval_loss": 1.6097954511642456,
-    "eval_runtime": 2.2046,
-    "eval_samples_per_second": 58.968,
-    "eval_steps_per_second": 0.907
+    "epoch": 250.0,
+    "eval_accuracy": 0.7615384615384615,
+    "eval_loss": 1.3439607620239258,
+    "eval_runtime": 2.1945,
+    "eval_samples_per_second": 59.239,
+    "eval_steps_per_second": 0.911
 }

runs/Jan17_22-32-09_c6ad14a30b7d/events.out.tfevents.1705532949.c6ad14a30b7d.23778.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7183f6d2fc8c073961f22def15c7cc3b4a4196910ca6a9a40c935f4fd32b53ce
+size 411

train_results.json

@@ -1,7 +1,7 @@
 {
-    "epoch": 200.0,
-    "train_loss": 0.39147548845836094,
-    "train_runtime": 3403.5317,
-    "train_samples_per_second": 30.556,
-    "train_steps_per_second": 0.411
+    "epoch": 250.0,
+    "train_loss": 0.09994067628043038,
+    "train_runtime": 2169.5998,
+    "train_samples_per_second": 59.919,
+    "train_steps_per_second": 0.807
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6097954511642456,
-  "best_model_checkpoint": "./outputs_letter3/checkpoint-1386",
-  "epoch": 200.0,
+  "best_metric": 1.3439607620239258,
+  "best_model_checkpoint": "./outputs_letter3/checkpoint-1736",
+  "epoch": 250.0,
   "eval_steps": 500,
-  "global_step": 1400,
+  "global_step": 1750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2674,14 +2674,683 @@
       "train_runtime": 3403.5317,
       "train_samples_per_second": 30.556,
       "train_steps_per_second": 0.411
+    },
+    {
+      "epoch": 201.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.6449843645095825,
+      "eval_runtime": 2.095,
+      "eval_samples_per_second": 62.053,
+      "eval_steps_per_second": 0.955,
+      "step": 1407
+    },
+    {
+      "epoch": 201.43,
+      "learning_rate": 1.988571428571429e-05,
+      "loss": 0.706,
+      "step": 1410
+    },
+    {
+      "epoch": 202.0,
+      "eval_accuracy": 0.7538461538461538,
+      "eval_loss": 1.646350622177124,
+      "eval_runtime": 2.1984,
+      "eval_samples_per_second": 59.134,
+      "eval_steps_per_second": 0.91,
+      "step": 1414
+    },
+    {
+      "epoch": 202.86,
+      "learning_rate": 1.9771428571428574e-05,
+      "loss": 0.6746,
+      "step": 1420
+    },
+    {
+      "epoch": 203.0,
+      "eval_accuracy": 0.7615384615384615,
+      "eval_loss": 1.6431909799575806,
+      "eval_runtime": 2.1397,
+      "eval_samples_per_second": 60.755,
+      "eval_steps_per_second": 0.935,
+      "step": 1421
+    },
+    {
+      "epoch": 204.0,
+      "eval_accuracy": 0.7615384615384615,
+      "eval_loss": 1.6220970153808594,
+      "eval_runtime": 2.2125,
+      "eval_samples_per_second": 58.756,
+      "eval_steps_per_second": 0.904,
+      "step": 1428
+    },
+    {
+      "epoch": 204.29,
+      "learning_rate": 1.9657142857142858e-05,
+      "loss": 0.6282,
+      "step": 1430
+    },
+    {
+      "epoch": 205.0,
+      "eval_accuracy": 0.7769230769230769,
+      "eval_loss": 1.5988324880599976,
+      "eval_runtime": 2.3558,
+      "eval_samples_per_second": 55.182,
+      "eval_steps_per_second": 0.849,
+      "step": 1435
+    },
+    {
+      "epoch": 205.71,
+      "learning_rate": 1.9542857142857143e-05,
+      "loss": 0.618,
+      "step": 1440
+    },
+    {
+      "epoch": 206.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.6031513214111328,
+      "eval_runtime": 2.2121,
+      "eval_samples_per_second": 58.767,
+      "eval_steps_per_second": 0.904,
+      "step": 1442
+    },
+    {
+      "epoch": 207.0,
+      "eval_accuracy": 0.7923076923076923,
+      "eval_loss": 1.561190128326416,
+      "eval_runtime": 2.2132,
+      "eval_samples_per_second": 58.739,
+      "eval_steps_per_second": 0.904,
+      "step": 1449
+    },
+    {
+      "epoch": 207.14,
+      "learning_rate": 1.942857142857143e-05,
+      "loss": 0.6053,
+      "step": 1450
+    },
+    {
+      "epoch": 208.0,
+      "eval_accuracy": 0.7769230769230769,
+      "eval_loss": 1.5888561010360718,
+      "eval_runtime": 2.1847,
+      "eval_samples_per_second": 59.504,
+      "eval_steps_per_second": 0.915,
+      "step": 1456
+    },
+    {
+      "epoch": 208.57,
+      "learning_rate": 1.9314285714285718e-05,
+      "loss": 0.5977,
+      "step": 1460
+    },
+    {
+      "epoch": 209.0,
+      "eval_accuracy": 0.7692307692307693,
+      "eval_loss": 1.566961646080017,
+      "eval_runtime": 2.2023,
+      "eval_samples_per_second": 59.03,
+      "eval_steps_per_second": 0.908,
+      "step": 1463
+    },
+    {
+      "epoch": 210.0,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.6131,
+      "step": 1470
+    },
+    {
+      "epoch": 210.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.5975637435913086,
+      "eval_runtime": 2.3397,
+      "eval_samples_per_second": 55.564,
+      "eval_steps_per_second": 0.855,
+      "step": 1470
+    },
+    {
+      "epoch": 211.0,
+      "eval_accuracy": 0.7538461538461538,
+      "eval_loss": 1.5593103170394897,
+      "eval_runtime": 2.2361,
+      "eval_samples_per_second": 58.136,
+      "eval_steps_per_second": 0.894,
+      "step": 1477
+    },
+    {
+      "epoch": 211.43,
+      "learning_rate": 1.9085714285714287e-05,
+      "loss": 0.5753,
+      "step": 1480
+    },
+    {
+      "epoch": 212.0,
+      "eval_accuracy": 0.7384615384615385,
+      "eval_loss": 1.5974284410476685,
+      "eval_runtime": 2.3233,
+      "eval_samples_per_second": 55.955,
+      "eval_steps_per_second": 0.861,
+      "step": 1484
+    },
+    {
+      "epoch": 212.86,
+      "learning_rate": 1.8971428571428575e-05,
+      "loss": 0.576,
+      "step": 1490
+    },
+    {
+      "epoch": 213.0,
+      "eval_accuracy": 0.7769230769230769,
+      "eval_loss": 1.573266863822937,
+      "eval_runtime": 2.2312,
+      "eval_samples_per_second": 58.264,
+      "eval_steps_per_second": 0.896,
+      "step": 1491
+    },
+    {
+      "epoch": 214.0,
+      "eval_accuracy": 0.7769230769230769,
+      "eval_loss": 1.497517466545105,
+      "eval_runtime": 2.3929,
+      "eval_samples_per_second": 54.328,
+      "eval_steps_per_second": 0.836,
+      "step": 1498
+    },
+    {
+      "epoch": 214.29,
+      "learning_rate": 1.885714285714286e-05,
+      "loss": 0.5744,
+      "step": 1500
+    },
+    {
+      "epoch": 215.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.562217116355896,
+      "eval_runtime": 2.2169,
+      "eval_samples_per_second": 58.642,
+      "eval_steps_per_second": 0.902,
+      "step": 1505
+    },
+    {
+      "epoch": 215.71,
+      "learning_rate": 1.8742857142857143e-05,
+      "loss": 0.5658,
+      "step": 1510
+    },
+    {
+      "epoch": 216.0,
+      "eval_accuracy": 0.7538461538461538,
+      "eval_loss": 1.5334222316741943,
+      "eval_runtime": 2.3054,
+      "eval_samples_per_second": 56.388,
+      "eval_steps_per_second": 0.868,
+      "step": 1512
+    },
+    {
+      "epoch": 217.0,
+      "eval_accuracy": 0.7538461538461538,
+      "eval_loss": 1.5438138246536255,
+      "eval_runtime": 2.3277,
+      "eval_samples_per_second": 55.849,
+      "eval_steps_per_second": 0.859,
+      "step": 1519
+    },
+    {
+      "epoch": 217.14,
+      "learning_rate": 1.8628571428571428e-05,
+      "loss": 0.5507,
+      "step": 1520
+    },
+    {
+      "epoch": 218.0,
+      "eval_accuracy": 0.7307692307692307,
+      "eval_loss": 1.5617175102233887,
+      "eval_runtime": 2.3945,
+      "eval_samples_per_second": 54.291,
+      "eval_steps_per_second": 0.835,
+      "step": 1526
+    },
+    {
+      "epoch": 218.57,
+      "learning_rate": 1.8514285714285716e-05,
+      "loss": 0.5474,
+      "step": 1530
+    },
+    {
+      "epoch": 219.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.542279601097107,
+      "eval_runtime": 2.1837,
+      "eval_samples_per_second": 59.533,
+      "eval_steps_per_second": 0.916,
+      "step": 1533
+    },
+    {
+      "epoch": 220.0,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.5095,
+      "step": 1540
+    },
+    {
+      "epoch": 220.0,
+      "eval_accuracy": 0.7769230769230769,
+      "eval_loss": 1.509877324104309,
+      "eval_runtime": 2.1925,
+      "eval_samples_per_second": 59.293,
+      "eval_steps_per_second": 0.912,
+      "step": 1540
+    },
+    {
+      "epoch": 221.0,
+      "eval_accuracy": 0.7692307692307693,
+      "eval_loss": 1.5009371042251587,
+      "eval_runtime": 2.1917,
+      "eval_samples_per_second": 59.315,
+      "eval_steps_per_second": 0.913,
+      "step": 1547
+    },
+    {
+      "epoch": 221.43,
+      "learning_rate": 1.8285714285714288e-05,
+      "loss": 0.5263,
+      "step": 1550
+    },
+    {
+      "epoch": 222.0,
+      "eval_accuracy": 0.7615384615384615,
+      "eval_loss": 1.4717506170272827,
+      "eval_runtime": 2.1826,
+      "eval_samples_per_second": 59.561,
+      "eval_steps_per_second": 0.916,
+      "step": 1554
+    },
+    {
+      "epoch": 222.86,
+      "learning_rate": 1.8171428571428572e-05,
+      "loss": 0.4934,
+      "step": 1560
+    },
+    {
+      "epoch": 223.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.5150481462478638,
+      "eval_runtime": 2.1689,
+      "eval_samples_per_second": 59.939,
+      "eval_steps_per_second": 0.922,
+      "step": 1561
+    },
+    {
+      "epoch": 224.0,
+      "eval_accuracy": 0.7615384615384615,
+      "eval_loss": 1.5133140087127686,
+      "eval_runtime": 2.2493,
+      "eval_samples_per_second": 57.795,
+      "eval_steps_per_second": 0.889,
+      "step": 1568
+    },
+    {
+      "epoch": 224.29,
+      "learning_rate": 1.8057142857142857e-05,
+      "loss": 0.4935,
+      "step": 1570
+    },
+    {
+      "epoch": 225.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.5053058862686157,
+      "eval_runtime": 2.2888,
+      "eval_samples_per_second": 56.799,
+      "eval_steps_per_second": 0.874,
+      "step": 1575
+    },
+    {
+      "epoch": 225.71,
+      "learning_rate": 1.7942857142857144e-05,
+      "loss": 0.4808,
+      "step": 1580
+    },
+    {
+      "epoch": 226.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.5152372121810913,
+      "eval_runtime": 2.3287,
+      "eval_samples_per_second": 55.824,
+      "eval_steps_per_second": 0.859,
+      "step": 1582
+    },
+    {
+      "epoch": 227.0,
+      "eval_accuracy": 0.7384615384615385,
+      "eval_loss": 1.521767497062683,
+      "eval_runtime": 2.2464,
+      "eval_samples_per_second": 57.871,
+      "eval_steps_per_second": 0.89,
+      "step": 1589
+    },
+    {
+      "epoch": 227.14,
+      "learning_rate": 1.7828571428571432e-05,
+      "loss": 0.5039,
+      "step": 1590
+    },
+    {
+      "epoch": 228.0,
+      "eval_accuracy": 0.7615384615384615,
+      "eval_loss": 1.4631297588348389,
+      "eval_runtime": 2.1868,
+      "eval_samples_per_second": 59.449,
+      "eval_steps_per_second": 0.915,
+      "step": 1596
+    },
+    {
+      "epoch": 228.57,
+      "learning_rate": 1.7714285714285717e-05,
+      "loss": 0.4516,
+      "step": 1600
+    },
+    {
+      "epoch": 229.0,
+      "eval_accuracy": 0.7692307692307693,
+      "eval_loss": 1.4795747995376587,
+      "eval_runtime": 2.3162,
+      "eval_samples_per_second": 56.126,
+      "eval_steps_per_second": 0.863,
+      "step": 1603
+    },
+    {
+      "epoch": 230.0,
+      "learning_rate": 1.76e-05,
+      "loss": 0.4655,
+      "step": 1610
+    },
+    {
+      "epoch": 230.0,
+      "eval_accuracy": 0.7769230769230769,
+      "eval_loss": 1.4648711681365967,
+      "eval_runtime": 2.3186,
+      "eval_samples_per_second": 56.068,
+      "eval_steps_per_second": 0.863,
+      "step": 1610
+    },
+    {
+      "epoch": 231.0,
+      "eval_accuracy": 0.7846153846153846,
+      "eval_loss": 1.4528415203094482,
+      "eval_runtime": 2.2367,
+      "eval_samples_per_second": 58.12,
+      "eval_steps_per_second": 0.894,
+      "step": 1617
+    },
+    {
+      "epoch": 231.43,
+      "learning_rate": 1.748571428571429e-05,
+      "loss": 0.4487,
+      "step": 1620
+    },
+    {
+      "epoch": 232.0,
+      "eval_accuracy": 0.7769230769230769,
+      "eval_loss": 1.4157787561416626,
+      "eval_runtime": 2.2157,
+      "eval_samples_per_second": 58.673,
+      "eval_steps_per_second": 0.903,
+      "step": 1624
+    },
+    {
+      "epoch": 232.86,
+      "learning_rate": 1.7371428571428573e-05,
+      "loss": 0.453,
+      "step": 1630
+    },
+    {
+      "epoch": 233.0,
+      "eval_accuracy": 0.7538461538461538,
+      "eval_loss": 1.4378057718276978,
+      "eval_runtime": 2.2298,
+      "eval_samples_per_second": 58.301,
+      "eval_steps_per_second": 0.897,
+      "step": 1631
+    },
+    {
+      "epoch": 234.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.4233053922653198,
+      "eval_runtime": 2.2254,
+      "eval_samples_per_second": 58.416,
+      "eval_steps_per_second": 0.899,
+      "step": 1638
+    },
+    {
+      "epoch": 234.29,
+      "learning_rate": 1.7257142857142857e-05,
+      "loss": 0.4248,
+      "step": 1640
+    },
+    {
+      "epoch": 235.0,
+      "eval_accuracy": 0.7615384615384615,
+      "eval_loss": 1.4437103271484375,
+      "eval_runtime": 2.2018,
+      "eval_samples_per_second": 59.042,
+      "eval_steps_per_second": 0.908,
+      "step": 1645
+    },
+    {
+      "epoch": 235.71,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 0.4103,
+      "step": 1650
+    },
+    {
+      "epoch": 236.0,
+      "eval_accuracy": 0.7384615384615385,
+      "eval_loss": 1.4489341974258423,
+      "eval_runtime": 2.3267,
+      "eval_samples_per_second": 55.872,
+      "eval_steps_per_second": 0.86,
+      "step": 1652
+    },
+    {
+      "epoch": 237.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.437820315361023,
+      "eval_runtime": 2.2082,
+      "eval_samples_per_second": 58.871,
+      "eval_steps_per_second": 0.906,
+      "step": 1659
+    },
+    {
+      "epoch": 237.14,
+      "learning_rate": 1.702857142857143e-05,
+      "loss": 0.4146,
+      "step": 1660
+    },
+    {
+      "epoch": 238.0,
+      "eval_accuracy": 0.7384615384615385,
+      "eval_loss": 1.4532761573791504,
+      "eval_runtime": 2.2013,
+      "eval_samples_per_second": 59.057,
+      "eval_steps_per_second": 0.909,
+      "step": 1666
+    },
+    {
+      "epoch": 238.57,
+      "learning_rate": 1.6914285714285717e-05,
+      "loss": 0.4313,
+      "step": 1670
+    },
+    {
+      "epoch": 239.0,
+      "eval_accuracy": 0.7615384615384615,
+      "eval_loss": 1.444754958152771,
+      "eval_runtime": 2.2195,
+      "eval_samples_per_second": 58.573,
+      "eval_steps_per_second": 0.901,
+      "step": 1673
+    },
+    {
+      "epoch": 240.0,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.408,
+      "step": 1680
+    },
+    {
+      "epoch": 240.0,
+      "eval_accuracy": 0.7692307692307693,
+      "eval_loss": 1.428984522819519,
+      "eval_runtime": 2.3419,
+      "eval_samples_per_second": 55.51,
+      "eval_steps_per_second": 0.854,
+      "step": 1680
+    },
+    {
+      "epoch": 241.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.4546881914138794,
+      "eval_runtime": 2.2356,
+      "eval_samples_per_second": 58.149,
+      "eval_steps_per_second": 0.895,
+      "step": 1687
+    },
+    {
+      "epoch": 241.43,
+      "learning_rate": 1.6685714285714286e-05,
+      "loss": 0.4145,
+      "step": 1690
+    },
+    {
+      "epoch": 242.0,
+      "eval_accuracy": 0.7461538461538462,
+      "eval_loss": 1.3930408954620361,
+      "eval_runtime": 2.2411,
+      "eval_samples_per_second": 58.006,
+      "eval_steps_per_second": 0.892,
+      "step": 1694
+    },
+    {
+      "epoch": 242.86,
+      "learning_rate": 1.6571428571428574e-05,
+      "loss": 0.4193,
+      "step": 1700
+    },
+    {
+      "epoch": 243.0,
+      "eval_accuracy": 0.7538461538461538,
+      "eval_loss": 1.4186941385269165,
+      "eval_runtime": 2.3409,
+      "eval_samples_per_second": 55.534,
+      "eval_steps_per_second": 0.854,
+      "step": 1701
+    },
+    {
+      "epoch": 244.0,
+      "eval_accuracy": 0.7615384615384615,
+      "eval_loss": 1.3854211568832397,
+      "eval_runtime": 2.288,
+      "eval_samples_per_second": 56.817,
+      "eval_steps_per_second": 0.874,
+      "step": 1708
+    },
+    {
+      "epoch": 244.29,
+      "learning_rate": 1.645714285714286e-05,
+      "loss": 0.3951,
+      "step": 1710
+    },
+    {
+      "epoch": 245.0,
+      "eval_accuracy": 0.7615384615384615,
+      "eval_loss": 1.3977891206741333,
+      "eval_runtime": 2.2608,
+      "eval_samples_per_second": 57.502,
+      "eval_steps_per_second": 0.885,
+      "step": 1715
+    },
+    {
+      "epoch": 245.71,
+      "learning_rate": 1.6342857142857146e-05,
+      "loss": 0.3871,
+      "step": 1720
+    },
+    {
+      "epoch": 246.0,
+      "eval_accuracy": 0.7538461538461538,
+      "eval_loss": 1.3596566915512085,
+      "eval_runtime": 2.3275,
+      "eval_samples_per_second": 55.853,
+      "eval_steps_per_second": 0.859,
+      "step": 1722
+    },
+    {
+      "epoch": 247.0,
+      "eval_accuracy": 0.7692307692307693,
+      "eval_loss": 1.346314549446106,
+      "eval_runtime": 2.3219,
+      "eval_samples_per_second": 55.989,
+      "eval_steps_per_second": 0.861,
+      "step": 1729
+    },
+    {
+      "epoch": 247.14,
+      "learning_rate": 1.622857142857143e-05,
+      "loss": 0.3679,
+      "step": 1730
+    },
+    {
+      "epoch": 248.0,
+      "eval_accuracy": 0.7615384615384615,
+      "eval_loss": 1.3439607620239258,
+      "eval_runtime": 2.249,
+      "eval_samples_per_second": 57.803,
+      "eval_steps_per_second": 0.889,
+      "step": 1736
+    },
+    {
+      "epoch": 248.57,
+      "learning_rate": 1.6114285714285715e-05,
+      "loss": 0.3788,
+      "step": 1740
+    },
+    {
+      "epoch": 249.0,
+      "eval_accuracy": 0.7692307692307693,
+      "eval_loss": 1.3646103143692017,
+      "eval_runtime": 2.1853,
+      "eval_samples_per_second": 59.489,
+      "eval_steps_per_second": 0.915,
+      "step": 1743
+    },
+    {
+      "epoch": 250.0,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.379,
+      "step": 1750
+    },
+    {
+      "epoch": 250.0,
+      "eval_accuracy": 0.7538461538461538,
+      "eval_loss": 1.3682621717453003,
+      "eval_runtime": 2.2333,
+      "eval_samples_per_second": 58.209,
+      "eval_steps_per_second": 0.896,
+      "step": 1750
+    },
+    {
+      "epoch": 250.0,
+      "step": 1750,
+      "total_flos": 1.007847313514496e+19,
+      "train_loss": 0.09994067628043038,
+      "train_runtime": 2169.5998,
+      "train_samples_per_second": 59.919,
+      "train_steps_per_second": 0.807
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1400,
+  "max_steps": 1750,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 200,
+  "num_train_epochs": 250,
   "save_steps": 500,
-  "total_flos": 8.062778508115968e+18,
+  "total_flos": 1.007847313514496e+19,
   "train_batch_size": 80,
   "trial_name": null,
   "trial_params": null