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
 metrics:
 - accuracy
@@ -15,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-beans
 
-This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
+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 beans dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.1031
 - Accuracy: 0.9699

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.9774436090225563,
-    "eval_loss": 0.0845332145690918,
-    "eval_runtime": 10.101,
-    "eval_samples_per_second": 13.167,
-    "eval_steps_per_second": 1.683,
-    "train_loss": 0.22195113337956943,
-    "train_runtime": 1469.4325,
-    "train_samples_per_second": 3.518,
-    "train_steps_per_second": 0.442
+    "eval_accuracy": 0.9699248120300752,
+    "eval_loss": 0.10305669158697128,
+    "eval_runtime": 4.1012,
+    "eval_samples_per_second": 32.429,
+    "eval_steps_per_second": 4.145,
+    "train_loss": 0.2459418410521287,
+    "train_runtime": 635.7149,
+    "train_samples_per_second": 8.133,
+    "train_steps_per_second": 1.022
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "eval_accuracy": 0.9774436090225563,
-    "eval_loss": 0.0845332145690918,
-    "eval_runtime": 10.101,
-    "eval_samples_per_second": 13.167,
-    "eval_steps_per_second": 1.683
+    "eval_accuracy": 0.9699248120300752,
+    "eval_loss": 0.10305669158697128,
+    "eval_runtime": 4.1012,
+    "eval_samples_per_second": 32.429,
+    "eval_steps_per_second": 4.145
 }

runs/Jan23_01-16-58_VM-231-254-tencentos/events.out.tfevents.1705944735.VM-231-254-tencentos.10920.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08efb62acbe18779e312c23c1798decbf47ad67855ffe74b6aecf9fa7d124ecf
+size 411

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 5.0,
-    "train_loss": 0.22195113337956943,
-    "train_runtime": 1469.4325,
-    "train_samples_per_second": 3.518,
-    "train_steps_per_second": 0.442
+    "train_loss": 0.2459418410521287,
+    "train_runtime": 635.7149,
+    "train_samples_per_second": 8.133,
+    "train_steps_per_second": 1.022
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.0845332145690918,
+  "best_metric": 0.10305669158697128,
   "best_model_checkpoint": "./beans_outputs/checkpoint-650",
   "epoch": 5.0,
   "eval_steps": 500,
@@ -11,446 +11,446 @@
     {
       "epoch": 0.08,
       "learning_rate": 1.9692307692307696e-05,
-      "loss": 1.0085,
+      "loss": 1.0642,
       "step": 10
     },
     {
       "epoch": 0.15,
       "learning_rate": 1.9384615384615386e-05,
-      "loss": 0.9842,
+      "loss": 0.9643,
       "step": 20
     },
     {
       "epoch": 0.23,
       "learning_rate": 1.907692307692308e-05,
-      "loss": 0.8397,
+      "loss": 0.87,
       "step": 30
     },
     {
       "epoch": 0.31,
       "learning_rate": 1.876923076923077e-05,
-      "loss": 0.7043,
+      "loss": 0.7859,
       "step": 40
     },
     {
       "epoch": 0.38,
       "learning_rate": 1.8461538461538465e-05,
-      "loss": 0.6544,
+      "loss": 0.784,
       "step": 50
     },
     {
       "epoch": 0.46,
       "learning_rate": 1.8153846153846155e-05,
-      "loss": 0.5941,
+      "loss": 0.6837,
       "step": 60
     },
     {
       "epoch": 0.54,
       "learning_rate": 1.784615384615385e-05,
-      "loss": 0.512,
+      "loss": 0.6064,
       "step": 70
     },
     {
       "epoch": 0.62,
       "learning_rate": 1.753846153846154e-05,
-      "loss": 0.4054,
+      "loss": 0.5462,
       "step": 80
     },
     {
       "epoch": 0.69,
       "learning_rate": 1.7230769230769234e-05,
-      "loss": 0.3482,
+      "loss": 0.495,
       "step": 90
     },
     {
       "epoch": 0.77,
       "learning_rate": 1.6923076923076924e-05,
-      "loss": 0.3136,
+      "loss": 0.4116,
       "step": 100
     },
     {
       "epoch": 0.85,
       "learning_rate": 1.6615384615384618e-05,
-      "loss": 0.3272,
+      "loss": 0.3804,
       "step": 110
     },
     {
       "epoch": 0.92,
       "learning_rate": 1.630769230769231e-05,
-      "loss": 0.2494,
+      "loss": 0.2978,
       "step": 120
     },
     {
       "epoch": 1.0,
       "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.2975,
+      "loss": 0.2939,
       "step": 130
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 0.9699248120300752,
-      "eval_loss": 0.214076429605484,
-      "eval_runtime": 10.0362,
-      "eval_samples_per_second": 13.252,
-      "eval_steps_per_second": 1.694,
+      "eval_loss": 0.25765204429626465,
+      "eval_runtime": 7.4965,
+      "eval_samples_per_second": 17.742,
+      "eval_steps_per_second": 2.268,
       "step": 130
     },
     {
       "epoch": 1.08,
       "learning_rate": 1.5692307692307693e-05,
-      "loss": 0.2616,
+      "loss": 0.252,
       "step": 140
     },
     {
       "epoch": 1.15,
       "learning_rate": 1.5384615384615387e-05,
-      "loss": 0.2538,
+      "loss": 0.2343,
       "step": 150
     },
     {
       "epoch": 1.23,
       "learning_rate": 1.5076923076923078e-05,
-      "loss": 0.206,
+      "loss": 0.244,
       "step": 160
     },
     {
       "epoch": 1.31,
       "learning_rate": 1.4769230769230772e-05,
-      "loss": 0.1474,
+      "loss": 0.2801,
       "step": 170
     },
     {
       "epoch": 1.38,
       "learning_rate": 1.4461538461538462e-05,
-      "loss": 0.1829,
+      "loss": 0.2289,
       "step": 180
     },
     {
       "epoch": 1.46,
       "learning_rate": 1.4153846153846156e-05,
-      "loss": 0.1971,
+      "loss": 0.15,
       "step": 190
     },
     {
       "epoch": 1.54,
       "learning_rate": 1.3846153846153847e-05,
-      "loss": 0.1447,
+      "loss": 0.1836,
       "step": 200
     },
     {
       "epoch": 1.62,
       "learning_rate": 1.353846153846154e-05,
-      "loss": 0.1431,
+      "loss": 0.1619,
       "step": 210
     },
     {
       "epoch": 1.69,
       "learning_rate": 1.3230769230769231e-05,
-      "loss": 0.1951,
+      "loss": 0.1807,
       "step": 220
     },
     {
       "epoch": 1.77,
       "learning_rate": 1.2923076923076925e-05,
-      "loss": 0.1733,
+      "loss": 0.2437,
       "step": 230
     },
     {
       "epoch": 1.85,
       "learning_rate": 1.2615384615384616e-05,
-      "loss": 0.1553,
+      "loss": 0.1846,
       "step": 240
     },
     {
       "epoch": 1.92,
       "learning_rate": 1.230769230769231e-05,
-      "loss": 0.2003,
+      "loss": 0.204,
       "step": 250
     },
     {
       "epoch": 2.0,
       "learning_rate": 1.2e-05,
-      "loss": 0.2145,
+      "loss": 0.1955,
       "step": 260
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.9699248120300752,
-      "eval_loss": 0.14527635276317596,
-      "eval_runtime": 10.1355,
-      "eval_samples_per_second": 13.122,
-      "eval_steps_per_second": 1.677,
+      "eval_accuracy": 0.9774436090225563,
+      "eval_loss": 0.12117066234350204,
+      "eval_runtime": 3.2409,
+      "eval_samples_per_second": 41.038,
+      "eval_steps_per_second": 5.245,
       "step": 260
     },
     {
       "epoch": 2.08,
       "learning_rate": 1.1692307692307694e-05,
-      "loss": 0.165,
+      "loss": 0.2005,
       "step": 270
     },
     {
       "epoch": 2.15,
       "learning_rate": 1.1384615384615385e-05,
-      "loss": 0.1718,
+      "loss": 0.204,
       "step": 280
     },
     {
       "epoch": 2.23,
       "learning_rate": 1.1076923076923079e-05,
-      "loss": 0.2084,
+      "loss": 0.1161,
       "step": 290
     },
     {
       "epoch": 2.31,
       "learning_rate": 1.076923076923077e-05,
-      "loss": 0.1401,
+      "loss": 0.1683,
       "step": 300
     },
     {
       "epoch": 2.38,
       "learning_rate": 1.0461538461538463e-05,
-      "loss": 0.1988,
+      "loss": 0.0973,
       "step": 310
     },
     {
       "epoch": 2.46,
       "learning_rate": 1.0153846153846154e-05,
-      "loss": 0.1873,
+      "loss": 0.1829,
       "step": 320
     },
     {
       "epoch": 2.54,
       "learning_rate": 9.846153846153848e-06,
-      "loss": 0.0985,
+      "loss": 0.0821,
       "step": 330
     },
     {
       "epoch": 2.62,
       "learning_rate": 9.53846153846154e-06,
-      "loss": 0.1586,
+      "loss": 0.1581,
       "step": 340
     },
     {
       "epoch": 2.69,
       "learning_rate": 9.230769230769232e-06,
-      "loss": 0.1068,
+      "loss": 0.1108,
       "step": 350
     },
     {
       "epoch": 2.77,
       "learning_rate": 8.923076923076925e-06,
-      "loss": 0.149,
+      "loss": 0.0781,
       "step": 360
     },
     {
       "epoch": 2.85,
       "learning_rate": 8.615384615384617e-06,
-      "loss": 0.1359,
+      "loss": 0.1254,
       "step": 370
     },
     {
       "epoch": 2.92,
       "learning_rate": 8.307692307692309e-06,
-      "loss": 0.1002,
+      "loss": 0.2467,
       "step": 380
     },
     {
       "epoch": 3.0,
       "learning_rate": 8.000000000000001e-06,
-      "loss": 0.202,
+      "loss": 0.2097,
       "step": 390
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 0.9699248120300752,
-      "eval_loss": 0.12530653178691864,
-      "eval_runtime": 10.4778,
-      "eval_samples_per_second": 12.694,
-      "eval_steps_per_second": 1.622,
+      "eval_loss": 0.10580819845199585,
+      "eval_runtime": 3.4978,
+      "eval_samples_per_second": 38.024,
+      "eval_steps_per_second": 4.86,
       "step": 390
     },
     {
       "epoch": 3.08,
       "learning_rate": 7.692307692307694e-06,
-      "loss": 0.1149,
+      "loss": 0.1117,
       "step": 400
     },
     {
       "epoch": 3.15,
       "learning_rate": 7.384615384615386e-06,
-      "loss": 0.1173,
+      "loss": 0.2338,
       "step": 410
     },
     {
       "epoch": 3.23,
       "learning_rate": 7.076923076923078e-06,
-      "loss": 0.0971,
+      "loss": 0.1288,
       "step": 420
     },
     {
       "epoch": 3.31,
       "learning_rate": 6.76923076923077e-06,
-      "loss": 0.1177,
+      "loss": 0.1391,
       "step": 430
     },
     {
       "epoch": 3.38,
       "learning_rate": 6.461538461538463e-06,
-      "loss": 0.1329,
+      "loss": 0.0704,
       "step": 440
     },
     {
       "epoch": 3.46,
       "learning_rate": 6.153846153846155e-06,
-      "loss": 0.0957,
+      "loss": 0.095,
       "step": 450
     },
     {
       "epoch": 3.54,
       "learning_rate": 5.846153846153847e-06,
-      "loss": 0.1204,
+      "loss": 0.1368,
       "step": 460
     },
     {
       "epoch": 3.62,
       "learning_rate": 5.538461538461539e-06,
-      "loss": 0.1482,
+      "loss": 0.1134,
       "step": 470
     },
     {
       "epoch": 3.69,
       "learning_rate": 5.230769230769232e-06,
-      "loss": 0.0967,
+      "loss": 0.0782,
       "step": 480
     },
     {
       "epoch": 3.77,
       "learning_rate": 4.923076923076924e-06,
-      "loss": 0.0745,
+      "loss": 0.1359,
       "step": 490
     },
     {
       "epoch": 3.85,
       "learning_rate": 4.615384615384616e-06,
-      "loss": 0.06,
+      "loss": 0.1233,
       "step": 500
     },
     {
       "epoch": 3.92,
       "learning_rate": 4.307692307692308e-06,
-      "loss": 0.1301,
+      "loss": 0.1643,
       "step": 510
     },
     {
       "epoch": 4.0,
       "learning_rate": 4.000000000000001e-06,
-      "loss": 0.0878,
+      "loss": 0.1102,
       "step": 520
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9774436090225563,
-      "eval_loss": 0.0966341495513916,
-      "eval_runtime": 10.1707,
-      "eval_samples_per_second": 13.077,
-      "eval_steps_per_second": 1.671,
+      "eval_accuracy": 0.9699248120300752,
+      "eval_loss": 0.11457930505275726,
+      "eval_runtime": 3.3129,
+      "eval_samples_per_second": 40.146,
+      "eval_steps_per_second": 5.131,
       "step": 520
     },
     {
       "epoch": 4.08,
       "learning_rate": 3.692307692307693e-06,
-      "loss": 0.1232,
+      "loss": 0.0823,
       "step": 530
     },
     {
       "epoch": 4.15,
       "learning_rate": 3.384615384615385e-06,
-      "loss": 0.0549,
+      "loss": 0.1432,
       "step": 540
     },
     {
       "epoch": 4.23,
       "learning_rate": 3.0769230769230774e-06,
-      "loss": 0.1781,
+      "loss": 0.072,
       "step": 550
     },
     {
       "epoch": 4.31,
       "learning_rate": 2.7692307692307697e-06,
-      "loss": 0.1129,
+      "loss": 0.0617,
       "step": 560
     },
     {
       "epoch": 4.38,
       "learning_rate": 2.461538461538462e-06,
-      "loss": 0.1065,
+      "loss": 0.0633,
       "step": 570
     },
     {
       "epoch": 4.46,
       "learning_rate": 2.153846153846154e-06,
-      "loss": 0.0777,
+      "loss": 0.1001,
       "step": 580
     },
     {
       "epoch": 4.54,
       "learning_rate": 1.8461538461538465e-06,
-      "loss": 0.0863,
+      "loss": 0.1575,
       "step": 590
     },
     {
       "epoch": 4.62,
       "learning_rate": 1.5384615384615387e-06,
-      "loss": 0.0634,
+      "loss": 0.0862,
       "step": 600
     },
     {
       "epoch": 4.69,
       "learning_rate": 1.230769230769231e-06,
-      "loss": 0.0839,
+      "loss": 0.1861,
       "step": 610
     },
     {
       "epoch": 4.77,
       "learning_rate": 9.230769230769232e-07,
-      "loss": 0.0866,
+      "loss": 0.0578,
       "step": 620
     },
     {
       "epoch": 4.85,
       "learning_rate": 6.153846153846155e-07,
-      "loss": 0.1012,
+      "loss": 0.1501,
       "step": 630
     },
     {
       "epoch": 4.92,
       "learning_rate": 3.0769230769230774e-07,
-      "loss": 0.1167,
+      "loss": 0.0968,
       "step": 640
     },
     {
       "epoch": 5.0,
       "learning_rate": 0.0,
-      "loss": 0.106,
+      "loss": 0.1813,
       "step": 650
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9774436090225563,
-      "eval_loss": 0.0845332145690918,
-      "eval_runtime": 10.1948,
-      "eval_samples_per_second": 13.046,
-      "eval_steps_per_second": 1.668,
+      "eval_accuracy": 0.9699248120300752,
+      "eval_loss": 0.10305669158697128,
+      "eval_runtime": 3.3514,
+      "eval_samples_per_second": 39.685,
+      "eval_steps_per_second": 5.072,
       "step": 650
     },
     {
       "epoch": 5.0,
       "step": 650,
       "total_flos": 4.006371770595533e+17,
-      "train_loss": 0.22195113337956943,
-      "train_runtime": 1469.4325,
-      "train_samples_per_second": 3.518,
-      "train_steps_per_second": 0.442
+      "train_loss": 0.2459418410521287,
+      "train_runtime": 635.7149,
+      "train_samples_per_second": 8.133,
+      "train_steps_per_second": 1.022
     }
   ],
   "logging_steps": 10,