🍻 cheers

README.md

@@ -2,6 +2,7 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -15,7 +16,7 @@ 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: 0.0221
 - Accuracy: 0.9925

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 0.9924812030075187,
-    "eval_loss": 0.03386877477169037,
-    "eval_runtime": 1.7511,
-    "eval_samples_per_second": 75.95,
-    "eval_steps_per_second": 9.708,
+    "eval_loss": 0.022105108946561813,
+    "eval_runtime": 1.7561,
+    "eval_samples_per_second": 75.737,
+    "eval_steps_per_second": 9.681,
     "total_flos": 3.205097416476426e+17,
-    "train_loss": 0.1224416760297922,
-    "train_runtime": 70.5477,
-    "train_samples_per_second": 58.627,
-    "train_steps_per_second": 3.685
+    "train_loss": 0.11380191872326227,
+    "train_runtime": 79.0957,
+    "train_samples_per_second": 52.291,
+    "train_steps_per_second": 3.287
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "eval_accuracy": 0.9924812030075187,
-    "eval_loss": 0.03386877477169037,
-    "eval_runtime": 1.7511,
-    "eval_samples_per_second": 75.95,
-    "eval_steps_per_second": 9.708
+    "eval_loss": 0.022105108946561813,
+    "eval_runtime": 1.7561,
+    "eval_samples_per_second": 75.737,
+    "eval_steps_per_second": 9.681
 }

runs/Apr16_05-18-40_ip-172-16-49-2.ec2.internal/events.out.tfevents.1713244837.ip-172-16-49-2.ec2.internal.28494.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f14b913200f938c06ffa66d716e53d9a82723e67b0dbe44a2e10f227b3b1b1
+size 411

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.0,
     "total_flos": 3.205097416476426e+17,
-    "train_loss": 0.1224416760297922,
-    "train_runtime": 70.5477,
-    "train_samples_per_second": 58.627,
-    "train_steps_per_second": 3.685
+    "train_loss": 0.11380191872326227,
+    "train_runtime": 79.0957,
+    "train_samples_per_second": 52.291,
+    "train_steps_per_second": 3.287
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.03386877477169037,
+  "best_metric": 0.022105108946561813,
   "best_model_checkpoint": "./vit-base-beans/checkpoint-200",
   "epoch": 4.0,
   "eval_steps": 100,
@@ -10,212 +10,212 @@
   "log_history": [
     {
       "epoch": 0.15,
-      "grad_norm": 2.295685052871704,
+      "grad_norm": 1.248571515083313,
       "learning_rate": 0.00019230769230769233,
-      "loss": 0.8646,
+      "loss": 0.724,
       "step": 10
     },
     {
       "epoch": 0.31,
-      "grad_norm": 1.1776849031448364,
+      "grad_norm": 2.3788352012634277,
       "learning_rate": 0.00018461538461538463,
-      "loss": 0.3374,
+      "loss": 0.2693,
       "step": 20
     },
     {
       "epoch": 0.46,
-      "grad_norm": 0.9071102738380432,
+      "grad_norm": 3.0690412521362305,
       "learning_rate": 0.00017692307692307693,
-      "loss": 0.2223,
+      "loss": 0.2057,
       "step": 30
     },
     {
       "epoch": 0.62,
-      "grad_norm": 0.580019474029541,
+      "grad_norm": 5.163357257843018,
       "learning_rate": 0.00016923076923076923,
-      "loss": 0.2125,
+      "loss": 0.2455,
       "step": 40
     },
     {
       "epoch": 0.77,
-      "grad_norm": 9.19766902923584,
+      "grad_norm": 1.3465059995651245,
       "learning_rate": 0.00016153846153846155,
-      "loss": 0.1555,
+      "loss": 0.13,
       "step": 50
     },
     {
       "epoch": 0.92,
-      "grad_norm": 2.0074708461761475,
+      "grad_norm": 1.7656354904174805,
       "learning_rate": 0.00015384615384615385,
-      "loss": 0.2388,
+      "loss": 0.2854,
       "step": 60
     },
     {
       "epoch": 1.08,
-      "grad_norm": 0.7031182050704956,
+      "grad_norm": 3.6763484477996826,
       "learning_rate": 0.00014615384615384615,
-      "loss": 0.1481,
+      "loss": 0.1867,
       "step": 70
     },
     {
       "epoch": 1.23,
-      "grad_norm": 6.785604953765869,
+      "grad_norm": 0.21904461085796356,
       "learning_rate": 0.00013846153846153847,
-      "loss": 0.1322,
+      "loss": 0.132,
       "step": 80
     },
     {
       "epoch": 1.38,
-      "grad_norm": 0.13774830102920532,
+      "grad_norm": 0.25529107451438904,
       "learning_rate": 0.00013076923076923077,
-      "loss": 0.0722,
+      "loss": 0.0762,
       "step": 90
     },
     {
       "epoch": 1.54,
-      "grad_norm": 0.8483244776725769,
+      "grad_norm": 1.4750274419784546,
       "learning_rate": 0.0001230769230769231,
-      "loss": 0.0517,
+      "loss": 0.0717,
       "step": 100
     },
     {
       "epoch": 1.54,
-      "eval_accuracy": 0.9849624060150376,
-      "eval_loss": 0.05896018445491791,
-      "eval_runtime": 1.8056,
-      "eval_samples_per_second": 73.661,
-      "eval_steps_per_second": 9.415,
+      "eval_accuracy": 1.0,
+      "eval_loss": 0.03406519070267677,
+      "eval_runtime": 1.8018,
+      "eval_samples_per_second": 73.813,
+      "eval_steps_per_second": 9.435,
       "step": 100
     },
     {
       "epoch": 1.69,
-      "grad_norm": 0.10988904535770416,
+      "grad_norm": 1.6858314275741577,
       "learning_rate": 0.00011538461538461538,
-      "loss": 0.0433,
+      "loss": 0.1123,
       "step": 110
     },
     {
       "epoch": 1.85,
-      "grad_norm": 0.3253529369831085,
-      "learning_rate": 0.00010846153846153846,
-      "loss": 0.1515,
+      "grad_norm": 2.8304824829101562,
+      "learning_rate": 0.0001076923076923077,
+      "loss": 0.1281,
       "step": 120
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.0863533690571785,
-      "learning_rate": 0.00010076923076923077,
-      "loss": 0.1029,
+      "grad_norm": 0.1025494933128357,
+      "learning_rate": 0.0001,
+      "loss": 0.0345,
       "step": 130
     },
     {
       "epoch": 2.15,
-      "grad_norm": 0.2501890957355499,
-      "learning_rate": 9.307692307692309e-05,
-      "loss": 0.071,
+      "grad_norm": 0.08757635951042175,
+      "learning_rate": 9.230769230769232e-05,
+      "loss": 0.0815,
       "step": 140
     },
     {
       "epoch": 2.31,
-      "grad_norm": 0.09559178352355957,
-      "learning_rate": 8.538461538461538e-05,
-      "loss": 0.0328,
+      "grad_norm": 4.281369686126709,
+      "learning_rate": 8.461538461538461e-05,
+      "loss": 0.0501,
       "step": 150
     },
     {
       "epoch": 2.46,
-      "grad_norm": 0.08136636763811111,
-      "learning_rate": 7.76923076923077e-05,
-      "loss": 0.0154,
+      "grad_norm": 0.11551445722579956,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 0.0401,
       "step": 160
     },
     {
       "epoch": 2.62,
-      "grad_norm": 1.6561012268066406,
-      "learning_rate": 7e-05,
-      "loss": 0.0145,
+      "grad_norm": 2.2672688961029053,
+      "learning_rate": 6.923076923076924e-05,
+      "loss": 0.0211,
       "step": 170
     },
     {
       "epoch": 2.77,
-      "grad_norm": 9.944978713989258,
-      "learning_rate": 6.23076923076923e-05,
-      "loss": 0.0785,
+      "grad_norm": 0.12683047354221344,
+      "learning_rate": 6.153846153846155e-05,
+      "loss": 0.0387,
       "step": 180
     },
     {
       "epoch": 2.92,
-      "grad_norm": 0.1309250295162201,
-      "learning_rate": 5.461538461538461e-05,
-      "loss": 0.0327,
+      "grad_norm": 2.012118339538574,
+      "learning_rate": 5.384615384615385e-05,
+      "loss": 0.0165,
       "step": 190
     },
     {
       "epoch": 3.08,
-      "grad_norm": 0.0702584758400917,
-      "learning_rate": 4.692307692307693e-05,
-      "loss": 0.0723,
+      "grad_norm": 0.06524123251438141,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.038,
       "step": 200
     },
     {
       "epoch": 3.08,
       "eval_accuracy": 0.9924812030075187,
-      "eval_loss": 0.03386877477169037,
-      "eval_runtime": 1.7639,
-      "eval_samples_per_second": 75.402,
-      "eval_steps_per_second": 9.638,
+      "eval_loss": 0.022105108946561813,
+      "eval_runtime": 1.7507,
+      "eval_samples_per_second": 75.968,
+      "eval_steps_per_second": 9.71,
       "step": 200
     },
     {
       "epoch": 3.23,
-      "grad_norm": 0.05829323083162308,
-      "learning_rate": 3.923076923076923e-05,
-      "loss": 0.0117,
+      "grad_norm": 0.06961577385663986,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 0.0139,
       "step": 210
     },
     {
       "epoch": 3.38,
-      "grad_norm": 0.06120636686682701,
-      "learning_rate": 3.153846153846154e-05,
-      "loss": 0.0119,
+      "grad_norm": 0.0649501383304596,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 0.0117,
       "step": 220
     },
     {
       "epoch": 3.54,
-      "grad_norm": 0.06219624727964401,
-      "learning_rate": 2.384615384615385e-05,
-      "loss": 0.0519,
+      "grad_norm": 0.06359098851680756,
+      "learning_rate": 2.307692307692308e-05,
+      "loss": 0.0123,
       "step": 230
     },
     {
       "epoch": 3.69,
-      "grad_norm": 0.9760288596153259,
-      "learning_rate": 1.6153846153846154e-05,
-      "loss": 0.0174,
+      "grad_norm": 0.07035394012928009,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.0111,
       "step": 240
     },
     {
       "epoch": 3.85,
-      "grad_norm": 0.06477300822734833,
-      "learning_rate": 8.461538461538462e-06,
-      "loss": 0.0116,
+      "grad_norm": 0.07381828874349594,
+      "learning_rate": 7.692307692307694e-06,
+      "loss": 0.0113,
       "step": 250
     },
     {
       "epoch": 4.0,
-      "grad_norm": 0.05689156800508499,
-      "learning_rate": 7.692307692307694e-07,
-      "loss": 0.0287,
+      "grad_norm": 0.05646485462784767,
+      "learning_rate": 0.0,
+      "loss": 0.0112,
       "step": 260
     },
     {
       "epoch": 4.0,
       "step": 260,
       "total_flos": 3.205097416476426e+17,
-      "train_loss": 0.1224416760297922,
-      "train_runtime": 70.5477,
-      "train_samples_per_second": 58.627,
-      "train_steps_per_second": 3.685
+      "train_loss": 0.11380191872326227,
+      "train_runtime": 79.0957,
+      "train_samples_per_second": 52.291,
+      "train_steps_per_second": 3.287
     }
   ],
   "logging_steps": 10,