ChrisGuarino/yummy_model

README.md

@@ -17,7 +17,7 @@ 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 an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0138
+- Loss: 0.0137
 - Accuracy: 1.0
 
 ## Model description
@@ -49,15 +49,15 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.5106        | 1.0   | 13   | 0.0975          | 1.0      |
-| 0.0781        | 2.0   | 26   | 0.0292          | 1.0      |
-| 0.035         | 3.0   | 39   | 0.0159          | 1.0      |
-| 0.0129        | 4.0   | 52   | 0.0138          | 1.0      |
+| 0.4194        | 1.0   | 13   | 0.0737          | 1.0      |
+| 0.063         | 2.0   | 26   | 0.0266          | 1.0      |
+| 0.051         | 3.0   | 39   | 0.0151          | 1.0      |
+| 0.014         | 4.0   | 52   | 0.0137          | 1.0      |
 
 
 ### Framework versions
 
 - Transformers 4.37.1
-- Pytorch 2.1.2
+- Pytorch 2.1.0.post103
 - Datasets 2.16.1
 - Tokenizers 0.15.1

all_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 4.0,
-    "train_loss": 0.12617188778061134,
-    "train_runtime": 693.3707,
-    "train_samples_per_second": 1.194,
-    "train_steps_per_second": 0.075
+    "train_loss": 0.11166981543199374,
+    "train_runtime": 294.988,
+    "train_samples_per_second": 2.807,
+    "train_steps_per_second": 0.176
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48c188ef4b5810780e2aa604cb71945b6fd7d98fa5c83de83fa11952ff2ae6ae
+oid sha256:7c63a80ea478d192a254c72090c1d314539ba1b3014c9a59bbe9e97f3e5c924d
 size 343223968

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 4.0,
-    "train_loss": 0.12617188778061134,
-    "train_runtime": 693.3707,
-    "train_samples_per_second": 1.194,
-    "train_steps_per_second": 0.075
+    "train_loss": 0.11166981543199374,
+    "train_runtime": 294.988,
+    "train_samples_per_second": 2.807,
+    "train_steps_per_second": 0.176
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.013783477246761322,
+  "best_metric": 0.013692905195057392,
   "best_model_checkpoint": "cat_ds/checkpoint-52",
   "epoch": 4.0,
   "eval_steps": 100,
@@ -11,77 +11,77 @@
     {
       "epoch": 0.77,
       "learning_rate": 0.00016153846153846155,
-      "loss": 0.5106,
+      "loss": 0.4194,
       "step": 10
     },
     {
       "epoch": 1.0,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.09747540950775146,
-      "eval_runtime": 10.6319,
-      "eval_samples_per_second": 2.257,
-      "eval_steps_per_second": 0.282,
+      "eval_loss": 0.07365512102842331,
+      "eval_runtime": 5.5846,
+      "eval_samples_per_second": 4.298,
+      "eval_steps_per_second": 0.537,
       "step": 13
     },
     {
       "epoch": 1.54,
       "learning_rate": 0.0001230769230769231,
-      "loss": 0.0781,
+      "loss": 0.063,
       "step": 20
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.02915300987660885,
-      "eval_runtime": 10.2096,
-      "eval_samples_per_second": 2.351,
-      "eval_steps_per_second": 0.294,
+      "eval_loss": 0.026600712910294533,
+      "eval_runtime": 5.1625,
+      "eval_samples_per_second": 4.649,
+      "eval_steps_per_second": 0.581,
       "step": 26
     },
     {
       "epoch": 2.31,
       "learning_rate": 8.461538461538461e-05,
-      "loss": 0.035,
+      "loss": 0.051,
       "step": 30
     },
     {
       "epoch": 3.0,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.015924831852316856,
-      "eval_runtime": 10.3279,
-      "eval_samples_per_second": 2.324,
-      "eval_steps_per_second": 0.29,
+      "eval_loss": 0.015066702850162983,
+      "eval_runtime": 4.9529,
+      "eval_samples_per_second": 4.846,
+      "eval_steps_per_second": 0.606,
       "step": 39
     },
     {
       "epoch": 3.08,
       "learning_rate": 4.615384615384616e-05,
-      "loss": 0.0171,
+      "loss": 0.0308,
       "step": 40
     },
     {
       "epoch": 3.85,
       "learning_rate": 7.692307692307694e-06,
-      "loss": 0.0129,
+      "loss": 0.014,
       "step": 50
     },
     {
       "epoch": 4.0,
       "eval_accuracy": 1.0,
-      "eval_loss": 0.013783477246761322,
-      "eval_runtime": 10.0744,
-      "eval_samples_per_second": 2.382,
-      "eval_steps_per_second": 0.298,
+      "eval_loss": 0.013692905195057392,
+      "eval_runtime": 4.8268,
+      "eval_samples_per_second": 4.972,
+      "eval_steps_per_second": 0.622,
       "step": 52
     },
     {
       "epoch": 4.0,
       "step": 52,
       "total_flos": 6.416336740088218e+16,
-      "train_loss": 0.12617188778061134,
-      "train_runtime": 693.3707,
-      "train_samples_per_second": 1.194,
-      "train_steps_per_second": 0.075
+      "train_loss": 0.11166981543199374,
+      "train_runtime": 294.988,
+      "train_samples_per_second": 2.807,
+      "train_steps_per_second": 0.176
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df755787eb5b8231df295a90163694f1a3182a8c5007401d2c7fc797e1c039bd
+oid sha256:524ce2ef9ca1e27cc37ea90486b3f0499f280abaa57ede2315ab5c908badf848
 size 4664