End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0949
+- Loss: 0.1355
 
 ## Model description
 
@@ -49,11 +49,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 0.84  | 4    | 0.1084          |
-| No log        | 1.89  | 9    | 0.0994          |
-| 0.0064        | 2.95  | 14   | 0.1109          |
-| 0.0064        | 4.0   | 19   | 0.0949          |
-| 0.0594        | 4.21  | 20   | 0.0992          |
+| No log        | 0.84  | 4    | 0.6557          |
+| No log        | 1.89  | 9    | 0.1355          |
+| 0.0289        | 2.95  | 14   | 0.2163          |
+| 0.0289        | 4.0   | 19   | 0.1560          |
+| 0.0616        | 4.21  | 20   | 0.1556          |
 
 
 ### Framework versions

all_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 4.21,
-    "eval_loss": 0.09485718607902527,
-    "eval_runtime": 2.2406,
-    "eval_samples_per_second": 58.913,
-    "eval_steps_per_second": 1.339,
+    "eval_loss": 0.1355326622724533,
+    "eval_runtime": 2.2928,
+    "eval_samples_per_second": 57.572,
+    "eval_steps_per_second": 1.308,
     "total_flos": 1.2713250126082867e+17,
-    "train_loss": 0.03291104771196842,
-    "train_runtime": 113.6566,
-    "train_samples_per_second": 51.911,
-    "train_steps_per_second": 0.176
+    "train_loss": 0.04524529278278351,
+    "train_runtime": 114.2042,
+    "train_samples_per_second": 51.662,
+    "train_steps_per_second": 0.175
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 4.21,
-    "eval_loss": 0.09485718607902527,
-    "eval_runtime": 2.2406,
-    "eval_samples_per_second": 58.913,
-    "eval_steps_per_second": 1.339
+    "eval_loss": 0.1355326622724533,
+    "eval_runtime": 2.2928,
+    "eval_samples_per_second": 57.572,
+    "eval_steps_per_second": 1.308
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e9ffcaa5e45c4cc241ef9b0880f7ec96d36e1e368f732afc02666f0a5a311a4
+oid sha256:6015446eefc0b825750f160d47825ece7ec95ec20cd49b985d526e5633dfeb6f
 size 113412768

runs/Apr21_17-38-15_51d30877b6e2/events.out.tfevents.1713721096.51d30877b6e2.34.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f546fa98badbc34e21070094589ca3e3fa57479f46adc606c9006e7e4967bcd
+size 76237

runs/Apr21_17-38-15_51d30877b6e2/events.out.tfevents.1713721213.51d30877b6e2.34.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8bf345f3bb8bcb748c3156f2913ed67adb5f9d8a5ef0f9d870d31f85cf2ac2
+size 354

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 4.21,
     "total_flos": 1.2713250126082867e+17,
-    "train_loss": 0.03291104771196842,
-    "train_runtime": 113.6566,
-    "train_samples_per_second": 51.911,
-    "train_steps_per_second": 0.176
+    "train_loss": 0.04524529278278351,
+    "train_runtime": 114.2042,
+    "train_samples_per_second": 51.662,
+    "train_steps_per_second": 0.175
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.09485718607902527,
-  "best_model_checkpoint": "microsoft/swin-tiny-patch4-window7-224/checkpoint-19",
+  "best_metric": 0.1355326622724533,
+  "best_model_checkpoint": "microsoft/swin-tiny-patch4-window7-224/checkpoint-9",
   "epoch": 4.2105263157894735,
   "eval_steps": 500,
   "global_step": 20,
@@ -10,66 +10,66 @@
   "log_history": [
     {
       "epoch": 0.84,
-      "eval_loss": 0.10838964581489563,
-      "eval_runtime": 2.1432,
-      "eval_samples_per_second": 61.591,
-      "eval_steps_per_second": 1.4,
+      "eval_loss": 0.6557008028030396,
+      "eval_runtime": 2.3009,
+      "eval_samples_per_second": 57.37,
+      "eval_steps_per_second": 1.304,
       "step": 4
     },
     {
       "epoch": 1.89,
-      "eval_loss": 0.0993674173951149,
-      "eval_runtime": 2.1471,
-      "eval_samples_per_second": 61.478,
-      "eval_steps_per_second": 1.397,
+      "eval_loss": 0.1355326622724533,
+      "eval_runtime": 2.1272,
+      "eval_samples_per_second": 62.052,
+      "eval_steps_per_second": 1.41,
       "step": 9
     },
     {
       "epoch": 2.11,
-      "grad_norm": 5.258437633514404,
+      "grad_norm": 11.091564178466797,
       "learning_rate": 2.777777777777778e-05,
-      "loss": 0.0064,
+      "loss": 0.0289,
       "step": 10
     },
     {
       "epoch": 2.95,
-      "eval_loss": 0.11093668639659882,
-      "eval_runtime": 2.1002,
-      "eval_samples_per_second": 62.851,
-      "eval_steps_per_second": 1.428,
+      "eval_loss": 0.21629740297794342,
+      "eval_runtime": 2.0797,
+      "eval_samples_per_second": 63.472,
+      "eval_steps_per_second": 1.443,
       "step": 14
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.09485718607902527,
-      "eval_runtime": 2.1285,
-      "eval_samples_per_second": 62.014,
-      "eval_steps_per_second": 1.409,
+      "eval_loss": 0.1559712290763855,
+      "eval_runtime": 2.1584,
+      "eval_samples_per_second": 61.156,
+      "eval_steps_per_second": 1.39,
       "step": 19
     },
     {
       "epoch": 4.21,
-      "grad_norm": 12.606084823608398,
+      "grad_norm": 14.637483596801758,
       "learning_rate": 0.0,
-      "loss": 0.0594,
+      "loss": 0.0616,
       "step": 20
     },
     {
       "epoch": 4.21,
-      "eval_loss": 0.09918802976608276,
-      "eval_runtime": 2.1364,
-      "eval_samples_per_second": 61.786,
-      "eval_steps_per_second": 1.404,
+      "eval_loss": 0.15557000041007996,
+      "eval_runtime": 2.0834,
+      "eval_samples_per_second": 63.359,
+      "eval_steps_per_second": 1.44,
       "step": 20
     },
     {
       "epoch": 4.21,
       "step": 20,
       "total_flos": 1.2713250126082867e+17,
-      "train_loss": 0.03291104771196842,
-      "train_runtime": 113.6566,
-      "train_samples_per_second": 51.911,
-      "train_steps_per_second": 0.176
+      "train_loss": 0.04524529278278351,
+      "train_runtime": 114.2042,
+      "train_samples_per_second": 51.662,
+      "train_steps_per_second": 0.175
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4136ad41440be17e9854998fa3ee1ff6230f98cf3848dc429e89c05f04c4b4c
+oid sha256:955fbccfb056fd45980d796c9bd392d21f7f68a03856b0e6d69e15cf1c7c4bd1
 size 4984