Training in progress, step 500

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.0014388489208633094,
+    "eval_loss": 9.965200424194336,
+    "eval_runtime": 19.8708,
+    "eval_samples_per_second": 69.952,
+    "eval_steps_per_second": 8.757,
+    "total_flos": 1.8890449427391898e+18,
+    "train_loss": 3.100843106976088,
+    "train_runtime": 1215.6267,
+    "train_samples_per_second": 20.027,
+    "train_steps_per_second": 2.505
+}

config.json

@@ -1,27 +1,13 @@
 {
-  "_name_or_path": "microsoft/resnet-50",
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
   "architectures": [
     "ViTForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "depths": [
-    3,
-    4,
-    6,
-    3
-  ],
-  "downsample_in_first_stage": false,
-  "embedding_size": 64,
   "encoder_stride": 16,
-  "hidden_act": "relu",
+  "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
-  "hidden_sizes": [
-    256,
-    512,
-    1024,
-    2048
-  ],
   "id2label": {
     "0": "Porygon",
     "1": "Goldeen",
@@ -330,7 +316,6 @@
     "Zubat": "58"
   },
   "layer_norm_eps": 1e-12,
-  "layer_type": "bottleneck",
   "model_type": "vit",
   "num_attention_heads": 12,
   "num_channels": 3,

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.0014388489208633094,
+    "eval_loss": 9.965200424194336,
+    "eval_runtime": 19.8708,
+    "eval_samples_per_second": 69.952,
+    "eval_steps_per_second": 8.757
+}

preprocessor_config.json

@@ -1,21 +1,19 @@
 {
-  "crop_pct": 0.875,
   "do_normalize": true,
   "do_rescale": true,
   "do_resize": true,
-  "feature_extractor_type": "ConvNextFeatureExtractor",
   "image_mean": [
-    0.485,
-    0.456,
-    0.406
+    0.5,
+    0.5,
+    0.5
   ],
   "image_processor_type": "ViTFeatureExtractor",
   "image_std": [
-    0.229,
-    0.224,
-    0.225
+    0.5,
+    0.5,
+    0.5
   ],
-  "resample": 3,
+  "resample": 2,
   "rescale_factor": 0.00392156862745098,
   "size": {
     "height": 224,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d8ecb46ae676d3a066d5f1bc10ba2168a39da61ac50f84c6baa0007db5fd35
+oid sha256:5ff6b4d036ae85dc3856cb9a06ed9bea056d3916563caa966d4b9cc24d8db950
 size 343723949

runs/Apr25_03-19-25_7626d6fa6bff/events.out.tfevents.1682394094.7626d6fa6bff.149.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:293717aea2ee4d8e4b784677f00974b40fecf2ed07539844b93e5d052ab30ea6
+size 411

runs/Apr25_03-47-00_7626d6fa6bff/1682394456.302469/events.out.tfevents.1682394456.7626d6fa6bff.149.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e216263065f0e8355953102ef7b50fa721f179fa9d99b23ad3599ce648cd6aae
+size 5951

runs/Apr25_03-47-00_7626d6fa6bff/events.out.tfevents.1682394456.7626d6fa6bff.149.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f98926c4909215c5e62eccd6307d51d747ba6b4c1475654f0eda142010f7057
+size 10946

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1.8890449427391898e+18,
+    "train_loss": 3.100843106976088,
+    "train_runtime": 1215.6267,
+    "train_samples_per_second": 20.027,
+    "train_steps_per_second": 2.505
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4052e03a2d1c4f70c186b8c6e8a0c9628c17d23e0318274a9d7a51c14db9e9ec
+oid sha256:3bf6a82183b97db3b1fb2a47966a3e237008df2b8458632237e02eaa60399d3b
 size 3643