Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 19.73,
-    "total_flos": 1.0467617957139087e+18,
-    "train_loss": 0.1206296275369823,
-    "train_runtime": 722.4002,
-    "train_samples_per_second": 18.937,
-    "train_steps_per_second": 0.055
+    "total_flos": 2.8684782950326272e+17,
+    "train_loss": 0.7573485970497131,
+    "train_runtime": 850.4827,
+    "train_samples_per_second": 16.085,
+    "train_steps_per_second": 0.047
 }

config.json

@@ -1,35 +1,32 @@
 {
-  "_name_or_path": "microsoft/resnet-50",
+  "_name_or_path": "google/vit-base-patch16-224",
   "architectures": [
-    "ResNetForImageClassification"
-  ],
-  "depths": [
-    3,
-    4,
-    6,
-    3
-  ],
-  "downsample_in_first_stage": false,
-  "embedding_size": 64,
-  "hidden_act": "relu",
-  "hidden_sizes": [
-    256,
-    512,
-    1024,
-    2048
+    "ViTForImageClassification"
   ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
   "id2label": {
     "0": "0",
     "1": "1"
   },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "0": "0",
     "1": "1"
   },
-  "layer_type": "bottleneck",
-  "model_type": "resnet",
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
   "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
   "problem_type": "single_label_classification",
+  "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.24.0"
 }

preprocessor_config.json

@@ -1,18 +1,17 @@
 {
-  "crop_pct": 0.875,
   "do_normalize": true,
   "do_resize": true,
-  "feature_extractor_type": "ConvNextFeatureExtractor",
+  "feature_extractor_type": "ViTFeatureExtractor",
   "image_mean": [
-    0.485,
-    0.456,
-    0.406
+    0.5,
+    0.5,
+    0.5
   ],
   "image_std": [
-    0.229,
-    0.224,
-    0.225
+    0.5,
+    0.5,
+    0.5
   ],
-  "resample": 3,
+  "resample": 2,
   "size": 224
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a78cc492ee7d6c6cd121fa0ee689ac6852a6fc5c01412cf1621cb5a8da16cf86
-size 94374989
+oid sha256:2efd549849ed3c43becc4b01cbcc3112c779811b9ad9efdd039b5dbcc2db006b
+size 343268717

runs/Jul11_19-19-38_teesta/events.out.tfevents.1689083389.teesta.13011.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f2ae96998169fbe766d8097fb107f225557e462071bc8aa05c988914e0f7cf5
-size 12816
+oid sha256:1f21c335504ce0f8563bfc513d1282ac9961bac25bfb574dba54ea7fb852575c
+size 13781

runs/Jul11_19-56-05_teesta/1689085573.8332648/events.out.tfevents.1689085573.teesta.24348.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a122b395fa00b3f48f953f2e59bc76dd9f8295b5be99432650d0e9d60631669
+size 5427

runs/Jul11_19-56-05_teesta/events.out.tfevents.1689085573.teesta.24348.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bbf2eaf56c6638509455ce905b087a447081c0215233e7a76dc1fb16c75faad
+size 4111

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 19.73,
-    "total_flos": 1.0467617957139087e+18,
-    "train_loss": 0.1206296275369823,
-    "train_runtime": 722.4002,
-    "train_samples_per_second": 18.937,
-    "train_steps_per_second": 0.055
+    "total_flos": 2.8684782950326272e+17,
+    "train_loss": 0.7573485970497131,
+    "train_runtime": 850.4827,
+    "train_samples_per_second": 16.085,
+    "train_steps_per_second": 0.047
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9722222222222222,
-  "best_model_checkpoint": "test/checkpoint-10",
+  "best_metric": 0.8055555555555556,
+  "best_model_checkpoint": "test/checkpoint-6",
   "epoch": 19.727272727272727,
   "global_step": 40,
   "is_hyper_param_search": false,
@@ -9,281 +9,281 @@
   "log_history": [
     {
       "epoch": 0.73,
-      "eval_accuracy": 0.6111111111111112,
-      "eval_f1": 0.5246913580246914,
-      "eval_loss": 0.6317432522773743,
-      "eval_precision": 0.6313131313131313,
-      "eval_recall": 0.6111111111111112,
-      "eval_runtime": 4.9562,
-      "eval_samples_per_second": 7.264,
-      "eval_steps_per_second": 0.202,
+      "eval_accuracy": 0.6388888888888888,
+      "eval_f1": 0.6477582846003898,
+      "eval_loss": 0.679732084274292,
+      "eval_precision": 0.6572420634920635,
+      "eval_recall": 0.6388888888888888,
+      "eval_runtime": 5.9427,
+      "eval_samples_per_second": 6.058,
+      "eval_steps_per_second": 0.168,
       "step": 2
     },
     {
       "epoch": 1.73,
       "eval_accuracy": 0.75,
-      "eval_f1": 0.7298136645962733,
-      "eval_loss": 0.5041863322257996,
-      "eval_precision": 0.78125,
+      "eval_f1": 0.6904761904761904,
+      "eval_loss": 0.6750033497810364,
+      "eval_precision": 0.6397058823529411,
       "eval_recall": 0.75,
-      "eval_runtime": 6.0833,
-      "eval_samples_per_second": 5.918,
-      "eval_steps_per_second": 0.164,
+      "eval_runtime": 4.9005,
+      "eval_samples_per_second": 7.346,
+      "eval_steps_per_second": 0.204,
       "step": 4
     },
     {
       "epoch": 2.73,
-      "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.8616574875426174,
-      "eval_loss": 0.2850046753883362,
-      "eval_precision": 0.8635416666666668,
-      "eval_recall": 0.8611111111111112,
-      "eval_runtime": 5.0775,
-      "eval_samples_per_second": 7.09,
-      "eval_steps_per_second": 0.197,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.6533546447753906,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.9351,
+      "eval_samples_per_second": 7.295,
+      "eval_steps_per_second": 0.203,
       "step": 6
     },
     {
       "epoch": 3.73,
-      "eval_accuracy": 0.9444444444444444,
-      "eval_f1": 0.9444444444444444,
-      "eval_loss": 0.1754457652568817,
-      "eval_precision": 0.9444444444444444,
-      "eval_recall": 0.9444444444444444,
-      "eval_runtime": 4.5876,
-      "eval_samples_per_second": 7.847,
-      "eval_steps_per_second": 0.218,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.6294739842414856,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.7154,
+      "eval_samples_per_second": 7.635,
+      "eval_steps_per_second": 0.212,
       "step": 8
     },
     {
       "epoch": 4.73,
       "learning_rate": 0.0001,
-      "loss": 0.4534,
+      "loss": 0.8452,
       "step": 10
     },
     {
       "epoch": 4.73,
-      "eval_accuracy": 0.9722222222222222,
-      "eval_f1": 0.9720662924351777,
-      "eval_loss": 0.16017672419548035,
-      "eval_precision": 0.9734848484848485,
-      "eval_recall": 0.9722222222222222,
-      "eval_runtime": 4.5324,
-      "eval_samples_per_second": 7.943,
-      "eval_steps_per_second": 0.221,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.6180709600448608,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 5.3103,
+      "eval_samples_per_second": 6.779,
+      "eval_steps_per_second": 0.188,
       "step": 10
     },
     {
       "epoch": 5.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9169944925255703,
-      "eval_loss": 0.15476307272911072,
-      "eval_precision": 0.9187500000000001,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 4.8524,
-      "eval_samples_per_second": 7.419,
-      "eval_steps_per_second": 0.206,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.6019383668899536,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.7577,
+      "eval_samples_per_second": 7.567,
+      "eval_steps_per_second": 0.21,
       "step": 12
     },
     {
       "epoch": 6.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9169944925255703,
-      "eval_loss": 0.17422601580619812,
-      "eval_precision": 0.9187500000000001,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 4.9424,
-      "eval_samples_per_second": 7.284,
-      "eval_steps_per_second": 0.202,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.6006457805633545,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.7756,
+      "eval_samples_per_second": 7.538,
+      "eval_steps_per_second": 0.209,
       "step": 14
     },
     {
       "epoch": 7.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9169944925255703,
-      "eval_loss": 0.17327123880386353,
-      "eval_precision": 0.9187500000000001,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 4.5548,
-      "eval_samples_per_second": 7.904,
-      "eval_steps_per_second": 0.22,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.584420919418335,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 5.7897,
+      "eval_samples_per_second": 6.218,
+      "eval_steps_per_second": 0.173,
       "step": 16
     },
     {
       "epoch": 8.73,
-      "eval_accuracy": 0.9722222222222222,
-      "eval_f1": 0.9720662924351777,
-      "eval_loss": 0.1823543906211853,
-      "eval_precision": 0.9734848484848485,
-      "eval_recall": 0.9722222222222222,
-      "eval_runtime": 5.5657,
-      "eval_samples_per_second": 6.468,
-      "eval_steps_per_second": 0.18,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5822530388832092,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.7388,
+      "eval_samples_per_second": 7.597,
+      "eval_steps_per_second": 0.211,
       "step": 18
     },
     {
       "epoch": 9.73,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 0.0241,
+      "loss": 0.7824,
       "step": 20
     },
     {
       "epoch": 9.73,
-      "eval_accuracy": 0.9722222222222222,
-      "eval_f1": 0.9720662924351777,
-      "eval_loss": 0.1839684247970581,
-      "eval_precision": 0.9734848484848485,
-      "eval_recall": 0.9722222222222222,
-      "eval_runtime": 4.9083,
-      "eval_samples_per_second": 7.334,
-      "eval_steps_per_second": 0.204,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5739169716835022,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.8104,
+      "eval_samples_per_second": 7.484,
+      "eval_steps_per_second": 0.208,
       "step": 20
     },
     {
       "epoch": 10.73,
-      "eval_accuracy": 0.9722222222222222,
-      "eval_f1": 0.9720662924351777,
-      "eval_loss": 0.1734018176794052,
-      "eval_precision": 0.9734848484848485,
-      "eval_recall": 0.9722222222222222,
-      "eval_runtime": 6.4832,
-      "eval_samples_per_second": 5.553,
-      "eval_steps_per_second": 0.154,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5697076916694641,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.6974,
+      "eval_samples_per_second": 7.664,
+      "eval_steps_per_second": 0.213,
       "step": 22
     },
     {
       "epoch": 11.73,
-      "eval_accuracy": 0.9722222222222222,
-      "eval_f1": 0.9720662924351777,
-      "eval_loss": 0.1677979975938797,
-      "eval_precision": 0.9734848484848485,
-      "eval_recall": 0.9722222222222222,
-      "eval_runtime": 4.5856,
-      "eval_samples_per_second": 7.851,
-      "eval_steps_per_second": 0.218,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5695454478263855,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.9353,
+      "eval_samples_per_second": 7.294,
+      "eval_steps_per_second": 0.203,
       "step": 24
     },
     {
       "epoch": 12.73,
-      "eval_accuracy": 0.9722222222222222,
-      "eval_f1": 0.9720662924351777,
-      "eval_loss": 0.17028245329856873,
-      "eval_precision": 0.9734848484848485,
-      "eval_recall": 0.9722222222222222,
-      "eval_runtime": 4.5474,
-      "eval_samples_per_second": 7.917,
-      "eval_steps_per_second": 0.22,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5626423954963684,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 5.8521,
+      "eval_samples_per_second": 6.152,
+      "eval_steps_per_second": 0.171,
       "step": 26
     },
     {
       "epoch": 13.73,
-      "eval_accuracy": 0.9444444444444444,
-      "eval_f1": 0.9444444444444444,
-      "eval_loss": 0.16881698369979858,
-      "eval_precision": 0.9444444444444444,
-      "eval_recall": 0.9444444444444444,
-      "eval_runtime": 4.8334,
-      "eval_samples_per_second": 7.448,
-      "eval_steps_per_second": 0.207,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5666201710700989,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 5.1217,
+      "eval_samples_per_second": 7.029,
+      "eval_steps_per_second": 0.195,
       "step": 28
     },
     {
       "epoch": 14.73,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.0034,
+      "loss": 0.7149,
       "step": 30
     },
     {
       "epoch": 14.73,
-      "eval_accuracy": 0.9444444444444444,
-      "eval_f1": 0.9444444444444444,
-      "eval_loss": 0.17170244455337524,
-      "eval_precision": 0.9444444444444444,
-      "eval_recall": 0.9444444444444444,
-      "eval_runtime": 4.5214,
-      "eval_samples_per_second": 7.962,
-      "eval_steps_per_second": 0.221,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5559208989143372,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 5.1084,
+      "eval_samples_per_second": 7.047,
+      "eval_steps_per_second": 0.196,
       "step": 30
     },
     {
       "epoch": 15.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9169944925255703,
-      "eval_loss": 0.1789499670267105,
-      "eval_precision": 0.9187500000000001,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 4.4892,
-      "eval_samples_per_second": 8.019,
-      "eval_steps_per_second": 0.223,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5556015372276306,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 6.0749,
+      "eval_samples_per_second": 5.926,
+      "eval_steps_per_second": 0.165,
       "step": 32
     },
     {
       "epoch": 16.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9169944925255703,
-      "eval_loss": 0.18086858093738556,
-      "eval_precision": 0.9187500000000001,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 5.0111,
-      "eval_samples_per_second": 7.184,
-      "eval_steps_per_second": 0.2,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5465428233146667,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.8659,
+      "eval_samples_per_second": 7.398,
+      "eval_steps_per_second": 0.206,
       "step": 34
     },
     {
       "epoch": 17.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9169944925255703,
-      "eval_loss": 0.18351683020591736,
-      "eval_precision": 0.9187500000000001,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 5.4555,
-      "eval_samples_per_second": 6.599,
-      "eval_steps_per_second": 0.183,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5558464527130127,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.8604,
+      "eval_samples_per_second": 7.407,
+      "eval_steps_per_second": 0.206,
       "step": 36
     },
     {
       "epoch": 18.73,
-      "eval_accuracy": 0.9444444444444444,
-      "eval_f1": 0.9444444444444444,
-      "eval_loss": 0.17979858815670013,
-      "eval_precision": 0.9444444444444444,
-      "eval_recall": 0.9444444444444444,
-      "eval_runtime": 4.4686,
-      "eval_samples_per_second": 8.056,
-      "eval_steps_per_second": 0.224,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5543624758720398,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 4.7553,
+      "eval_samples_per_second": 7.57,
+      "eval_steps_per_second": 0.21,
       "step": 38
     },
     {
       "epoch": 19.73,
       "learning_rate": 0.0,
-      "loss": 0.0016,
+      "loss": 0.6869,
       "step": 40
     },
     {
       "epoch": 19.73,
-      "eval_accuracy": 0.9444444444444444,
-      "eval_f1": 0.9444444444444444,
-      "eval_loss": 0.175317645072937,
-      "eval_precision": 0.9444444444444444,
-      "eval_recall": 0.9444444444444444,
-      "eval_runtime": 10.5431,
-      "eval_samples_per_second": 3.415,
-      "eval_steps_per_second": 0.095,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7188034188034188,
+      "eval_loss": 0.5504012107849121,
+      "eval_precision": 0.6489197530864197,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 5.3116,
+      "eval_samples_per_second": 6.778,
+      "eval_steps_per_second": 0.188,
       "step": 40
     },
     {
       "epoch": 19.73,
       "step": 40,
-      "total_flos": 1.0467617957139087e+18,
-      "train_loss": 0.1206296275369823,
-      "train_runtime": 722.4002,
-      "train_samples_per_second": 18.937,
-      "train_steps_per_second": 0.055
+      "total_flos": 2.8684782950326272e+17,
+      "train_loss": 0.7573485970497131,
+      "train_runtime": 850.4827,
+      "train_samples_per_second": 16.085,
+      "train_steps_per_second": 0.047
     }
   ],
   "max_steps": 40,
   "num_train_epochs": 20,
-  "total_flos": 1.0467617957139087e+18,
+  "total_flos": 2.8684782950326272e+17,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fe1b76553a123f969afd14442e731585a0c8f336c4756939320fa0f48cec7de
+oid sha256:8de4400f120774ada20ad7f5cb8675659945a53f257b9b772200142e86a1e8b0
 size 3387