Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 19.73,
-    "total_flos": 2.8684782950326272e+17,
-    "train_loss": 0.7766409039497375,
-    "train_runtime": 765.0969,
-    "train_samples_per_second": 17.88,
-    "train_steps_per_second": 0.052
+    "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
 }

config.json

@@ -1,32 +1,35 @@
 {
-  "_name_or_path": "google/vit-base-patch16-224",
+  "_name_or_path": "microsoft/resnet-50",
   "architectures": [
-    "ViTForImageClassification"
+    "ResNetForImageClassification"
+  ],
+  "depths": [
+    3,
+    4,
+    6,
+    3
+  ],
+  "downsample_in_first_stage": false,
+  "embedding_size": 64,
+  "hidden_act": "relu",
+  "hidden_sizes": [
+    256,
+    512,
+    1024,
+    2048
   ],
-  "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_norm_eps": 1e-12,
-  "model_type": "vit",
-  "num_attention_heads": 12,
+  "layer_type": "bottleneck",
+  "model_type": "resnet",
   "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

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

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5308f25808e7a1f56f7fdf26bfc7f0d3b85dfe504128f8270f12193586fb4ae9
-size 343268717
+oid sha256:ad69d08277a4d5af0a0fc36682719fcc9b35e0bb8fbe9f62e3b3ddd57c264324
+size 94374989

runs/Jul11_18-58-09_teesta/events.out.tfevents.1689082094.teesta.26387.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:959c92ec5779ed1f19484402bf5f518e168c55651c1560b1c5714fc726f74ea6
-size 11518
+oid sha256:813ef6800f56832266f17a72355bd073a6b4821ee85b79713129d504156d08de
+size 13872

runs/Jul11_19-19-38_teesta/1689083389.0590198/events.out.tfevents.1689083389.teesta.13011.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a46ffe31d5b116459035cde7a61d69e561239b29eface825f0b2bfcfec946fb9
+size 5427

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7454f1dd8d4ff8edce2f72343fe5f7f5efae83fb661b2e1346b54501b38803b9
+size 4020

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 19.73,
-    "total_flos": 2.8684782950326272e+17,
-    "train_loss": 0.7766409039497375,
-    "train_runtime": 765.0969,
-    "train_samples_per_second": 17.88,
-    "train_steps_per_second": 0.052
+    "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
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.7222222222222222,
-  "best_model_checkpoint": "test/checkpoint-38",
+  "best_metric": 0.9722222222222222,
+  "best_model_checkpoint": "test/checkpoint-10",
   "epoch": 19.727272727272727,
   "global_step": 40,
   "is_hyper_param_search": false,
@@ -9,281 +9,281 @@
   "log_history": [
     {
       "epoch": 0.73,
-      "eval_accuracy": 0.5555555555555556,
-      "eval_f1": 0.5500515995872033,
-      "eval_loss": 0.6894996762275696,
-      "eval_precision": 0.6031215161649944,
-      "eval_recall": 0.5555555555555556,
-      "eval_runtime": 5.7626,
-      "eval_samples_per_second": 6.247,
-      "eval_steps_per_second": 0.174,
+      "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,
       "step": 2
     },
     {
       "epoch": 1.73,
-      "eval_accuracy": 0.5555555555555556,
-      "eval_f1": 0.5555555555555556,
-      "eval_loss": 0.6830022931098938,
-      "eval_precision": 0.5873015873015873,
-      "eval_recall": 0.5555555555555556,
-      "eval_runtime": 4.5734,
-      "eval_samples_per_second": 7.872,
-      "eval_steps_per_second": 0.219,
+      "eval_accuracy": 0.75,
+      "eval_f1": 0.7298136645962733,
+      "eval_loss": 0.5041863322257996,
+      "eval_precision": 0.78125,
+      "eval_recall": 0.75,
+      "eval_runtime": 6.0833,
+      "eval_samples_per_second": 5.918,
+      "eval_steps_per_second": 0.164,
       "step": 4
     },
     {
       "epoch": 2.73,
-      "eval_accuracy": 0.6388888888888888,
-      "eval_f1": 0.6097308488612837,
-      "eval_loss": 0.6679378151893616,
-      "eval_precision": 0.6354166666666666,
-      "eval_recall": 0.6388888888888888,
-      "eval_runtime": 4.4512,
-      "eval_samples_per_second": 8.088,
-      "eval_steps_per_second": 0.225,
+      "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,
       "step": 6
     },
     {
       "epoch": 3.73,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1": 0.5925925925925926,
-      "eval_loss": 0.6436803340911865,
-      "eval_precision": 0.7878787878787878,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 4.5113,
-      "eval_samples_per_second": 7.98,
-      "eval_steps_per_second": 0.222,
+      "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,
       "step": 8
     },
     {
       "epoch": 4.73,
       "learning_rate": 0.0001,
-      "loss": 0.8791,
+      "loss": 0.4534,
       "step": 10
     },
     {
       "epoch": 4.73,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1": 0.5925925925925926,
-      "eval_loss": 0.623996913433075,
-      "eval_precision": 0.7878787878787878,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 5.2505,
-      "eval_samples_per_second": 6.856,
-      "eval_steps_per_second": 0.19,
+      "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,
       "step": 10
     },
     {
       "epoch": 5.73,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1": 0.5925925925925926,
-      "eval_loss": 0.6131853461265564,
-      "eval_precision": 0.7878787878787878,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 4.5398,
-      "eval_samples_per_second": 7.93,
-      "eval_steps_per_second": 0.22,
+      "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,
       "step": 12
     },
     {
       "epoch": 6.73,
-      "eval_accuracy": 0.6388888888888888,
-      "eval_f1": 0.54349376114082,
-      "eval_loss": 0.6025312542915344,
-      "eval_precision": 0.7769607843137254,
-      "eval_recall": 0.6388888888888888,
-      "eval_runtime": 4.5856,
-      "eval_samples_per_second": 7.851,
-      "eval_steps_per_second": 0.218,
+      "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,
       "step": 14
     },
     {
       "epoch": 7.73,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1": 0.5925925925925926,
-      "eval_loss": 0.5876591801643372,
-      "eval_precision": 0.7878787878787878,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 5.1342,
-      "eval_samples_per_second": 7.012,
-      "eval_steps_per_second": 0.195,
+      "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,
       "step": 16
     },
     {
       "epoch": 8.73,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1": 0.5925925925925926,
-      "eval_loss": 0.5760440826416016,
-      "eval_precision": 0.7878787878787878,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 7.2043,
-      "eval_samples_per_second": 4.997,
-      "eval_steps_per_second": 0.139,
+      "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,
       "step": 18
     },
     {
       "epoch": 9.73,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 0.8159,
+      "loss": 0.0241,
       "step": 20
     },
     {
       "epoch": 9.73,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1": 0.5925925925925926,
-      "eval_loss": 0.5643935203552246,
-      "eval_precision": 0.7878787878787878,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 4.6428,
-      "eval_samples_per_second": 7.754,
-      "eval_steps_per_second": 0.215,
+      "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,
       "step": 20
     },
     {
       "epoch": 10.73,
-      "eval_accuracy": 0.6388888888888888,
-      "eval_f1": 0.54349376114082,
-      "eval_loss": 0.5555585026741028,
-      "eval_precision": 0.7769607843137254,
-      "eval_recall": 0.6388888888888888,
-      "eval_runtime": 4.7967,
-      "eval_samples_per_second": 7.505,
-      "eval_steps_per_second": 0.208,
+      "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,
       "step": 22
     },
     {
       "epoch": 11.73,
-      "eval_accuracy": 0.6388888888888888,
-      "eval_f1": 0.54349376114082,
-      "eval_loss": 0.5496361255645752,
-      "eval_precision": 0.7769607843137254,
-      "eval_recall": 0.6388888888888888,
-      "eval_runtime": 5.6005,
-      "eval_samples_per_second": 6.428,
-      "eval_steps_per_second": 0.179,
+      "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,
       "step": 24
     },
     {
       "epoch": 12.73,
-      "eval_accuracy": 0.6944444444444444,
-      "eval_f1": 0.6377027474346243,
-      "eval_loss": 0.5442889332771301,
-      "eval_precision": 0.7994791666666666,
-      "eval_recall": 0.6944444444444444,
-      "eval_runtime": 4.7841,
-      "eval_samples_per_second": 7.525,
-      "eval_steps_per_second": 0.209,
+      "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,
       "step": 26
     },
     {
       "epoch": 13.73,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1": 0.5925925925925926,
-      "eval_loss": 0.535383939743042,
-      "eval_precision": 0.7878787878787878,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 5.1928,
-      "eval_samples_per_second": 6.933,
-      "eval_steps_per_second": 0.193,
+      "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,
       "step": 28
     },
     {
       "epoch": 14.73,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.7292,
+      "loss": 0.0034,
       "step": 30
     },
     {
       "epoch": 14.73,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1": 0.5925925925925926,
-      "eval_loss": 0.5252864360809326,
-      "eval_precision": 0.7878787878787878,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 4.8597,
-      "eval_samples_per_second": 7.408,
-      "eval_steps_per_second": 0.206,
+      "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,
       "step": 30
     },
     {
       "epoch": 15.73,
-      "eval_accuracy": 0.6944444444444444,
-      "eval_f1": 0.6377027474346243,
-      "eval_loss": 0.5212194323539734,
-      "eval_precision": 0.7994791666666666,
-      "eval_recall": 0.6944444444444444,
-      "eval_runtime": 5.2963,
-      "eval_samples_per_second": 6.797,
-      "eval_steps_per_second": 0.189,
+      "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,
       "step": 32
     },
     {
       "epoch": 16.73,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1": 0.5925925925925926,
-      "eval_loss": 0.523496150970459,
-      "eval_precision": 0.7878787878787878,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 7.0142,
-      "eval_samples_per_second": 5.132,
-      "eval_steps_per_second": 0.143,
+      "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,
       "step": 34
     },
     {
       "epoch": 17.73,
-      "eval_accuracy": 0.6666666666666666,
-      "eval_f1": 0.5925925925925926,
-      "eval_loss": 0.5156899690628052,
-      "eval_precision": 0.7878787878787878,
-      "eval_recall": 0.6666666666666666,
-      "eval_runtime": 4.6107,
-      "eval_samples_per_second": 7.808,
-      "eval_steps_per_second": 0.217,
+      "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,
       "step": 36
     },
     {
       "epoch": 18.73,
-      "eval_accuracy": 0.7222222222222222,
-      "eval_f1": 0.6794871794871795,
-      "eval_loss": 0.5120455026626587,
-      "eval_precision": 0.8118279569892474,
-      "eval_recall": 0.7222222222222222,
-      "eval_runtime": 4.5305,
-      "eval_samples_per_second": 7.946,
-      "eval_steps_per_second": 0.221,
+      "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,
       "step": 38
     },
     {
       "epoch": 19.73,
       "learning_rate": 0.0,
-      "loss": 0.6824,
+      "loss": 0.0016,
       "step": 40
     },
     {
       "epoch": 19.73,
-      "eval_accuracy": 0.6944444444444444,
-      "eval_f1": 0.6377027474346243,
-      "eval_loss": 0.5125255584716797,
-      "eval_precision": 0.7994791666666666,
-      "eval_recall": 0.6944444444444444,
-      "eval_runtime": 4.5168,
-      "eval_samples_per_second": 7.97,
-      "eval_steps_per_second": 0.221,
+      "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,
       "step": 40
     },
     {
       "epoch": 19.73,
       "step": 40,
-      "total_flos": 2.8684782950326272e+17,
-      "train_loss": 0.7766409039497375,
-      "train_runtime": 765.0969,
-      "train_samples_per_second": 17.88,
-      "train_steps_per_second": 0.052
+      "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
     }
   ],
   "max_steps": 40,
   "num_train_epochs": 20,
-  "total_flos": 2.8684782950326272e+17,
+  "total_flos": 1.0467617957139087e+18,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ee97ead06ef6d616947529660f588401a58017ac4455d562b62ca892eca9da
+oid sha256:4fe1b76553a123f969afd14442e731585a0c8f336c4756939320fa0f48cec7de
 size 3387