Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 19.73,
-    "total_flos": 1.0467617957139087e+18,
-    "train_loss": 0.12968791872262955,
-    "train_runtime": 733.2509,
-    "train_samples_per_second": 18.657,
-    "train_steps_per_second": 0.055
+    "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
 }

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:a9ad20554b145ac41382b83909a2270bcac1f51c14fb7cff265bd0379a4e2690
-size 94374989
+oid sha256:be62b153d076ee83877e0b286d842807c42fe1e59346d4b24eb6293a66c8a1ed
+size 343268717

runs/Jul11_18-43-01_teesta/events.out.tfevents.1689081191.teesta.26387.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f4ff523edab575a36a00ce7a3d001bd4b225c0d0390db1c9d95883a5040e069
-size 12816
+oid sha256:5e23da3a839c006c201e7d1de109a481744a2380970096380cb635ce95f97720
+size 13781

runs/Jul11_18-58-09_teesta/1689082094.113389/events.out.tfevents.1689082094.teesta.26387.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb49da1ce9301192140ba995f571fff40629fbd6d8f509179dc24a5fe2e753f0
+size 5427

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb8a4dd835dd9aa42f3b6fe54796f0c5914cf57739d294586c44234f9bed8016
+size 4111

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 19.73,
-    "total_flos": 1.0467617957139087e+18,
-    "train_loss": 0.12968791872262955,
-    "train_runtime": 733.2509,
-    "train_samples_per_second": 18.657,
-    "train_steps_per_second": 0.055
+    "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
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.9166666666666666,
-  "best_model_checkpoint": "test/checkpoint-16",
+  "best_metric": 0.7222222222222222,
+  "best_model_checkpoint": "test/checkpoint-38",
   "epoch": 19.727272727272727,
   "global_step": 40,
   "is_hyper_param_search": false,
@@ -9,281 +9,281 @@
   "log_history": [
     {
       "epoch": 0.73,
-      "eval_accuracy": 0.6388888888888888,
-      "eval_f1": 0.5581699346405229,
-      "eval_loss": 0.6255224943161011,
-      "eval_precision": 0.6481481481481481,
-      "eval_recall": 0.6388888888888888,
-      "eval_runtime": 5.2731,
-      "eval_samples_per_second": 6.827,
-      "eval_steps_per_second": 0.19,
+      "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,
       "step": 2
     },
     {
       "epoch": 1.73,
-      "eval_accuracy": 0.75,
-      "eval_f1": 0.7120158887785502,
-      "eval_loss": 0.4980746805667877,
-      "eval_precision": 0.8225806451612904,
-      "eval_recall": 0.75,
-      "eval_runtime": 6.1411,
-      "eval_samples_per_second": 5.862,
-      "eval_steps_per_second": 0.163,
+      "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,
       "step": 4
     },
     {
       "epoch": 2.73,
-      "eval_accuracy": 0.75,
-      "eval_f1": 0.7429787234042554,
-      "eval_loss": 0.4359954297542572,
-      "eval_precision": 0.7472727272727272,
-      "eval_recall": 0.75,
-      "eval_runtime": 4.7783,
-      "eval_samples_per_second": 7.534,
-      "eval_steps_per_second": 0.209,
+      "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,
       "step": 6
     },
     {
       "epoch": 3.73,
-      "eval_accuracy": 0.8055555555555556,
-      "eval_f1": 0.7943409247757074,
-      "eval_loss": 0.38212475180625916,
-      "eval_precision": 0.8209876543209876,
-      "eval_recall": 0.8055555555555556,
-      "eval_runtime": 4.9721,
-      "eval_samples_per_second": 7.24,
-      "eval_steps_per_second": 0.201,
+      "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,
       "step": 8
     },
     {
       "epoch": 4.73,
       "learning_rate": 0.0001,
-      "loss": 0.4879,
+      "loss": 0.8791,
       "step": 10
     },
     {
       "epoch": 4.73,
-      "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.857210401891253,
-      "eval_loss": 0.26968610286712646,
-      "eval_precision": 0.8668686868686869,
-      "eval_recall": 0.8611111111111112,
-      "eval_runtime": 4.5739,
-      "eval_samples_per_second": 7.871,
-      "eval_steps_per_second": 0.219,
+      "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,
       "step": 10
     },
     {
       "epoch": 5.73,
-      "eval_accuracy": 0.8333333333333334,
-      "eval_f1": 0.8263888888888888,
-      "eval_loss": 0.3342033922672272,
-      "eval_precision": 0.8435897435897436,
-      "eval_recall": 0.8333333333333334,
-      "eval_runtime": 4.9205,
-      "eval_samples_per_second": 7.316,
-      "eval_steps_per_second": 0.203,
+      "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,
       "step": 12
     },
     {
       "epoch": 6.73,
-      "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.857210401891253,
-      "eval_loss": 0.26710909605026245,
-      "eval_precision": 0.8668686868686869,
-      "eval_recall": 0.8611111111111112,
-      "eval_runtime": 5.0847,
-      "eval_samples_per_second": 7.08,
-      "eval_steps_per_second": 0.197,
+      "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,
       "step": 14
     },
     {
       "epoch": 7.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9160493827160493,
-      "eval_loss": 0.2436762899160385,
-      "eval_precision": 0.9169453734671126,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 4.7098,
-      "eval_samples_per_second": 7.644,
-      "eval_steps_per_second": 0.212,
+      "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,
       "step": 16
     },
     {
       "epoch": 8.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9160493827160493,
-      "eval_loss": 0.23434966802597046,
-      "eval_precision": 0.9169453734671126,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 4.6359,
-      "eval_samples_per_second": 7.766,
-      "eval_steps_per_second": 0.216,
+      "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,
       "step": 18
     },
     {
       "epoch": 9.73,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 0.0279,
+      "loss": 0.8159,
       "step": 20
     },
     {
       "epoch": 9.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9160493827160493,
-      "eval_loss": 0.24419277906417847,
-      "eval_precision": 0.9169453734671126,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 4.7814,
-      "eval_samples_per_second": 7.529,
-      "eval_steps_per_second": 0.209,
+      "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,
       "step": 20
     },
     {
       "epoch": 10.73,
-      "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.857210401891253,
-      "eval_loss": 0.253448486328125,
-      "eval_precision": 0.8668686868686869,
-      "eval_recall": 0.8611111111111112,
-      "eval_runtime": 6.6388,
-      "eval_samples_per_second": 5.423,
-      "eval_steps_per_second": 0.151,
+      "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,
       "step": 22
     },
     {
       "epoch": 11.73,
-      "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.857210401891253,
-      "eval_loss": 0.28706809878349304,
-      "eval_precision": 0.8668686868686869,
-      "eval_recall": 0.8611111111111112,
-      "eval_runtime": 4.5584,
-      "eval_samples_per_second": 7.898,
-      "eval_steps_per_second": 0.219,
+      "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,
       "step": 24
     },
     {
       "epoch": 12.73,
-      "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.857210401891253,
-      "eval_loss": 0.27148592472076416,
-      "eval_precision": 0.8668686868686869,
-      "eval_recall": 0.8611111111111112,
-      "eval_runtime": 4.6864,
-      "eval_samples_per_second": 7.682,
-      "eval_steps_per_second": 0.213,
+      "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,
       "step": 26
     },
     {
       "epoch": 13.73,
-      "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.857210401891253,
-      "eval_loss": 0.28809821605682373,
-      "eval_precision": 0.8668686868686869,
-      "eval_recall": 0.8611111111111112,
-      "eval_runtime": 4.7378,
-      "eval_samples_per_second": 7.598,
-      "eval_steps_per_second": 0.211,
+      "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,
       "step": 28
     },
     {
       "epoch": 14.73,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.0021,
+      "loss": 0.7292,
       "step": 30
     },
     {
       "epoch": 14.73,
-      "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.857210401891253,
-      "eval_loss": 0.27546411752700806,
-      "eval_precision": 0.8668686868686869,
-      "eval_recall": 0.8611111111111112,
-      "eval_runtime": 4.6181,
-      "eval_samples_per_second": 7.795,
-      "eval_steps_per_second": 0.217,
+      "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,
       "step": 30
     },
     {
       "epoch": 15.73,
-      "eval_accuracy": 0.8888888888888888,
-      "eval_f1": 0.8870308435525827,
-      "eval_loss": 0.2769797444343567,
-      "eval_precision": 0.8912037037037036,
-      "eval_recall": 0.8888888888888888,
-      "eval_runtime": 4.8337,
-      "eval_samples_per_second": 7.448,
-      "eval_steps_per_second": 0.207,
+      "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,
       "step": 32
     },
     {
       "epoch": 16.73,
-      "eval_accuracy": 0.8888888888888888,
-      "eval_f1": 0.8870308435525827,
-      "eval_loss": 0.2637002766132355,
-      "eval_precision": 0.8912037037037036,
-      "eval_recall": 0.8888888888888888,
-      "eval_runtime": 4.74,
-      "eval_samples_per_second": 7.595,
-      "eval_steps_per_second": 0.211,
+      "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,
       "step": 34
     },
     {
       "epoch": 17.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9160493827160493,
-      "eval_loss": 0.24998606741428375,
-      "eval_precision": 0.9169453734671126,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 4.6548,
-      "eval_samples_per_second": 7.734,
-      "eval_steps_per_second": 0.215,
+      "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,
       "step": 36
     },
     {
       "epoch": 18.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9160493827160493,
-      "eval_loss": 0.25946107506752014,
-      "eval_precision": 0.9169453734671126,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 4.7568,
-      "eval_samples_per_second": 7.568,
-      "eval_steps_per_second": 0.21,
+      "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,
       "step": 38
     },
     {
       "epoch": 19.73,
       "learning_rate": 0.0,
-      "loss": 0.0008,
+      "loss": 0.6824,
       "step": 40
     },
     {
       "epoch": 19.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9160493827160493,
-      "eval_loss": 0.26713693141937256,
-      "eval_precision": 0.9169453734671126,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 5.5818,
-      "eval_samples_per_second": 6.45,
-      "eval_steps_per_second": 0.179,
+      "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,
       "step": 40
     },
     {
       "epoch": 19.73,
       "step": 40,
-      "total_flos": 1.0467617957139087e+18,
-      "train_loss": 0.12968791872262955,
-      "train_runtime": 733.2509,
-      "train_samples_per_second": 18.657,
-      "train_steps_per_second": 0.055
+      "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
     }
   ],
   "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 sha256:0705ed4bcd2ea47577fac168032ea4c5359152d6f647bf7eff84ac562864b95f
+oid sha256:30ee97ead06ef6d616947529660f588401a58017ac4455d562b62ca892eca9da
 size 3387