Training in progress, epoch 0

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 19.73,
-    "total_flos": 1.0463143975579976e+18,
-    "train_loss": 0.15636180818546563,
-    "train_runtime": 744.5374,
-    "train_samples_per_second": 18.374,
-    "train_steps_per_second": 0.054
+    "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
 }

config.json

@@ -1,32 +1,35 @@
 {
-  "_name_or_path": "facebook/deit-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 sha256:552e1105c89f29f368fc4fb2d534e5b03870afc6a90fa308d3791b2d2a94dd32
-size 343268717
+oid sha256:6285256dbc0a92256ee4fc77deec06dfa8fc3b0ffaec7ee81edc435a18959866
+size 94374989

runs/Jul10_19-45-51_teesta/events.out.tfevents.1688998557.teesta.35180.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d610674e6fd248d9cb911306ee0a5715f30850a9bd2f3a5aef95c76729b1adab
-size 11058
+oid sha256:5e95f5210c8711959b763d85651a8bd110ad2626605050f9de4ad6d2727e33d3
+size 13875

runs/Jul11_18-43-01_teesta/1689081191.4010158/events.out.tfevents.1689081191.teesta.26387.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2892c74424cd73936c452b95c912cc1523908ac30026b0d07a3ea017c50118
+size 5427

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b7891e60fd6e652afc1cb31e1c723b2fea6dc813b5497be1a04d00d7112f6e
+size 4020

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 19.73,
-    "total_flos": 1.0463143975579976e+18,
-    "train_loss": 0.15636180818546563,
-    "train_runtime": 744.5374,
-    "train_samples_per_second": 18.374,
-    "train_steps_per_second": 0.054
+    "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
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_metric": 0.9166666666666666,
-  "best_model_checkpoint": "test/checkpoint-20",
+  "best_model_checkpoint": "test/checkpoint-16",
   "epoch": 19.727272727272727,
   "global_step": 40,
   "is_hyper_param_search": false,
@@ -9,281 +9,281 @@
   "log_history": [
     {
       "epoch": 0.73,
-      "eval_accuracy": 0.7222222222222222,
-      "eval_f1": 0.6707818930041152,
-      "eval_loss": 0.561225950717926,
-      "eval_precision": 0.8090277777777778,
-      "eval_recall": 0.7222222222222222,
-      "eval_runtime": 5.7451,
-      "eval_samples_per_second": 6.266,
-      "eval_steps_per_second": 0.174,
+      "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,
       "step": 2
     },
     {
       "epoch": 1.73,
-      "eval_accuracy": 0.7777777777777778,
-      "eval_f1": 0.7608080808080808,
-      "eval_loss": 0.3748733699321747,
-      "eval_precision": 0.7986111111111112,
-      "eval_recall": 0.7777777777777778,
-      "eval_runtime": 5.1904,
-      "eval_samples_per_second": 6.936,
-      "eval_steps_per_second": 0.193,
+      "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,
       "step": 4
     },
     {
       "epoch": 2.73,
-      "eval_accuracy": 0.8055555555555556,
-      "eval_f1": 0.8066066066066067,
-      "eval_loss": 0.522664487361908,
-      "eval_precision": 0.8703703703703703,
-      "eval_recall": 0.8055555555555556,
-      "eval_runtime": 5.3959,
-      "eval_samples_per_second": 6.672,
-      "eval_steps_per_second": 0.185,
+      "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,
       "step": 6
     },
     {
       "epoch": 3.73,
       "eval_accuracy": 0.8055555555555556,
-      "eval_f1": 0.7864923747276689,
-      "eval_loss": 0.5397895574569702,
-      "eval_precision": 0.8524904214559387,
+      "eval_f1": 0.7943409247757074,
+      "eval_loss": 0.38212475180625916,
+      "eval_precision": 0.8209876543209876,
       "eval_recall": 0.8055555555555556,
-      "eval_runtime": 5.524,
-      "eval_samples_per_second": 6.517,
-      "eval_steps_per_second": 0.181,
+      "eval_runtime": 4.9721,
+      "eval_samples_per_second": 7.24,
+      "eval_steps_per_second": 0.201,
       "step": 8
     },
     {
       "epoch": 4.73,
       "learning_rate": 0.0001,
-      "loss": 0.5735,
+      "loss": 0.4879,
       "step": 10
     },
     {
       "epoch": 4.73,
       "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.8600823045267489,
-      "eval_loss": 0.24970261752605438,
-      "eval_precision": 0.8604607952434039,
+      "eval_f1": 0.857210401891253,
+      "eval_loss": 0.26968610286712646,
+      "eval_precision": 0.8668686868686869,
       "eval_recall": 0.8611111111111112,
-      "eval_runtime": 5.1179,
-      "eval_samples_per_second": 7.034,
-      "eval_steps_per_second": 0.195,
+      "eval_runtime": 4.5739,
+      "eval_samples_per_second": 7.871,
+      "eval_steps_per_second": 0.219,
       "step": 10
     },
     {
       "epoch": 5.73,
-      "eval_accuracy": 0.8888888888888888,
-      "eval_f1": 0.8899470899470899,
-      "eval_loss": 0.26077044010162354,
-      "eval_precision": 0.8965277777777777,
-      "eval_recall": 0.8888888888888888,
-      "eval_runtime": 4.7095,
-      "eval_samples_per_second": 7.644,
-      "eval_steps_per_second": 0.212,
+      "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,
       "step": 12
     },
     {
       "epoch": 6.73,
       "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.8618907600463335,
-      "eval_loss": 0.2541900873184204,
-      "eval_precision": 0.8640211640211641,
+      "eval_f1": 0.857210401891253,
+      "eval_loss": 0.26710909605026245,
+      "eval_precision": 0.8668686868686869,
       "eval_recall": 0.8611111111111112,
-      "eval_runtime": 5.4129,
-      "eval_samples_per_second": 6.651,
-      "eval_steps_per_second": 0.185,
+      "eval_runtime": 5.0847,
+      "eval_samples_per_second": 7.08,
+      "eval_steps_per_second": 0.197,
       "step": 14
     },
     {
       "epoch": 7.73,
-      "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.857210401891253,
-      "eval_loss": 0.2999325394630432,
-      "eval_precision": 0.8668686868686869,
-      "eval_recall": 0.8611111111111112,
-      "eval_runtime": 5.0159,
-      "eval_samples_per_second": 7.177,
-      "eval_steps_per_second": 0.199,
+      "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,
       "step": 16
     },
     {
       "epoch": 8.73,
-      "eval_accuracy": 0.8888888888888888,
-      "eval_f1": 0.8870308435525827,
-      "eval_loss": 0.2993186116218567,
-      "eval_precision": 0.8912037037037036,
-      "eval_recall": 0.8888888888888888,
-      "eval_runtime": 4.9756,
-      "eval_samples_per_second": 7.235,
-      "eval_steps_per_second": 0.201,
+      "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,
       "step": 18
     },
     {
       "epoch": 9.73,
       "learning_rate": 6.666666666666667e-05,
-      "loss": 0.0476,
+      "loss": 0.0279,
       "step": 20
     },
     {
       "epoch": 9.73,
       "eval_accuracy": 0.9166666666666666,
       "eval_f1": 0.9160493827160493,
-      "eval_loss": 0.2704654335975647,
+      "eval_loss": 0.24419277906417847,
       "eval_precision": 0.9169453734671126,
       "eval_recall": 0.9166666666666666,
-      "eval_runtime": 6.2342,
-      "eval_samples_per_second": 5.775,
-      "eval_steps_per_second": 0.16,
+      "eval_runtime": 4.7814,
+      "eval_samples_per_second": 7.529,
+      "eval_steps_per_second": 0.209,
       "step": 20
     },
     {
       "epoch": 10.73,
-      "eval_accuracy": 0.8888888888888888,
-      "eval_f1": 0.8888888888888888,
-      "eval_loss": 0.28197962045669556,
-      "eval_precision": 0.8888888888888888,
-      "eval_recall": 0.8888888888888888,
-      "eval_runtime": 5.1606,
-      "eval_samples_per_second": 6.976,
-      "eval_steps_per_second": 0.194,
+      "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,
       "step": 22
     },
     {
       "epoch": 11.73,
       "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.8618907600463335,
-      "eval_loss": 0.275021493434906,
-      "eval_precision": 0.8640211640211641,
+      "eval_f1": 0.857210401891253,
+      "eval_loss": 0.28706809878349304,
+      "eval_precision": 0.8668686868686869,
       "eval_recall": 0.8611111111111112,
-      "eval_runtime": 4.8026,
-      "eval_samples_per_second": 7.496,
-      "eval_steps_per_second": 0.208,
+      "eval_runtime": 4.5584,
+      "eval_samples_per_second": 7.898,
+      "eval_steps_per_second": 0.219,
       "step": 24
     },
     {
       "epoch": 12.73,
-      "eval_accuracy": 0.8888888888888888,
-      "eval_f1": 0.8888888888888888,
-      "eval_loss": 0.2932831346988678,
-      "eval_precision": 0.8888888888888888,
-      "eval_recall": 0.8888888888888888,
-      "eval_runtime": 4.6825,
-      "eval_samples_per_second": 7.688,
-      "eval_steps_per_second": 0.214,
+      "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,
       "step": 26
     },
     {
       "epoch": 13.73,
       "eval_accuracy": 0.8611111111111112,
-      "eval_f1": 0.8618907600463335,
-      "eval_loss": 0.2971099317073822,
-      "eval_precision": 0.8640211640211641,
+      "eval_f1": 0.857210401891253,
+      "eval_loss": 0.28809821605682373,
+      "eval_precision": 0.8668686868686869,
       "eval_recall": 0.8611111111111112,
-      "eval_runtime": 5.7546,
-      "eval_samples_per_second": 6.256,
-      "eval_steps_per_second": 0.174,
+      "eval_runtime": 4.7378,
+      "eval_samples_per_second": 7.598,
+      "eval_steps_per_second": 0.211,
       "step": 28
     },
     {
       "epoch": 14.73,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.003,
+      "loss": 0.0021,
       "step": 30
     },
     {
       "epoch": 14.73,
-      "eval_accuracy": 0.8888888888888888,
-      "eval_f1": 0.8888888888888888,
-      "eval_loss": 0.29043230414390564,
-      "eval_precision": 0.8888888888888888,
-      "eval_recall": 0.8888888888888888,
-      "eval_runtime": 9.7959,
-      "eval_samples_per_second": 3.675,
-      "eval_steps_per_second": 0.102,
+      "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,
       "step": 30
     },
     {
       "epoch": 15.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9160493827160493,
-      "eval_loss": 0.305411696434021,
-      "eval_precision": 0.9169453734671126,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 5.2177,
-      "eval_samples_per_second": 6.9,
-      "eval_steps_per_second": 0.192,
+      "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,
       "step": 32
     },
     {
       "epoch": 16.73,
-      "eval_accuracy": 0.9166666666666666,
-      "eval_f1": 0.9160493827160493,
-      "eval_loss": 0.29818451404571533,
-      "eval_precision": 0.9169453734671126,
-      "eval_recall": 0.9166666666666666,
-      "eval_runtime": 4.9626,
-      "eval_samples_per_second": 7.254,
-      "eval_steps_per_second": 0.202,
+      "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,
       "step": 34
     },
     {
       "epoch": 17.73,
       "eval_accuracy": 0.9166666666666666,
       "eval_f1": 0.9160493827160493,
-      "eval_loss": 0.30663102865219116,
+      "eval_loss": 0.24998606741428375,
       "eval_precision": 0.9169453734671126,
       "eval_recall": 0.9166666666666666,
-      "eval_runtime": 4.7376,
-      "eval_samples_per_second": 7.599,
-      "eval_steps_per_second": 0.211,
+      "eval_runtime": 4.6548,
+      "eval_samples_per_second": 7.734,
+      "eval_steps_per_second": 0.215,
       "step": 36
     },
     {
       "epoch": 18.73,
-      "eval_accuracy": 0.8888888888888888,
-      "eval_f1": 0.8870308435525827,
-      "eval_loss": 0.30919915437698364,
-      "eval_precision": 0.8912037037037036,
-      "eval_recall": 0.8888888888888888,
-      "eval_runtime": 6.3085,
-      "eval_samples_per_second": 5.707,
-      "eval_steps_per_second": 0.159,
+      "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,
       "step": 38
     },
     {
       "epoch": 19.73,
       "learning_rate": 0.0,
-      "loss": 0.0013,
+      "loss": 0.0008,
       "step": 40
     },
     {
       "epoch": 19.73,
-      "eval_accuracy": 0.8888888888888888,
-      "eval_f1": 0.8870308435525827,
-      "eval_loss": 0.3030144274234772,
-      "eval_precision": 0.8912037037037036,
-      "eval_recall": 0.8888888888888888,
-      "eval_runtime": 4.7135,
-      "eval_samples_per_second": 7.638,
-      "eval_steps_per_second": 0.212,
+      "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,
       "step": 40
     },
     {
       "epoch": 19.73,
       "step": 40,
-      "total_flos": 1.0463143975579976e+18,
-      "train_loss": 0.15636180818546563,
-      "train_runtime": 744.5374,
-      "train_samples_per_second": 18.374,
-      "train_steps_per_second": 0.054
+      "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
     }
   ],
   "max_steps": 40,
   "num_train_epochs": 20,
-  "total_flos": 1.0463143975579976e+18,
+  "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 sha256:7461b0cb9b4b366e4551fef7c56538fb52d6a1008d314c875bdc23478b386ac2
+oid sha256:0705ed4bcd2ea47577fac168032ea4c5359152d6f647bf7eff84ac562864b95f
 size 3387