Training in progress, epoch 0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 19.73,
+    "total_flos": 2.8684782950326272e+17,
+    "train_loss": 0.7429648399353027,
+    "train_runtime": 749.9349,
+    "train_samples_per_second": 18.242,
+    "train_steps_per_second": 0.053
+}

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 sha256:81d4e2be21fdfabd08da50cddb2fc32a8ba682bd580f83abb3c7a4f1ce374e00
-size 94374989
+oid sha256:d1a393d5c405cee748fda7e709009ea5ab626e84aa28e9d01806cb9496361daa
+size 343268717

runs/Jul10_14-05-53_teesta/events.out.tfevents.1688978218.teesta.5195.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7db2d6bf7dd8f8cad910eab69b5b7144435f57a8a7cc668eff25874c679bdf46
-size 12816
+oid sha256:f6c4144db30cab3651c6896721a5043e3d98e74f2576736d0bb26289b7b76d36
+size 13781

runs/Jul10_17-16-51_teesta/1688989619.5585573/events.out.tfevents.1688989619.teesta.40693.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c010539d5e0c3bca5cbafaf84b7711ab71bac4a756f1cf09bfa2d88abb5a18b2
+size 5427

runs/Jul10_17-16-51_teesta/events.out.tfevents.1688989619.teesta.40693.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11380609e58276ea697f90b0e21013432e60251a38e5f1d6019da0b293c91e2e
+size 4111

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 19.73,
+    "total_flos": 2.8684782950326272e+17,
+    "train_loss": 0.7429648399353027,
+    "train_runtime": 749.9349,
+    "train_samples_per_second": 18.242,
+    "train_steps_per_second": 0.053
+}

trainer_state.json

@@ -0,0 +1,289 @@
+{
+  "best_metric": 0.8333333333333334,
+  "best_model_checkpoint": "test/checkpoint-34",
+  "epoch": 19.727272727272727,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.73,
+      "eval_accuracy": 0.7777777777777778,
+      "eval_f1": 0.770940170940171,
+      "eval_loss": 0.6720435619354248,
+      "eval_precision": 0.7695473251028806,
+      "eval_recall": 0.7777777777777778,
+      "eval_runtime": 7.169,
+      "eval_samples_per_second": 5.022,
+      "eval_steps_per_second": 0.139,
+      "step": 2
+    },
+    {
+      "epoch": 1.73,
+      "eval_accuracy": 0.7777777777777778,
+      "eval_f1": 0.7613168724279835,
+      "eval_loss": 0.6651345491409302,
+      "eval_precision": 0.7690202517788725,
+      "eval_recall": 0.7777777777777778,
+      "eval_runtime": 5.928,
+      "eval_samples_per_second": 6.073,
+      "eval_steps_per_second": 0.169,
+      "step": 4
+    },
+    {
+      "epoch": 2.73,
+      "eval_accuracy": 0.6944444444444444,
+      "eval_f1": 0.6119802984209763,
+      "eval_loss": 0.6359639763832092,
+      "eval_precision": 0.6429738562091504,
+      "eval_recall": 0.6944444444444444,
+      "eval_runtime": 4.9898,
+      "eval_samples_per_second": 7.215,
+      "eval_steps_per_second": 0.2,
+      "step": 6
+    },
+    {
+      "epoch": 3.73,
+      "eval_accuracy": 0.6666666666666666,
+      "eval_f1": 0.5555555555555556,
+      "eval_loss": 0.6130982041358948,
+      "eval_precision": 0.47619047619047616,
+      "eval_recall": 0.6666666666666666,
+      "eval_runtime": 5.5773,
+      "eval_samples_per_second": 6.455,
+      "eval_steps_per_second": 0.179,
+      "step": 8
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 0.0001,
+      "loss": 0.85,
+      "step": 10
+    },
+    {
+      "epoch": 4.73,
+      "eval_accuracy": 0.6944444444444444,
+      "eval_f1": 0.569216757741348,
+      "eval_loss": 0.5958656668663025,
+      "eval_precision": 0.48225308641975306,
+      "eval_recall": 0.6944444444444444,
+      "eval_runtime": 5.3816,
+      "eval_samples_per_second": 6.689,
+      "eval_steps_per_second": 0.186,
+      "step": 10
+    },
+    {
+      "epoch": 5.73,
+      "eval_accuracy": 0.6944444444444444,
+      "eval_f1": 0.569216757741348,
+      "eval_loss": 0.5696195960044861,
+      "eval_precision": 0.48225308641975306,
+      "eval_recall": 0.6944444444444444,
+      "eval_runtime": 5.4307,
+      "eval_samples_per_second": 6.629,
+      "eval_steps_per_second": 0.184,
+      "step": 12
+    },
+    {
+      "epoch": 6.73,
+      "eval_accuracy": 0.6944444444444444,
+      "eval_f1": 0.569216757741348,
+      "eval_loss": 0.5393776297569275,
+      "eval_precision": 0.48225308641975306,
+      "eval_recall": 0.6944444444444444,
+      "eval_runtime": 5.3348,
+      "eval_samples_per_second": 6.748,
+      "eval_steps_per_second": 0.187,
+      "step": 14
+    },
+    {
+      "epoch": 7.73,
+      "eval_accuracy": 0.6944444444444444,
+      "eval_f1": 0.569216757741348,
+      "eval_loss": 0.525506317615509,
+      "eval_precision": 0.48225308641975306,
+      "eval_recall": 0.6944444444444444,
+      "eval_runtime": 4.9234,
+      "eval_samples_per_second": 7.312,
+      "eval_steps_per_second": 0.203,
+      "step": 16
+    },
+    {
+      "epoch": 8.73,
+      "eval_accuracy": 0.7222222222222222,
+      "eval_f1": 0.6296296296296295,
+      "eval_loss": 0.5029427409172058,
+      "eval_precision": 0.8015873015873016,
+      "eval_recall": 0.7222222222222222,
+      "eval_runtime": 4.9254,
+      "eval_samples_per_second": 7.309,
+      "eval_steps_per_second": 0.203,
+      "step": 18
+    },
+    {
+      "epoch": 9.73,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.7809,
+      "step": 20
+    },
+    {
+      "epoch": 9.73,
+      "eval_accuracy": 0.7222222222222222,
+      "eval_f1": 0.6296296296296295,
+      "eval_loss": 0.49091774225234985,
+      "eval_precision": 0.8015873015873016,
+      "eval_recall": 0.7222222222222222,
+      "eval_runtime": 5.0878,
+      "eval_samples_per_second": 7.076,
+      "eval_steps_per_second": 0.197,
+      "step": 20
+    },
+    {
+      "epoch": 10.73,
+      "eval_accuracy": 0.6944444444444444,
+      "eval_f1": 0.569216757741348,
+      "eval_loss": 0.47324174642562866,
+      "eval_precision": 0.48225308641975306,
+      "eval_recall": 0.6944444444444444,
+      "eval_runtime": 6.264,
+      "eval_samples_per_second": 5.747,
+      "eval_steps_per_second": 0.16,
+      "step": 22
+    },
+    {
+      "epoch": 11.73,
+      "eval_accuracy": 0.7222222222222222,
+      "eval_f1": 0.6296296296296295,
+      "eval_loss": 0.47097042202949524,
+      "eval_precision": 0.8015873015873016,
+      "eval_recall": 0.7222222222222222,
+      "eval_runtime": 4.8001,
+      "eval_samples_per_second": 7.5,
+      "eval_steps_per_second": 0.208,
+      "step": 24
+    },
+    {
+      "epoch": 12.73,
+      "eval_accuracy": 0.7222222222222222,
+      "eval_f1": 0.6296296296296295,
+      "eval_loss": 0.4540965259075165,
+      "eval_precision": 0.8015873015873016,
+      "eval_recall": 0.7222222222222222,
+      "eval_runtime": 4.7617,
+      "eval_samples_per_second": 7.56,
+      "eval_steps_per_second": 0.21,
+      "step": 26
+    },
+    {
+      "epoch": 13.73,
+      "eval_accuracy": 0.7777777777777778,
+      "eval_f1": 0.7296113847837985,
+      "eval_loss": 0.44506168365478516,
+      "eval_precision": 0.8316498316498316,
+      "eval_recall": 0.7777777777777778,
+      "eval_runtime": 4.873,
+      "eval_samples_per_second": 7.388,
+      "eval_steps_per_second": 0.205,
+      "step": 28
+    },
+    {
+      "epoch": 14.73,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.6976,
+      "step": 30
+    },
+    {
+      "epoch": 14.73,
+      "eval_accuracy": 0.7777777777777778,
+      "eval_f1": 0.7296113847837985,
+      "eval_loss": 0.44511425495147705,
+      "eval_precision": 0.8316498316498316,
+      "eval_recall": 0.7777777777777778,
+      "eval_runtime": 5.299,
+      "eval_samples_per_second": 6.794,
+      "eval_steps_per_second": 0.189,
+      "step": 30
+    },
+    {
+      "epoch": 15.73,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7721247563352827,
+      "eval_loss": 0.4380625784397125,
+      "eval_precision": 0.8480902777777778,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 5.0388,
+      "eval_samples_per_second": 7.145,
+      "eval_steps_per_second": 0.198,
+      "step": 32
+    },
+    {
+      "epoch": 16.73,
+      "eval_accuracy": 0.8333333333333334,
+      "eval_f1": 0.8110119047619047,
+      "eval_loss": 0.4326169788837433,
+      "eval_precision": 0.8655913978494624,
+      "eval_recall": 0.8333333333333334,
+      "eval_runtime": 5.6799,
+      "eval_samples_per_second": 6.338,
+      "eval_steps_per_second": 0.176,
+      "step": 34
+    },
+    {
+      "epoch": 17.73,
+      "eval_accuracy": 0.7777777777777778,
+      "eval_f1": 0.7296113847837985,
+      "eval_loss": 0.4337227940559387,
+      "eval_precision": 0.8316498316498316,
+      "eval_recall": 0.7777777777777778,
+      "eval_runtime": 4.7411,
+      "eval_samples_per_second": 7.593,
+      "eval_steps_per_second": 0.211,
+      "step": 36
+    },
+    {
+      "epoch": 18.73,
+      "eval_accuracy": 0.8055555555555556,
+      "eval_f1": 0.7721247563352827,
+      "eval_loss": 0.4260648787021637,
+      "eval_precision": 0.8480902777777778,
+      "eval_recall": 0.8055555555555556,
+      "eval_runtime": 5.2317,
+      "eval_samples_per_second": 6.881,
+      "eval_steps_per_second": 0.191,
+      "step": 38
+    },
+    {
+      "epoch": 19.73,
+      "learning_rate": 0.0,
+      "loss": 0.6433,
+      "step": 40
+    },
+    {
+      "epoch": 19.73,
+      "eval_accuracy": 0.75,
+      "eval_f1": 0.6825293350717081,
+      "eval_loss": 0.42079275846481323,
+      "eval_precision": 0.8161764705882353,
+      "eval_recall": 0.75,
+      "eval_runtime": 6.4007,
+      "eval_samples_per_second": 5.624,
+      "eval_steps_per_second": 0.156,
+      "step": 40
+    },
+    {
+      "epoch": 19.73,
+      "step": 40,
+      "total_flos": 2.8684782950326272e+17,
+      "train_loss": 0.7429648399353027,
+      "train_runtime": 749.9349,
+      "train_samples_per_second": 18.242,
+      "train_steps_per_second": 0.053
+    }
+  ],
+  "max_steps": 40,
+  "num_train_epochs": 20,
+  "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 sha256:3a4f6ad3d4d4c2e6e28c4b2a1849ee786225b86f4fc813b7dc7307369c0e8bf8
+oid sha256:a24e0b9bc7c80089107c68a211b86b5a64a5036f730fcfc386da6a2e2aef4e1f
 size 3387