End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9099756690997567
+      value: 0.9172749391727494
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-tiny-patch4-window7-224](https://huggingface.co/microsoft/swin-tiny-patch4-window7-224) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2154
-- Accuracy: 0.9100
+- Loss: 0.2099
+- Accuracy: 0.9173
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 9.836065573770492,
-    "eval_accuracy": 0.8856447688564477,
-    "eval_loss": 0.26367661356925964,
-    "eval_runtime": 46.9001,
-    "eval_samples_per_second": 8.763,
+    "eval_accuracy": 0.9172749391727494,
+    "eval_loss": 0.20992133021354675,
+    "eval_runtime": 46.8426,
+    "eval_samples_per_second": 8.774,
     "eval_steps_per_second": 0.149,
-    "total_flos": 1.9063087726729052e+18,
-    "train_loss": 0.3090126927693685,
-    "train_runtime": 8089.4797,
-    "train_samples_per_second": 9.637,
+    "total_flos": 1.9365344998357156e+18,
+    "train_loss": 0.1960654123624166,
+    "train_runtime": 8023.8475,
+    "train_samples_per_second": 9.716,
     "train_steps_per_second": 0.037
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.836065573770492,
-    "eval_accuracy": 0.8856447688564477,
-    "eval_loss": 0.26367661356925964,
-    "eval_runtime": 46.9001,
-    "eval_samples_per_second": 8.763,
+    "eval_accuracy": 0.9172749391727494,
+    "eval_loss": 0.20992133021354675,
+    "eval_runtime": 46.8426,
+    "eval_samples_per_second": 8.774,
     "eval_steps_per_second": 0.149
 }

runs/Jul08_05-22-33_fc6b70f312e9/events.out.tfevents.1720431376.fc6b70f312e9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178ffa910a31d0ae727342ad4f3ea9bdc009699ec9c308501ca9dee58eaca810
+size 191

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 9.836065573770492,
-    "total_flos": 1.9063087726729052e+18,
-    "train_loss": 0.3090126927693685,
-    "train_runtime": 8089.4797,
-    "train_samples_per_second": 9.637,
+    "total_flos": 1.9365344998357156e+18,
+    "train_loss": 0.1960654123624166,
+    "train_runtime": 8023.8475,
+    "train_samples_per_second": 9.716,
     "train_steps_per_second": 0.037
 }

trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.8856447688564477,
-  "best_model_checkpoint": "swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification/checkpoint-183",
+  "best_metric": 0.9172749391727494,
+  "best_model_checkpoint": "swin-tiny-patch4-window7-224-Mid-NonMidMarket-Classification/checkpoint-61",
   "epoch": 9.836065573770492,
   "eval_steps": 500,
   "global_step": 300,
@@ -10,311 +10,311 @@
   "log_history": [
     {
       "epoch": 0.32786885245901637,
-      "grad_norm": 4.936834812164307,
+      "grad_norm": 2.2764179706573486,
       "learning_rate": 1.6666666666666667e-05,
-      "loss": 0.9945,
+      "loss": 0.2374,
       "step": 10
     },
     {
       "epoch": 0.6557377049180327,
-      "grad_norm": 2.4745380878448486,
+      "grad_norm": 3.2821102142333984,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.5619,
+      "loss": 0.251,
       "step": 20
     },
     {
       "epoch": 0.9836065573770492,
-      "grad_norm": 3.340874433517456,
+      "grad_norm": 2.859771251678467,
       "learning_rate": 5e-05,
-      "loss": 0.4494,
+      "loss": 0.2558,
       "step": 30
     },
     {
       "epoch": 0.9836065573770492,
-      "eval_accuracy": 0.8223844282238443,
-      "eval_loss": 0.495254784822464,
-      "eval_runtime": 47.0869,
-      "eval_samples_per_second": 8.729,
-      "eval_steps_per_second": 0.149,
+      "eval_accuracy": 0.9124087591240876,
+      "eval_loss": 0.2283840924501419,
+      "eval_runtime": 46.3956,
+      "eval_samples_per_second": 8.859,
+      "eval_steps_per_second": 0.151,
       "step": 30
     },
     {
       "epoch": 1.3114754098360657,
-      "grad_norm": 2.102787733078003,
+      "grad_norm": 2.7073123455047607,
       "learning_rate": 4.814814814814815e-05,
-      "loss": 0.3852,
+      "loss": 0.2405,
       "step": 40
     },
     {
       "epoch": 1.639344262295082,
-      "grad_norm": 1.9069348573684692,
+      "grad_norm": 2.072742462158203,
       "learning_rate": 4.62962962962963e-05,
-      "loss": 0.3536,
+      "loss": 0.2385,
       "step": 50
     },
     {
       "epoch": 1.9672131147540983,
-      "grad_norm": 2.154897451400757,
+      "grad_norm": 3.4507081508636475,
       "learning_rate": 4.4444444444444447e-05,
-      "loss": 0.3369,
+      "loss": 0.2409,
       "step": 60
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8832116788321168,
-      "eval_loss": 0.3206270635128021,
-      "eval_runtime": 46.9296,
-      "eval_samples_per_second": 8.758,
-      "eval_steps_per_second": 0.149,
+      "eval_accuracy": 0.9172749391727494,
+      "eval_loss": 0.20992133021354675,
+      "eval_runtime": 46.6612,
+      "eval_samples_per_second": 8.808,
+      "eval_steps_per_second": 0.15,
       "step": 61
     },
     {
       "epoch": 2.2950819672131146,
-      "grad_norm": 2.829212188720703,
+      "grad_norm": 2.1165263652801514,
       "learning_rate": 4.259259259259259e-05,
-      "loss": 0.3171,
+      "loss": 0.2279,
       "step": 70
     },
     {
       "epoch": 2.6229508196721314,
-      "grad_norm": 2.4426212310791016,
+      "grad_norm": 2.485424757003784,
       "learning_rate": 4.074074074074074e-05,
-      "loss": 0.3019,
+      "loss": 0.2246,
       "step": 80
     },
     {
       "epoch": 2.9508196721311473,
-      "grad_norm": 2.601443290710449,
+      "grad_norm": 3.2937915325164795,
       "learning_rate": 3.888888888888889e-05,
-      "loss": 0.3173,
+      "loss": 0.2151,
       "step": 90
     },
     {
       "epoch": 2.9836065573770494,
-      "eval_accuracy": 0.8734793187347932,
-      "eval_loss": 0.3022870123386383,
-      "eval_runtime": 47.009,
-      "eval_samples_per_second": 8.743,
-      "eval_steps_per_second": 0.149,
+      "eval_accuracy": 0.9051094890510949,
+      "eval_loss": 0.2273489087820053,
+      "eval_runtime": 46.5349,
+      "eval_samples_per_second": 8.832,
+      "eval_steps_per_second": 0.15,
       "step": 91
     },
     {
       "epoch": 3.278688524590164,
-      "grad_norm": 1.8936508893966675,
+      "grad_norm": 3.282068967819214,
       "learning_rate": 3.7037037037037037e-05,
-      "loss": 0.3082,
+      "loss": 0.2005,
       "step": 100
     },
     {
       "epoch": 3.6065573770491803,
-      "grad_norm": 2.6445701122283936,
+      "grad_norm": 3.5282602310180664,
       "learning_rate": 3.518518518518519e-05,
-      "loss": 0.2837,
+      "loss": 0.2105,
       "step": 110
     },
     {
       "epoch": 3.9344262295081966,
-      "grad_norm": 4.797309875488281,
+      "grad_norm": 3.1445822715759277,
       "learning_rate": 3.3333333333333335e-05,
-      "loss": 0.2865,
+      "loss": 0.2085,
       "step": 120
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8734793187347932,
-      "eval_loss": 0.2900189161300659,
-      "eval_runtime": 46.7107,
-      "eval_samples_per_second": 8.799,
-      "eval_steps_per_second": 0.15,
+      "eval_accuracy": 0.9002433090024331,
+      "eval_loss": 0.2337980419397354,
+      "eval_runtime": 46.9689,
+      "eval_samples_per_second": 8.75,
+      "eval_steps_per_second": 0.149,
       "step": 122
     },
     {
       "epoch": 4.262295081967213,
-      "grad_norm": 2.120328664779663,
+      "grad_norm": 2.4089198112487793,
       "learning_rate": 3.148148148148148e-05,
-      "loss": 0.2838,
+      "loss": 0.1954,
       "step": 130
     },
     {
       "epoch": 4.590163934426229,
-      "grad_norm": 2.334688663482666,
+      "grad_norm": 3.176950693130493,
       "learning_rate": 2.962962962962963e-05,
-      "loss": 0.2709,
+      "loss": 0.1936,
       "step": 140
     },
     {
       "epoch": 4.918032786885246,
-      "grad_norm": 2.006906747817993,
+      "grad_norm": 3.4379076957702637,
       "learning_rate": 2.777777777777778e-05,
-      "loss": 0.2612,
+      "loss": 0.1793,
       "step": 150
     },
     {
       "epoch": 4.983606557377049,
-      "eval_accuracy": 0.8710462287104623,
-      "eval_loss": 0.28622761368751526,
-      "eval_runtime": 47.1214,
-      "eval_samples_per_second": 8.722,
-      "eval_steps_per_second": 0.149,
+      "eval_accuracy": 0.9051094890510949,
+      "eval_loss": 0.22886711359024048,
+      "eval_runtime": 46.6942,
+      "eval_samples_per_second": 8.802,
+      "eval_steps_per_second": 0.15,
       "step": 152
     },
     {
       "epoch": 5.245901639344262,
-      "grad_norm": 2.6484014987945557,
+      "grad_norm": 3.050398826599121,
       "learning_rate": 2.5925925925925925e-05,
-      "loss": 0.2525,
+      "loss": 0.206,
       "step": 160
     },
     {
       "epoch": 5.573770491803279,
-      "grad_norm": 2.379870891571045,
+      "grad_norm": 4.712157726287842,
       "learning_rate": 2.4074074074074074e-05,
-      "loss": 0.2548,
+      "loss": 0.1786,
       "step": 170
     },
     {
       "epoch": 5.901639344262295,
-      "grad_norm": 2.97287917137146,
+      "grad_norm": 2.9319636821746826,
       "learning_rate": 2.2222222222222223e-05,
-      "loss": 0.2412,
+      "loss": 0.1817,
       "step": 180
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.8856447688564477,
-      "eval_loss": 0.26367661356925964,
-      "eval_runtime": 46.9018,
-      "eval_samples_per_second": 8.763,
-      "eval_steps_per_second": 0.149,
+      "eval_accuracy": 0.9075425790754258,
+      "eval_loss": 0.21736063063144684,
+      "eval_runtime": 46.7917,
+      "eval_samples_per_second": 8.784,
+      "eval_steps_per_second": 0.15,
       "step": 183
     },
     {
       "epoch": 6.229508196721311,
-      "grad_norm": 2.9260308742523193,
+      "grad_norm": 2.2905595302581787,
       "learning_rate": 2.037037037037037e-05,
-      "loss": 0.246,
+      "loss": 0.1596,
       "step": 190
     },
     {
       "epoch": 6.557377049180328,
-      "grad_norm": 3.2257614135742188,
+      "grad_norm": 2.4842424392700195,
       "learning_rate": 1.8518518518518518e-05,
-      "loss": 0.2434,
+      "loss": 0.18,
       "step": 200
     },
     {
       "epoch": 6.885245901639344,
-      "grad_norm": 2.4753129482269287,
+      "grad_norm": 2.992955207824707,
       "learning_rate": 1.6666666666666667e-05,
-      "loss": 0.2533,
+      "loss": 0.1852,
       "step": 210
     },
     {
       "epoch": 6.983606557377049,
-      "eval_accuracy": 0.878345498783455,
-      "eval_loss": 0.27688971161842346,
-      "eval_runtime": 46.8021,
+      "eval_accuracy": 0.9002433090024331,
+      "eval_loss": 0.22296269237995148,
+      "eval_runtime": 46.8007,
       "eval_samples_per_second": 8.782,
       "eval_steps_per_second": 0.15,
       "step": 213
     },
     {
       "epoch": 7.213114754098361,
-      "grad_norm": 2.772411584854126,
+      "grad_norm": 3.4494433403015137,
       "learning_rate": 1.4814814814814815e-05,
-      "loss": 0.2399,
+      "loss": 0.1667,
       "step": 220
     },
     {
       "epoch": 7.540983606557377,
-      "grad_norm": 2.4606740474700928,
+      "grad_norm": 2.3728301525115967,
       "learning_rate": 1.2962962962962962e-05,
-      "loss": 0.2454,
+      "loss": 0.1626,
       "step": 230
     },
     {
       "epoch": 7.868852459016393,
-      "grad_norm": 2.5486361980438232,
+      "grad_norm": 3.760058641433716,
       "learning_rate": 1.1111111111111112e-05,
-      "loss": 0.2413,
+      "loss": 0.1739,
       "step": 240
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.8832116788321168,
-      "eval_loss": 0.26485782861709595,
-      "eval_runtime": 47.0631,
-      "eval_samples_per_second": 8.733,
+      "eval_accuracy": 0.9099756690997567,
+      "eval_loss": 0.21712711453437805,
+      "eval_runtime": 46.8608,
+      "eval_samples_per_second": 8.771,
       "eval_steps_per_second": 0.149,
       "step": 244
     },
     {
       "epoch": 8.19672131147541,
-      "grad_norm": 4.631506443023682,
+      "grad_norm": 3.204749584197998,
       "learning_rate": 9.259259259259259e-06,
-      "loss": 0.2199,
+      "loss": 0.1717,
       "step": 250
     },
     {
       "epoch": 8.524590163934427,
-      "grad_norm": 2.3710556030273438,
+      "grad_norm": 3.4265105724334717,
       "learning_rate": 7.4074074074074075e-06,
-      "loss": 0.2372,
+      "loss": 0.1585,
       "step": 260
     },
     {
       "epoch": 8.852459016393443,
-      "grad_norm": 4.1779608726501465,
+      "grad_norm": 3.0664563179016113,
       "learning_rate": 5.555555555555556e-06,
-      "loss": 0.2139,
+      "loss": 0.1569,
       "step": 270
     },
     {
       "epoch": 8.98360655737705,
-      "eval_accuracy": 0.878345498783455,
-      "eval_loss": 0.2632748484611511,
-      "eval_runtime": 46.7653,
-      "eval_samples_per_second": 8.789,
-      "eval_steps_per_second": 0.15,
+      "eval_accuracy": 0.9148418491484185,
+      "eval_loss": 0.2113640010356903,
+      "eval_runtime": 47.0024,
+      "eval_samples_per_second": 8.744,
+      "eval_steps_per_second": 0.149,
       "step": 274
     },
     {
       "epoch": 9.180327868852459,
-      "grad_norm": 2.4798853397369385,
+      "grad_norm": 4.030396461486816,
       "learning_rate": 3.7037037037037037e-06,
-      "loss": 0.2365,
+      "loss": 0.1555,
       "step": 280
     },
     {
       "epoch": 9.508196721311476,
-      "grad_norm": 3.2969157695770264,
+      "grad_norm": 2.520259380340576,
       "learning_rate": 1.8518518518518519e-06,
-      "loss": 0.2242,
+      "loss": 0.1667,
       "step": 290
     },
     {
       "epoch": 9.836065573770492,
-      "grad_norm": 2.2613918781280518,
+      "grad_norm": 2.792572021484375,
       "learning_rate": 0.0,
-      "loss": 0.2087,
+      "loss": 0.1589,
       "step": 300
     },
     {
       "epoch": 9.836065573770492,
-      "eval_accuracy": 0.8807785888077859,
-      "eval_loss": 0.2599342465400696,
-      "eval_runtime": 47.0372,
-      "eval_samples_per_second": 8.738,
-      "eval_steps_per_second": 0.149,
+      "eval_accuracy": 0.9099756690997567,
+      "eval_loss": 0.21540850400924683,
+      "eval_runtime": 46.8053,
+      "eval_samples_per_second": 8.781,
+      "eval_steps_per_second": 0.15,
       "step": 300
     },
     {
       "epoch": 9.836065573770492,
       "step": 300,
-      "total_flos": 1.9063087726729052e+18,
-      "train_loss": 0.3090126927693685,
-      "train_runtime": 8089.4797,
-      "train_samples_per_second": 9.637,
+      "total_flos": 1.9365344998357156e+18,
+      "train_loss": 0.1960654123624166,
+      "train_runtime": 8023.8475,
+      "train_samples_per_second": 9.716,
       "train_steps_per_second": 0.037
     }
   ],
@@ -335,7 +335,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9063087726729052e+18,
+  "total_flos": 1.9365344998357156e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null