End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8708677685950413
+      value: 0.8729338842975206
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/swin-base-patch4-window7-224-in22k](https://huggingface.co/microsoft/swin-base-patch4-window7-224-in22k) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3443
-- Accuracy: 0.8709
+- Loss: 0.3427
+- Accuracy: 0.8729
 
 ## Model description
 

all_results.json

@@ -1,13 +1,13 @@
 {
-    "epoch": 6.686567164179104,
-    "eval_accuracy": 0.8639652677279306,
-    "eval_loss": 0.3239884674549103,
-    "eval_runtime": 76.2847,
-    "eval_samples_per_second": 9.058,
+    "epoch": 6.885245901639344,
+    "eval_accuracy": 0.8729338842975206,
+    "eval_loss": 0.34267309308052063,
+    "eval_runtime": 203.1004,
+    "eval_samples_per_second": 9.532,
     "eval_steps_per_second": 0.079,
-    "total_flos": 4.4574447113624494e+18,
-    "train_loss": 0.43422421866229605,
-    "train_runtime": 7488.3728,
-    "train_samples_per_second": 7.947,
-    "train_steps_per_second": 0.015
+    "total_flos": 4.180411553219629e+18,
+    "train_loss": 0.4180879854020618,
+    "train_runtime": 6613.2188,
+    "train_samples_per_second": 8.194,
+    "train_steps_per_second": 0.016
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 6.686567164179104,
-    "eval_accuracy": 0.8639652677279306,
-    "eval_loss": 0.3239884674549103,
-    "eval_runtime": 76.2847,
-    "eval_samples_per_second": 9.058,
+    "epoch": 6.885245901639344,
+    "eval_accuracy": 0.8729338842975206,
+    "eval_loss": 0.34267309308052063,
+    "eval_runtime": 203.1004,
+    "eval_samples_per_second": 9.532,
     "eval_steps_per_second": 0.079
 }

runs/Aug23_04-58-01_data-science-wbi/events.out.tfevents.1724395926.data-science-wbi

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6348eba7eeb30f931b5d1c17800381b93399959311d3c8e48d017ce710f9bfed
+size 87

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 6.686567164179104,
-    "total_flos": 4.4574447113624494e+18,
-    "train_loss": 0.43422421866229605,
-    "train_runtime": 7488.3728,
-    "train_samples_per_second": 7.947,
-    "train_steps_per_second": 0.015
+    "epoch": 6.885245901639344,
+    "total_flos": 4.180411553219629e+18,
+    "train_loss": 0.4180879854020618,
+    "train_runtime": 6613.2188,
+    "train_samples_per_second": 8.194,
+    "train_steps_per_second": 0.016
 }

trainer_state.json

@@ -1,165 +1,158 @@
 {
-  "best_metric": 0.8639652677279306,
-  "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-MM_Classification_base_V10/checkpoint-100",
-  "epoch": 6.686567164179104,
+  "best_metric": 0.8729338842975206,
+  "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-MM_Classification_base_V10/checkpoint-91",
+  "epoch": 6.885245901639344,
   "eval_steps": 500,
-  "global_step": 112,
+  "global_step": 105,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.5970149253731343,
-      "grad_norm": 3.4567720890045166,
-      "learning_rate": 4.166666666666667e-05,
-      "loss": 0.9254,
+      "epoch": 0.6557377049180327,
+      "grad_norm": 1.847607135772705,
+      "learning_rate": 4.545454545454546e-05,
+      "loss": 0.7948,
       "step": 10
     },
     {
-      "epoch": 0.9552238805970149,
-      "eval_accuracy": 0.8133140376266281,
-      "eval_loss": 0.4842127859592438,
-      "eval_runtime": 115.4192,
-      "eval_samples_per_second": 5.987,
-      "eval_steps_per_second": 0.052,
-      "step": 16
+      "epoch": 0.9836065573770492,
+      "eval_accuracy": 0.8352272727272727,
+      "eval_loss": 0.4498441815376282,
+      "eval_runtime": 204.2611,
+      "eval_samples_per_second": 9.478,
+      "eval_steps_per_second": 0.078,
+      "step": 15
     },
     {
-      "epoch": 1.1940298507462686,
-      "grad_norm": 2.1373002529144287,
-      "learning_rate": 4.600000000000001e-05,
-      "loss": 0.5607,
+      "epoch": 1.3114754098360657,
+      "grad_norm": 2.3756892681121826,
+      "learning_rate": 4.5212765957446815e-05,
+      "loss": 0.5062,
       "step": 20
     },
     {
-      "epoch": 1.7910447761194028,
-      "grad_norm": 1.4010789394378662,
-      "learning_rate": 4.1e-05,
-      "loss": 0.4552,
+      "epoch": 1.9672131147540983,
+      "grad_norm": 1.4792882204055786,
+      "learning_rate": 3.9893617021276594e-05,
+      "loss": 0.4439,
       "step": 30
     },
     {
-      "epoch": 1.9701492537313432,
-      "eval_accuracy": 0.849493487698987,
-      "eval_loss": 0.3855249881744385,
-      "eval_runtime": 118.0615,
-      "eval_samples_per_second": 5.853,
-      "eval_steps_per_second": 0.051,
-      "step": 33
+      "epoch": 1.9672131147540983,
+      "eval_accuracy": 0.8589876033057852,
+      "eval_loss": 0.38362234830856323,
+      "eval_runtime": 210.2217,
+      "eval_samples_per_second": 9.209,
+      "eval_steps_per_second": 0.076,
+      "step": 30
     },
     {
-      "epoch": 2.388059701492537,
-      "grad_norm": 3.225425958633423,
-      "learning_rate": 3.6e-05,
-      "loss": 0.4006,
+      "epoch": 2.6229508196721314,
+      "grad_norm": 2.130309581756592,
+      "learning_rate": 3.4574468085106386e-05,
+      "loss": 0.4024,
       "step": 40
     },
     {
-      "epoch": 2.9850746268656714,
-      "grad_norm": 1.8630387783050537,
-      "learning_rate": 3.1e-05,
-      "loss": 0.4034,
-      "step": 50
+      "epoch": 2.9508196721311473,
+      "eval_accuracy": 0.8600206611570248,
+      "eval_loss": 0.36524850130081177,
+      "eval_runtime": 204.4105,
+      "eval_samples_per_second": 9.471,
+      "eval_steps_per_second": 0.078,
+      "step": 45
     },
     {
-      "epoch": 2.9850746268656714,
-      "eval_accuracy": 0.8610709117221418,
-      "eval_loss": 0.34522491693496704,
-      "eval_runtime": 76.1197,
-      "eval_samples_per_second": 9.078,
-      "eval_steps_per_second": 0.079,
+      "epoch": 3.278688524590164,
+      "grad_norm": 2.3738443851470947,
+      "learning_rate": 2.925531914893617e-05,
+      "loss": 0.3801,
       "step": 50
     },
     {
-      "epoch": 3.582089552238806,
-      "grad_norm": 2.277456521987915,
-      "learning_rate": 2.6000000000000002e-05,
-      "loss": 0.3583,
+      "epoch": 3.9344262295081966,
+      "grad_norm": 3.785062074661255,
+      "learning_rate": 2.393617021276596e-05,
+      "loss": 0.3562,
       "step": 60
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8581765557163531,
-      "eval_loss": 0.33568304777145386,
-      "eval_runtime": 76.3565,
-      "eval_samples_per_second": 9.05,
-      "eval_steps_per_second": 0.079,
-      "step": 67
+      "eval_accuracy": 0.8641528925619835,
+      "eval_loss": 0.34744057059288025,
+      "eval_runtime": 203.8324,
+      "eval_samples_per_second": 9.498,
+      "eval_steps_per_second": 0.078,
+      "step": 61
     },
     {
-      "epoch": 4.17910447761194,
-      "grad_norm": 1.8838659524917603,
-      "learning_rate": 2.1e-05,
-      "loss": 0.3683,
+      "epoch": 4.590163934426229,
+      "grad_norm": 3.449556827545166,
+      "learning_rate": 1.8617021276595745e-05,
+      "loss": 0.345,
       "step": 70
     },
     {
-      "epoch": 4.776119402985074,
-      "grad_norm": 2.815551996231079,
-      "learning_rate": 1.6000000000000003e-05,
-      "loss": 0.353,
-      "step": 80
+      "epoch": 4.983606557377049,
+      "eval_accuracy": 0.868801652892562,
+      "eval_loss": 0.34286215901374817,
+      "eval_runtime": 203.6664,
+      "eval_samples_per_second": 9.506,
+      "eval_steps_per_second": 0.079,
+      "step": 76
     },
     {
-      "epoch": 4.955223880597015,
-      "eval_accuracy": 0.8625180897250362,
-      "eval_loss": 0.32812753319740295,
-      "eval_runtime": 76.4607,
-      "eval_samples_per_second": 9.037,
-      "eval_steps_per_second": 0.078,
-      "step": 83
+      "epoch": 5.245901639344262,
+      "grad_norm": 2.114426851272583,
+      "learning_rate": 1.3297872340425532e-05,
+      "loss": 0.3374,
+      "step": 80
     },
     {
-      "epoch": 5.373134328358209,
-      "grad_norm": 2.2589757442474365,
-      "learning_rate": 1.1000000000000001e-05,
-      "loss": 0.3218,
+      "epoch": 5.901639344262295,
+      "grad_norm": 4.8909759521484375,
+      "learning_rate": 7.97872340425532e-06,
+      "loss": 0.3379,
       "step": 90
     },
     {
-      "epoch": 5.970149253731344,
-      "grad_norm": 2.3260316848754883,
-      "learning_rate": 6e-06,
-      "loss": 0.3387,
-      "step": 100
-    },
-    {
-      "epoch": 5.970149253731344,
-      "eval_accuracy": 0.8639652677279306,
-      "eval_loss": 0.3239884674549103,
-      "eval_runtime": 76.5373,
-      "eval_samples_per_second": 9.028,
+      "epoch": 5.967213114754099,
+      "eval_accuracy": 0.8729338842975206,
+      "eval_loss": 0.34267309308052063,
+      "eval_runtime": 204.1334,
+      "eval_samples_per_second": 9.484,
       "eval_steps_per_second": 0.078,
-      "step": 100
+      "step": 91
     },
     {
-      "epoch": 6.567164179104478,
-      "grad_norm": 2.35009765625,
-      "learning_rate": 1.0000000000000002e-06,
-      "loss": 0.3157,
-      "step": 110
+      "epoch": 6.557377049180328,
+      "grad_norm": 3.155640125274658,
+      "learning_rate": 2.6595744680851065e-06,
+      "loss": 0.3213,
+      "step": 100
     },
     {
-      "epoch": 6.686567164179104,
-      "eval_accuracy": 0.8639652677279306,
-      "eval_loss": 0.325300008058548,
-      "eval_runtime": 76.553,
-      "eval_samples_per_second": 9.026,
-      "eval_steps_per_second": 0.078,
-      "step": 112
+      "epoch": 6.885245901639344,
+      "eval_accuracy": 0.8708677685950413,
+      "eval_loss": 0.3443421423435211,
+      "eval_runtime": 203.5472,
+      "eval_samples_per_second": 9.511,
+      "eval_steps_per_second": 0.079,
+      "step": 105
     },
     {
-      "epoch": 6.686567164179104,
-      "step": 112,
-      "total_flos": 4.4574447113624494e+18,
-      "train_loss": 0.43422421866229605,
-      "train_runtime": 7488.3728,
-      "train_samples_per_second": 7.947,
-      "train_steps_per_second": 0.015
+      "epoch": 6.885245901639344,
+      "step": 105,
+      "total_flos": 4.180411553219629e+18,
+      "train_loss": 0.4180879854020618,
+      "train_runtime": 6613.2188,
+      "train_samples_per_second": 8.194,
+      "train_steps_per_second": 0.016
     }
   ],
   "logging_steps": 10,
-  "max_steps": 112,
+  "max_steps": 105,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 7,
   "save_steps": 500,
@@ -175,7 +168,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.4574447113624494e+18,
+  "total_flos": 4.180411553219629e+18,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null