End of training

README.md

@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8758002560819462
+      value: 0.882202304737516
 ---
 
 <!-- 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-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: 0.2967
-- Accuracy: 0.8758
+- Loss: 0.3018
+- Accuracy: 0.8822
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.882202304737516,
+    "eval_loss": 0.30182477831840515,
+    "eval_runtime": 76.9874,
+    "eval_samples_per_second": 10.145,
+    "eval_steps_per_second": 0.091,
+    "total_flos": 5.277497331917003e+18,
+    "train_loss": 0.41070275199144407,
+    "train_runtime": 6937.9689,
+    "train_samples_per_second": 9.709,
+    "train_steps_per_second": 0.019
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "eval_accuracy": 0.882202304737516,
+    "eval_loss": 0.30182477831840515,
+    "eval_runtime": 76.9874,
+    "eval_samples_per_second": 10.145,
+    "eval_steps_per_second": 0.091
+}

runs/Jul30_08-40-19_567981ebf77b/events.out.tfevents.1722335861.567981ebf77b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74e042b3d9435989dafb314cbf65f8bc377672c9b5d1a3bfb0a004516ef41fe
+size 88

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 7.0,
+    "total_flos": 5.277497331917003e+18,
+    "train_loss": 0.41070275199144407,
+    "train_runtime": 6937.9689,
+    "train_samples_per_second": 9.709,
+    "train_steps_per_second": 0.019
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": 0.882202304737516,
+  "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-MM_Classification_base_V2/checkpoint-95",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 133,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 3.8548967838287354,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.0086,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8104993597951344,
+      "eval_loss": 0.46133849024772644,
+      "eval_runtime": 105.6355,
+      "eval_samples_per_second": 7.393,
+      "eval_steps_per_second": 0.066,
+      "step": 19
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 2.950881004333496,
+      "learning_rate": 4.747899159663866e-05,
+      "loss": 0.5973,
+      "step": 20
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 2.2539196014404297,
+      "learning_rate": 4.327731092436975e-05,
+      "loss": 0.4528,
+      "step": 30
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8591549295774648,
+      "eval_loss": 0.34540724754333496,
+      "eval_runtime": 76.8371,
+      "eval_samples_per_second": 10.164,
+      "eval_steps_per_second": 0.091,
+      "step": 38
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 3.1359307765960693,
+      "learning_rate": 3.907563025210084e-05,
+      "loss": 0.4012,
+      "step": 40
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 2.3296256065368652,
+      "learning_rate": 3.487394957983193e-05,
+      "loss": 0.3556,
+      "step": 50
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8604353393085787,
+      "eval_loss": 0.3289111256599426,
+      "eval_runtime": 76.7315,
+      "eval_samples_per_second": 10.178,
+      "eval_steps_per_second": 0.091,
+      "step": 57
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 2.8277525901794434,
+      "learning_rate": 3.0672268907563026e-05,
+      "loss": 0.3617,
+      "step": 60
+    },
+    {
+      "epoch": 3.6842105263157894,
+      "grad_norm": 4.305710315704346,
+      "learning_rate": 2.647058823529412e-05,
+      "loss": 0.3404,
+      "step": 70
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8783610755441741,
+      "eval_loss": 0.31966593861579895,
+      "eval_runtime": 76.5627,
+      "eval_samples_per_second": 10.201,
+      "eval_steps_per_second": 0.091,
+      "step": 76
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 2.8584775924682617,
+      "learning_rate": 2.226890756302521e-05,
+      "loss": 0.3185,
+      "step": 80
+    },
+    {
+      "epoch": 4.7368421052631575,
+      "grad_norm": 2.855238914489746,
+      "learning_rate": 1.8067226890756303e-05,
+      "loss": 0.3175,
+      "step": 90
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.882202304737516,
+      "eval_loss": 0.30182477831840515,
+      "eval_runtime": 76.8406,
+      "eval_samples_per_second": 10.164,
+      "eval_steps_per_second": 0.091,
+      "step": 95
+    },
+    {
+      "epoch": 5.2631578947368425,
+      "grad_norm": 3.1406571865081787,
+      "learning_rate": 1.3865546218487396e-05,
+      "loss": 0.3057,
+      "step": 100
+    },
+    {
+      "epoch": 5.7894736842105265,
+      "grad_norm": 1.8491476774215698,
+      "learning_rate": 9.663865546218488e-06,
+      "loss": 0.3007,
+      "step": 110
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8809218950064021,
+      "eval_loss": 0.3006611168384552,
+      "eval_runtime": 76.8476,
+      "eval_samples_per_second": 10.163,
+      "eval_steps_per_second": 0.091,
+      "step": 114
+    },
+    {
+      "epoch": 6.315789473684211,
+      "grad_norm": 1.944622278213501,
+      "learning_rate": 5.46218487394958e-06,
+      "loss": 0.304,
+      "step": 120
+    },
+    {
+      "epoch": 6.842105263157895,
+      "grad_norm": 2.5420796871185303,
+      "learning_rate": 1.2605042016806724e-06,
+      "loss": 0.2968,
+      "step": 130
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8758002560819462,
+      "eval_loss": 0.2966699004173279,
+      "eval_runtime": 77.233,
+      "eval_samples_per_second": 10.112,
+      "eval_steps_per_second": 0.091,
+      "step": 133
+    },
+    {
+      "epoch": 7.0,
+      "step": 133,
+      "total_flos": 5.277497331917003e+18,
+      "train_loss": 0.41070275199144407,
+      "train_runtime": 6937.9689,
+      "train_samples_per_second": 9.709,
+      "train_steps_per_second": 0.019
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 133,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.277497331917003e+18,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}