End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.8879227053140096
+      value: 0.9497584541062802
 ---
 
 <!-- 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 [facebook/vit-msn-small](https://huggingface.co/facebook/vit-msn-small) on the imagefolder dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3520
-- Accuracy: 0.8879
+- Loss: 0.1871
+- Accuracy: 0.9498
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 18.46153846153846,
+    "eval_accuracy": 0.9497584541062802,
+    "eval_loss": 0.1871330887079239,
+    "eval_runtime": 4.3162,
+    "eval_samples_per_second": 239.797,
+    "eval_steps_per_second": 3.939,
+    "total_flos": 2.9458314315627725e+17,
+    "train_loss": 0.35900469223658243,
+    "train_runtime": 212.0852,
+    "train_samples_per_second": 76.856,
+    "train_steps_per_second": 0.283
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 18.46153846153846,
+    "eval_accuracy": 0.9497584541062802,
+    "eval_loss": 0.1871330887079239,
+    "eval_runtime": 4.3162,
+    "eval_samples_per_second": 239.797,
+    "eval_steps_per_second": 3.939
+}

runs/Jan14_17-38-22_c583982b4f3d/events.out.tfevents.1736876536.c583982b4f3d.215.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21caf6cc841fb69179ec969142789a3901dcdcfe6451bd8a6d89dff3e5f75a3b
+size 722

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 18.46153846153846,
+    "total_flos": 2.9458314315627725e+17,
+    "train_loss": 0.35900469223658243,
+    "train_runtime": 212.0852,
+    "train_samples_per_second": 76.856,
+    "train_steps_per_second": 0.283
+}

trainer_state.json

@@ -0,0 +1,255 @@
+{
+  "best_metric": 0.9497584541062802,
+  "best_model_checkpoint": "vit-msn-small-corect_deepcleaned_dataset_lateral_flow_ivalidation/checkpoint-22",
+  "epoch": 18.46153846153846,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9230769230769231,
+      "eval_accuracy": 0.8927536231884058,
+      "eval_loss": 0.3933483958244324,
+      "eval_runtime": 4.3694,
+      "eval_samples_per_second": 236.874,
+      "eval_steps_per_second": 3.891,
+      "step": 3
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "eval_accuracy": 0.9188405797101449,
+      "eval_loss": 0.4166622459888458,
+      "eval_runtime": 4.2818,
+      "eval_samples_per_second": 241.72,
+      "eval_steps_per_second": 3.97,
+      "step": 6
+    },
+    {
+      "epoch": 2.769230769230769,
+      "eval_accuracy": 0.4966183574879227,
+      "eval_loss": 0.933142364025116,
+      "eval_runtime": 4.3066,
+      "eval_samples_per_second": 240.328,
+      "eval_steps_per_second": 3.947,
+      "step": 9
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 62.32957458496094,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.615,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9178743961352657,
+      "eval_loss": 0.3084805905818939,
+      "eval_runtime": 4.3796,
+      "eval_samples_per_second": 236.322,
+      "eval_steps_per_second": 3.882,
+      "step": 13
+    },
+    {
+      "epoch": 4.923076923076923,
+      "eval_accuracy": 0.9333333333333333,
+      "eval_loss": 0.22097891569137573,
+      "eval_runtime": 4.3446,
+      "eval_samples_per_second": 238.226,
+      "eval_steps_per_second": 3.913,
+      "step": 16
+    },
+    {
+      "epoch": 5.846153846153846,
+      "eval_accuracy": 0.9391304347826087,
+      "eval_loss": 0.21061654388904572,
+      "eval_runtime": 4.4485,
+      "eval_samples_per_second": 232.66,
+      "eval_steps_per_second": 3.821,
+      "step": 19
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 3.9477076530456543,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.3763,
+      "step": 20
+    },
+    {
+      "epoch": 6.769230769230769,
+      "eval_accuracy": 0.9497584541062802,
+      "eval_loss": 0.1871330887079239,
+      "eval_runtime": 4.3598,
+      "eval_samples_per_second": 237.396,
+      "eval_steps_per_second": 3.899,
+      "step": 22
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9371980676328503,
+      "eval_loss": 0.20427261292934418,
+      "eval_runtime": 4.2827,
+      "eval_samples_per_second": 241.673,
+      "eval_steps_per_second": 3.97,
+      "step": 26
+    },
+    {
+      "epoch": 8.923076923076923,
+      "eval_accuracy": 0.8888888888888888,
+      "eval_loss": 0.31205740571022034,
+      "eval_runtime": 4.4195,
+      "eval_samples_per_second": 234.192,
+      "eval_steps_per_second": 3.847,
+      "step": 29
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 4.070008754730225,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.3511,
+      "step": 30
+    },
+    {
+      "epoch": 9.846153846153847,
+      "eval_accuracy": 0.9314009661835749,
+      "eval_loss": 0.20154337584972382,
+      "eval_runtime": 4.2969,
+      "eval_samples_per_second": 240.871,
+      "eval_steps_per_second": 3.956,
+      "step": 32
+    },
+    {
+      "epoch": 10.76923076923077,
+      "eval_accuracy": 0.8376811594202899,
+      "eval_loss": 0.44852134585380554,
+      "eval_runtime": 4.3709,
+      "eval_samples_per_second": 236.795,
+      "eval_steps_per_second": 3.889,
+      "step": 35
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.9285024154589372,
+      "eval_loss": 0.24452261626720428,
+      "eval_runtime": 4.3262,
+      "eval_samples_per_second": 239.241,
+      "eval_steps_per_second": 3.93,
+      "step": 39
+    },
+    {
+      "epoch": 12.307692307692308,
+      "grad_norm": 7.704187393188477,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.2962,
+      "step": 40
+    },
+    {
+      "epoch": 12.923076923076923,
+      "eval_accuracy": 0.9053140096618357,
+      "eval_loss": 0.30447185039520264,
+      "eval_runtime": 4.2886,
+      "eval_samples_per_second": 241.336,
+      "eval_steps_per_second": 3.964,
+      "step": 42
+    },
+    {
+      "epoch": 13.846153846153847,
+      "eval_accuracy": 0.8714975845410629,
+      "eval_loss": 0.3914734721183777,
+      "eval_runtime": 4.4006,
+      "eval_samples_per_second": 235.195,
+      "eval_steps_per_second": 3.863,
+      "step": 45
+    },
+    {
+      "epoch": 14.76923076923077,
+      "eval_accuracy": 0.893719806763285,
+      "eval_loss": 0.31650951504707336,
+      "eval_runtime": 4.327,
+      "eval_samples_per_second": 239.195,
+      "eval_steps_per_second": 3.929,
+      "step": 48
+    },
+    {
+      "epoch": 15.384615384615385,
+      "grad_norm": 5.901269912719727,
+      "learning_rate": 9.259259259259259e-06,
+      "loss": 0.2553,
+      "step": 50
+    },
+    {
+      "epoch": 16.0,
+      "eval_accuracy": 0.9082125603864735,
+      "eval_loss": 0.28225788474082947,
+      "eval_runtime": 4.4633,
+      "eval_samples_per_second": 231.89,
+      "eval_steps_per_second": 3.809,
+      "step": 52
+    },
+    {
+      "epoch": 16.923076923076923,
+      "eval_accuracy": 0.8869565217391304,
+      "eval_loss": 0.3504292070865631,
+      "eval_runtime": 4.37,
+      "eval_samples_per_second": 236.841,
+      "eval_steps_per_second": 3.89,
+      "step": 55
+    },
+    {
+      "epoch": 17.846153846153847,
+      "eval_accuracy": 0.8869565217391304,
+      "eval_loss": 0.36792051792144775,
+      "eval_runtime": 4.4082,
+      "eval_samples_per_second": 234.792,
+      "eval_steps_per_second": 3.856,
+      "step": 58
+    },
+    {
+      "epoch": 18.46153846153846,
+      "grad_norm": 7.85857629776001,
+      "learning_rate": 0.0,
+      "loss": 0.2601,
+      "step": 60
+    },
+    {
+      "epoch": 18.46153846153846,
+      "eval_accuracy": 0.8879227053140096,
+      "eval_loss": 0.3520191013813019,
+      "eval_runtime": 4.3424,
+      "eval_samples_per_second": 238.347,
+      "eval_steps_per_second": 3.915,
+      "step": 60
+    },
+    {
+      "epoch": 18.46153846153846,
+      "step": 60,
+      "total_flos": 2.9458314315627725e+17,
+      "train_loss": 0.35900469223658243,
+      "train_runtime": 212.0852,
+      "train_samples_per_second": 76.856,
+      "train_steps_per_second": 0.283
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "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": 2.9458314315627725e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}