End of training

README.md

@@ -23,7 +23,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.7304832713754646
+      value: 0.8810408921933085
 ---
 
 <!-- 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: 0.5725
-- Accuracy: 0.7305
+- Loss: 0.2823
+- Accuracy: 0.8810
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 9.23076923076923,
+    "eval_accuracy": 0.8810408921933085,
+    "eval_loss": 0.28232070803642273,
+    "eval_runtime": 2.2781,
+    "eval_samples_per_second": 236.157,
+    "eval_steps_per_second": 3.951,
+    "total_flos": 2.915891733872517e+17,
+    "train_loss": 0.38718650341033933,
+    "train_runtime": 154.7877,
+    "train_samples_per_second": 104.207,
+    "train_steps_per_second": 0.388
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.23076923076923,
+    "eval_accuracy": 0.8810408921933085,
+    "eval_loss": 0.28232070803642273,
+    "eval_runtime": 2.2781,
+    "eval_samples_per_second": 236.157,
+    "eval_steps_per_second": 3.951
+}

runs/Jan15_17-47-09_c583982b4f3d/events.out.tfevents.1736963429.c583982b4f3d.215.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:306b2a042f385622c45a533a1583b001d603aa78d96f7f08f017fa7cb90ef877
+size 405

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 9.23076923076923,
+    "total_flos": 2.915891733872517e+17,
+    "train_loss": 0.38718650341033933,
+    "train_runtime": 154.7877,
+    "train_samples_per_second": 104.207,
+    "train_steps_per_second": 0.388
+}

trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_metric": 0.28232070803642273,
+  "best_model_checkpoint": "vit-msn-small-lateral_flow_ivalidation_green_test/checkpoint-13",
+  "epoch": 9.23076923076923,
+  "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": 0.79182156133829,
+      "eval_loss": 0.4105704724788666,
+      "eval_runtime": 2.4272,
+      "eval_samples_per_second": 221.657,
+      "eval_steps_per_second": 3.708,
+      "step": 6
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 35.90373229980469,
+      "learning_rate": 4.62962962962963e-05,
+      "loss": 0.5328,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8810408921933085,
+      "eval_loss": 0.28232070803642273,
+      "eval_runtime": 2.428,
+      "eval_samples_per_second": 221.579,
+      "eval_steps_per_second": 3.707,
+      "step": 13
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "eval_accuracy": 0.8587360594795539,
+      "eval_loss": 0.3050999343395233,
+      "eval_runtime": 2.3639,
+      "eval_samples_per_second": 227.587,
+      "eval_steps_per_second": 3.807,
+      "step": 19
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 7.078850269317627,
+      "learning_rate": 3.7037037037037037e-05,
+      "loss": 0.4244,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8996282527881041,
+      "eval_loss": 0.2912784218788147,
+      "eval_runtime": 2.5552,
+      "eval_samples_per_second": 210.551,
+      "eval_steps_per_second": 3.522,
+      "step": 26
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 7.146331310272217,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.3755,
+      "step": 30
+    },
+    {
+      "epoch": 4.923076923076923,
+      "eval_accuracy": 0.9052044609665427,
+      "eval_loss": 0.2840980887413025,
+      "eval_runtime": 2.4709,
+      "eval_samples_per_second": 217.734,
+      "eval_steps_per_second": 3.642,
+      "step": 32
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8828996282527881,
+      "eval_loss": 0.32043400406837463,
+      "eval_runtime": 2.4097,
+      "eval_samples_per_second": 223.265,
+      "eval_steps_per_second": 3.735,
+      "step": 39
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 5.55441427230835,
+      "learning_rate": 1.8518518518518518e-05,
+      "loss": 0.3569,
+      "step": 40
+    },
+    {
+      "epoch": 6.923076923076923,
+      "eval_accuracy": 0.8810408921933085,
+      "eval_loss": 0.2981695532798767,
+      "eval_runtime": 2.3262,
+      "eval_samples_per_second": 231.282,
+      "eval_steps_per_second": 3.869,
+      "step": 45
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 4.577017784118652,
+      "learning_rate": 9.259259259259259e-06,
+      "loss": 0.3157,
+      "step": 50
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8643122676579925,
+      "eval_loss": 0.33173713088035583,
+      "eval_runtime": 2.3575,
+      "eval_samples_per_second": 228.205,
+      "eval_steps_per_second": 3.818,
+      "step": 52
+    },
+    {
+      "epoch": 8.923076923076923,
+      "eval_accuracy": 0.724907063197026,
+      "eval_loss": 0.5731077194213867,
+      "eval_runtime": 2.4282,
+      "eval_samples_per_second": 221.561,
+      "eval_steps_per_second": 3.706,
+      "step": 58
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 6.767743110656738,
+      "learning_rate": 0.0,
+      "loss": 0.3177,
+      "step": 60
+    },
+    {
+      "epoch": 9.23076923076923,
+      "eval_accuracy": 0.7304832713754646,
+      "eval_loss": 0.5724764466285706,
+      "eval_runtime": 2.3931,
+      "eval_samples_per_second": 224.808,
+      "eval_steps_per_second": 3.761,
+      "step": 60
+    },
+    {
+      "epoch": 9.23076923076923,
+      "step": 60,
+      "total_flos": 2.915891733872517e+17,
+      "train_loss": 0.38718650341033933,
+      "train_runtime": 154.7877,
+      "train_samples_per_second": 104.207,
+      "train_steps_per_second": 0.388
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 2.915891733872517e+17,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}