TirathP/humanAction

README.md

@@ -2,6 +2,7 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224
 tags:
+- image-classification
 - generated_from_trainer
 metrics:
 - accuracy
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # fine-tuned
 
-This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on an unknown dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the custom-huggingface dataset.
 It achieves the following results on the evaluation set:
 - Loss: 7.3529
 - Accuracy: 0.0596

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 1.0,
-    "eval_f1": 1.0,
-    "eval_loss": 0.1679225116968155,
-    "eval_runtime": 0.396,
-    "eval_samples_per_second": 22.727,
-    "eval_steps_per_second": 5.05,
-    "total_flos": 2092302472071168.0,
-    "train_loss": 0.6137605508168539,
-    "train_runtime": 2.2498,
-    "train_samples_per_second": 12.001,
-    "train_steps_per_second": 1.333
+    "eval_accuracy": 0.05962962962962963,
+    "eval_f1": 0.007503204007922637,
+    "eval_loss": 7.352860927581787,
+    "eval_runtime": 93.5379,
+    "eval_samples_per_second": 57.731,
+    "eval_steps_per_second": 7.216,
+    "total_flos": 2.9295385025163264e+18,
+    "train_loss": 0.3275312578617619,
+    "train_runtime": 1623.2173,
+    "train_samples_per_second": 23.287,
+    "train_steps_per_second": 0.728
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
-    "eval_accuracy": 1.0,
-    "eval_f1": 1.0,
-    "eval_loss": 0.1679225116968155,
-    "eval_runtime": 0.396,
-    "eval_samples_per_second": 22.727,
-    "eval_steps_per_second": 5.05
+    "eval_accuracy": 0.05962962962962963,
+    "eval_f1": 0.007503204007922637,
+    "eval_loss": 7.352860927581787,
+    "eval_runtime": 93.5379,
+    "eval_samples_per_second": 57.731,
+    "eval_steps_per_second": 7.216
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "total_flos": 2092302472071168.0,
-    "train_loss": 0.6137605508168539,
-    "train_runtime": 2.2498,
-    "train_samples_per_second": 12.001,
-    "train_steps_per_second": 1.333
+    "total_flos": 2.9295385025163264e+18,
+    "train_loss": 0.3275312578617619,
+    "train_runtime": 1623.2173,
+    "train_samples_per_second": 23.287,
+    "train_steps_per_second": 0.728
 }

trainer_state.json

@@ -1,28 +1,44 @@
 {
-  "best_metric": null,
-  "best_model_checkpoint": null,
+  "best_metric": 7.352860927581787,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-1000",
   "epoch": 3.0,
   "eval_steps": 1000,
-  "global_step": 3,
+  "global_step": 1182,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 2.54,
+      "learning_rate": 7.698815566835872e-06,
+      "loss": 0.3773,
+      "step": 1000
+    },
+    {
+      "epoch": 2.54,
+      "eval_accuracy": 0.05962962962962963,
+      "eval_f1": 0.007503204007922637,
+      "eval_loss": 7.352860927581787,
+      "eval_runtime": 94.3853,
+      "eval_samples_per_second": 57.212,
+      "eval_steps_per_second": 7.152,
+      "step": 1000
+    },
     {
       "epoch": 3.0,
-      "step": 3,
-      "total_flos": 2092302472071168.0,
-      "train_loss": 0.6137605508168539,
-      "train_runtime": 2.2498,
-      "train_samples_per_second": 12.001,
-      "train_steps_per_second": 1.333
+      "step": 1182,
+      "total_flos": 2.9295385025163264e+18,
+      "train_loss": 0.3275312578617619,
+      "train_runtime": 1623.2173,
+      "train_samples_per_second": 23.287,
+      "train_steps_per_second": 0.728
     }
   ],
   "logging_steps": 1000,
-  "max_steps": 3,
+  "max_steps": 1182,
   "num_train_epochs": 3,
   "save_steps": 1000,
-  "total_flos": 2092302472071168.0,
+  "total_flos": 2.9295385025163264e+18,
   "trial_name": null,
   "trial_params": null
 }