End of training

README.md

@@ -15,11 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [tigeryi/imagenet1k](https://huggingface.co/tigeryi/imagenet1k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.0970
-- eval_accuracy: 0.99
-- eval_runtime: 75.5064
-- eval_samples_per_second: 1.324
-- eval_steps_per_second: 0.331
+- eval_loss: 1.0022
+- eval_accuracy: 0.7605
+- eval_runtime: 1004.8381
+- eval_samples_per_second: 49.759
+- eval_steps_per_second: 1.555
 - step: 0
 
 ## Model description
@@ -40,8 +40,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 4
-- eval_batch_size: 4
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 1
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear

runs/May03_21-12-03_7deca0b8a2f9/events.out.tfevents.1714771874.7deca0b8a2f9.829.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de576cba1b8836567c7341400dc88123a56fc84b81fb489a9625b6160beffd8f
+size 346

trainer_state.json

@@ -9,11 +9,11 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "eval_accuracy": 0.83548,
-      "eval_loss": 0.7309545874595642,
-      "eval_runtime": 912.2558,
-      "eval_samples_per_second": 54.809,
-      "eval_steps_per_second": 1.713,
+      "eval_accuracy": 0.76046,
+      "eval_loss": 1.0021899938583374,
+      "eval_runtime": 1004.8381,
+      "eval_samples_per_second": 49.759,
+      "eval_steps_per_second": 1.555,
       "step": 0
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13c7ca9b9235867f16649916325b0f322b565a323a678d56050e36e0270b09d4
+oid sha256:11d852ed0ea50bad28da851992b7a413c9a2786d5851d87045407cf0e02ea853
 size 4984