End of training

README.md

@@ -15,13 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the food101 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.3595
-- eval_accuracy: 0.9112
-- eval_runtime: 154.85
-- eval_samples_per_second: 97.837
-- eval_steps_per_second: 6.116
-- epoch: 30.62
-- step: 29000
+- eval_loss: 0.3569
+- eval_accuracy: 0.9102
+- eval_runtime: 155.9707
+- eval_samples_per_second: 97.134
+- eval_steps_per_second: 6.072
+- epoch: 31.68
+- step: 30000
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c887d55def546210bc4ceef896ad0f8ae3c0b47adf85f85bc301526ce52a496
+oid sha256:05ba4dc04a7d736621a5007cef1288ef9e1714619f5fb17f8be5709dddc9e936
 size 343528508

runs/Feb06_02-52-53_2bd6d982b8e8/events.out.tfevents.1707187974.2bd6d982b8e8.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d24cd5316b0a8f4f6af0c081d448e77ba28e7ffe2485f2c37f8791ff4e1f515
-size 10870
+oid sha256:938510b1010abc105a39d7056da34762791037d24f53736ccda49b2bd317315d
+size 11359

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9113531353135313,
   "best_model_checkpoint": "food-image-classification/checkpoint-28000",
-  "epoch": 30.623020063357973,
+  "epoch": 31.678986272439282,
   "eval_steps": 1000,
-  "global_step": 29000,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -442,6 +442,21 @@
       "eval_samples_per_second": 97.837,
       "eval_steps_per_second": 6.116,
       "step": 29000
+    },
+    {
+      "epoch": 31.68,
+      "learning_rate": 4.223864836325238e-06,
+      "loss": 0.3297,
+      "step": 30000
+    },
+    {
+      "epoch": 31.68,
+      "eval_accuracy": 0.9101650165016502,
+      "eval_loss": 0.35688260197639465,
+      "eval_runtime": 155.9707,
+      "eval_samples_per_second": 97.134,
+      "eval_steps_per_second": 6.072,
+      "step": 30000
     }
   ],
   "logging_steps": 1000,
@@ -449,7 +464,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 1000,
-  "total_flos": 1.4393413500305818e+20,
+  "total_flos": 1.4889740243371498e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null