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: 0.4331
-- eval_accuracy: 0.8927
-- eval_runtime: 154.5274
-- eval_samples_per_second: 98.041
-- eval_steps_per_second: 6.128
-- epoch: 47.52
-- step: 45000
+- eval_loss: 0.4335
+- eval_accuracy: 0.8939
+- eval_runtime: 155.962
+- eval_samples_per_second: 97.139
+- eval_steps_per_second: 6.072
+- epoch: 48.57
+- step: 46000
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d97ad7a329ddac1ea54d0306e25de373ee14cbab75bdfb1efe46a677ed2b569
+oid sha256:1c3169a5c2f1b48c1ec92ea05add639120b229ea6e05c047f7fd55f4c24c1564
 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 sha256:8479c36629f591e04ef278cf9298ed94b257161a25dd5fcee9312e04a706f2bb
-size 18694
+oid sha256:23b73fe52cfff7457a9cc31d9263f5ea60ea46316c753948b9628ae50d0bd4d1
+size 19183

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9115511551155115,
   "best_model_checkpoint": "food-image-classification/checkpoint-35000",
-  "epoch": 47.518479408658926,
+  "epoch": 48.57444561774023,
   "eval_steps": 1000,
-  "global_step": 45000,
+  "global_step": 46000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -682,6 +682,21 @@
       "eval_samples_per_second": 98.041,
       "eval_steps_per_second": 6.128,
       "step": 45000
+    },
+    {
+      "epoch": 48.57,
+      "learning_rate": 2.1119324181626187e-05,
+      "loss": 0.2333,
+      "step": 46000
+    },
+    {
+      "epoch": 48.57,
+      "eval_accuracy": 0.8938613861386139,
+      "eval_loss": 0.43345457315444946,
+      "eval_runtime": 155.962,
+      "eval_samples_per_second": 97.139,
+      "eval_steps_per_second": 6.072,
+      "step": 46000
     }
   ],
   "logging_steps": 1000,
@@ -689,7 +704,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 1000,
-  "total_flos": 2.2334579340757788e+20,
+  "total_flos": 2.2830906083823472e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null