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: 0.4206
-- eval_accuracy: 0.8940
-- eval_runtime: 156.2155
-- eval_samples_per_second: 96.981
-- eval_steps_per_second: 6.062
-- epoch: 46.46
-- step: 44000
+- 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
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e000a0f05b18fcec85191d1563a2e5221e2e57d35ab7be4be32a4b5a8e39d767
+oid sha256:6d97ad7a329ddac1ea54d0306e25de373ee14cbab75bdfb1efe46a677ed2b569
 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:e82fa2bf6b1cf111b29e5fcfc8d322df502109190dd76254af7c68d359ddddb3
-size 18205
+oid sha256:8479c36629f591e04ef278cf9298ed94b257161a25dd5fcee9312e04a706f2bb
+size 18694

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9115511551155115,
   "best_model_checkpoint": "food-image-classification/checkpoint-35000",
-  "epoch": 46.462513199577614,
+  "epoch": 47.518479408658926,
   "eval_steps": 1000,
-  "global_step": 44000,
+  "global_step": 45000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -667,6 +667,21 @@
       "eval_samples_per_second": 96.981,
       "eval_steps_per_second": 6.062,
       "step": 44000
+    },
+    {
+      "epoch": 47.52,
+      "learning_rate": 2.006335797254488e-05,
+      "loss": 0.2351,
+      "step": 45000
+    },
+    {
+      "epoch": 47.52,
+      "eval_accuracy": 0.8926732673267327,
+      "eval_loss": 0.4330624043941498,
+      "eval_runtime": 154.5274,
+      "eval_samples_per_second": 98.041,
+      "eval_steps_per_second": 6.128,
+      "step": 45000
     }
   ],
   "logging_steps": 1000,
@@ -674,7 +689,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 1000,
-  "total_flos": 2.1838252597692105e+20,
+  "total_flos": 2.2334579340757788e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null