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: 0.3977
-- eval_accuracy: 0.9011
-- eval_runtime: 155.7863
-- eval_samples_per_second: 97.249
-- eval_steps_per_second: 6.079
-- epoch: 43.29
-- step: 41000
+- eval_loss: 0.4055
+- eval_accuracy: 0.8992
+- eval_runtime: 154.9661
+- eval_samples_per_second: 97.763
+- eval_steps_per_second: 6.111
+- epoch: 44.35
+- step: 42000
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:936ff4ba77db213e42e7d4a6fd31a9bd247c53544aa1bb748716e59e63d2e0fd
+oid sha256:8ff04edbd88a66dd5ef52aa917f432fad1548f9c152be0350c52be844c984ff4
 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 sha256:820e67c4db3204ff5ae0466943e6db6c335f3369a0fa30514fffb6ce95775fc4
-size 16738
+oid sha256:898f3c4dde3e3f9895b854c23c385f74cf329dc7e63eb963a6da44845c273699
+size 17227

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9115511551155115,
   "best_model_checkpoint": "food-image-classification/checkpoint-35000",
-  "epoch": 43.294614572333685,
+  "epoch": 44.350580781415,
   "eval_steps": 1000,
-  "global_step": 41000,
+  "global_step": 42000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -622,6 +622,21 @@
       "eval_samples_per_second": 97.249,
       "eval_steps_per_second": 6.079,
       "step": 41000
+    },
+    {
+      "epoch": 44.35,
+      "learning_rate": 1.6895459345300952e-05,
+      "loss": 0.2431,
+      "step": 42000
+    },
+    {
+      "epoch": 44.35,
+      "eval_accuracy": 0.8992079207920792,
+      "eval_loss": 0.40550053119659424,
+      "eval_runtime": 154.9661,
+      "eval_samples_per_second": 97.763,
+      "eval_steps_per_second": 6.111,
+      "step": 42000
     }
   ],
   "logging_steps": 1000,
@@ -629,7 +644,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 1000,
-  "total_flos": 2.0349272368495054e+20,
+  "total_flos": 2.0845599111560738e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null