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: 0.4055
-- 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
+- eval_loss: 0.4173
+- eval_accuracy: 0.8976
+- eval_runtime: 154.5817
+- eval_samples_per_second: 98.006
+- eval_steps_per_second: 6.126
+- epoch: 45.41
+- step: 43000
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff04edbd88a66dd5ef52aa917f432fad1548f9c152be0350c52be844c984ff4
+oid sha256:1cf3e3af0215ba37ed6c88eafbbee5f117639bc0a9f20584b9a7142abacac81c
 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 sha256:898f3c4dde3e3f9895b854c23c385f74cf329dc7e63eb963a6da44845c273699
-size 17227
+oid sha256:fcf09a474b078470b544bd5012f2ebedacb1609b50c88775d3e9e0e31cae7000
+size 17716

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9115511551155115,
   "best_model_checkpoint": "food-image-classification/checkpoint-35000",
-  "epoch": 44.350580781415,
+  "epoch": 45.4065469904963,
   "eval_steps": 1000,
-  "global_step": 42000,
+  "global_step": 43000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -637,6 +637,21 @@
       "eval_samples_per_second": 97.763,
       "eval_steps_per_second": 6.111,
       "step": 42000
+    },
+    {
+      "epoch": 45.41,
+      "learning_rate": 1.795142555438226e-05,
+      "loss": 0.2429,
+      "step": 43000
+    },
+    {
+      "epoch": 45.41,
+      "eval_accuracy": 0.8975577557755775,
+      "eval_loss": 0.4172586500644684,
+      "eval_runtime": 154.5817,
+      "eval_samples_per_second": 98.006,
+      "eval_steps_per_second": 6.126,
+      "step": 43000
     }
   ],
   "logging_steps": 1000,
@@ -644,7 +659,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 1000,
-  "total_flos": 2.0845599111560738e+20,
+  "total_flos": 2.134192585462642e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null