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: 0.3752
-- eval_accuracy: 0.9038
-- eval_runtime: 155.8581
-- eval_samples_per_second: 97.204
-- eval_steps_per_second: 6.076
-- epoch: 39.07
-- step: 37000
+- eval_loss: 0.3814
+- eval_accuracy: 0.9055
+- eval_runtime: 155.1819
+- eval_samples_per_second: 97.627
+- eval_steps_per_second: 6.103
+- epoch: 40.13
+- step: 38000
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e201d5e3e797fce5206b0870dd5fc920ccbf96de958375136b0b3c88768508
+oid sha256:8845051a121991c392088f425e4e9a87738814fab958f8c17a066da5b5b45dbb
 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:b31632af0078b38a89594ba23def943d035da8a7f98b6ba49e363f614adfd6f0
-size 14782
+oid sha256:be5676bcb27f2bb50848208fdea5f42ac6f069cfdd78719958d55bc3046f9b50
+size 15271

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9115511551155115,
   "best_model_checkpoint": "food-image-classification/checkpoint-35000",
-  "epoch": 39.070749736008445,
+  "epoch": 40.12671594508976,
   "eval_steps": 1000,
-  "global_step": 37000,
+  "global_step": 38000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -562,6 +562,21 @@
       "eval_samples_per_second": 97.204,
       "eval_steps_per_second": 6.076,
       "step": 37000
+    },
+    {
+      "epoch": 40.13,
+      "learning_rate": 1.2671594508975712e-05,
+      "loss": 0.2644,
+      "step": 38000
+    },
+    {
+      "epoch": 40.13,
+      "eval_accuracy": 0.9054785478547854,
+      "eval_loss": 0.3814030885696411,
+      "eval_runtime": 155.1819,
+      "eval_samples_per_second": 97.627,
+      "eval_steps_per_second": 6.103,
+      "step": 38000
     }
   ],
   "logging_steps": 1000,
@@ -569,7 +584,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 1000,
-  "total_flos": 1.836396539623232e+20,
+  "total_flos": 1.8860292139298003e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null