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: 0.3593
-- eval_accuracy: 0.9100
-- eval_runtime: 155.6871
-- eval_samples_per_second: 97.311
-- eval_steps_per_second: 6.083
-- epoch: 38.01
-- step: 36000
+- 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
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:090baa98a4499d17bcd8d5b1280d393120cc877bc4ee264cf0b598101ac03775
+oid sha256:a3e201d5e3e797fce5206b0870dd5fc920ccbf96de958375136b0b3c88768508
 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 sha256:29e613ef805dda57393317c1853dd23006487a17a5428cbdea0a812e55d38e2f
-size 14293
+oid sha256:b31632af0078b38a89594ba23def943d035da8a7f98b6ba49e363f614adfd6f0
+size 14782

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9115511551155115,
   "best_model_checkpoint": "food-image-classification/checkpoint-35000",
-  "epoch": 38.01478352692714,
+  "epoch": 39.070749736008445,
   "eval_steps": 1000,
-  "global_step": 36000,
+  "global_step": 37000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -547,6 +547,21 @@
       "eval_samples_per_second": 97.311,
       "eval_steps_per_second": 6.083,
       "step": 36000
+    },
+    {
+      "epoch": 39.07,
+      "learning_rate": 1.1615628299894405e-05,
+      "loss": 0.2674,
+      "step": 37000
+    },
+    {
+      "epoch": 39.07,
+      "eval_accuracy": 0.9037623762376238,
+      "eval_loss": 0.37522387504577637,
+      "eval_runtime": 155.8581,
+      "eval_samples_per_second": 97.204,
+      "eval_steps_per_second": 6.076,
+      "step": 37000
     }
   ],
   "logging_steps": 1000,
@@ -554,7 +569,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 1000,
-  "total_flos": 1.786763865316664e+20,
+  "total_flos": 1.836396539623232e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null