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: 0.3488
-- eval_accuracy: 0.9116
-- eval_runtime: 156.4541
-- eval_samples_per_second: 96.834
-- eval_steps_per_second: 6.053
-- epoch: 36.96
-- step: 35000
+- 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
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c951d0b59eec32774555025b62e83aa6a4229bcc65e9db5bee420f322c59e1c
+oid sha256:090baa98a4499d17bcd8d5b1280d393120cc877bc4ee264cf0b598101ac03775
 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 sha256:154aec5476517b77cb389ff612637c9a75c60856318ddae8d49ff88db8d2b435
-size 13804
+oid sha256:29e613ef805dda57393317c1853dd23006487a17a5428cbdea0a812e55d38e2f
+size 14293

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9113531353135313,
-  "best_model_checkpoint": "food-image-classification/checkpoint-28000",
-  "epoch": 36.95881731784583,
+  "best_metric": 0.9115511551155115,
+  "best_model_checkpoint": "food-image-classification/checkpoint-35000",
+  "epoch": 38.01478352692714,
   "eval_steps": 1000,
-  "global_step": 35000,
+  "global_step": 36000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -532,6 +532,21 @@
       "eval_samples_per_second": 96.834,
       "eval_steps_per_second": 6.053,
       "step": 35000
+    },
+    {
+      "epoch": 38.01,
+      "learning_rate": 1.0559662090813093e-05,
+      "loss": 0.2811,
+      "step": 36000
+    },
+    {
+      "epoch": 38.01,
+      "eval_accuracy": 0.90996699669967,
+      "eval_loss": 0.3593011796474457,
+      "eval_runtime": 155.6871,
+      "eval_samples_per_second": 97.311,
+      "eval_steps_per_second": 6.083,
+      "step": 36000
     }
   ],
   "logging_steps": 1000,
@@ -539,7 +554,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 1000,
-  "total_flos": 1.7371373958699916e+20,
+  "total_flos": 1.786763865316664e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null