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: 0.9114
-- eval_runtime: 156.9177
-- eval_samples_per_second: 96.547
-- eval_steps_per_second: 6.035
-- epoch: 29.57
-- step: 28000
+- eval_loss: 0.3595
+- eval_accuracy: 0.9112
+- eval_runtime: 154.85
+- eval_samples_per_second: 97.837
+- eval_steps_per_second: 6.116
+- epoch: 30.62
+- step: 29000
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea84ecb93a3813905e7686d20be0d4c3ef0f0c446ab38e390c62f79c75d6ccf5
+oid sha256:7c887d55def546210bc4ceef896ad0f8ae3c0b47adf85f85bc301526ce52a496
 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 sha256:7feae54c2b0d2f978a6455ab8bb343dd3e609b62e21fd6a4b61342a7e76fc100
-size 10381
+oid sha256:3d24cd5316b0a8f4f6af0c081d448e77ba28e7ffe2485f2c37f8791ff4e1f515
+size 10870

trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9097029702970297,
-  "best_model_checkpoint": "food-image-classification/checkpoint-27000",
-  "epoch": 29.56705385427666,
+  "best_metric": 0.9113531353135313,
+  "best_model_checkpoint": "food-image-classification/checkpoint-28000",
+  "epoch": 30.623020063357973,
   "eval_steps": 1000,
-  "global_step": 28000,
+  "global_step": 29000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,6 +427,21 @@
       "eval_samples_per_second": 96.547,
       "eval_steps_per_second": 6.035,
       "step": 28000
+    },
+    {
+      "epoch": 30.62,
+      "learning_rate": 3.167898627243928e-06,
+      "loss": 0.3494,
+      "step": 29000
+    },
+    {
+      "epoch": 30.62,
+      "eval_accuracy": 0.9111551155115512,
+      "eval_loss": 0.3594682812690735,
+      "eval_runtime": 154.85,
+      "eval_samples_per_second": 97.837,
+      "eval_steps_per_second": 6.116,
+      "step": 29000
     }
   ],
   "logging_steps": 1000,
@@ -434,7 +449,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 1000,
-  "total_flos": 1.3897086757240136e+20,
+  "total_flos": 1.4393413500305818e+20,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null