End of training

README.md

@@ -17,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the food101 dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.9754
-- eval_accuracy: 0.7336
-- eval_runtime: 156.8793
-- eval_samples_per_second: 96.571
-- eval_steps_per_second: 6.036
-- epoch: 8.45
-- step: 8000
+- eval_loss: 1.6087
+- eval_accuracy: 0.7577
+- eval_runtime: 154.5661
+- eval_samples_per_second: 98.016
+- eval_steps_per_second: 6.127
+- epoch: 9.5
+- step: 9000
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b20edeb0fe7d3b161c0a46a58cae188fa221d032d8c7766255b9a02137a73c09
+oid sha256:7003b62c05cc4a3a4b6bbe5ba0e3ccfad6a308b200d2885c2120cebe195b2270
 size 343528508

runs/Feb05_03-08-58_983d148b451b/events.out.tfevents.1707102539.983d148b451b.26.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a033a1a586ec82c34e1ea9c30d4c0e829e843a9fd4da33e9e4e02374982ce418
-size 13141
+oid sha256:64e1b4c293cf33cdc2de20d5b790df43e32e72d52f1f69cd50b68e6278944da9
+size 13621

trainer_state.json

@@ -1,9 +1,9 @@
 {
- "best_metric": 0.7070627062706271,
- "best_model_checkpoint": "food-image-classification/checkpoint-7000",
- "epoch": 8.447729672650475,
+ "best_metric": 0.7335973597359736,
+ "best_model_checkpoint": "food-image-classification/checkpoint-8000",
+ "epoch": 9.503695881731785,
  "eval_steps": 1000,
- "global_step": 8000,
+ "global_step": 9000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
@@ -127,6 +127,21 @@
  "eval_samples_per_second": 96.571,
  "eval_steps_per_second": 6.036,
  "step": 8000
+ },
+ {
+ "epoch": 9.5,
+ "learning_rate": 9.503695881731786e-06,
+ "loss": 1.7383,
+ "step": 9000
+ },
+ {
+ "epoch": 9.5,
+ "eval_accuracy": 0.7576897689768977,
+ "eval_loss": 1.608676552772522,
+ "eval_runtime": 154.5661,
+ "eval_samples_per_second": 98.016,
+ "eval_steps_per_second": 6.127,
+ "step": 9000
  }
  ],
  "logging_steps": 1000,
@@ -134,7 +149,7 @@
  "num_input_tokens_seen": 0,
  "num_train_epochs": 500,
  "save_steps": 1000,
- "total_flos": 3.970613944525455e+19,
+ "total_flos": 4.466940687591137e+19,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null