End of training

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
 tags:
 - generated_from_trainer
 model-index:
@@ -11,15 +13,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # food-image-classification
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 1.5642
-- eval_accuracy: 0.896
-- eval_runtime: 15.4357
-- eval_samples_per_second: 64.785
-- eval_steps_per_second: 4.081
-- epoch: 0.32
-- step: 20
+- eval_loss: 4.6215
+- eval_accuracy: 0.0094
+- eval_runtime: 140.7774
+- eval_samples_per_second: 107.617
+- eval_steps_per_second: 6.727
+- epoch: 0.01
+- step: 10
 
 ## Model description
 
@@ -48,6 +50,7 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 5
+- mixed_precision_training: Native AMP
 
 ### Framework versions
 

config.json

@@ -1,5 +1,5 @@
 {
- "_name_or_path": "/content/food-image-classification",
+ "_name_or_path": "google/vit-base-patch16-224-in21k",
  "architectures": [
  "ViTForImageClassification"
  ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd65022906a0ab5f82a88756f55cc79380928935ba4c8d864da8c5b57a3acff
+oid sha256:656c18fc5cba130c6fa5494776dee859077d1a75b06682410dbbdab4bc139c6c
 size 343528508

runs/Feb04_07-25-37_0bc3247a45bd/events.out.tfevents.1707031537.0bc3247a45bd.819.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d53e8ac1c0476273215c4ffe9bf269d110f3d655cbff853b316355639f029e0f
+size 9228

runs/Feb04_07-42-31_0bc3247a45bd/events.out.tfevents.1707032552.0bc3247a45bd.819.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b31d75e5331ab79a98d2f2a9c2ee6210da2cd396afc921b98dc29ea7528019
+size 9287

runs/Feb04_07-48-42_0bc3247a45bd/events.out.tfevents.1707032923.0bc3247a45bd.819.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25254f1aaefd9f6625f4d8c82f31a729e6d2d62e63f2a5b9fc79af946e941b6f
+size 9623

trainer_state.json

@@ -1,49 +1,34 @@
 {
  "best_metric": null,
  "best_model_checkpoint": null,
- "epoch": 0.32,
+ "epoch": 0.010559662090813094,
  "eval_steps": 10,
- "global_step": 20,
+ "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
  {
- "epoch": 0.16,
- "learning_rate": 1.6129032258064517e-05,
- "loss": 1.5807,
+ "epoch": 0.01,
+ "learning_rate": 1.0548523206751055e-06,
+ "loss": 4.6245,
  "step": 10
  },
  {
- "epoch": 0.16,
- "eval_accuracy": 0.889,
- "eval_loss": 1.6238535642623901,
- "eval_runtime": 15.4204,
- "eval_samples_per_second": 64.849,
- "eval_steps_per_second": 4.085,
+ "epoch": 0.01,
+ "eval_accuracy": 0.00943894389438944,
+ "eval_loss": 4.621488094329834,
+ "eval_runtime": 140.7774,
+ "eval_samples_per_second": 107.617,
+ "eval_steps_per_second": 6.727,
  "step": 10
- },
- {
- "epoch": 0.32,
- "learning_rate": 3.2258064516129034e-05,
- "loss": 1.5408,
- "step": 20
- },
- {
- "epoch": 0.32,
- "eval_accuracy": 0.896,
- "eval_loss": 1.56419038772583,
- "eval_runtime": 15.4357,
- "eval_samples_per_second": 64.785,
- "eval_steps_per_second": 4.081,
- "step": 20
  }
  ],
  "logging_steps": 10,
- "max_steps": 310,
+ "max_steps": 4735,
  "num_train_epochs": 5,
  "save_steps": 500,
- "total_flos": 9.9277758332928e+16,
+ "total_flos": 4.9638879166464e+16,
  "trial_name": null,
  "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acef5c93ba342252b268b9013a40d50d329bbe50e1a0a135a0e8029a3284d5e8
+oid sha256:84434c2eca9b38915402890f1cae162ac37c75e9a0bb9cc160870a5a1bd9a643
 size 4600