End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
 - generated_from_trainer
+datasets:
+- food101
 model-index:
 - name: food-image-classification
   results: []
@@ -13,15 +15,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 # food-image-classification
 
-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.
+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: 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
+- eval_loss: 4.5759
+- eval_accuracy: 0.0349
+- eval_runtime: 157.053
+- eval_samples_per_second: 96.464
+- eval_steps_per_second: 6.03
+- epoch: 1.06
+- step: 1000
 
 ## Model description
 
@@ -49,12 +51,11 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 5
-- mixed_precision_training: Native AMP
+- num_epochs: 500
 
 ### Framework versions
 
-- Transformers 4.35.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.16.1
+- Transformers 4.37.0
+- Pytorch 2.1.2
+- Datasets 2.1.0
 - Tokenizers 0.15.1

config.json

@@ -226,5 +226,5 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2"
+  "transformers_version": "4.37.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:656c18fc5cba130c6fa5494776dee859077d1a75b06682410dbbdab4bc139c6c
+oid sha256:4eabec32f0ba76003916089cd24abcbfceda6bc9f6dbc42c9f42b2fc063a8f2e
 size 343528508

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8637b62b758fd8d7af76bf6901bf4667283d0e4976458e3bb304993167e435a2
+size 9781

trainer_state.json

@@ -1,34 +1,36 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010559662090813094,
-  "eval_steps": 10,
-  "global_step": 10,
+  "epoch": 1.0559662090813093,
+  "eval_steps": 1000,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.01,
-      "learning_rate": 1.0548523206751055e-06,
-      "loss": 4.6245,
-      "step": 10
+      "epoch": 1.06,
+      "learning_rate": 1.0559662090813095e-06,
+      "loss": 4.6112,
+      "step": 1000
     },
     {
-      "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": 1.06,
+      "eval_accuracy": 0.034851485148514855,
+      "eval_loss": 4.575930118560791,
+      "eval_runtime": 157.053,
+      "eval_samples_per_second": 96.464,
+      "eval_steps_per_second": 6.03,
+      "step": 1000
     }
   ],
-  "logging_steps": 10,
-  "max_steps": 4735,
-  "num_train_epochs": 5,
-  "save_steps": 500,
-  "total_flos": 4.9638879166464e+16,
+  "logging_steps": 1000,
+  "max_steps": 473500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 500,
+  "save_steps": 1000,
+  "total_flos": 4.963267430656819e+18,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84434c2eca9b38915402890f1cae162ac37c75e9a0bb9cc160870a5a1bd9a643
-size 4600
+oid sha256:1ca936ea37d67465f6b7da7602257a39b9b8d2060f5086611932979851932935
+size 4728