🍻 cheers

README.md

@@ -2,6 +2,7 @@
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
 - generated_from_trainer
 model-index:
 - name: ryan_model3272024
@@ -13,7 +14,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # ryan_model3272024
 
-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 None 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 beans dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.8228
+- Na Accuracy: 0.8
+- Ordinal Accuracy: 0.5
+- Ordinal Mae: 8.6653
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 1.8227792978286743,
+    "eval_na_accuracy": 0.8,
+    "eval_ordinal_accuracy": 0.5,
+    "eval_ordinal_mae": 8.665261681005358,
+    "eval_runtime": 1.3319,
+    "eval_samples_per_second": 7.508,
+    "eval_steps_per_second": 1.502,
+    "train_loss": 1.6283700466156006,
+    "train_runtime": 32.1209,
+    "train_samples_per_second": 12.453,
+    "train_steps_per_second": 0.872
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 4.0,
+    "eval_loss": 1.8227792978286743,
+    "eval_na_accuracy": 0.8,
+    "eval_ordinal_accuracy": 0.5,
+    "eval_ordinal_mae": 8.665261681005358,
+    "eval_runtime": 1.3319,
+    "eval_samples_per_second": 7.508,
+    "eval_steps_per_second": 1.502
+}

runs/Mar27_15-49-59_ryanserver/events.out.tfevents.1711569105.ryanserver.24581.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e6c1d6f79110b42a1029a0fa49f95b974164d1203f115913e7569bcf8fe9926
+size 521

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "train_loss": 1.6283700466156006,
+    "train_runtime": 32.1209,
+    "train_samples_per_second": 12.453,
+    "train_steps_per_second": 0.872
+}

trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 100,
+  "global_step": 28,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.43,
+      "grad_norm": 1.993449091911316,
+      "learning_rate": 0.00012857142857142858,
+      "loss": 1.9695,
+      "step": 10
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 1.4520915746688843,
+      "learning_rate": 5.714285714285714e-05,
+      "loss": 1.524,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "step": 28,
+      "total_flos": 3.0997907103744e+16,
+      "train_loss": 1.6283700466156006,
+      "train_runtime": 32.1209,
+      "train_samples_per_second": 12.453,
+      "train_steps_per_second": 0.872
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 28,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "total_flos": 3.0997907103744e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}