End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: apache-2.0
 base_model: google/vit-base-patch16-224-in21k
 tags:
+- image-classification
+- vision
 - generated_from_trainer
 model-index:
 - name: vit-base-patch16-224-in21k
@@ -14,7 +16,18 @@ should probably proofread and complete it, then remove this comment. -->
 
 # vit-base-patch16-224-in21k
 
-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 chainyo/rvl-cdip dataset.
+It achieves the following results on the evaluation set:
+- eval_loss: 2.7757
+- eval_model_preparation_time: 0.0077
+- eval_accuracy: 0.0569
+- eval_runtime: 242.1935
+- eval_samples_per_second: 198.189
+- eval_steps_per_second: 3.097
+- memory_allocated (GB): 0.68
+- max_memory_allocated (GB): 0.76
+- total_memory_available (GB): 126.62
+- step: 0
 
 ## Model description
 
@@ -41,13 +54,9 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 3.0
 
-### Training results
-
-
-
 ### Framework versions
 
 - Transformers 4.45.2
-- Pytorch 2.5.0a0+git6bdd7f4
+- Pytorch 2.4.0a0+git12138a8
 - Datasets 3.1.0
 - Tokenizers 0.20.3

all_results.json

@@ -1,16 +1,11 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.06302083333333333,
-    "eval_loss": NaN,
-    "eval_runtime": 242.9557,
-    "eval_samples_per_second": 197.567,
-    "eval_steps_per_second": 3.087,
-    "max_memory_allocated (GB)": 1.61,
-    "memory_allocated (GB)": 1.53,
-    "total_flos": 6.324139790696448e+19,
-    "total_memory_available (GB)": 126.62,
-    "train_loss": 0.0,
-    "train_runtime": 0.0058,
-    "train_samples_per_second": 140961263.636,
-    "train_steps_per_second": 17620222.735
+    "eval_accuracy": 0.056854166666666664,
+    "eval_loss": 2.775695562362671,
+    "eval_model_preparation_time": 0.0077,
+    "eval_runtime": 242.1935,
+    "eval_samples_per_second": 198.189,
+    "eval_steps_per_second": 3.097,
+    "max_memory_allocated (GB)": 0.76,
+    "memory_allocated (GB)": 0.68,
+    "total_memory_available (GB)": 126.62
 }

eval_results.json

@@ -1,11 +1,11 @@
 {
-    "epoch": 3.0,
-    "eval_accuracy": 0.06302083333333333,
-    "eval_loss": NaN,
-    "eval_runtime": 242.9557,
-    "eval_samples_per_second": 197.567,
-    "eval_steps_per_second": 3.087,
-    "max_memory_allocated (GB)": 1.61,
-    "memory_allocated (GB)": 1.53,
+    "eval_accuracy": 0.056854166666666664,
+    "eval_loss": 2.775695562362671,
+    "eval_model_preparation_time": 0.0077,
+    "eval_runtime": 242.1935,
+    "eval_samples_per_second": 198.189,
+    "eval_steps_per_second": 3.097,
+    "max_memory_allocated (GB)": 0.76,
+    "memory_allocated (GB)": 0.68,
     "total_memory_available (GB)": 126.62
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cee937384821f6a29edd22802024c28f69d8d2f494c9e3f9226139369360880f
+oid sha256:e19e27533b68b1a92962c45efb7747d6958b8e330b232bef39e45f6353f2b20b
 size 343267040

runs/Nov07_16-54-53_gtown-28NZK54/events.out.tfevents.1730998742.gtown-28NZK54.5246.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d4c7a774dbe16c01f9c94c443f1cf3bf052c9725a754d57251211af0dc94112
+size 560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c918ca48e8707d0ec9cca8c7f991990d16019ca7aef9c462322d1bd3ede7b72
+oid sha256:4a2d98ff30a5170f30cb47e0160611c448ea2f3c18d9809dca93793ed9059dd5
 size 5112