Model save

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: microsoft/dit-base-finetuned-rvlcdip
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
 tags:
 - generated_from_trainer
 metrics:
@@ -14,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # donut-base-beans
 
-This model is a fine-tuned version of [microsoft/dit-base-finetuned-rvlcdip](https://huggingface.co/microsoft/dit-base-finetuned-rvlcdip) 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:
 - F1: 0.9705
-- Loss: 0.0391
+- Loss: 0.0429
 
 ## Model description
 
@@ -46,13 +47,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | F1     | Validation Loss |
-|:-------------:|:-----:|:----:|:------:|:---------------:|
-| 0.0594        | 1.0   | 1981 | 0.9705 | 0.0440          |
-| 0.0678        | 2.0   | 3962 | 0.9705 | 0.0447          |
-| 0.0615        | 3.0   | 5943 | 0.9705 | 0.0416          |
-| 0.0685        | 4.0   | 7924 | 0.9705 | 0.0385          |
-| 0.0582        | 5.0   | 9905 | 0.9705 | 0.0391          |
+| Training Loss | Epoch | Step  | F1     | Validation Loss |
+|:-------------:|:-----:|:-----:|:------:|:---------------:|
+| 0.0796        | 1.0   | 3367  | 0.4973 | 0.0687          |
+| 0.0611        | 2.0   | 6734  | 0.4973 | 0.0585          |
+| 0.0581        | 3.0   | 10101 | 0.4973 | 0.0591          |
+| 0.059         | 4.0   | 13468 | 0.4973 | 0.0550          |
+| 0.0563        | 5.0   | 16835 | 0.4973 | 0.0540          |
+| 0.0532        | 5.0   | 19805 | 0.9705 | 0.0429          |
 
 
 ### Framework versions

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 5.0,
     "eval_f1": 0.9705180789481339,
-    "eval_loss": 0.038467586040496826,
-    "eval_runtime": 568.9178,
-    "eval_samples_per_second": 362.552,
-    "eval_steps_per_second": 2.833,
-    "total_flos": 9.82152667464321e+19,
+    "eval_loss": 0.04290876165032387,
+    "eval_runtime": 1022.6751,
+    "eval_samples_per_second": 201.689,
+    "eval_steps_per_second": 1.576,
+    "total_flos": 9.82001462664467e+19,
     "train_loss": 0.0,
-    "train_runtime": 6.156,
-    "train_samples_per_second": 205862.798,
-    "train_steps_per_second": 1608.988
+    "train_runtime": 0.0658,
+    "train_samples_per_second": 19271134.706,
+    "train_steps_per_second": 301163.752
 }

config.json

@@ -1,15 +1,10 @@
 {
-  "_name_or_path": "microsoft/dit-base-finetuned-rvlcdip",
-  "add_fpn": false,
+  "_name_or_path": "google/vit-base-patch16-224-in21k",
   "architectures": [
-    "BeitForImageClassification"
+    "ViTForImageClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "auxiliary_channels": 256,
-  "auxiliary_concat_input": false,
-  "auxiliary_loss_weight": 0.4,
-  "auxiliary_num_convs": 1,
-  "drop_path_rate": 0.1,
+  "encoder_stride": 16,
   "finetuning_task": "image-classification",
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.0,
@@ -24,54 +19,12 @@
     "Value(dtype='int64', id=None)": "0"
   },
   "layer_norm_eps": 1e-12,
-  "layer_scale_init_value": 0.1,
-  "model_type": "beit",
+  "model_type": "vit",
   "num_attention_heads": 12,
   "num_channels": 3,
   "num_hidden_layers": 12,
-  "out_features": [
-    "stage3",
-    "stage5",
-    "stage7",
-    "stage11"
-  ],
-  "out_indices": [
-    3,
-    5,
-    7,
-    11
-  ],
   "patch_size": 16,
-  "pool_scales": [
-    1,
-    2,
-    3,
-    6
-  ],
-  "reshape_hidden_states": true,
-  "semantic_loss_ignore_index": 255,
-  "stage_names": [
-    "stem",
-    "stage1",
-    "stage2",
-    "stage3",
-    "stage4",
-    "stage5",
-    "stage6",
-    "stage7",
-    "stage8",
-    "stage9",
-    "stage10",
-    "stage11",
-    "stage12"
-  ],
+  "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.43.0.dev0",
-  "use_absolute_position_embeddings": true,
-  "use_auxiliary_head": true,
-  "use_mask_token": false,
-  "use_mean_pooling": true,
-  "use_relative_position_bias": false,
-  "use_shared_relative_position_bias": false,
-  "vocab_size": 8192
+  "transformers_version": "4.43.0.dev0"
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
     "eval_f1": 0.9705180789481339,
-    "eval_loss": 0.038467586040496826,
-    "eval_runtime": 568.9178,
-    "eval_samples_per_second": 362.552,
-    "eval_steps_per_second": 2.833
+    "eval_loss": 0.04290876165032387,
+    "eval_runtime": 1022.6751,
+    "eval_samples_per_second": 201.689,
+    "eval_steps_per_second": 1.576
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5e6ad99f326c79142618188e2f2311b61803f4a73856b3c1a458bcde5366aa2
-size 343258940
+oid sha256:472717343c19fb122138fc3fa7339902c64523b4ea7aca0a6a002c718da0878b
+size 343220892

preprocessor_config.json

@@ -1,11 +1,5 @@
 {
-  "crop_size": {
-    "height": 224,
-    "width": 224
-  },
-  "do_center_crop": false,
   "do_normalize": true,
-  "do_reduce_labels": false,
   "do_rescale": true,
   "do_resize": true,
   "image_mean": [
@@ -13,7 +7,7 @@
     0.5,
     0.5
   ],
-  "image_processor_type": "BeitImageProcessor",
+  "image_processor_type": "ViTImageProcessor",
   "image_std": [
     0.5,
     0.5,

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 5.0,
-    "total_flos": 9.82152667464321e+19,
+    "total_flos": 9.82001462664467e+19,
     "train_loss": 0.0,
-    "train_runtime": 6.156,
-    "train_samples_per_second": 205862.798,
-    "train_steps_per_second": 1608.988
+    "train_runtime": 0.0658,
+    "train_samples_per_second": 19271134.706,
+    "train_steps_per_second": 301163.752
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b5bbd410b0d921bd96223a242b45cfe2043deb7fe3439cab79bb84116d43059
-size 5368
+oid sha256:e104975fcf71ba3d0065679db7750233952c0e6a408fb5817afaecb13c2dba4c
+size 5240