Model save

README.md

@@ -1,9 +1,9 @@
 ---
 library_name: transformers
+license: cc-by-nc-4.0
+base_model: MCG-NJU/videomae-base
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: Intoxicated_Classification_Fine_Tuned_14_epochs
   results: []
@@ -14,10 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Intoxicated_Classification_Fine_Tuned_14_epochs
 
-This model was trained from scratch on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.5795
-- Accuracy: 0.7187
+This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
 
 ## Model description
 
@@ -45,22 +42,6 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - training_steps: 6980
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.4767        | 0.1   | 698  | 1.9866          | 0.5738   |
-| 0.2627        | 1.1   | 1396 | 1.2988          | 0.6354   |
-| 0.0815        | 2.1   | 2094 | 1.6103          | 0.6692   |
-| 0.1119        | 3.1   | 2792 | 1.4690          | 0.7069   |
-| 0.0006        | 4.1   | 3490 | 1.2770          | 0.7225   |
-| 0.001         | 5.1   | 4188 | 1.7738          | 0.6552   |
-| 0.001         | 6.1   | 4886 | 1.9460          | 0.6490   |
-| 0.0005        | 7.1   | 5584 | 1.9181          | 0.6830   |
-| 0.1412        | 8.1   | 6282 | 1.3001          | 0.7553   |
-| 0.001         | 9.1   | 6980 | 1.5795          | 0.7187   |
-
-
 ### Framework versions
 
 - Transformers 4.48.0

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "D:\\Thesis\\Scripts\\Intoxicated_Classification_Fine_Tuned_videomae-base\\checkpoint-2792",
+  "_name_or_path": "MCG-NJU/videomae-base",
   "architectures": [
     "VideoMAEForVideoClassification"
   ],
@@ -12,15 +12,15 @@
   "hidden_dropout_prob": 0.0,
   "hidden_size": 768,
   "id2label": {
-    "0": "Drunk",
-    "1": "Sober"
+    "0": "train",
+    "1": "val"
   },
   "image_size": 224,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "Drunk": 0,
-    "Sober": 1
+    "train": 0,
+    "val": 1
   },
   "layer_norm_eps": 1e-12,
   "model_type": "videomae",
@@ -30,7 +30,6 @@
   "num_frames": 16,
   "num_hidden_layers": 12,
   "patch_size": 16,
-  "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.0",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eedcefe36d61f2af18b84d2a4e74e3701c42b6f64281ec03b1e585927466144d
+oid sha256:ca83cebdde916b389632537035cfbce24269efd220262d6707ecaa8f7f2f2025
 size 344937368

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225e57c5d99482c9b760eab45e0cb0bf6ac0661ac5415c7ef4658423ac3124f9
+oid sha256:de9eaa472d44cc8884201b1ddff9f2ea3a196728c35c022a2e920cc9a31f9ec4
 size 5432