Training in progress, step 200

README.md

@@ -4,8 +4,6 @@ license: cc-by-nc-4.0
 base_model: MCG-NJU/videomae-base
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
 model-index:
 - name: videomae-base-finetuned-ucf101-subset-hand
   results: []
@@ -17,9 +15,6 @@ should probably proofread and complete it, then remove this comment. -->
 # videomae-base-finetuned-ucf101-subset-hand
 
 This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.3731
-- Accuracy: 0.5789
 
 ## Model description
 
@@ -47,19 +42,9 @@ The following hyperparameters were used during training:
 - lr_scheduler_warmup_ratio: 0.1
 - training_steps: 48
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 1.5885        | 0.25  | 12   | 1.5427          | 0.2105   |
-| 1.6172        | 1.25  | 24   | 1.6134          | 0.1579   |
-| 1.5115        | 2.25  | 36   | 1.5245          | 0.3158   |
-| 1.3108        | 3.25  | 48   | 1.3731          | 0.5789   |
-
-
 ### Framework versions
 
-- Transformers 4.45.2
+- Transformers 4.45.0
 - Pytorch 2.4.1+cu118
-- Datasets 3.0.1
-- Tokenizers 0.20.1
+- Datasets 3.0.0
+- Tokenizers 0.20.0

config.json

@@ -39,7 +39,7 @@
   "problem_type": "single_label_classification",
   "qkv_bias": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.45.2",
+  "transformers_version": "4.45.0",
   "tubelet_size": 2,
   "use_mean_pooling": false
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0dee6060956719aebff25002ee211f6cf28dc0236c74d09963f6595da9c5b82
+oid sha256:6dfa2d2fde8ef746e9dcab94070c93bd70996762bf61ed040848223123acbc86
 size 344946604

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e102cb409da7b8848f72fa0a921ab5cbbf8a4d6def0b5ff9a7018c8bdd14b2
+oid sha256:b3ca091a5aae627f9f7416b8b88bd6eaf5077cf04451054c6e785d91dccdce8a
 size 5240