Model save

README.md

@@ -3,6 +3,8 @@ license: cc-by-nc-4.0
 base_model: MCG-NJU/videomae-base
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: videomae-base-finetuned-SLT-subset
   results: []
@@ -15,13 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 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:
-- eval_loss: 3.4305
-- eval_accuracy: 0.05
-- eval_runtime: 91.6701
-- eval_samples_per_second: 0.436
-- eval_steps_per_second: 0.218
-- epoch: 3.0625
-- step: 236
+- Loss: 3.5419
+- Accuracy: 0.075
 
 ## Model description
 
@@ -47,11 +44,22 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- training_steps: 944
+- training_steps: 295
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 4.0073        | 0.2   | 59   | 3.7164          | 0.025    |
+| 3.922         | 1.2   | 118  | 3.6887          | 0.05     |
+| 3.8127        | 2.2   | 177  | 3.6308          | 0.075    |
+| 3.7016        | 3.2   | 236  | 3.5723          | 0.075    |
+| 3.5277        | 4.2   | 295  | 3.5419          | 0.075    |
+
 
 ### Framework versions
 
 - Transformers 4.44.0
-- Pytorch 2.1.0+cu121
+- Pytorch 2.4.0
 - Datasets 2.21.0
 - Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1584360330ef16576abb53979725ef4f1e050c37aa74b677f9cad1cfd70e8700
+oid sha256:1f5e5bc797ef3cb21b16f319e18d5b4ad5bc0b156c330597c7b61355d9e4465a
 size 345054272

runs/Sep08_12-39-14_d0b9a74a01d1/events.out.tfevents.1725799165.d0b9a74a01d1.36.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:772cab0de4fa4391a11461ccda97ba645b6685bad5cb586c09fd33d2257d086d
-size 16800
+oid sha256:ebdc782021b5f9f4c081478ba3cc2e78319bfec0904caf67f129955fa8c12f87
+size 17477