Hugging Face's logo

shylhy
/
videomae-large-finetuned-deepfake-subset

Video Classification
Transformers
Safetensors
videomae
Generated from Trainer
Inference Endpoints
Model card Files Community
shylhy commited on
Commit
3255554
·
verified ·
1 Parent(s): df20bae

Training in progress, epoch 0

Browse files
Files changed (7) hide show
  1. README.md +12 -7
  2. all_results.json +5 -5
  3. config.json +1 -1
  4. model.safetensors +2 -2
  5. test_results.json +5 -5
  6. trainer_state.json +0 -0
  7. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [MCG-NJU/videomae-large](https://huggingface.co/MCG-NJU/videomae-large) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.4257
20
 
21
  ## Model description
22
 
@@ -42,17 +42,22 @@ The following hyperparameters were used during training:
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_ratio: 0.1
45
- - training_steps: 2235
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
- | 0.7063 | 0.2 | 447 | 0.6715 |
52
- | 0.6721 | 1.2 | 894 | 0.6247 |
53
- | 0.4569 | 2.2 | 1341 | 0.6014 |
54
- | 0.3716 | 3.2 | 1788 | 0.5119 |
55
- | 0.3029 | 4.2 | 2235 | 0.4187 |
 
 
 
 
 
56
 
57
 
58
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [MCG-NJU/videomae-large](https://huggingface.co/MCG-NJU/videomae-large) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.3932
20
 
21
  ## Model description
22
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_ratio: 0.1
45
+ - training_steps: 4470
46
 
47
  ### Training results
48
 
49
  | Training Loss | Epoch | Step | Validation Loss |
50
  |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.6361 | 0.1 | 447 | 0.6478 |
52
+ | 0.6774 | 1.1 | 894 | 0.6047 |
53
+ | 0.4168 | 2.1 | 1341 | 0.4852 |
54
+ | 0.4427 | 3.1 | 1788 | 0.8547 |
55
+ | 0.4496 | 4.1 | 2235 | 0.3795 |
56
+ | 0.3433 | 5.1 | 2682 | 0.4119 |
57
+ | 0.2287 | 6.1 | 3129 | 0.4823 |
58
+ | 0.1297 | 7.1 | 3576 | 0.4295 |
59
+ | 0.3104 | 8.1 | 4023 | 0.4096 |
60
+ | 0.0525 | 9.1 | 4470 | 0.4154 |
61
 
62
 
63
  ### Framework versions
all_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 4.2,
3
- "eval_loss": 0.42570874094963074,
4
- "eval_runtime": 1996.1684,
5
- "eval_samples_per_second": 9.919,
6
- "eval_steps_per_second": 1.24
7
  }
 
1
  {
2
+ "epoch": 9.1,
3
+ "eval_loss": 0.39315125346183777,
4
+ "eval_runtime": 426.8234,
5
+ "eval_samples_per_second": 2.577,
6
+ "eval_steps_per_second": 0.323
7
  }
config.json CHANGED
@@ -27,7 +27,7 @@
27
  "norm_pix_loss": true,
28
  "num_attention_heads": 16,
29
  "num_channels": 3,
30
- "num_frames": 16,
31
  "num_hidden_layers": 24,
32
  "patch_size": 16,
33
  "problem_type": "single_label_classification",
 
27
  "norm_pix_loss": true,
28
  "num_attention_heads": 16,
29
  "num_channels": 3,
30
+ "num_frames": 24,
31
  "num_hidden_layers": 24,
32
  "patch_size": 16,
33
  "problem_type": "single_label_classification",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8a5a5fd53f2332c3a406e96d82b4a205141b32a23899d61efc041af6b2db3c9
3
- size 607770476
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b2a820649ec150c6b3f8624c614c25ba4b58e6c157423f294589a1b5ba3168
3
+ size 1215496248
test_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "epoch": 4.2,
3
- "eval_loss": 0.42570874094963074,
4
- "eval_runtime": 1996.1684,
5
- "eval_samples_per_second": 9.919,
6
- "eval_steps_per_second": 1.24
7
  }
 
1
  {
2
+ "epoch": 9.1,
3
+ "eval_loss": 0.39315125346183777,
4
+ "eval_runtime": 426.8234,
5
+ "eval_samples_per_second": 2.577,
6
+ "eval_steps_per_second": 0.323
7
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01a112613c865f994cbccea1bcf9259c90dca35ee00515fe413ecacd862d2da9
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e962655c185a779d829f8a4f97e6fb4b2e6c32bcc264b8fb531c5d5599c6d579
3
  size 5240