namnh2002 commited on
Commit
236282e
1 Parent(s): eb18dc4

End of training

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  license: cc-by-nc-4.0
3
- base_model: namnh2002/model_timesformer_subset_02
4
  tags:
5
  - generated_from_trainer
6
  metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # model_timesformer_subset_02
17
 
18
- This model is a fine-tuned version of [namnh2002/model_timesformer_subset_02](https://huggingface.co/namnh2002/model_timesformer_subset_02) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 1.8445
21
- - Accuracy: 0.5395
22
 
23
  ## Model description
24
 
@@ -46,20 +46,24 @@ The following hyperparameters were used during training:
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
- - training_steps: 2000
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
- | 0.9537 | 0.12 | 250 | 1.6973 | 0.5245 |
56
- | 0.8751 | 1.12 | 500 | 1.7124 | 0.5345 |
57
- | 0.7491 | 2.12 | 750 | 1.7508 | 0.5365 |
58
- | 0.6867 | 3.12 | 1000 | 1.7845 | 0.5325 |
59
- | 0.5597 | 4.12 | 1250 | 1.8160 | 0.539 |
60
- | 0.4531 | 5.12 | 1500 | 1.8213 | 0.5455 |
61
- | 0.3253 | 6.12 | 1750 | 1.9083 | 0.5435 |
62
- | 0.3531 | 7.12 | 2000 | 1.8445 | 0.5395 |
 
 
 
 
63
 
64
 
65
  ### Framework versions
 
1
  ---
2
  license: cc-by-nc-4.0
3
+ base_model: facebook/timesformer-base-finetuned-k600
4
  tags:
5
  - generated_from_trainer
6
  metrics:
 
15
 
16
  # model_timesformer_subset_02
17
 
18
+ This model is a fine-tuned version of [facebook/timesformer-base-finetuned-k600](https://huggingface.co/facebook/timesformer-base-finetuned-k600) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 1.7125
21
+ - Accuracy: 0.5446
22
 
23
  ## Model description
24
 
 
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_ratio: 0.1
49
+ - training_steps: 2997
50
 
51
  ### Training results
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
54
  |:-------------:|:-----:|:----:|:---------------:|:--------:|
55
+ | 1.8295 | 0.08 | 250 | 1.9005 | 0.4684 |
56
+ | 1.6577 | 1.08 | 500 | 1.7229 | 0.4908 |
57
+ | 1.4384 | 2.08 | 750 | 1.6627 | 0.5172 |
58
+ | 1.2867 | 3.08 | 1000 | 1.7071 | 0.5182 |
59
+ | 1.0143 | 4.08 | 1250 | 1.6543 | 0.5381 |
60
+ | 0.8775 | 5.08 | 1500 | 1.6755 | 0.5286 |
61
+ | 0.9622 | 6.08 | 1750 | 1.6568 | 0.5401 |
62
+ | 0.5627 | 7.08 | 2000 | 1.6966 | 0.5371 |
63
+ | 0.6586 | 8.08 | 2250 | 1.6735 | 0.5531 |
64
+ | 0.4577 | 9.08 | 2500 | 1.7446 | 0.5267 |
65
+ | 0.4552 | 10.08 | 2750 | 1.7490 | 0.5371 |
66
+ | 0.4488 | 11.08 | 2997 | 1.7125 | 0.5446 |
67
 
68
 
69
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01d6747bc2c104e44085d23a8cc6cd8679a2e9a335a0469cf1a98065f59e28f2
3
  size 485127632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9716821aed8dcf30732362f613daa36cb8fb4f12d7635ce778ec97f3fb8e0d3e
3
  size 485127632
runs/Mar05_14-36-23_0758646c4f0b/events.out.tfevents.1709649466.0758646c4f0b.35.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1825dbd8acc38dc121898e60891cc45690b6bb9dc0968cfe2b4784d9afad224a
3
- size 72545
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39575d6c8674e84cf1a206edcfc7bc5bd1dfc7dc05147534ffca8f755b551a34
3
+ size 72899