Hugging Face's logo

m21041
/
VideoMAEv2-Base-finetuned-ucf101-subset

Transformers
TensorBoard
Safetensors
Generated from Trainer
Model card Files
xet
 Metrics Community
m21041 commited on
Commit
13965d3
·
verified ·
1 Parent(s): 0e04717

Model save

Browse files
Files changed (5) hide show
  1. README.md +1 -1
  2. all_results.json +8 -0
  3. runs/Nov15_09-49-44_26911715db76/events.out.tfevents.1763201248.26911715db76.2430.1 +3 -0
  4. test_results.json +8 -0
  5. trainer_state.json +137 -0
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [OpenGVLab/VideoMAEv2-Base](https://huggingface.co/OpenGVLab/VideoMAEv2-Base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.0281
22
  - Accuracy: 1.0
23
 
24
  ## Model description
 
18
 
19
  This model is a fine-tuned version of [OpenGVLab/VideoMAEv2-Base](https://huggingface.co/OpenGVLab/VideoMAEv2-Base) on an unknown dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4690
22
  - Accuracy: 1.0
23
 
24
  ## Model description
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.2083333333333335,
3
+ "eval_accuracy": 1.0,
4
+ "eval_loss": 0.4690203368663788,
5
+ "eval_runtime": 53.9134,
6
+ "eval_samples_per_second": 2.875,
7
+ "eval_steps_per_second": 0.185
8
+ }
runs/Nov15_09-49-44_26911715db76/events.out.tfevents.1763201248.26911715db76.2430.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ead58b2c4d131c9c02dccd68faacc3a9db079c7e1a37ba823262a2a528e91201
3
+ size 405
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.2083333333333335,
3
+ "eval_accuracy": 1.0,
4
+ "eval_loss": 0.4690203368663788,
5
+ "eval_runtime": 53.9134,
6
+ "eval_samples_per_second": 2.875,
7
+ "eval_steps_per_second": 0.185
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 19,
3
+ "best_metric": 1.0,
4
+ "best_model_checkpoint": "VideoMAEv2-Base-finetuned-ucf101-subset/checkpoint-19",
5
+ "epoch": 3.2083333333333335,
6
+ "eval_steps": 500,
7
+ "global_step": 72,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.1388888888888889,
14
+ "grad_norm": 9.568665504455566,
15
+ "learning_rate": 4.921875e-05,
16
+ "loss": 2.1288,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.2638888888888889,
21
+ "eval_accuracy": 1.0,
22
+ "eval_loss": 0.4425038993358612,
23
+ "eval_runtime": 22.424,
24
+ "eval_samples_per_second": 3.122,
25
+ "eval_steps_per_second": 0.223,
26
+ "step": 19
27
+ },
28
+ {
29
+ "epoch": 1.0138888888888888,
30
+ "grad_norm": 6.739668846130371,
31
+ "learning_rate": 4.140625e-05,
32
+ "loss": 0.949,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 1.1527777777777777,
37
+ "grad_norm": 7.086241722106934,
38
+ "learning_rate": 3.359375e-05,
39
+ "loss": 0.2366,
40
+ "step": 30
41
+ },
42
+ {
43
+ "epoch": 1.2638888888888888,
44
+ "eval_accuracy": 1.0,
45
+ "eval_loss": 0.06767228245735168,
46
+ "eval_runtime": 22.4196,
47
+ "eval_samples_per_second": 3.122,
48
+ "eval_steps_per_second": 0.223,
49
+ "step": 38
50
+ },
51
+ {
52
+ "epoch": 2.0277777777777777,
53
+ "grad_norm": 0.7161458730697632,
54
+ "learning_rate": 2.578125e-05,
55
+ "loss": 0.0963,
56
+ "step": 40
57
+ },
58
+ {
59
+ "epoch": 2.1666666666666665,
60
+ "grad_norm": 0.4962587356567383,
61
+ "learning_rate": 1.796875e-05,
62
+ "loss": 0.0428,
63
+ "step": 50
64
+ },
65
+ {
66
+ "epoch": 2.263888888888889,
67
+ "eval_accuracy": 1.0,
68
+ "eval_loss": 0.03534603491425514,
69
+ "eval_runtime": 21.9482,
70
+ "eval_samples_per_second": 3.189,
71
+ "eval_steps_per_second": 0.228,
72
+ "step": 57
73
+ },
74
+ {
75
+ "epoch": 3.0416666666666665,
76
+ "grad_norm": 0.2468690574169159,
77
+ "learning_rate": 1.0156250000000001e-05,
78
+ "loss": 0.0201,
79
+ "step": 60
80
+ },
81
+ {
82
+ "epoch": 3.1805555555555554,
83
+ "grad_norm": 0.20965361595153809,
84
+ "learning_rate": 2.3437500000000002e-06,
85
+ "loss": 0.0239,
86
+ "step": 70
87
+ },
88
+ {
89
+ "epoch": 3.2083333333333335,
90
+ "eval_accuracy": 1.0,
91
+ "eval_loss": 0.028124911710619926,
92
+ "eval_runtime": 22.0601,
93
+ "eval_samples_per_second": 3.173,
94
+ "eval_steps_per_second": 0.227,
95
+ "step": 72
96
+ },
97
+ {
98
+ "epoch": 3.2083333333333335,
99
+ "step": 72,
100
+ "total_flos": 0.0,
101
+ "train_loss": 0.48614118706124526,
102
+ "train_runtime": 889.8242,
103
+ "train_samples_per_second": 1.295,
104
+ "train_steps_per_second": 0.081
105
+ },
106
+ {
107
+ "epoch": 3.2083333333333335,
108
+ "eval_accuracy": 1.0,
109
+ "eval_loss": 0.4690203368663788,
110
+ "eval_runtime": 53.9134,
111
+ "eval_samples_per_second": 2.875,
112
+ "eval_steps_per_second": 0.185,
113
+ "step": 72
114
+ }
115
+ ],
116
+ "logging_steps": 10,
117
+ "max_steps": 72,
118
+ "num_input_tokens_seen": 0,
119
+ "num_train_epochs": 9223372036854775807,
120
+ "save_steps": 500,
121
+ "stateful_callbacks": {
122
+ "TrainerControl": {
123
+ "args": {
124
+ "should_epoch_stop": false,
125
+ "should_evaluate": false,
126
+ "should_log": false,
127
+ "should_save": true,
128
+ "should_training_stop": true
129
+ },
130
+ "attributes": {}
131
+ }
132
+ },
133
+ "total_flos": 0.0,
134
+ "train_batch_size": 16,
135
+ "trial_name": null,
136
+ "trial_params": null
137
+ }