Hugging Face's logo

Tommidi
/
spatial_vit_temporal_vit-finetuned-ucf101-subset

Transformers
TensorBoard
Safetensors
st_vit
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Tommidi commited on
Commit
e7d5dfd
•
1 Parent(s): 07a8ffa

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +8 -0
  2. runs/Feb06_18-21-39_4a4c6f005344/events.out.tfevents.1707249567.4a4c6f005344.303.1 +2 -2
  3. test_results.json +8 -0
  4. trainer_state.json +168 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.23,
3
+ "eval_accuracy": 0.68,
4
+ "eval_loss": 1.317222237586975,
5
+ "eval_runtime": 271.9717,
6
+ "eval_samples_per_second": 0.276,
7
+ "eval_steps_per_second": 0.037
8
+ }
runs/Feb06_18-21-39_4a4c6f005344/events.out.tfevents.1707249567.4a4c6f005344.303.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cd4ef6cb9cfec9e7cbb17ce1e476fdbcf88e6f454b44dd116cf325136c6e3f7
3
- size 411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0d29579fcf3a867935709fa850b9212aaa09d699ca138a31546438025d8838c
3
+ size 734
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.23,
3
+ "eval_accuracy": 0.68,
4
+ "eval_loss": 1.317222237586975,
5
+ "eval_runtime": 271.9717,
6
+ "eval_samples_per_second": 0.276,
7
+ "eval_steps_per_second": 0.037
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7333333333333333,
3
+ "best_model_checkpoint": "spatial_vit_temporal_vit-finetuned-ucf101-subset/checkpoint-148",
4
+ "epoch": 3.22972972972973,
5
+ "eval_steps": 500,
6
+ "global_step": 148,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.07,
13
+ "learning_rate": 3.3333333333333335e-05,
14
+ "loss": 2.3018,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.14,
19
+ "learning_rate": 4.81203007518797e-05,
20
+ "loss": 2.2636,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.2,
25
+ "learning_rate": 4.43609022556391e-05,
26
+ "loss": 2.2165,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.26,
31
+ "eval_accuracy": 0.26666666666666666,
32
+ "eval_loss": 2.0699431896209717,
33
+ "eval_runtime": 107.0916,
34
+ "eval_samples_per_second": 0.28,
35
+ "eval_steps_per_second": 0.037,
36
+ "step": 38
37
+ },
38
+ {
39
+ "epoch": 1.01,
40
+ "learning_rate": 4.0601503759398494e-05,
41
+ "loss": 2.1348,
42
+ "step": 40
43
+ },
44
+ {
45
+ "epoch": 1.08,
46
+ "learning_rate": 3.6842105263157895e-05,
47
+ "loss": 2.008,
48
+ "step": 50
49
+ },
50
+ {
51
+ "epoch": 1.15,
52
+ "learning_rate": 3.3082706766917295e-05,
53
+ "loss": 1.9693,
54
+ "step": 60
55
+ },
56
+ {
57
+ "epoch": 1.22,
58
+ "learning_rate": 2.9323308270676693e-05,
59
+ "loss": 1.8229,
60
+ "step": 70
61
+ },
62
+ {
63
+ "epoch": 1.26,
64
+ "eval_accuracy": 0.5,
65
+ "eval_loss": 1.816007375717163,
66
+ "eval_runtime": 108.4965,
67
+ "eval_samples_per_second": 0.277,
68
+ "eval_steps_per_second": 0.037,
69
+ "step": 76
70
+ },
71
+ {
72
+ "epoch": 2.03,
73
+ "learning_rate": 2.556390977443609e-05,
74
+ "loss": 1.8013,
75
+ "step": 80
76
+ },
77
+ {
78
+ "epoch": 2.09,
79
+ "learning_rate": 2.1804511278195487e-05,
80
+ "loss": 1.6652,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 2.16,
85
+ "learning_rate": 1.8045112781954888e-05,
86
+ "loss": 1.6004,
87
+ "step": 100
88
+ },
89
+ {
90
+ "epoch": 2.23,
91
+ "learning_rate": 1.4285714285714285e-05,
92
+ "loss": 1.4707,
93
+ "step": 110
94
+ },
95
+ {
96
+ "epoch": 2.26,
97
+ "eval_accuracy": 0.7,
98
+ "eval_loss": 1.4157180786132812,
99
+ "eval_runtime": 108.1494,
100
+ "eval_samples_per_second": 0.277,
101
+ "eval_steps_per_second": 0.037,
102
+ "step": 114
103
+ },
104
+ {
105
+ "epoch": 3.04,
106
+ "learning_rate": 1.0526315789473684e-05,
107
+ "loss": 1.4613,
108
+ "step": 120
109
+ },
110
+ {
111
+ "epoch": 3.11,
112
+ "learning_rate": 6.766917293233083e-06,
113
+ "loss": 1.3109,
114
+ "step": 130
115
+ },
116
+ {
117
+ "epoch": 3.18,
118
+ "learning_rate": 3.007518796992481e-06,
119
+ "loss": 1.3886,
120
+ "step": 140
121
+ },
122
+ {
123
+ "epoch": 3.23,
124
+ "eval_accuracy": 0.7333333333333333,
125
+ "eval_loss": 1.3519634008407593,
126
+ "eval_runtime": 108.7503,
127
+ "eval_samples_per_second": 0.276,
128
+ "eval_steps_per_second": 0.037,
129
+ "step": 148
130
+ },
131
+ {
132
+ "epoch": 3.23,
133
+ "step": 148,
134
+ "total_flos": 0.0,
135
+ "train_loss": 1.7922898885366079,
136
+ "train_runtime": 5180.8771,
137
+ "train_samples_per_second": 0.229,
138
+ "train_steps_per_second": 0.029
139
+ },
140
+ {
141
+ "epoch": 3.23,
142
+ "eval_accuracy": 0.68,
143
+ "eval_loss": 1.317222237586975,
144
+ "eval_runtime": 274.8188,
145
+ "eval_samples_per_second": 0.273,
146
+ "eval_steps_per_second": 0.036,
147
+ "step": 148
148
+ },
149
+ {
150
+ "epoch": 3.23,
151
+ "eval_accuracy": 0.68,
152
+ "eval_loss": 1.317222237586975,
153
+ "eval_runtime": 271.9717,
154
+ "eval_samples_per_second": 0.276,
155
+ "eval_steps_per_second": 0.037,
156
+ "step": 148
157
+ }
158
+ ],
159
+ "logging_steps": 10,
160
+ "max_steps": 148,
161
+ "num_input_tokens_seen": 0,
162
+ "num_train_epochs": 9223372036854775807,
163
+ "save_steps": 500,
164
+ "total_flos": 0.0,
165
+ "train_batch_size": 8,
166
+ "trial_name": null,
167
+ "trial_params": null
168
+ }