Hugging Face's logo

BTX24
/
hiera-finetuned-busi

Image Classification
Transformers
TensorBoard
Safetensors
hiera
Generated from Trainer
Model card Files
xet
Metrics Community
BTX24 commited on
Commit
c2572fa
·
verified ·
1 Parent(s): c589e5d

Upload trained model

Browse files
Files changed (4) hide show
  1. all_results.json +8 -0
  2. runs/Jul05_23-43-59_50943675aa63/events.out.tfevents.1751759712.50943675aa63.10911.2 +3 -0
  3. train_results.json +8 -0
  4. trainer_state.json +154 -0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 48.0,
3
+ "total_flos": 1.3730970154696704e+18,
4
+ "train_loss": 0.17117963035901387,
5
+ "train_runtime": 645.3789,
6
+ "train_samples_per_second": 46.41,
7
+ "train_steps_per_second": 0.744
8
+ }
runs/Jul05_23-43-59_50943675aa63/events.out.tfevents.1751759712.50943675aa63.10911.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7a397be8fe5e396ccf6ad9e2f8bbec68f20819d4ef230b1876d1667f3beffe6
3
+ size 560
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 48.0,
3
+ "total_flos": 1.3730970154696704e+18,
4
+ "train_loss": 0.17117963035901387,
5
+ "train_runtime": 645.3789,
6
+ "train_samples_per_second": 46.41,
7
+ "train_steps_per_second": 0.744
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 400,
3
+ "best_metric": 0.9678384954963574,
4
+ "best_model_checkpoint": "BTX24/hiera-finetuned-busi/checkpoint-400",
5
+ "epoch": 48.0,
6
+ "eval_steps": 100,
7
+ "global_step": 480,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 5.0,
14
+ "grad_norm": 10.227621078491211,
15
+ "learning_rate": 1.9999735576321776e-05,
16
+ "loss": 0.6534,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 10.0,
21
+ "grad_norm": 8.809008598327637,
22
+ "learning_rate": 1.9346189253489888e-05,
23
+ "loss": 0.2276,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 10.0,
28
+ "eval_accuracy": 0.9615384615384616,
29
+ "eval_f1": 0.9610639894395369,
30
+ "eval_loss": 0.16655339300632477,
31
+ "eval_precision": 0.964046822742475,
32
+ "eval_recall": 0.9615384615384616,
33
+ "eval_runtime": 2.0085,
34
+ "eval_samples_per_second": 77.671,
35
+ "eval_steps_per_second": 9.958,
36
+ "step": 100
37
+ },
38
+ {
39
+ "epoch": 15.0,
40
+ "grad_norm": 5.131218910217285,
41
+ "learning_rate": 1.7470250712409963e-05,
42
+ "loss": 0.1848,
43
+ "step": 150
44
+ },
45
+ {
46
+ "epoch": 20.0,
47
+ "grad_norm": 27.55030059814453,
48
+ "learning_rate": 1.4617486132350343e-05,
49
+ "loss": 0.1447,
50
+ "step": 200
51
+ },
52
+ {
53
+ "epoch": 20.0,
54
+ "eval_accuracy": 0.9358974358974359,
55
+ "eval_f1": 0.9351834928758006,
56
+ "eval_loss": 0.18257668614387512,
57
+ "eval_precision": 0.9425747863247864,
58
+ "eval_recall": 0.9358974358974359,
59
+ "eval_runtime": 1.8774,
60
+ "eval_samples_per_second": 83.092,
61
+ "eval_steps_per_second": 10.653,
62
+ "step": 200
63
+ },
64
+ {
65
+ "epoch": 25.0,
66
+ "grad_norm": 4.577565670013428,
67
+ "learning_rate": 1.1160929141252303e-05,
68
+ "loss": 0.1148,
69
+ "step": 250
70
+ },
71
+ {
72
+ "epoch": 30.0,
73
+ "grad_norm": 7.3700270652771,
74
+ "learning_rate": 7.623141076738271e-06,
75
+ "loss": 0.0882,
76
+ "step": 300
77
+ },
78
+ {
79
+ "epoch": 30.0,
80
+ "eval_accuracy": 0.9615384615384616,
81
+ "eval_f1": 0.9611905417400026,
82
+ "eval_loss": 0.16116316616535187,
83
+ "eval_precision": 0.9612915234951416,
84
+ "eval_recall": 0.9615384615384616,
85
+ "eval_runtime": 1.8625,
86
+ "eval_samples_per_second": 83.757,
87
+ "eval_steps_per_second": 10.738,
88
+ "step": 300
89
+ },
90
+ {
91
+ "epoch": 35.0,
92
+ "grad_norm": 1.2752153873443604,
93
+ "learning_rate": 4.323957196315714e-06,
94
+ "loss": 0.0728,
95
+ "step": 350
96
+ },
97
+ {
98
+ "epoch": 40.0,
99
+ "grad_norm": 5.241044044494629,
100
+ "learning_rate": 1.7669848724331984e-06,
101
+ "loss": 0.0606,
102
+ "step": 400
103
+ },
104
+ {
105
+ "epoch": 40.0,
106
+ "eval_accuracy": 0.967948717948718,
107
+ "eval_f1": 0.9678384954963574,
108
+ "eval_loss": 0.1380443274974823,
109
+ "eval_precision": 0.9678410301752478,
110
+ "eval_recall": 0.967948717948718,
111
+ "eval_runtime": 1.8643,
112
+ "eval_samples_per_second": 83.679,
113
+ "eval_steps_per_second": 10.728,
114
+ "step": 400
115
+ },
116
+ {
117
+ "epoch": 45.0,
118
+ "grad_norm": 13.990592956542969,
119
+ "learning_rate": 2.865793018673857e-07,
120
+ "loss": 0.0628,
121
+ "step": 450
122
+ },
123
+ {
124
+ "epoch": 48.0,
125
+ "step": 480,
126
+ "total_flos": 1.3730970154696704e+18,
127
+ "train_loss": 0.17117963035901387,
128
+ "train_runtime": 645.3789,
129
+ "train_samples_per_second": 46.41,
130
+ "train_steps_per_second": 0.744
131
+ }
132
+ ],
133
+ "logging_steps": 50,
134
+ "max_steps": 480,
135
+ "num_input_tokens_seen": 0,
136
+ "num_train_epochs": 48,
137
+ "save_steps": 100,
138
+ "stateful_callbacks": {
139
+ "TrainerControl": {
140
+ "args": {
141
+ "should_epoch_stop": false,
142
+ "should_evaluate": false,
143
+ "should_log": false,
144
+ "should_save": true,
145
+ "should_training_stop": true
146
+ },
147
+ "attributes": {}
148
+ }
149
+ },
150
+ "total_flos": 1.3730970154696704e+18,
151
+ "train_batch_size": 16,
152
+ "trial_name": null,
153
+ "trial_params": null
154
+ }