Hugging Face's logo

hoanbklucky
/
dinov2-small-imagenet1k-1-layer-finetuned-noh

Image Classification
Transformers
TensorBoard
Safetensors
dinov2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
hoanbklucky commited on
Commit
c6b4907
·
verified ·
1 Parent(s): 5f97bf2

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +13 -0
  2. eval_results.json +8 -0
  3. runs/Dec16_17-37-52_d27792686cb1/events.out.tfevents.1734373487.d27792686cb1.1788.1 +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +111 -0
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9333333333333336,
3
+ "eval_accuracy": 0.9014778325123153,
4
+ "eval_loss": 0.3210342824459076,
5
+ "eval_runtime": 178.0058,
6
+ "eval_samples_per_second": 3.421,
7
+ "eval_steps_per_second": 0.219,
8
+ "total_flos": 8.411145538115174e+16,
9
+ "train_loss": 0.5577786402268843,
10
+ "train_runtime": 2627.8256,
11
+ "train_samples_per_second": 1.643,
12
+ "train_steps_per_second": 0.025
13
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9333333333333336,
3
+ "eval_accuracy": 0.9014778325123153,
4
+ "eval_loss": 0.3210342824459076,
5
+ "eval_runtime": 178.0058,
6
+ "eval_samples_per_second": 3.421,
7
+ "eval_steps_per_second": 0.219
8
+ }
runs/Dec16_17-37-52_d27792686cb1/events.out.tfevents.1734373487.d27792686cb1.1788.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4601891381cc42cb59c1b04f8bcc7eed5a6e9a2128a6e304913ce6361c00a586
3
+ size 405
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9333333333333336,
3
+ "total_flos": 8.411145538115174e+16,
4
+ "train_loss": 0.5577786402268843,
5
+ "train_runtime": 2627.8256,
6
+ "train_samples_per_second": 1.643,
7
+ "train_steps_per_second": 0.025
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9014778325123153,
3
+ "best_model_checkpoint": "dinov2-small-imagenet1k-1-layer-finetuned-noh/checkpoint-66",
4
+ "epoch": 2.9333333333333336,
5
+ "eval_steps": 500,
6
+ "global_step": 66,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4444444444444444,
13
+ "grad_norm": 223.80079650878906,
14
+ "learning_rate": 4.745762711864407e-05,
15
+ "loss": 0.8188,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.8888888888888888,
20
+ "grad_norm": 90.21881103515625,
21
+ "learning_rate": 3.898305084745763e-05,
22
+ "loss": 0.6437,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.9777777777777777,
27
+ "eval_accuracy": 0.7619047619047619,
28
+ "eval_loss": 0.47078460454940796,
29
+ "eval_runtime": 425.2287,
30
+ "eval_samples_per_second": 1.432,
31
+ "eval_steps_per_second": 0.092,
32
+ "step": 22
33
+ },
34
+ {
35
+ "epoch": 1.3333333333333333,
36
+ "grad_norm": 154.34889221191406,
37
+ "learning_rate": 3.050847457627119e-05,
38
+ "loss": 0.6102,
39
+ "step": 30
40
+ },
41
+ {
42
+ "epoch": 1.7777777777777777,
43
+ "grad_norm": 38.342926025390625,
44
+ "learning_rate": 2.2033898305084748e-05,
45
+ "loss": 0.5057,
46
+ "step": 40
47
+ },
48
+ {
49
+ "epoch": 2.0,
50
+ "eval_accuracy": 0.8850574712643678,
51
+ "eval_loss": 0.33653634786605835,
52
+ "eval_runtime": 178.3005,
53
+ "eval_samples_per_second": 3.416,
54
+ "eval_steps_per_second": 0.219,
55
+ "step": 45
56
+ },
57
+ {
58
+ "epoch": 2.2222222222222223,
59
+ "grad_norm": 36.97127914428711,
60
+ "learning_rate": 1.3559322033898305e-05,
61
+ "loss": 0.4065,
62
+ "step": 50
63
+ },
64
+ {
65
+ "epoch": 2.6666666666666665,
66
+ "grad_norm": 55.42195129394531,
67
+ "learning_rate": 5.084745762711865e-06,
68
+ "loss": 0.4411,
69
+ "step": 60
70
+ },
71
+ {
72
+ "epoch": 2.9333333333333336,
73
+ "eval_accuracy": 0.9014778325123153,
74
+ "eval_loss": 0.3210342824459076,
75
+ "eval_runtime": 175.5054,
76
+ "eval_samples_per_second": 3.47,
77
+ "eval_steps_per_second": 0.222,
78
+ "step": 66
79
+ },
80
+ {
81
+ "epoch": 2.9333333333333336,
82
+ "step": 66,
83
+ "total_flos": 8.411145538115174e+16,
84
+ "train_loss": 0.5577786402268843,
85
+ "train_runtime": 2627.8256,
86
+ "train_samples_per_second": 1.643,
87
+ "train_steps_per_second": 0.025
88
+ }
89
+ ],
90
+ "logging_steps": 10,
91
+ "max_steps": 66,
92
+ "num_input_tokens_seen": 0,
93
+ "num_train_epochs": 3,
94
+ "save_steps": 500,
95
+ "stateful_callbacks": {
96
+ "TrainerControl": {
97
+ "args": {
98
+ "should_epoch_stop": false,
99
+ "should_evaluate": false,
100
+ "should_log": false,
101
+ "should_save": true,
102
+ "should_training_stop": true
103
+ },
104
+ "attributes": {}
105
+ }
106
+ },
107
+ "total_flos": 8.411145538115174e+16,
108
+ "train_batch_size": 16,
109
+ "trial_name": null,
110
+ "trial_params": null
111
+ }