Hugging Face's logo

t1msan
/
swin-base-patch4-window7-224-in22k-Kontur-competition-1.3K

Image Classification
Transformers
TensorBoard
Safetensors
swin
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
t1msan commited on
Commit
eab20ae
•
1 Parent(s): 96c6007

Training in progress, epoch 0

Browse files
Files changed (6) hide show
  1. all_results.json +8 -0
  2. model.safetensors +1 -1
  3. runs/Apr18_19-54-13_c91955ade82b/events.out.tfevents.1713470054.c91955ade82b.34.1 +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +91 -0
  6. training_args.bin +1 -1
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.8,
3
+ "total_flos": 4.4500275596722176e+17,
4
+ "train_loss": 0.1861822952826818,
5
+ "train_runtime": 258.3418,
6
+ "train_samples_per_second": 22.838,
7
+ "train_steps_per_second": 0.116
8
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc175bcd451f6b11cbdfe79b08f4e3b273191ecf030409e1d738eff13babbad3
3
  size 347498816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac4133e14cedfd4d1f2ca5939e1dabded9714b5c40dae2da28feca02f64817a6
3
  size 347498816
runs/Apr18_19-54-13_c91955ade82b/events.out.tfevents.1713470054.c91955ade82b.34.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75fe715831418a96ada32f5f020a46b3852949992373076e0de679a8c95c312f
3
+ size 5375
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.8,
3
+ "total_flos": 4.4500275596722176e+17,
4
+ "train_loss": 0.1861822952826818,
5
+ "train_runtime": 258.3418,
6
+ "train_samples_per_second": 22.838,
7
+ "train_steps_per_second": 0.116
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.030113982036709785,
3
+ "best_model_checkpoint": "swin-base-patch4-window7-224-in22k-Kontur-competition-1.3K/checkpoint-18",
4
+ "epoch": 4.8,
5
+ "eval_steps": 500,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.96,
13
+ "eval_loss": 0.3283247947692871,
14
+ "eval_runtime": 3.7851,
15
+ "eval_samples_per_second": 34.874,
16
+ "eval_steps_per_second": 0.793,
17
+ "step": 6
18
+ },
19
+ {
20
+ "epoch": 1.6,
21
+ "grad_norm": 3.094001293182373,
22
+ "learning_rate": 3.7037037037037037e-05,
23
+ "loss": 0.4531,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 1.92,
28
+ "eval_loss": 0.08094710856676102,
29
+ "eval_runtime": 2.5203,
30
+ "eval_samples_per_second": 52.376,
31
+ "eval_steps_per_second": 1.19,
32
+ "step": 12
33
+ },
34
+ {
35
+ "epoch": 2.88,
36
+ "eval_loss": 0.030113982036709785,
37
+ "eval_runtime": 2.6775,
38
+ "eval_samples_per_second": 49.299,
39
+ "eval_steps_per_second": 1.12,
40
+ "step": 18
41
+ },
42
+ {
43
+ "epoch": 3.2,
44
+ "grad_norm": 5.238066673278809,
45
+ "learning_rate": 1.8518518518518518e-05,
46
+ "loss": 0.069,
47
+ "step": 20
48
+ },
49
+ {
50
+ "epoch": 4.0,
51
+ "eval_loss": 0.12024853378534317,
52
+ "eval_runtime": 2.6542,
53
+ "eval_samples_per_second": 49.733,
54
+ "eval_steps_per_second": 1.13,
55
+ "step": 25
56
+ },
57
+ {
58
+ "epoch": 4.8,
59
+ "grad_norm": 3.4171395301818848,
60
+ "learning_rate": 0.0,
61
+ "loss": 0.0364,
62
+ "step": 30
63
+ },
64
+ {
65
+ "epoch": 4.8,
66
+ "eval_loss": 0.0865083634853363,
67
+ "eval_runtime": 2.5761,
68
+ "eval_samples_per_second": 51.24,
69
+ "eval_steps_per_second": 1.165,
70
+ "step": 30
71
+ },
72
+ {
73
+ "epoch": 4.8,
74
+ "step": 30,
75
+ "total_flos": 4.4500275596722176e+17,
76
+ "train_loss": 0.1861822952826818,
77
+ "train_runtime": 258.3418,
78
+ "train_samples_per_second": 22.838,
79
+ "train_steps_per_second": 0.116
80
+ }
81
+ ],
82
+ "logging_steps": 10,
83
+ "max_steps": 30,
84
+ "num_input_tokens_seen": 0,
85
+ "num_train_epochs": 5,
86
+ "save_steps": 500,
87
+ "total_flos": 4.4500275596722176e+17,
88
+ "train_batch_size": 48,
89
+ "trial_name": null,
90
+ "trial_params": null
91
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f81e494949595b61152fffda0c72a237480d3f7663ae685843a07b48c38d1f3
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db8d559b9ad165518ccca52fe3dd951ac828455ce1b000177aaaa403cbfdc2a7
3
  size 5048