Hugging Face's logo

hchcsuim
/
detr-resnet-50_finetuned_cppe5

TensorBoard
Safetensors
detr
Generated from Trainer
Model card Files Metrics Community
hchcsuim commited on
Commit
e265aec
•
1 Parent(s): 4182941

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +4 -4
  2. train_results.json +4 -4
  3. trainer_state.json +20 -20
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
  "total_flos": 9.4894217943552e+17,
4
- "train_loss": 1.8031856994628905,
5
- "train_runtime": 142.4314,
6
- "train_samples_per_second": 13.944,
7
- "train_steps_per_second": 1.755
8
  }
 
1
  {
2
  "epoch": 2.0,
3
  "total_flos": 9.4894217943552e+17,
4
+ "train_loss": 2.5065918884277343,
5
+ "train_runtime": 246.2795,
6
+ "train_samples_per_second": 8.064,
7
+ "train_steps_per_second": 1.015
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 2.0,
3
  "total_flos": 9.4894217943552e+17,
4
- "train_loss": 1.8031856994628905,
5
- "train_runtime": 142.4314,
6
- "train_samples_per_second": 13.944,
7
- "train_steps_per_second": 1.755
8
  }
 
1
  {
2
  "epoch": 2.0,
3
  "total_flos": 9.4894217943552e+17,
4
+ "train_loss": 2.5065918884277343,
5
+ "train_runtime": 246.2795,
6
+ "train_samples_per_second": 8.064,
7
+ "train_steps_per_second": 1.015
8
  }
trainer_state.json CHANGED
@@ -10,54 +10,54 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.4,
13
- "grad_norm": 30.619651794433594,
14
- "learning_rate": 8.16e-06,
15
- "loss": 1.8291,
16
  "step": 50
17
  },
18
  {
19
  "epoch": 0.8,
20
- "grad_norm": 155.9861297607422,
21
- "learning_rate": 6.24e-06,
22
- "loss": 1.8251,
23
  "step": 100
24
  },
25
  {
26
  "epoch": 1.2,
27
- "grad_norm": 59.954654693603516,
28
- "learning_rate": 4.2800000000000005e-06,
29
- "loss": 1.8171,
30
  "step": 150
31
  },
32
  {
33
  "epoch": 1.6,
34
- "grad_norm": 32.81400680541992,
35
- "learning_rate": 2.28e-06,
36
- "loss": 1.7688,
37
  "step": 200
38
  },
39
  {
40
  "epoch": 2.0,
41
- "grad_norm": 64.24483489990234,
42
- "learning_rate": 2.8e-07,
43
- "loss": 1.7759,
44
  "step": 250
45
  },
46
  {
47
  "epoch": 2.0,
48
  "step": 250,
49
  "total_flos": 9.4894217943552e+17,
50
- "train_loss": 1.8031856994628905,
51
- "train_runtime": 142.4314,
52
- "train_samples_per_second": 13.944,
53
- "train_steps_per_second": 1.755
54
  }
55
  ],
56
  "logging_steps": 50,
57
  "max_steps": 250,
58
  "num_input_tokens_seen": 0,
59
  "num_train_epochs": 2,
60
- "save_steps": 200,
61
  "stateful_callbacks": {
62
  "TrainerControl": {
63
  "args": {
 
10
  "log_history": [
11
  {
12
  "epoch": 0.4,
13
+ "grad_norm": 83.9439697265625,
14
+ "learning_rate": 4.555555555555556e-05,
15
+ "loss": 3.2962,
16
  "step": 50
17
  },
18
  {
19
  "epoch": 0.8,
20
+ "grad_norm": 82.1087417602539,
21
+ "learning_rate": 3.466666666666667e-05,
22
+ "loss": 2.6118,
23
  "step": 100
24
  },
25
  {
26
  "epoch": 1.2,
27
+ "grad_norm": 99.78679656982422,
28
+ "learning_rate": 2.3555555555555556e-05,
29
+ "loss": 2.4529,
30
  "step": 150
31
  },
32
  {
33
  "epoch": 1.6,
34
+ "grad_norm": 94.11151885986328,
35
+ "learning_rate": 1.2444444444444445e-05,
36
+ "loss": 2.1187,
37
  "step": 200
38
  },
39
  {
40
  "epoch": 2.0,
41
+ "grad_norm": 85.35782623291016,
42
+ "learning_rate": 1.3333333333333334e-06,
43
+ "loss": 2.0534,
44
  "step": 250
45
  },
46
  {
47
  "epoch": 2.0,
48
  "step": 250,
49
  "total_flos": 9.4894217943552e+17,
50
+ "train_loss": 2.5065918884277343,
51
+ "train_runtime": 246.2795,
52
+ "train_samples_per_second": 8.064,
53
+ "train_steps_per_second": 1.015
54
  }
55
  ],
56
  "logging_steps": 50,
57
  "max_steps": 250,
58
  "num_input_tokens_seen": 0,
59
  "num_train_epochs": 2,
60
+ "save_steps": 500,
61
  "stateful_callbacks": {
62
  "TrainerControl": {
63
  "args": {