Hugging Face's logo

zkdeng
/
convnextv2-tiny-22k-384-finetuned-spiderTraining100-1000-finetuned-spiderTraining5-100

PyTorch
convnextv2
Generated from Trainer
Model card Files Community
zkdeng commited on
Commit
fc7af11
·
verified ·
1 Parent(s): 35ad9bd

Training in progress, epoch 0

Browse files
Files changed (6) hide show
  1. all_results.json +15 -0
  2. eval_results.json +10 -0
  3. pytorch_model.bin +1 -1
  4. train_results.json +7 -0
  5. trainer_state.json +106 -0
  6. training_args.bin +1 -1
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.8,
3
+ "eval_accuracy": 1.0,
4
+ "eval_f1": 1.0,
5
+ "eval_loss": 0.08419864624738693,
6
+ "eval_precision": 1.0,
7
+ "eval_recall": 1.0,
8
+ "eval_runtime": 2.1229,
9
+ "eval_samples_per_second": 23.552,
10
+ "eval_steps_per_second": 1.884,
11
+ "train_loss": 0.5696131110191345,
12
+ "train_runtime": 63.9531,
13
+ "train_samples_per_second": 31.038,
14
+ "train_steps_per_second": 0.469
15
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_accuracy": 1.0,
3
+ "eval_f1": 1.0,
4
+ "eval_loss": 0.08419864624738693,
5
+ "eval_precision": 1.0,
6
+ "eval_recall": 1.0,
7
+ "eval_runtime": 2.1229,
8
+ "eval_samples_per_second": 23.552,
9
+ "eval_steps_per_second": 1.884
10
+ }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8df2da6cabd36d52f60bcd59741fd25c9ce3ce8e494c27244396faac63d2bd33
3
  size 111550573
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c305516e52c4652d135e16a34e27f2724c8fbde8c55879b6c3171e3607d75e3d
3
  size 111550573
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.8,
3
+ "train_loss": 0.5696131110191345,
4
+ "train_runtime": 63.9531,
5
+ "train_samples_per_second": 31.038,
6
+ "train_steps_per_second": 0.469
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0,
3
+ "best_model_checkpoint": "convnextv2-tiny-22k-384-finetuned-spiderTraining100-1000-finetuned-spiderTraining5-100/checkpoint-12",
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_accuracy": 0.9,
14
+ "eval_f1": 0.9035725677830941,
15
+ "eval_loss": 0.5551295280456543,
16
+ "eval_precision": 0.9178571428571429,
17
+ "eval_recall": 0.9121212121212121,
18
+ "eval_runtime": 2.9056,
19
+ "eval_samples_per_second": 17.208,
20
+ "eval_steps_per_second": 1.377,
21
+ "step": 6
22
+ },
23
+ {
24
+ "epoch": 1.6,
25
+ "learning_rate": 3.7037037037037037e-05,
26
+ "loss": 1.3767,
27
+ "step": 10
28
+ },
29
+ {
30
+ "epoch": 1.92,
31
+ "eval_accuracy": 1.0,
32
+ "eval_f1": 1.0,
33
+ "eval_loss": 0.094626285135746,
34
+ "eval_precision": 1.0,
35
+ "eval_recall": 1.0,
36
+ "eval_runtime": 2.1597,
37
+ "eval_samples_per_second": 23.151,
38
+ "eval_steps_per_second": 1.852,
39
+ "step": 12
40
+ },
41
+ {
42
+ "epoch": 2.88,
43
+ "eval_accuracy": 1.0,
44
+ "eval_f1": 1.0,
45
+ "eval_loss": 0.04393688589334488,
46
+ "eval_precision": 1.0,
47
+ "eval_recall": 1.0,
48
+ "eval_runtime": 2.0599,
49
+ "eval_samples_per_second": 24.272,
50
+ "eval_steps_per_second": 1.942,
51
+ "step": 18
52
+ },
53
+ {
54
+ "epoch": 3.2,
55
+ "learning_rate": 1.8518518518518518e-05,
56
+ "loss": 0.1899,
57
+ "step": 20
58
+ },
59
+ {
60
+ "epoch": 4.0,
61
+ "eval_accuracy": 0.98,
62
+ "eval_f1": 0.9779710144927536,
63
+ "eval_loss": 0.041164983063936234,
64
+ "eval_precision": 0.975,
65
+ "eval_recall": 0.9833333333333334,
66
+ "eval_runtime": 2.1688,
67
+ "eval_samples_per_second": 23.054,
68
+ "eval_steps_per_second": 1.844,
69
+ "step": 25
70
+ },
71
+ {
72
+ "epoch": 4.8,
73
+ "learning_rate": 0.0,
74
+ "loss": 0.1423,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 4.8,
79
+ "eval_accuracy": 1.0,
80
+ "eval_f1": 1.0,
81
+ "eval_loss": 0.03655298054218292,
82
+ "eval_precision": 1.0,
83
+ "eval_recall": 1.0,
84
+ "eval_runtime": 2.4104,
85
+ "eval_samples_per_second": 20.743,
86
+ "eval_steps_per_second": 1.659,
87
+ "step": 30
88
+ },
89
+ {
90
+ "epoch": 4.8,
91
+ "step": 30,
92
+ "total_flos": 1.411417875855442e+17,
93
+ "train_loss": 0.5696131110191345,
94
+ "train_runtime": 63.9531,
95
+ "train_samples_per_second": 31.038,
96
+ "train_steps_per_second": 0.469
97
+ }
98
+ ],
99
+ "logging_steps": 10,
100
+ "max_steps": 30,
101
+ "num_train_epochs": 5,
102
+ "save_steps": 500,
103
+ "total_flos": 1.411417875855442e+17,
104
+ "trial_name": null,
105
+ "trial_params": null
106
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b5a1dda555b78bf799381d646e832f99515c904ec62359c89e6b29adebe4c36
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da7b3a1404352de8fe9769966077e9eba94245ba02f6cead53777debcd83666
3
  size 4219