Hugging Face's logo

JeremiahZ
/
bert-base-uncased-mrpc

Text Classification
Transformers
PyTorch
TensorBoard
English
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
3
Jeremiah Zhou commited on
Commit
08705fe
•
1 Parent(s): 0804d9d

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +16 -0
  2. eval_results.json +11 -0
  3. runs/Jun21_20-19-29_pikachu/events.out.tfevents.1655814668.pikachu.3216750.2 +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +92 -0
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8578431372549019,
4
+ "eval_combined_score": 0.8801000198059021,
5
+ "eval_f1": 0.9023569023569024,
6
+ "eval_loss": 0.557181179523468,
7
+ "eval_runtime": 1.1896,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 342.971,
10
+ "eval_steps_per_second": 42.871,
11
+ "train_loss": 0.24623984295388926,
12
+ "train_runtime": 263.949,
13
+ "train_samples": 3668,
14
+ "train_samples_per_second": 69.483,
15
+ "train_steps_per_second": 4.357
16
+ }
eval_results.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.8578431372549019,
4
+ "eval_combined_score": 0.8801000198059021,
5
+ "eval_f1": 0.9023569023569024,
6
+ "eval_loss": 0.557181179523468,
7
+ "eval_runtime": 1.1896,
8
+ "eval_samples": 408,
9
+ "eval_samples_per_second": 342.971,
10
+ "eval_steps_per_second": 42.871
11
+ }
runs/Jun21_20-19-29_pikachu/events.out.tfevents.1655814668.pikachu.3216750.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f05e5eba2c61b6ffbb0e736ab0e7dc3c4933bb5d2421a4b7566ad594924fd5
3
+ size 467
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.24623984295388926,
4
+ "train_runtime": 263.949,
5
+ "train_samples": 3668,
6
+ "train_samples_per_second": 69.483,
7
+ "train_steps_per_second": 4.357
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.8578431372549019,
3
+ "best_model_checkpoint": "./fine-tune/bert-base-uncased/mrpc/checkpoint-690",
4
+ "epoch": 5.0,
5
+ "global_step": 1150,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "eval_accuracy": 0.8088235294117647,
13
+ "eval_combined_score": 0.8396277115497361,
14
+ "eval_f1": 0.8704318936877077,
15
+ "eval_loss": 0.4110628664493561,
16
+ "eval_runtime": 1.9445,
17
+ "eval_samples_per_second": 209.823,
18
+ "eval_steps_per_second": 26.228,
19
+ "step": 230
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_accuracy": 0.8480392156862745,
24
+ "eval_combined_score": 0.8711185839523523,
25
+ "eval_f1": 0.89419795221843,
26
+ "eval_loss": 0.3761928379535675,
27
+ "eval_runtime": 2.0026,
28
+ "eval_samples_per_second": 203.738,
29
+ "eval_steps_per_second": 25.467,
30
+ "step": 460
31
+ },
32
+ {
33
+ "epoch": 2.17,
34
+ "learning_rate": 1.2025901942645698e-05,
35
+ "loss": 0.4287,
36
+ "step": 500
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "eval_accuracy": 0.8578431372549019,
41
+ "eval_combined_score": 0.8801000198059021,
42
+ "eval_f1": 0.9023569023569024,
43
+ "eval_loss": 0.557181179523468,
44
+ "eval_runtime": 1.4976,
45
+ "eval_samples_per_second": 272.437,
46
+ "eval_steps_per_second": 34.055,
47
+ "step": 690
48
+ },
49
+ {
50
+ "epoch": 4.0,
51
+ "eval_accuracy": 0.8553921568627451,
52
+ "eval_combined_score": 0.8765695619669012,
53
+ "eval_f1": 0.8977469670710572,
54
+ "eval_loss": 0.6086517572402954,
55
+ "eval_runtime": 1.1289,
56
+ "eval_samples_per_second": 361.413,
57
+ "eval_steps_per_second": 45.177,
58
+ "step": 920
59
+ },
60
+ {
61
+ "epoch": 4.35,
62
+ "learning_rate": 2.7752081406105456e-06,
63
+ "loss": 0.1172,
64
+ "step": 1000
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "eval_accuracy": 0.8455882352941176,
69
+ "eval_combined_score": 0.86782029565753,
70
+ "eval_f1": 0.8900523560209423,
71
+ "eval_loss": 0.6524226069450378,
72
+ "eval_runtime": 1.1704,
73
+ "eval_samples_per_second": 348.589,
74
+ "eval_steps_per_second": 43.574,
75
+ "step": 1150
76
+ },
77
+ {
78
+ "epoch": 5.0,
79
+ "step": 1150,
80
+ "total_flos": 1206364188825600.0,
81
+ "train_loss": 0.24623984295388926,
82
+ "train_runtime": 263.949,
83
+ "train_samples_per_second": 69.483,
84
+ "train_steps_per_second": 4.357
85
+ }
86
+ ],
87
+ "max_steps": 1150,
88
+ "num_train_epochs": 5,
89
+ "total_flos": 1206364188825600.0,
90
+ "trial_name": null,
91
+ "trial_params": null
92
+ }