Hugging Face's logo

JeremiahZ
/
bert-base-uncased-sst2

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
English
bert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
Metrics Community
2
Jeremiah Zhou commited on
Commit
60af700
·
1 Parent(s): e8c9195

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +14 -0
  2. eval_results.json +9 -0
  3. runs/Jun21_14-48-15_mewtwo/events.out.tfevents.1655825695.mewtwo +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +124 -0
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9323394495412844,
4
+ "eval_loss": 0.2478291541337967,
5
+ "eval_runtime": 3.9031,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 223.413,
8
+ "eval_steps_per_second": 27.927,
9
+ "train_loss": 0.1281920957829588,
10
+ "train_runtime": 2481.1506,
11
+ "train_samples": 67349,
12
+ "train_samples_per_second": 81.433,
13
+ "train_steps_per_second": 2.545
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.9323394495412844,
4
+ "eval_loss": 0.2478291541337967,
5
+ "eval_runtime": 3.9031,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 223.413,
8
+ "eval_steps_per_second": 27.927
9
+ }
runs/Jun21_14-48-15_mewtwo/events.out.tfevents.1655825695.mewtwo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c10309ce8b4d2b861f73c5a43ff51497da794f395df02380e990a67353b2458f
3
+ size 40
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.1281920957829588,
4
+ "train_runtime": 2481.1506,
5
+ "train_samples": 67349,
6
+ "train_samples_per_second": 81.433,
7
+ "train_steps_per_second": 2.545
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,124 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9323394495412844,
3
+ "best_model_checkpoint": "./fine-tune/bert-base-uncased/sst2/checkpoint-4210",
4
+ "epoch": 3.0,
5
+ "global_step": 6315,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.24,
12
+ "learning_rate": 1.8416468725257326e-05,
13
+ "loss": 0.2904,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.48,
18
+ "learning_rate": 1.6832937450514647e-05,
19
+ "loss": 0.2097,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.71,
24
+ "learning_rate": 1.5249406175771972e-05,
25
+ "loss": 0.1752,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.95,
30
+ "learning_rate": 1.3665874901029297e-05,
31
+ "loss": 0.1668,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.0,
36
+ "eval_accuracy": 0.9174311926605505,
37
+ "eval_loss": 0.2512936294078827,
38
+ "eval_runtime": 4.0394,
39
+ "eval_samples_per_second": 215.874,
40
+ "eval_steps_per_second": 26.984,
41
+ "step": 2105
42
+ },
43
+ {
44
+ "epoch": 1.19,
45
+ "learning_rate": 1.208234362628662e-05,
46
+ "loss": 0.1199,
47
+ "step": 2500
48
+ },
49
+ {
50
+ "epoch": 1.43,
51
+ "learning_rate": 1.0498812351543943e-05,
52
+ "loss": 0.1049,
53
+ "step": 3000
54
+ },
55
+ {
56
+ "epoch": 1.66,
57
+ "learning_rate": 8.915281076801267e-06,
58
+ "loss": 0.1075,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 1.9,
63
+ "learning_rate": 7.331749802058591e-06,
64
+ "loss": 0.1119,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 2.0,
69
+ "eval_accuracy": 0.9323394495412844,
70
+ "eval_loss": 0.2478291541337967,
71
+ "eval_runtime": 4.1684,
72
+ "eval_samples_per_second": 209.192,
73
+ "eval_steps_per_second": 26.149,
74
+ "step": 4210
75
+ },
76
+ {
77
+ "epoch": 2.14,
78
+ "learning_rate": 5.748218527315916e-06,
79
+ "loss": 0.0828,
80
+ "step": 4500
81
+ },
82
+ {
83
+ "epoch": 2.38,
84
+ "learning_rate": 4.164687252573238e-06,
85
+ "loss": 0.0667,
86
+ "step": 5000
87
+ },
88
+ {
89
+ "epoch": 2.61,
90
+ "learning_rate": 2.581155977830562e-06,
91
+ "loss": 0.069,
92
+ "step": 5500
93
+ },
94
+ {
95
+ "epoch": 2.85,
96
+ "learning_rate": 9.976247030878861e-07,
97
+ "loss": 0.0699,
98
+ "step": 6000
99
+ },
100
+ {
101
+ "epoch": 3.0,
102
+ "eval_accuracy": 0.926605504587156,
103
+ "eval_loss": 0.2763631343841553,
104
+ "eval_runtime": 4.0199,
105
+ "eval_samples_per_second": 216.923,
106
+ "eval_steps_per_second": 27.115,
107
+ "step": 6315
108
+ },
109
+ {
110
+ "epoch": 3.0,
111
+ "step": 6315,
112
+ "total_flos": 1.329019985058048e+16,
113
+ "train_loss": 0.1281920957829588,
114
+ "train_runtime": 2481.1506,
115
+ "train_samples_per_second": 81.433,
116
+ "train_steps_per_second": 2.545
117
+ }
118
+ ],
119
+ "max_steps": 6315,
120
+ "num_train_epochs": 3,
121
+ "total_flos": 1.329019985058048e+16,
122
+ "trial_name": null,
123
+ "trial_params": null
124
+ }