Hugging Face's logo

Cheng98
/
bert-large-sst2

Text Classification
Transformers
PyTorch
English
bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
Cheng98 commited on
Commit
4387b42
·
1 Parent(s): 7a61cb5

End of training

Browse files
Files changed (4) hide show
  1. all_results.json +14 -0
  2. eval_results.json +9 -0
  3. train_results.json +8 -0
  4. trainer_state.json +85 -0
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9277522935779816,
4
+ "eval_loss": 0.2121734321117401,
5
+ "eval_runtime": 5.1507,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 169.297,
8
+ "eval_steps_per_second": 5.436,
9
+ "train_loss": 0.16908984673793778,
10
+ "train_runtime": 4642.5497,
11
+ "train_samples": 67349,
12
+ "train_samples_per_second": 58.028,
13
+ "train_steps_per_second": 0.453
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_accuracy": 0.9277522935779816,
4
+ "eval_loss": 0.2121734321117401,
5
+ "eval_runtime": 5.1507,
6
+ "eval_samples": 872,
7
+ "eval_samples_per_second": 169.297,
8
+ "eval_steps_per_second": 5.436
9
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 0.16908984673793778,
4
+ "train_runtime": 4642.5497,
5
+ "train_samples": 67349,
6
+ "train_samples_per_second": 58.028,
7
+ "train_steps_per_second": 0.453
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,85 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.998099762470309,
5
+ "global_step": 2104,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.95,
12
+ "learning_rate": 3.8236692015209125e-05,
13
+ "loss": 0.3476,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_accuracy": 0.8944954128440367,
19
+ "eval_loss": 0.3027590811252594,
20
+ "eval_runtime": 5.1932,
21
+ "eval_samples_per_second": 167.912,
22
+ "eval_steps_per_second": 5.392,
23
+ "step": 526
24
+ },
25
+ {
26
+ "epoch": 1.9,
27
+ "learning_rate": 2.6354562737642585e-05,
28
+ "loss": 0.1646,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 2.0,
33
+ "eval_accuracy": 0.911697247706422,
34
+ "eval_loss": 0.2424829751253128,
35
+ "eval_runtime": 5.1979,
36
+ "eval_samples_per_second": 167.759,
37
+ "eval_steps_per_second": 5.387,
38
+ "step": 1052
39
+ },
40
+ {
41
+ "epoch": 2.85,
42
+ "learning_rate": 1.4472433460076046e-05,
43
+ "loss": 0.1098,
44
+ "step": 1500
45
+ },
46
+ {
47
+ "epoch": 3.0,
48
+ "eval_accuracy": 0.9277522935779816,
49
+ "eval_loss": 0.2052551656961441,
50
+ "eval_runtime": 5.1738,
51
+ "eval_samples_per_second": 168.542,
52
+ "eval_steps_per_second": 5.412,
53
+ "step": 1578
54
+ },
55
+ {
56
+ "epoch": 3.8,
57
+ "learning_rate": 2.5903041825095057e-06,
58
+ "loss": 0.0767,
59
+ "step": 2000
60
+ },
61
+ {
62
+ "epoch": 4.0,
63
+ "eval_accuracy": 0.9277522935779816,
64
+ "eval_loss": 0.2121734321117401,
65
+ "eval_runtime": 5.1753,
66
+ "eval_samples_per_second": 168.492,
67
+ "eval_steps_per_second": 5.41,
68
+ "step": 2104
69
+ },
70
+ {
71
+ "epoch": 4.0,
72
+ "step": 2104,
73
+ "total_flos": 2.509495455856005e+17,
74
+ "train_loss": 0.16908984673793778,
75
+ "train_runtime": 4642.5497,
76
+ "train_samples_per_second": 58.028,
77
+ "train_steps_per_second": 0.453
78
+ }
79
+ ],
80
+ "max_steps": 2104,
81
+ "num_train_epochs": 4,
82
+ "total_flos": 2.509495455856005e+17,
83
+ "trial_name": null,
84
+ "trial_params": null
85
+ }