Hugging Face's logo

JeremiahZ
/
roberta-base-wnli

Text Classification
Transformers
PyTorch
TensorBoard
English
roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Jeremiah Zhou commited on
Commit
2eea97f
•
1 Parent(s): 71afdf9

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +14 -0
  2. eval_results.json +9 -0
  3. runs/Jun15_10-40-07_pikachu/events.out.tfevents.1655261192.pikachu.160822.2 +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +115 -0
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.5633802816901409,
4
+ "eval_loss": 0.6849406957626343,
5
+ "eval_runtime": 0.1546,
6
+ "eval_samples": 71,
7
+ "eval_samples_per_second": 459.24,
8
+ "eval_steps_per_second": 58.214,
9
+ "train_loss": 0.6946794891357422,
10
+ "train_runtime": 122.3783,
11
+ "train_samples": 635,
12
+ "train_samples_per_second": 51.888,
13
+ "train_steps_per_second": 3.269
14
+ }
eval_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_accuracy": 0.5633802816901409,
4
+ "eval_loss": 0.6849406957626343,
5
+ "eval_runtime": 0.1546,
6
+ "eval_samples": 71,
7
+ "eval_samples_per_second": 459.24,
8
+ "eval_steps_per_second": 58.214
9
+ }
runs/Jun15_10-40-07_pikachu/events.out.tfevents.1655261192.pikachu.160822.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67bed87deef9302255e97e229a1412d71d5536aa65cd87f08c55b2683476e2f0
3
+ size 363
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 0.6946794891357422,
4
+ "train_runtime": 122.3783,
5
+ "train_samples": 635,
6
+ "train_samples_per_second": 51.888,
7
+ "train_steps_per_second": 3.269
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,115 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5633802816901409,
3
+ "best_model_checkpoint": "./fine-tune/roberta-base/wnli/checkpoint-40",
4
+ "epoch": 10.0,
5
+ "global_step": 400,
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": 0.5633802816901409,
13
+ "eval_loss": 0.6849406957626343,
14
+ "eval_runtime": 0.2643,
15
+ "eval_samples_per_second": 268.645,
16
+ "eval_steps_per_second": 34.054,
17
+ "step": 40
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_accuracy": 0.5633802816901409,
22
+ "eval_loss": 0.6912119388580322,
23
+ "eval_runtime": 0.259,
24
+ "eval_samples_per_second": 274.159,
25
+ "eval_steps_per_second": 34.753,
26
+ "step": 80
27
+ },
28
+ {
29
+ "epoch": 3.0,
30
+ "eval_accuracy": 0.5633802816901409,
31
+ "eval_loss": 0.6918124556541443,
32
+ "eval_runtime": 0.3165,
33
+ "eval_samples_per_second": 224.361,
34
+ "eval_steps_per_second": 28.44,
35
+ "step": 120
36
+ },
37
+ {
38
+ "epoch": 4.0,
39
+ "eval_accuracy": 0.43661971830985913,
40
+ "eval_loss": 0.6964250802993774,
41
+ "eval_runtime": 0.2736,
42
+ "eval_samples_per_second": 259.529,
43
+ "eval_steps_per_second": 32.898,
44
+ "step": 160
45
+ },
46
+ {
47
+ "epoch": 5.0,
48
+ "eval_accuracy": 0.5633802816901409,
49
+ "eval_loss": 0.692846953868866,
50
+ "eval_runtime": 0.2609,
51
+ "eval_samples_per_second": 272.168,
52
+ "eval_steps_per_second": 34.5,
53
+ "step": 200
54
+ },
55
+ {
56
+ "epoch": 6.0,
57
+ "eval_accuracy": 0.43661971830985913,
58
+ "eval_loss": 0.7005417346954346,
59
+ "eval_runtime": 0.2776,
60
+ "eval_samples_per_second": 255.727,
61
+ "eval_steps_per_second": 32.416,
62
+ "step": 240
63
+ },
64
+ {
65
+ "epoch": 7.0,
66
+ "eval_accuracy": 0.30985915492957744,
67
+ "eval_loss": 0.6964187622070312,
68
+ "eval_runtime": 0.2676,
69
+ "eval_samples_per_second": 265.355,
70
+ "eval_steps_per_second": 33.637,
71
+ "step": 280
72
+ },
73
+ {
74
+ "epoch": 8.0,
75
+ "eval_accuracy": 0.352112676056338,
76
+ "eval_loss": 0.6986197233200073,
77
+ "eval_runtime": 0.2698,
78
+ "eval_samples_per_second": 263.149,
79
+ "eval_steps_per_second": 33.357,
80
+ "step": 320
81
+ },
82
+ {
83
+ "epoch": 9.0,
84
+ "eval_accuracy": 0.5492957746478874,
85
+ "eval_loss": 0.6969391107559204,
86
+ "eval_runtime": 0.263,
87
+ "eval_samples_per_second": 270.009,
88
+ "eval_steps_per_second": 34.226,
89
+ "step": 360
90
+ },
91
+ {
92
+ "epoch": 10.0,
93
+ "eval_accuracy": 0.5633802816901409,
94
+ "eval_loss": 0.697629451751709,
95
+ "eval_runtime": 0.2692,
96
+ "eval_samples_per_second": 263.768,
97
+ "eval_steps_per_second": 33.435,
98
+ "step": 400
99
+ },
100
+ {
101
+ "epoch": 10.0,
102
+ "step": 400,
103
+ "total_flos": 417688800384000.0,
104
+ "train_loss": 0.6946794891357422,
105
+ "train_runtime": 122.3783,
106
+ "train_samples_per_second": 51.888,
107
+ "train_steps_per_second": 3.269
108
+ }
109
+ ],
110
+ "max_steps": 400,
111
+ "num_train_epochs": 10,
112
+ "total_flos": 417688800384000.0,
113
+ "trial_name": null,
114
+ "trial_params": null
115
+ }