Hugging Face's logo

nbroad
/
fix_punct_cased_t5_small

Transformers
PyTorch
TensorBoard
t5
text2text-generation
Generated from Trainer
text-generation-inference
Model card Files
xet
 Metrics Community
1
nbroad commited on
Commit
eaa9c11
·
1 Parent(s): caf8b26

End of training

Browse files
Files changed (5) hide show
  1. all_results.json +18 -0
  2. eval_results.json +13 -0
  3. runs/Sep29_22-33-00_091133b7351c/events.out.tfevents.1664491614.091133b7351c.4285.2 +3 -0
  4. train_results.json +8 -0
  5. trainer_state.json +118 -0
all_results.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_gen_len": 46.072761585238,
4
+ "eval_loss": 0.2744140923023224,
5
+ "eval_rouge1": 93.3712,
6
+ "eval_rouge2": 91.0027,
7
+ "eval_rougeL": 93.3618,
8
+ "eval_rougeLsum": 93.3479,
9
+ "eval_runtime": 175.9082,
10
+ "eval_samples": 19076,
11
+ "eval_samples_per_second": 108.443,
12
+ "eval_steps_per_second": 0.426,
13
+ "train_loss": 1.343178202311198,
14
+ "train_runtime": 540.3542,
15
+ "train_samples": 76756,
16
+ "train_samples_per_second": 426.143,
17
+ "train_steps_per_second": 3.331
18
+ }
eval_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_gen_len": 46.072761585238,
4
+ "eval_loss": 0.2744140923023224,
5
+ "eval_rouge1": 93.3712,
6
+ "eval_rouge2": 91.0027,
7
+ "eval_rougeL": 93.3618,
8
+ "eval_rougeLsum": 93.3479,
9
+ "eval_runtime": 175.9082,
10
+ "eval_samples": 19076,
11
+ "eval_samples_per_second": 108.443,
12
+ "eval_steps_per_second": 0.426
13
+ }
runs/Sep29_22-33-00_091133b7351c/events.out.tfevents.1664491614.091133b7351c.4285.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9239d59956a4548e77e1479d2c166fe15b53fbb5faac9505263a3d0fd7df64ed
3
+ size 565
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 1.343178202311198,
4
+ "train_runtime": 540.3542,
5
+ "train_samples": 76756,
6
+ "train_samples_per_second": 426.143,
7
+ "train_steps_per_second": 3.331
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 1800,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.33,
12
+ "learning_rate": 7.11111111111111e-05,
13
+ "loss": 4.5408,
14
+ "step": 200
15
+ },
16
+ {
17
+ "epoch": 0.67,
18
+ "learning_rate": 6.222222222222223e-05,
19
+ "loss": 1.8252,
20
+ "step": 400
21
+ },
22
+ {
23
+ "epoch": 1.0,
24
+ "learning_rate": 5.333333333333333e-05,
25
+ "loss": 1.2254,
26
+ "step": 600
27
+ },
28
+ {
29
+ "epoch": 1.0,
30
+ "eval_gen_len": 16.26368211365066,
31
+ "eval_loss": 0.3500877618789673,
32
+ "eval_rouge1": 63.2952,
33
+ "eval_rouge2": 59.8766,
34
+ "eval_rougeL": 63.137,
35
+ "eval_rougeLsum": 63.2022,
36
+ "eval_runtime": 68.1179,
37
+ "eval_samples_per_second": 280.044,
38
+ "eval_steps_per_second": 1.101,
39
+ "step": 600
40
+ },
41
+ {
42
+ "epoch": 1.33,
43
+ "learning_rate": 4.444444444444445e-05,
44
+ "loss": 0.9521,
45
+ "step": 800
46
+ },
47
+ {
48
+ "epoch": 1.67,
49
+ "learning_rate": 3.555555555555555e-05,
50
+ "loss": 0.8012,
51
+ "step": 1000
52
+ },
53
+ {
54
+ "epoch": 2.0,
55
+ "learning_rate": 2.6666666666666667e-05,
56
+ "loss": 0.7345,
57
+ "step": 1200
58
+ },
59
+ {
60
+ "epoch": 2.0,
61
+ "eval_gen_len": 16.362549800796813,
62
+ "eval_loss": 0.28145653009414673,
63
+ "eval_rouge1": 64.896,
64
+ "eval_rouge2": 61.6256,
65
+ "eval_rougeL": 64.8677,
66
+ "eval_rougeLsum": 64.8728,
67
+ "eval_runtime": 68.0673,
68
+ "eval_samples_per_second": 280.252,
69
+ "eval_steps_per_second": 1.102,
70
+ "step": 1200
71
+ },
72
+ {
73
+ "epoch": 2.33,
74
+ "learning_rate": 1.7777777777777777e-05,
75
+ "loss": 0.6867,
76
+ "step": 1400
77
+ },
78
+ {
79
+ "epoch": 2.67,
80
+ "learning_rate": 8.888888888888888e-06,
81
+ "loss": 0.6691,
82
+ "step": 1600
83
+ },
84
+ {
85
+ "epoch": 3.0,
86
+ "learning_rate": 0.0,
87
+ "loss": 0.6536,
88
+ "step": 1800
89
+ },
90
+ {
91
+ "epoch": 3.0,
92
+ "eval_gen_len": 16.390595512686097,
93
+ "eval_loss": 0.2744140923023224,
94
+ "eval_rouge1": 64.8724,
95
+ "eval_rouge2": 61.6282,
96
+ "eval_rougeL": 64.8483,
97
+ "eval_rougeLsum": 64.8502,
98
+ "eval_runtime": 67.9884,
99
+ "eval_samples_per_second": 280.577,
100
+ "eval_steps_per_second": 1.103,
101
+ "step": 1800
102
+ },
103
+ {
104
+ "epoch": 3.0,
105
+ "step": 1800,
106
+ "total_flos": 4005219262537728.0,
107
+ "train_loss": 1.343178202311198,
108
+ "train_runtime": 540.3542,
109
+ "train_samples_per_second": 426.143,
110
+ "train_steps_per_second": 3.331
111
+ }
112
+ ],
113
+ "max_steps": 1800,
114
+ "num_train_epochs": 3,
115
+ "total_flos": 4005219262537728.0,
116
+ "trial_name": null,
117
+ "trial_params": null
118
+ }