Hugging Face's logo

JEdward7777
/
2-finetuned-xlm-r-masakhaner-swa-whole-word-phonetic

Fill-Mask
Transformers
PyTorch
TensorBoard
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
JEdward7777 commited on
Commit
70cd470
·
1 Parent(s): cd118f8

End of training

Browse files
Files changed (3) hide show
  1. all_results.json +7 -0
  2. train_results.json +7 -0
  3. trainer_state.json +111 -0
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 41.80477074795082,
4
+ "train_runtime": 454.8629,
5
+ "train_samples_per_second": 10.75,
6
+ "train_steps_per_second": 1.341
7
+ }
train_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 41.80477074795082,
4
+ "train_runtime": 454.8629,
5
+ "train_samples_per_second": 10.75,
6
+ "train_steps_per_second": 1.341
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.997955010224949,
5
+ "global_step": 610,
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_loss": 39.944950103759766,
13
+ "eval_runtime": 1.5442,
14
+ "eval_samples_per_second": 79.651,
15
+ "eval_steps_per_second": 10.361,
16
+ "step": 61
17
+ },
18
+ {
19
+ "epoch": 2.0,
20
+ "eval_loss": 39.573768615722656,
21
+ "eval_runtime": 1.5441,
22
+ "eval_samples_per_second": 79.656,
23
+ "eval_steps_per_second": 10.362,
24
+ "step": 122
25
+ },
26
+ {
27
+ "epoch": 3.0,
28
+ "eval_loss": 40.006507873535156,
29
+ "eval_runtime": 1.5451,
30
+ "eval_samples_per_second": 79.606,
31
+ "eval_steps_per_second": 10.355,
32
+ "step": 183
33
+ },
34
+ {
35
+ "epoch": 4.0,
36
+ "eval_loss": 39.271480560302734,
37
+ "eval_runtime": 1.5464,
38
+ "eval_samples_per_second": 79.54,
39
+ "eval_steps_per_second": 10.347,
40
+ "step": 244
41
+ },
42
+ {
43
+ "epoch": 5.0,
44
+ "eval_loss": 38.749183654785156,
45
+ "eval_runtime": 1.5468,
46
+ "eval_samples_per_second": 79.518,
47
+ "eval_steps_per_second": 10.344,
48
+ "step": 305
49
+ },
50
+ {
51
+ "epoch": 6.0,
52
+ "eval_loss": 38.856666564941406,
53
+ "eval_runtime": 1.5467,
54
+ "eval_samples_per_second": 79.525,
55
+ "eval_steps_per_second": 10.345,
56
+ "step": 366
57
+ },
58
+ {
59
+ "epoch": 7.0,
60
+ "eval_loss": 38.75959396362305,
61
+ "eval_runtime": 1.5455,
62
+ "eval_samples_per_second": 79.588,
63
+ "eval_steps_per_second": 10.353,
64
+ "step": 427
65
+ },
66
+ {
67
+ "epoch": 8.0,
68
+ "eval_loss": 38.665225982666016,
69
+ "eval_runtime": 1.5457,
70
+ "eval_samples_per_second": 79.578,
71
+ "eval_steps_per_second": 10.352,
72
+ "step": 488
73
+ },
74
+ {
75
+ "epoch": 8.2,
76
+ "learning_rate": 9.01639344262295e-09,
77
+ "loss": 42.1342,
78
+ "step": 500
79
+ },
80
+ {
81
+ "epoch": 9.0,
82
+ "eval_loss": 38.66032028198242,
83
+ "eval_runtime": 1.551,
84
+ "eval_samples_per_second": 79.304,
85
+ "eval_steps_per_second": 10.316,
86
+ "step": 549
87
+ },
88
+ {
89
+ "epoch": 10.0,
90
+ "eval_loss": 38.66507339477539,
91
+ "eval_runtime": 1.5562,
92
+ "eval_samples_per_second": 79.038,
93
+ "eval_steps_per_second": 10.281,
94
+ "step": 610
95
+ },
96
+ {
97
+ "epoch": 10.0,
98
+ "step": 610,
99
+ "total_flos": 322666370343936.0,
100
+ "train_loss": 41.80477074795082,
101
+ "train_runtime": 454.8629,
102
+ "train_samples_per_second": 10.75,
103
+ "train_steps_per_second": 1.341
104
+ }
105
+ ],
106
+ "max_steps": 610,
107
+ "num_train_epochs": 10,
108
+ "total_flos": 322666370343936.0,
109
+ "trial_name": null,
110
+ "trial_params": null
111
+ }