Hugging Face's logo

Davlan
/
xlm-roberta-large-finetuned-xhosa

Fill-Mask
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
Davlan commited on
Commit
49f2680
•
1 Parent(s): dee728f

Upload trainer_state.json

Browse files
Files changed (1) hide show
  1. trainer_state.json +193 -0
trainer_state.json ADDED
@@ -0,0 +1,193 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "global_step": 14052,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.11,
12
+ "learning_rate": 4.8220893822943356e-05,
13
+ "loss": 2.2627,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.21,
18
+ "learning_rate": 4.644178764588671e-05,
19
+ "loss": 1.8478,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.32,
24
+ "learning_rate": 4.466268146883006e-05,
25
+ "loss": 1.6547,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.43,
30
+ "learning_rate": 4.2883575291773416e-05,
31
+ "loss": 1.5303,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.53,
36
+ "learning_rate": 4.110446911471677e-05,
37
+ "loss": 1.4348,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.64,
42
+ "learning_rate": 3.9325362937660123e-05,
43
+ "loss": 1.36,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.75,
48
+ "learning_rate": 3.754625676060348e-05,
49
+ "loss": 1.3118,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.85,
54
+ "learning_rate": 3.5767150583546824e-05,
55
+ "loss": 1.2551,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.96,
60
+ "learning_rate": 3.3988044406490184e-05,
61
+ "loss": 1.2125,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 1.07,
66
+ "learning_rate": 3.220893822943353e-05,
67
+ "loss": 1.174,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 1.17,
72
+ "learning_rate": 3.0429832052376888e-05,
73
+ "loss": 1.1241,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 1.28,
78
+ "learning_rate": 2.8650725875320238e-05,
79
+ "loss": 1.0909,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 1.39,
84
+ "learning_rate": 2.6871619698263595e-05,
85
+ "loss": 1.061,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 1.49,
90
+ "learning_rate": 2.5092513521206945e-05,
91
+ "loss": 1.0389,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 1.6,
96
+ "learning_rate": 2.33134073441503e-05,
97
+ "loss": 1.0249,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 1.71,
102
+ "learning_rate": 2.1534301167093655e-05,
103
+ "loss": 0.9963,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 1.81,
108
+ "learning_rate": 1.975519499003701e-05,
109
+ "loss": 0.9854,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 1.92,
114
+ "learning_rate": 1.797608881298036e-05,
115
+ "loss": 0.9605,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 2.03,
120
+ "learning_rate": 1.6196982635923712e-05,
121
+ "loss": 0.9448,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 2.13,
126
+ "learning_rate": 1.4417876458867066e-05,
127
+ "loss": 0.9212,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 2.24,
132
+ "learning_rate": 1.263877028181042e-05,
133
+ "loss": 0.9118,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 2.35,
138
+ "learning_rate": 1.0859664104753773e-05,
139
+ "loss": 0.9049,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 2.46,
144
+ "learning_rate": 9.080557927697125e-06,
145
+ "loss": 0.8889,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 2.56,
150
+ "learning_rate": 7.301451750640478e-06,
151
+ "loss": 0.8752,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 2.67,
156
+ "learning_rate": 5.5223455735838315e-06,
157
+ "loss": 0.8754,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 2.78,
162
+ "learning_rate": 3.743239396527185e-06,
163
+ "loss": 0.8668,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 2.88,
168
+ "learning_rate": 1.964133219470538e-06,
169
+ "loss": 0.854,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 2.99,
174
+ "learning_rate": 1.8502704241389127e-07,
175
+ "loss": 0.8554,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 3.0,
180
+ "step": 14052,
181
+ "total_flos": 1.3105172644574003e+17,
182
+ "train_loss": 1.1496979724027274,
183
+ "train_runtime": 14912.9972,
184
+ "train_samples_per_second": 9.422,
185
+ "train_steps_per_second": 0.942
186
+ }
187
+ ],
188
+ "max_steps": 14052,
189
+ "num_train_epochs": 3,
190
+ "total_flos": 1.3105172644574003e+17,
191
+ "trial_name": null,
192
+ "trial_params": null
193
+ }