jfernandez commited on
Commit
35526ee
1 Parent(s): 9009663

Upload 21 files

Browse files

the same with the jfernandez/cebuano-filipino-language-model but adjusted the num_hidden_layers=6 to 12.

checkpoint-10000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.25.1",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91160eee1db76216afd308353375c9f494f6e781a232b2ae2583818604fd6bf8
3
+ size 1008371653
checkpoint-10000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d921c9b5783c18a69e774eae2f8617acf594c1b52a318e515bb7a9d8b0b239db
3
+ size 504200313
checkpoint-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8224438e545dc44682b781e69669a782d1f82627216a2e10ab35e1a5308e011
3
+ size 14575
checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7bbf9e806ad2f598caac8827f72c368ba00c05598ace363cb4ae46c81f47031
3
+ size 627
checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.3799969600243198,
5
+ "global_step": 10000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.90500075999392e-05,
13
+ "loss": 7.9101,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.81000151998784e-05,
19
+ "loss": 7.5794,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 4.7150022799817604e-05,
25
+ "loss": 7.5385,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.08,
30
+ "learning_rate": 4.620003039975681e-05,
31
+ "loss": 7.5241,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.09,
36
+ "learning_rate": 4.5250037999696e-05,
37
+ "loss": 7.5219,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.11,
42
+ "learning_rate": 4.4300045599635205e-05,
43
+ "loss": 7.5021,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.13,
48
+ "learning_rate": 4.33500531995744e-05,
49
+ "loss": 7.4248,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.15,
54
+ "learning_rate": 4.240006079951361e-05,
55
+ "loss": 7.4127,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.17,
60
+ "learning_rate": 4.145006839945281e-05,
61
+ "loss": 7.4314,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.19,
66
+ "learning_rate": 4.050007599939201e-05,
67
+ "loss": 7.4032,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.21,
72
+ "learning_rate": 3.9550083599331206e-05,
73
+ "loss": 7.4693,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.23,
78
+ "learning_rate": 3.860009119927041e-05,
79
+ "loss": 7.4423,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.25,
84
+ "learning_rate": 3.765009879920961e-05,
85
+ "loss": 7.444,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.27,
90
+ "learning_rate": 3.670010639914881e-05,
91
+ "loss": 7.4172,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.28,
96
+ "learning_rate": 3.575011399908801e-05,
97
+ "loss": 7.427,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.3,
102
+ "learning_rate": 3.4800121599027206e-05,
103
+ "loss": 7.422,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.32,
108
+ "learning_rate": 3.3850129198966415e-05,
109
+ "loss": 7.4367,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.34,
114
+ "learning_rate": 3.290013679890561e-05,
115
+ "loss": 7.4049,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.36,
120
+ "learning_rate": 3.1950144398844814e-05,
121
+ "loss": 7.3746,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.38,
126
+ "learning_rate": 3.100015199878401e-05,
127
+ "loss": 7.3933,
128
+ "step": 10000
129
+ }
130
+ ],
131
+ "max_steps": 26316,
132
+ "num_train_epochs": 1,
133
+ "total_flos": 2146459117908480.0,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f844e21af175bed928e71c83ee891be16e0b6e41b78430fc855c12a47223b03
3
+ size 3387
checkpoint-20000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.25.1",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
checkpoint-20000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:653e9fb9c94fa6730ae133e6c7dd0ba7c439446f08cdcb2699902dcb1117852c
3
+ size 1008371653
checkpoint-20000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a783e762274677c7517f1ddf2e073f2378ce523a389d52c8892cd1622daa20b
3
+ size 504200313
checkpoint-20000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93cb286cec93f72d6957d905f996892e40448975466bc8eaecdf6878e0392bcc
3
+ size 14575
checkpoint-20000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3e1ffe6371d869072c771c6170393d56abe3df02246c06033e673af6d8154c9
3
+ size 627
checkpoint-20000/trainer_state.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.7599939200486396,
5
+ "global_step": 20000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.90500075999392e-05,
13
+ "loss": 7.9101,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.81000151998784e-05,
19
+ "loss": 7.5794,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 4.7150022799817604e-05,
25
+ "loss": 7.5385,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.08,
30
+ "learning_rate": 4.620003039975681e-05,
31
+ "loss": 7.5241,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.09,
36
+ "learning_rate": 4.5250037999696e-05,
37
+ "loss": 7.5219,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.11,
42
+ "learning_rate": 4.4300045599635205e-05,
43
+ "loss": 7.5021,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.13,
48
+ "learning_rate": 4.33500531995744e-05,
49
+ "loss": 7.4248,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.15,
54
+ "learning_rate": 4.240006079951361e-05,
55
+ "loss": 7.4127,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.17,
60
+ "learning_rate": 4.145006839945281e-05,
61
+ "loss": 7.4314,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.19,
66
+ "learning_rate": 4.050007599939201e-05,
67
+ "loss": 7.4032,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.21,
72
+ "learning_rate": 3.9550083599331206e-05,
73
+ "loss": 7.4693,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.23,
78
+ "learning_rate": 3.860009119927041e-05,
79
+ "loss": 7.4423,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.25,
84
+ "learning_rate": 3.765009879920961e-05,
85
+ "loss": 7.444,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.27,
90
+ "learning_rate": 3.670010639914881e-05,
91
+ "loss": 7.4172,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.28,
96
+ "learning_rate": 3.575011399908801e-05,
97
+ "loss": 7.427,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.3,
102
+ "learning_rate": 3.4800121599027206e-05,
103
+ "loss": 7.422,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.32,
108
+ "learning_rate": 3.3850129198966415e-05,
109
+ "loss": 7.4367,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.34,
114
+ "learning_rate": 3.290013679890561e-05,
115
+ "loss": 7.4049,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.36,
120
+ "learning_rate": 3.1950144398844814e-05,
121
+ "loss": 7.3746,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.38,
126
+ "learning_rate": 3.100015199878401e-05,
127
+ "loss": 7.3933,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.4,
132
+ "learning_rate": 3.005015959872321e-05,
133
+ "loss": 7.3898,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.42,
138
+ "learning_rate": 2.9100167198662416e-05,
139
+ "loss": 7.4056,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.44,
144
+ "learning_rate": 2.8150174798601615e-05,
145
+ "loss": 7.3624,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.46,
150
+ "learning_rate": 2.7200182398540814e-05,
151
+ "loss": 7.3256,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.47,
156
+ "learning_rate": 2.6250189998480014e-05,
157
+ "loss": 7.3855,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.49,
162
+ "learning_rate": 2.5300197598419213e-05,
163
+ "loss": 7.3835,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.51,
168
+ "learning_rate": 2.4350205198358412e-05,
169
+ "loss": 7.4472,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.53,
174
+ "learning_rate": 2.3400212798297615e-05,
175
+ "loss": 7.3903,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.55,
180
+ "learning_rate": 2.2450220398236815e-05,
181
+ "loss": 7.3914,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.57,
186
+ "learning_rate": 2.1500227998176014e-05,
187
+ "loss": 7.3494,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.59,
192
+ "learning_rate": 2.0550235598115217e-05,
193
+ "loss": 7.3547,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.61,
198
+ "learning_rate": 1.9600243198054416e-05,
199
+ "loss": 7.4164,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.63,
204
+ "learning_rate": 1.865025079799362e-05,
205
+ "loss": 7.4019,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.65,
210
+ "learning_rate": 1.7700258397932818e-05,
211
+ "loss": 7.3963,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.66,
216
+ "learning_rate": 1.6750265997872018e-05,
217
+ "loss": 7.3885,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.68,
222
+ "learning_rate": 1.580027359781122e-05,
223
+ "loss": 7.317,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.7,
228
+ "learning_rate": 1.4850281197750418e-05,
229
+ "loss": 7.3519,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.72,
234
+ "learning_rate": 1.390028879768962e-05,
235
+ "loss": 7.3486,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.74,
240
+ "learning_rate": 1.295029639762882e-05,
241
+ "loss": 7.3544,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.76,
246
+ "learning_rate": 1.200030399756802e-05,
247
+ "loss": 7.3557,
248
+ "step": 20000
249
+ }
250
+ ],
251
+ "max_steps": 26316,
252
+ "num_train_epochs": 1,
253
+ "total_flos": 4297035955567104.0,
254
+ "trial_name": null,
255
+ "trial_params": null
256
+ }
checkpoint-20000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f844e21af175bed928e71c83ee891be16e0b6e41b78430fc855c12a47223b03
3
+ size 3387
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "RobertaForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-12,
15
+ "max_position_embeddings": 514,
16
+ "model_type": "roberta",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.25.1",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2fc345511011df68f4d14a799a9ef40bf66950886afab2a68c31c4e67cb1d44
3
+ size 504200313
runs/Jan08_17-51-40_afb25dfc9f94/1673200314.3909879/events.out.tfevents.1673200314.afb25dfc9f94.1055.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b648ae3407c2b3bc44ceff9a66fcfa8fd200ec80d853608fa8d3eeafad6132d
3
+ size 5515
runs/Jan08_17-51-40_afb25dfc9f94/1673200434.5242755/events.out.tfevents.1673200434.afb25dfc9f94.1055.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e99a4e731d8dff5ae2bc76ca270ba9c38de0d87f2770fd80a09f04e69f74586
3
+ size 5515
runs/Jan08_17-51-40_afb25dfc9f94/events.out.tfevents.1673200314.afb25dfc9f94.1055.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d42d045f838f19a8691d660ba4a4520785d8e98dc04566e11adffe102321e4
3
+ size 3958
runs/Jan08_17-51-40_afb25dfc9f94/events.out.tfevents.1673200434.afb25dfc9f94.1055.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ebfa68762aa10cfecc54012c1e2e6f4735ea5345fa91f2e4e1fa08fc691953a
3
+ size 12228
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f844e21af175bed928e71c83ee891be16e0b6e41b78430fc855c12a47223b03
3
+ size 3387