Hugging Face's logo

muhtasham
/
TajBERTo

Fill-Mask
Transformers
PyTorch
TensorBoard
Safetensors
Tajik
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
muhtasham commited on
Commit
4684a3a
•
1 Parent(s): bad0c5f

Initial commit

Browse files
Files changed (21) hide show
  1. checkpoint-10000/config.json +26 -0
  2. checkpoint-10000/optimizer.pt +3 -0
  3. checkpoint-10000/pytorch_model.bin +3 -0
  4. checkpoint-10000/rng_state.pth +3 -0
  5. checkpoint-10000/scheduler.pt +3 -0
  6. checkpoint-10000/trainer_state.json +136 -0
  7. checkpoint-10000/training_args.bin +3 -0
  8. checkpoint-20000/config.json +26 -0
  9. checkpoint-20000/optimizer.pt +3 -0
  10. checkpoint-20000/pytorch_model.bin +3 -0
  11. checkpoint-20000/rng_state.pth +3 -0
  12. checkpoint-20000/scheduler.pt +3 -0
  13. checkpoint-20000/trainer_state.json +256 -0
  14. checkpoint-20000/training_args.bin +3 -0
  15. config.json +26 -0
  16. merges.txt +0 -0
  17. pytorch_model.bin +3 -0
  18. runs/Oct04_09-01-38_00b6d4f8aacb/1633338113.7330546/events.out.tfevents.1633338113.00b6d4f8aacb.88.1 +3 -0
  19. runs/Oct04_09-01-38_00b6d4f8aacb/events.out.tfevents.1633338113.00b6d4f8aacb.88.0 +3 -0
  20. training_args.bin +3 -0
  21. vocab.json +0 -0
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": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.12.0.dev0",
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:a0e6d321154cb6ae5544d69e6ab4ac34837dcc08b4404e5c489ecbda2455c32d
3
+ size 668096473
checkpoint-10000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:908bd5047a916b329e924c286313c0449e4d26d141e4e3dc80fa1de10e432e5e
3
+ size 334056939
checkpoint-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baba60026e7b11e0f33175da2885dd273ec29b2a4cb8db413bffc7a43bb99034
3
+ size 14503
checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e36b1eceb19b05470d5dfd6fce7c128791cac69770db798f3bc8eab2a850ac9d
3
+ size 623
checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.40563014643248285,
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": 4.8985924633918794e-05,
13
+ "loss": 8.3189,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.7971849267837586e-05,
19
+ "loss": 7.6649,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 4.695777390175638e-05,
25
+ "loss": 7.424,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.08,
30
+ "learning_rate": 4.5943698535675176e-05,
31
+ "loss": 7.2422,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.1,
36
+ "learning_rate": 4.492962316959397e-05,
37
+ "loss": 7.0602,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.12,
42
+ "learning_rate": 4.391554780351276e-05,
43
+ "loss": 6.8806,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.14,
48
+ "learning_rate": 4.290147243743155e-05,
49
+ "loss": 6.7319,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.16,
54
+ "learning_rate": 4.188739707135034e-05,
55
+ "loss": 6.6085,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.18,
60
+ "learning_rate": 4.0873321705269134e-05,
61
+ "loss": 6.4786,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.2,
66
+ "learning_rate": 3.9859246339187925e-05,
67
+ "loss": 6.3686,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.22,
72
+ "learning_rate": 3.8845170973106724e-05,
73
+ "loss": 6.2653,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.24,
78
+ "learning_rate": 3.7831095607025515e-05,
79
+ "loss": 6.1734,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.26,
84
+ "learning_rate": 3.6817020240944314e-05,
85
+ "loss": 6.0843,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.28,
90
+ "learning_rate": 3.5802944874863105e-05,
91
+ "loss": 6.0259,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.3,
96
+ "learning_rate": 3.47888695087819e-05,
97
+ "loss": 5.9236,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.32,
102
+ "learning_rate": 3.377479414270069e-05,
103
+ "loss": 5.8589,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.34,
108
+ "learning_rate": 3.276071877661948e-05,
109
+ "loss": 5.8056,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.37,
114
+ "learning_rate": 3.174664341053827e-05,
115
+ "loss": 5.7384,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.39,
120
+ "learning_rate": 3.073256804445706e-05,
121
+ "loss": 5.7061,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.41,
126
+ "learning_rate": 2.9718492678375858e-05,
127
+ "loss": 5.6454,
128
+ "step": 10000
129
+ }
130
+ ],
131
+ "max_steps": 24653,
132
+ "num_train_epochs": 1,
133
+ "total_flos": 1.5983857767800832e+16,
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:a69c1f4b63b6f50ca047525771a60953259905d9c048ebae272e96cb644702de
3
+ size 2799
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": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.12.0.dev0",
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 sha256:216e7a09d88ae8e2f3afe7de2b46b9f6a929f417239d4eb57a0901305e40e09b
3
+ size 668096473
checkpoint-20000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:442f4b83f4f704ec9ee3d731b76fe10c25e14d71bdcd69d5d5be6fb1d08537d2
3
+ size 334056939
checkpoint-20000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aedd012890091d654e9f405e14ae88f77a946a43c1245fcb37aab8dd777f8a2b
3
+ size 14503
checkpoint-20000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd8aebdef0965470d676b4498468ca07267b025efcf8323faff9f22dd891b2bf
3
+ size 623
checkpoint-20000/trainer_state.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8112602928649657,
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": 4.8985924633918794e-05,
13
+ "loss": 8.3189,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.7971849267837586e-05,
19
+ "loss": 7.6649,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 4.695777390175638e-05,
25
+ "loss": 7.424,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.08,
30
+ "learning_rate": 4.5943698535675176e-05,
31
+ "loss": 7.2422,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.1,
36
+ "learning_rate": 4.492962316959397e-05,
37
+ "loss": 7.0602,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.12,
42
+ "learning_rate": 4.391554780351276e-05,
43
+ "loss": 6.8806,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.14,
48
+ "learning_rate": 4.290147243743155e-05,
49
+ "loss": 6.7319,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.16,
54
+ "learning_rate": 4.188739707135034e-05,
55
+ "loss": 6.6085,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.18,
60
+ "learning_rate": 4.0873321705269134e-05,
61
+ "loss": 6.4786,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.2,
66
+ "learning_rate": 3.9859246339187925e-05,
67
+ "loss": 6.3686,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.22,
72
+ "learning_rate": 3.8845170973106724e-05,
73
+ "loss": 6.2653,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.24,
78
+ "learning_rate": 3.7831095607025515e-05,
79
+ "loss": 6.1734,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.26,
84
+ "learning_rate": 3.6817020240944314e-05,
85
+ "loss": 6.0843,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.28,
90
+ "learning_rate": 3.5802944874863105e-05,
91
+ "loss": 6.0259,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.3,
96
+ "learning_rate": 3.47888695087819e-05,
97
+ "loss": 5.9236,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.32,
102
+ "learning_rate": 3.377479414270069e-05,
103
+ "loss": 5.8589,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.34,
108
+ "learning_rate": 3.276071877661948e-05,
109
+ "loss": 5.8056,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.37,
114
+ "learning_rate": 3.174664341053827e-05,
115
+ "loss": 5.7384,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.39,
120
+ "learning_rate": 3.073256804445706e-05,
121
+ "loss": 5.7061,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.41,
126
+ "learning_rate": 2.9718492678375858e-05,
127
+ "loss": 5.6454,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.43,
132
+ "learning_rate": 2.870441731229465e-05,
133
+ "loss": 5.6005,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.45,
138
+ "learning_rate": 2.7690341946213445e-05,
139
+ "loss": 5.5741,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.47,
144
+ "learning_rate": 2.6676266580132236e-05,
145
+ "loss": 5.5323,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.49,
150
+ "learning_rate": 2.5662191214051028e-05,
151
+ "loss": 5.4985,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.51,
156
+ "learning_rate": 2.4648115847969823e-05,
157
+ "loss": 5.4576,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.53,
162
+ "learning_rate": 2.3634040481888615e-05,
163
+ "loss": 5.4265,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.55,
168
+ "learning_rate": 2.2619965115807406e-05,
169
+ "loss": 5.3953,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.57,
174
+ "learning_rate": 2.16058897497262e-05,
175
+ "loss": 5.3739,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.59,
180
+ "learning_rate": 2.0591814383644993e-05,
181
+ "loss": 5.3361,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.61,
186
+ "learning_rate": 1.9577739017563788e-05,
187
+ "loss": 5.3105,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.63,
192
+ "learning_rate": 1.856366365148258e-05,
193
+ "loss": 5.2979,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.65,
198
+ "learning_rate": 1.754958828540137e-05,
199
+ "loss": 5.278,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.67,
204
+ "learning_rate": 1.6535512919320166e-05,
205
+ "loss": 5.2304,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.69,
210
+ "learning_rate": 1.5521437553238958e-05,
211
+ "loss": 5.2239,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.71,
216
+ "learning_rate": 1.450736218715775e-05,
217
+ "loss": 5.2037,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.73,
222
+ "learning_rate": 1.3493286821076543e-05,
223
+ "loss": 5.2013,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.75,
228
+ "learning_rate": 1.2479211454995336e-05,
229
+ "loss": 5.1625,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.77,
234
+ "learning_rate": 1.1465136088914129e-05,
235
+ "loss": 5.1583,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.79,
240
+ "learning_rate": 1.045106072283292e-05,
241
+ "loss": 5.1328,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.81,
246
+ "learning_rate": 9.436985356751714e-06,
247
+ "loss": 5.144,
248
+ "step": 20000
249
+ }
250
+ ],
251
+ "max_steps": 24653,
252
+ "num_train_epochs": 1,
253
+ "total_flos": 3.19689423366144e+16,
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:a69c1f4b63b6f50ca047525771a60953259905d9c048ebae272e96cb644702de
3
+ size 2799
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": 6,
19
+ "pad_token_id": 1,
20
+ "position_embedding_type": "absolute",
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.12.0.dev0",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 52000
26
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b82e72e1325d118a9aef84a76a535a463d11a0fd2c205aae0c1c3d8f53960c
3
+ size 334056939
runs/Oct04_09-01-38_00b6d4f8aacb/1633338113.7330546/events.out.tfevents.1633338113.00b6d4f8aacb.88.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37cf5c48e07a49eb420aebec91cdb611b3081ad114170d0a61bfa5e0d2e284cb
3
+ size 4495
runs/Oct04_09-01-38_00b6d4f8aacb/events.out.tfevents.1633338113.00b6d4f8aacb.88.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc6309379b4b4cc7c83f37a5f927f7810da1bd0e5939a2fc3c3022feb6a1f9a4
3
+ size 11156
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a69c1f4b63b6f50ca047525771a60953259905d9c048ebae272e96cb644702de
3
+ size 2799
vocab.json ADDED
The diff for this file is too large to render. See raw diff