Hugging Face's logo

MuhammadHelmy
/
camelbert-mix-AuthId-Aug

Safetensors
bert
Model card Files
xet
Community
MuhammadHelmy commited on
Commit
fd8ae5a
·
verified ·
1 Parent(s): 7e20af4

Upload folder using huggingface_hub

Browse files
Files changed (29) hide show
  1. checkpoint-17500/config.json +72 -0
  2. checkpoint-17500/model.safetensors +3 -0
  3. checkpoint-17500/optimizer.pt +3 -0
  4. checkpoint-17500/rng_state.pth +3 -0
  5. checkpoint-17500/scheduler.pt +3 -0
  6. checkpoint-17500/special_tokens_map.json +7 -0
  7. checkpoint-17500/tokenizer.json +0 -0
  8. checkpoint-17500/tokenizer_config.json +59 -0
  9. checkpoint-17500/trainer_state.json +279 -0
  10. checkpoint-17500/training_args.bin +3 -0
  11. checkpoint-17500/vocab.txt +0 -0
  12. checkpoint-17560/config.json +72 -0
  13. checkpoint-17560/model.safetensors +3 -0
  14. checkpoint-17560/optimizer.pt +3 -0
  15. checkpoint-17560/rng_state.pth +3 -0
  16. checkpoint-17560/scheduler.pt +3 -0
  17. checkpoint-17560/special_tokens_map.json +7 -0
  18. checkpoint-17560/tokenizer.json +0 -0
  19. checkpoint-17560/tokenizer_config.json +59 -0
  20. checkpoint-17560/trainer_state.json +279 -0
  21. checkpoint-17560/training_args.bin +3 -0
  22. checkpoint-17560/vocab.txt +0 -0
  23. config.json +72 -0
  24. model.safetensors +3 -0
  25. special_tokens_map.json +7 -0
  26. tokenizer.json +0 -0
  27. tokenizer_config.json +59 -0
  28. training_args.bin +3 -0
  29. vocab.txt +0 -0
checkpoint-17500/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_10": 10,
40
+ "LABEL_11": 11,
41
+ "LABEL_12": 12,
42
+ "LABEL_13": 13,
43
+ "LABEL_14": 14,
44
+ "LABEL_15": 15,
45
+ "LABEL_16": 16,
46
+ "LABEL_17": 17,
47
+ "LABEL_18": 18,
48
+ "LABEL_19": 19,
49
+ "LABEL_2": 2,
50
+ "LABEL_20": 20,
51
+ "LABEL_3": 3,
52
+ "LABEL_4": 4,
53
+ "LABEL_5": 5,
54
+ "LABEL_6": 6,
55
+ "LABEL_7": 7,
56
+ "LABEL_8": 8,
57
+ "LABEL_9": 9
58
+ },
59
+ "layer_norm_eps": 1e-12,
60
+ "max_position_embeddings": 512,
61
+ "model_type": "bert",
62
+ "num_attention_heads": 12,
63
+ "num_hidden_layers": 12,
64
+ "pad_token_id": 0,
65
+ "position_embedding_type": "absolute",
66
+ "problem_type": "single_label_classification",
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.52.4",
69
+ "type_vocab_size": 2,
70
+ "use_cache": true,
71
+ "vocab_size": 30000
72
+ }
checkpoint-17500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c707321bc7bb80a660a3eb52739c4e344a95751ae7c1410206f4743e0cadc59
3
+ size 436413500
checkpoint-17500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12cebd56013a38f59656802c18a87927d8b376494c702eaac950e0bc3682e586
3
+ size 872948026
checkpoint-17500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c0710207aec69e1c8fc657157452981e23cd04402332934c98fb4fba6d88a32
3
+ size 14244
checkpoint-17500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e896415950b77c26f9ecf1b9b8fe510ac2c17fc5a03ae4adef6190400a0b908
3
+ size 1064
checkpoint-17500/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-17500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17500/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "full_tokenizer_file": null,
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
checkpoint-17500/trainer_state.json ADDED
@@ -0,0 +1,279 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.9863325740318905,
6
+ "eval_steps": 500,
7
+ "global_step": 17500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.11389521640091116,
14
+ "grad_norm": 12.961915016174316,
15
+ "learning_rate": 2.2733485193621873e-05,
16
+ "loss": 2.138,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.22779043280182232,
21
+ "grad_norm": 20.78866958618164,
22
+ "learning_rate": 4.5512528473804106e-05,
23
+ "loss": 0.8384,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.3416856492027335,
28
+ "grad_norm": 15.086663246154785,
29
+ "learning_rate": 6.829157175398633e-05,
30
+ "loss": 0.6629,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.45558086560364464,
35
+ "grad_norm": 34.28147888183594,
36
+ "learning_rate": 7.99533422493134e-05,
37
+ "loss": 0.6011,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.5694760820045558,
42
+ "grad_norm": 42.04814529418945,
43
+ "learning_rate": 7.95645044782997e-05,
44
+ "loss": 0.5135,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.683371298405467,
49
+ "grad_norm": 2.5099027156829834,
50
+ "learning_rate": 7.878513717033947e-05,
51
+ "loss": 0.49,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.7972665148063781,
56
+ "grad_norm": 4.545470237731934,
57
+ "learning_rate": 7.762293322991625e-05,
58
+ "loss": 0.4222,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.9111617312072893,
63
+ "grad_norm": 3.895155668258667,
64
+ "learning_rate": 7.608936442882838e-05,
65
+ "loss": 0.4221,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.0250569476082005,
70
+ "grad_norm": 2.197298288345337,
71
+ "learning_rate": 7.419956817171832e-05,
72
+ "loss": 0.4035,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 1.1389521640091116,
77
+ "grad_norm": 4.543397426605225,
78
+ "learning_rate": 7.19721980792226e-05,
79
+ "loss": 0.3188,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.2528473804100229,
84
+ "grad_norm": 1.2027770280838013,
85
+ "learning_rate": 6.942923986359271e-05,
86
+ "loss": 0.301,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.366742596810934,
91
+ "grad_norm": 5.7361955642700195,
92
+ "learning_rate": 6.659579431422354e-05,
93
+ "loss": 0.3052,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 1.4806378132118452,
98
+ "grad_norm": 60.32481002807617,
99
+ "learning_rate": 6.349982953517576e-05,
100
+ "loss": 0.2945,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 1.5945330296127562,
105
+ "grad_norm": 24.024532318115234,
106
+ "learning_rate": 6.017190488028201e-05,
107
+ "loss": 0.262,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 1.7084282460136673,
112
+ "grad_norm": 5.258288860321045,
113
+ "learning_rate": 5.664486931079191e-05,
114
+ "loss": 0.2964,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 1.8223234624145785,
119
+ "grad_norm": 22.747085571289062,
120
+ "learning_rate": 5.295353715297871e-05,
121
+ "loss": 0.2934,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 1.9362186788154898,
126
+ "grad_norm": 1.9899779558181763,
127
+ "learning_rate": 4.913434445620825e-05,
128
+ "loss": 0.2535,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 2.050113895216401,
133
+ "grad_norm": 0.44854220747947693,
134
+ "learning_rate": 4.522498934345834e-05,
135
+ "loss": 0.1939,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 2.164009111617312,
140
+ "grad_norm": 12.502466201782227,
141
+ "learning_rate": 4.126405990428233e-05,
142
+ "loss": 0.161,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 2.277904328018223,
147
+ "grad_norm": 0.9645262360572815,
148
+ "learning_rate": 3.7290653303175396e-05,
149
+ "loss": 0.1656,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 2.3917995444191344,
154
+ "grad_norm": 0.041170768439769745,
155
+ "learning_rate": 3.334398986301262e-05,
156
+ "loss": 0.1394,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 2.5056947608200457,
161
+ "grad_norm": 56.7460823059082,
162
+ "learning_rate": 2.9463025932826876e-05,
163
+ "loss": 0.1377,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 2.619589977220957,
168
+ "grad_norm": 1.695715069770813,
169
+ "learning_rate": 2.5686069361194757e-05,
170
+ "loss": 0.1274,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 2.733485193621868,
175
+ "grad_norm": 0.49590688943862915,
176
+ "learning_rate": 2.205040137077874e-05,
177
+ "loss": 0.1508,
178
+ "step": 12000
179
+ },
180
+ {
181
+ "epoch": 2.847380410022779,
182
+ "grad_norm": 2.330212116241455,
183
+ "learning_rate": 1.8591908566390646e-05,
184
+ "loss": 0.13,
185
+ "step": 12500
186
+ },
187
+ {
188
+ "epoch": 2.9612756264236904,
189
+ "grad_norm": 0.003335492219775915,
190
+ "learning_rate": 1.5344728708915906e-05,
191
+ "loss": 0.1254,
192
+ "step": 13000
193
+ },
194
+ {
195
+ "epoch": 3.075170842824601,
196
+ "grad_norm": 0.9676417112350464,
197
+ "learning_rate": 1.2340913751559621e-05,
198
+ "loss": 0.0922,
199
+ "step": 13500
200
+ },
201
+ {
202
+ "epoch": 3.1890660592255125,
203
+ "grad_norm": 0.6340539455413818,
204
+ "learning_rate": 9.610113464484163e-06,
205
+ "loss": 0.0876,
206
+ "step": 14000
207
+ },
208
+ {
209
+ "epoch": 3.3029612756264237,
210
+ "grad_norm": 1.2587453126907349,
211
+ "learning_rate": 7.179282770685981e-06,
212
+ "loss": 0.0827,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 3.416856492027335,
217
+ "grad_norm": 2.4137210845947266,
218
+ "learning_rate": 5.072415681912745e-06,
219
+ "loss": 0.0827,
220
+ "step": 15000
221
+ },
222
+ {
223
+ "epoch": 3.5307517084282463,
224
+ "grad_norm": 1.391802191734314,
225
+ "learning_rate": 3.3103084608609646e-06,
226
+ "loss": 0.0803,
227
+ "step": 15500
228
+ },
229
+ {
230
+ "epoch": 3.644646924829157,
231
+ "grad_norm": 0.5722363591194153,
232
+ "learning_rate": 1.910354347409693e-06,
233
+ "loss": 0.0777,
234
+ "step": 16000
235
+ },
236
+ {
237
+ "epoch": 3.7585421412300684,
238
+ "grad_norm": 1.3810276985168457,
239
+ "learning_rate": 8.863718750874395e-07,
240
+ "loss": 0.0846,
241
+ "step": 16500
242
+ },
243
+ {
244
+ "epoch": 3.8724373576309796,
245
+ "grad_norm": 0.8889294862747192,
246
+ "learning_rate": 2.484684724094999e-07,
247
+ "loss": 0.0867,
248
+ "step": 17000
249
+ },
250
+ {
251
+ "epoch": 3.9863325740318905,
252
+ "grad_norm": 1.0857609510421753,
253
+ "learning_rate": 2.940695436648433e-09,
254
+ "loss": 0.0769,
255
+ "step": 17500
256
+ }
257
+ ],
258
+ "logging_steps": 500,
259
+ "max_steps": 17560,
260
+ "num_input_tokens_seen": 0,
261
+ "num_train_epochs": 4,
262
+ "save_steps": 500,
263
+ "stateful_callbacks": {
264
+ "TrainerControl": {
265
+ "args": {
266
+ "should_epoch_stop": false,
267
+ "should_evaluate": false,
268
+ "should_log": false,
269
+ "should_save": true,
270
+ "should_training_stop": false
271
+ },
272
+ "attributes": {}
273
+ }
274
+ },
275
+ "total_flos": 7.368366329856e+16,
276
+ "train_batch_size": 16,
277
+ "trial_name": null,
278
+ "trial_params": null
279
+ }
checkpoint-17500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fce205de8a659838747d0dcf16ab225b13230e69ffd93305eca7222bb06cc33
3
+ size 5304
checkpoint-17500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17560/config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_10": 10,
40
+ "LABEL_11": 11,
41
+ "LABEL_12": 12,
42
+ "LABEL_13": 13,
43
+ "LABEL_14": 14,
44
+ "LABEL_15": 15,
45
+ "LABEL_16": 16,
46
+ "LABEL_17": 17,
47
+ "LABEL_18": 18,
48
+ "LABEL_19": 19,
49
+ "LABEL_2": 2,
50
+ "LABEL_20": 20,
51
+ "LABEL_3": 3,
52
+ "LABEL_4": 4,
53
+ "LABEL_5": 5,
54
+ "LABEL_6": 6,
55
+ "LABEL_7": 7,
56
+ "LABEL_8": 8,
57
+ "LABEL_9": 9
58
+ },
59
+ "layer_norm_eps": 1e-12,
60
+ "max_position_embeddings": 512,
61
+ "model_type": "bert",
62
+ "num_attention_heads": 12,
63
+ "num_hidden_layers": 12,
64
+ "pad_token_id": 0,
65
+ "position_embedding_type": "absolute",
66
+ "problem_type": "single_label_classification",
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.52.4",
69
+ "type_vocab_size": 2,
70
+ "use_cache": true,
71
+ "vocab_size": 30000
72
+ }
checkpoint-17560/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace6833d859a59dddd87a72c0fc84526eea6d7173859b260f221e386b8c62ebf
3
+ size 436413500
checkpoint-17560/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1446a0ec44857819813c537ae4c3a8383ee07a78ab4a1813cd3e3bf1a77ad56
3
+ size 872948026
checkpoint-17560/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:401c0ac34ebbcafc08f1d7859291911ecc663099fc301347a9cad3fa7cd83bc1
3
+ size 14244
checkpoint-17560/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56d828570f0e0d2a1e5138ce8f82173ea06c81ec2305e381e8523125cb528546
3
+ size 1064
checkpoint-17560/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
checkpoint-17560/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-17560/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "full_tokenizer_file": null,
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
checkpoint-17560/trainer_state.json ADDED
@@ -0,0 +1,279 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 17560,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.11389521640091116,
14
+ "grad_norm": 12.961915016174316,
15
+ "learning_rate": 2.2733485193621873e-05,
16
+ "loss": 2.138,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.22779043280182232,
21
+ "grad_norm": 20.78866958618164,
22
+ "learning_rate": 4.5512528473804106e-05,
23
+ "loss": 0.8384,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.3416856492027335,
28
+ "grad_norm": 15.086663246154785,
29
+ "learning_rate": 6.829157175398633e-05,
30
+ "loss": 0.6629,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 0.45558086560364464,
35
+ "grad_norm": 34.28147888183594,
36
+ "learning_rate": 7.99533422493134e-05,
37
+ "loss": 0.6011,
38
+ "step": 2000
39
+ },
40
+ {
41
+ "epoch": 0.5694760820045558,
42
+ "grad_norm": 42.04814529418945,
43
+ "learning_rate": 7.95645044782997e-05,
44
+ "loss": 0.5135,
45
+ "step": 2500
46
+ },
47
+ {
48
+ "epoch": 0.683371298405467,
49
+ "grad_norm": 2.5099027156829834,
50
+ "learning_rate": 7.878513717033947e-05,
51
+ "loss": 0.49,
52
+ "step": 3000
53
+ },
54
+ {
55
+ "epoch": 0.7972665148063781,
56
+ "grad_norm": 4.545470237731934,
57
+ "learning_rate": 7.762293322991625e-05,
58
+ "loss": 0.4222,
59
+ "step": 3500
60
+ },
61
+ {
62
+ "epoch": 0.9111617312072893,
63
+ "grad_norm": 3.895155668258667,
64
+ "learning_rate": 7.608936442882838e-05,
65
+ "loss": 0.4221,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.0250569476082005,
70
+ "grad_norm": 2.197298288345337,
71
+ "learning_rate": 7.419956817171832e-05,
72
+ "loss": 0.4035,
73
+ "step": 4500
74
+ },
75
+ {
76
+ "epoch": 1.1389521640091116,
77
+ "grad_norm": 4.543397426605225,
78
+ "learning_rate": 7.19721980792226e-05,
79
+ "loss": 0.3188,
80
+ "step": 5000
81
+ },
82
+ {
83
+ "epoch": 1.2528473804100229,
84
+ "grad_norm": 1.2027770280838013,
85
+ "learning_rate": 6.942923986359271e-05,
86
+ "loss": 0.301,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 1.366742596810934,
91
+ "grad_norm": 5.7361955642700195,
92
+ "learning_rate": 6.659579431422354e-05,
93
+ "loss": 0.3052,
94
+ "step": 6000
95
+ },
96
+ {
97
+ "epoch": 1.4806378132118452,
98
+ "grad_norm": 60.32481002807617,
99
+ "learning_rate": 6.349982953517576e-05,
100
+ "loss": 0.2945,
101
+ "step": 6500
102
+ },
103
+ {
104
+ "epoch": 1.5945330296127562,
105
+ "grad_norm": 24.024532318115234,
106
+ "learning_rate": 6.017190488028201e-05,
107
+ "loss": 0.262,
108
+ "step": 7000
109
+ },
110
+ {
111
+ "epoch": 1.7084282460136673,
112
+ "grad_norm": 5.258288860321045,
113
+ "learning_rate": 5.664486931079191e-05,
114
+ "loss": 0.2964,
115
+ "step": 7500
116
+ },
117
+ {
118
+ "epoch": 1.8223234624145785,
119
+ "grad_norm": 22.747085571289062,
120
+ "learning_rate": 5.295353715297871e-05,
121
+ "loss": 0.2934,
122
+ "step": 8000
123
+ },
124
+ {
125
+ "epoch": 1.9362186788154898,
126
+ "grad_norm": 1.9899779558181763,
127
+ "learning_rate": 4.913434445620825e-05,
128
+ "loss": 0.2535,
129
+ "step": 8500
130
+ },
131
+ {
132
+ "epoch": 2.050113895216401,
133
+ "grad_norm": 0.44854220747947693,
134
+ "learning_rate": 4.522498934345834e-05,
135
+ "loss": 0.1939,
136
+ "step": 9000
137
+ },
138
+ {
139
+ "epoch": 2.164009111617312,
140
+ "grad_norm": 12.502466201782227,
141
+ "learning_rate": 4.126405990428233e-05,
142
+ "loss": 0.161,
143
+ "step": 9500
144
+ },
145
+ {
146
+ "epoch": 2.277904328018223,
147
+ "grad_norm": 0.9645262360572815,
148
+ "learning_rate": 3.7290653303175396e-05,
149
+ "loss": 0.1656,
150
+ "step": 10000
151
+ },
152
+ {
153
+ "epoch": 2.3917995444191344,
154
+ "grad_norm": 0.041170768439769745,
155
+ "learning_rate": 3.334398986301262e-05,
156
+ "loss": 0.1394,
157
+ "step": 10500
158
+ },
159
+ {
160
+ "epoch": 2.5056947608200457,
161
+ "grad_norm": 56.7460823059082,
162
+ "learning_rate": 2.9463025932826876e-05,
163
+ "loss": 0.1377,
164
+ "step": 11000
165
+ },
166
+ {
167
+ "epoch": 2.619589977220957,
168
+ "grad_norm": 1.695715069770813,
169
+ "learning_rate": 2.5686069361194757e-05,
170
+ "loss": 0.1274,
171
+ "step": 11500
172
+ },
173
+ {
174
+ "epoch": 2.733485193621868,
175
+ "grad_norm": 0.49590688943862915,
176
+ "learning_rate": 2.205040137077874e-05,
177
+ "loss": 0.1508,
178
+ "step": 12000
179
+ },
180
+ {
181
+ "epoch": 2.847380410022779,
182
+ "grad_norm": 2.330212116241455,
183
+ "learning_rate": 1.8591908566390646e-05,
184
+ "loss": 0.13,
185
+ "step": 12500
186
+ },
187
+ {
188
+ "epoch": 2.9612756264236904,
189
+ "grad_norm": 0.003335492219775915,
190
+ "learning_rate": 1.5344728708915906e-05,
191
+ "loss": 0.1254,
192
+ "step": 13000
193
+ },
194
+ {
195
+ "epoch": 3.075170842824601,
196
+ "grad_norm": 0.9676417112350464,
197
+ "learning_rate": 1.2340913751559621e-05,
198
+ "loss": 0.0922,
199
+ "step": 13500
200
+ },
201
+ {
202
+ "epoch": 3.1890660592255125,
203
+ "grad_norm": 0.6340539455413818,
204
+ "learning_rate": 9.610113464484163e-06,
205
+ "loss": 0.0876,
206
+ "step": 14000
207
+ },
208
+ {
209
+ "epoch": 3.3029612756264237,
210
+ "grad_norm": 1.2587453126907349,
211
+ "learning_rate": 7.179282770685981e-06,
212
+ "loss": 0.0827,
213
+ "step": 14500
214
+ },
215
+ {
216
+ "epoch": 3.416856492027335,
217
+ "grad_norm": 2.4137210845947266,
218
+ "learning_rate": 5.072415681912745e-06,
219
+ "loss": 0.0827,
220
+ "step": 15000
221
+ },
222
+ {
223
+ "epoch": 3.5307517084282463,
224
+ "grad_norm": 1.391802191734314,
225
+ "learning_rate": 3.3103084608609646e-06,
226
+ "loss": 0.0803,
227
+ "step": 15500
228
+ },
229
+ {
230
+ "epoch": 3.644646924829157,
231
+ "grad_norm": 0.5722363591194153,
232
+ "learning_rate": 1.910354347409693e-06,
233
+ "loss": 0.0777,
234
+ "step": 16000
235
+ },
236
+ {
237
+ "epoch": 3.7585421412300684,
238
+ "grad_norm": 1.3810276985168457,
239
+ "learning_rate": 8.863718750874395e-07,
240
+ "loss": 0.0846,
241
+ "step": 16500
242
+ },
243
+ {
244
+ "epoch": 3.8724373576309796,
245
+ "grad_norm": 0.8889294862747192,
246
+ "learning_rate": 2.484684724094999e-07,
247
+ "loss": 0.0867,
248
+ "step": 17000
249
+ },
250
+ {
251
+ "epoch": 3.9863325740318905,
252
+ "grad_norm": 1.0857609510421753,
253
+ "learning_rate": 2.940695436648433e-09,
254
+ "loss": 0.0769,
255
+ "step": 17500
256
+ }
257
+ ],
258
+ "logging_steps": 500,
259
+ "max_steps": 17560,
260
+ "num_input_tokens_seen": 0,
261
+ "num_train_epochs": 4,
262
+ "save_steps": 500,
263
+ "stateful_callbacks": {
264
+ "TrainerControl": {
265
+ "args": {
266
+ "should_epoch_stop": false,
267
+ "should_evaluate": false,
268
+ "should_log": false,
269
+ "should_save": true,
270
+ "should_training_stop": true
271
+ },
272
+ "attributes": {}
273
+ }
274
+ },
275
+ "total_flos": 7.393629300129792e+16,
276
+ "train_batch_size": 16,
277
+ "trial_name": null,
278
+ "trial_params": null
279
+ }
checkpoint-17560/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fce205de8a659838747d0dcf16ab225b13230e69ffd93305eca7222bb06cc33
3
+ size 5304
checkpoint-17560/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2",
15
+ "3": "LABEL_3",
16
+ "4": "LABEL_4",
17
+ "5": "LABEL_5",
18
+ "6": "LABEL_6",
19
+ "7": "LABEL_7",
20
+ "8": "LABEL_8",
21
+ "9": "LABEL_9",
22
+ "10": "LABEL_10",
23
+ "11": "LABEL_11",
24
+ "12": "LABEL_12",
25
+ "13": "LABEL_13",
26
+ "14": "LABEL_14",
27
+ "15": "LABEL_15",
28
+ "16": "LABEL_16",
29
+ "17": "LABEL_17",
30
+ "18": "LABEL_18",
31
+ "19": "LABEL_19",
32
+ "20": "LABEL_20"
33
+ },
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 3072,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_10": 10,
40
+ "LABEL_11": 11,
41
+ "LABEL_12": 12,
42
+ "LABEL_13": 13,
43
+ "LABEL_14": 14,
44
+ "LABEL_15": 15,
45
+ "LABEL_16": 16,
46
+ "LABEL_17": 17,
47
+ "LABEL_18": 18,
48
+ "LABEL_19": 19,
49
+ "LABEL_2": 2,
50
+ "LABEL_20": 20,
51
+ "LABEL_3": 3,
52
+ "LABEL_4": 4,
53
+ "LABEL_5": 5,
54
+ "LABEL_6": 6,
55
+ "LABEL_7": 7,
56
+ "LABEL_8": 8,
57
+ "LABEL_9": 9
58
+ },
59
+ "layer_norm_eps": 1e-12,
60
+ "max_position_embeddings": 512,
61
+ "model_type": "bert",
62
+ "num_attention_heads": 12,
63
+ "num_hidden_layers": 12,
64
+ "pad_token_id": 0,
65
+ "position_embedding_type": "absolute",
66
+ "problem_type": "single_label_classification",
67
+ "torch_dtype": "float32",
68
+ "transformers_version": "4.52.4",
69
+ "type_vocab_size": 2,
70
+ "use_cache": true,
71
+ "vocab_size": 30000
72
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace6833d859a59dddd87a72c0fc84526eea6d7173859b260f221e386b8c62ebf
3
+ size 436413500
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "extra_special_tokens": {},
49
+ "full_tokenizer_file": null,
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 1000000000000000019884624838656,
52
+ "never_split": null,
53
+ "pad_token": "[PAD]",
54
+ "sep_token": "[SEP]",
55
+ "strip_accents": null,
56
+ "tokenize_chinese_chars": true,
57
+ "tokenizer_class": "BertTokenizer",
58
+ "unk_token": "[UNK]"
59
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fce205de8a659838747d0dcf16ab225b13230e69ffd93305eca7222bb06cc33
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff