Hugging Face's logo

MuhammadHelmy
/
labse-Matryoshka-AuthId

Safetensors
bert
Model card Files
xet
 Community
MuhammadHelmy commited on
Commit
546a5d6
·
verified ·
1 Parent(s): 7988bf1

Upload folder using huggingface_hub

Browse files
Files changed (30) hide show
  1. .gitattributes +3 -0
  2. checkpoint-7500/config.json +78 -0
  3. checkpoint-7500/model.safetensors +3 -0
  4. checkpoint-7500/optimizer.pt +3 -0
  5. checkpoint-7500/rng_state.pth +3 -0
  6. checkpoint-7500/scheduler.pt +3 -0
  7. checkpoint-7500/special_tokens_map.json +37 -0
  8. checkpoint-7500/tokenizer.json +3 -0
  9. checkpoint-7500/tokenizer_config.json +66 -0
  10. checkpoint-7500/trainer_state.json +319 -0
  11. checkpoint-7500/training_args.bin +3 -0
  12. checkpoint-7500/vocab.txt +0 -0
  13. checkpoint-8236/config.json +78 -0
  14. checkpoint-8236/model.safetensors +3 -0
  15. checkpoint-8236/optimizer.pt +3 -0
  16. checkpoint-8236/rng_state.pth +3 -0
  17. checkpoint-8236/scheduler.pt +3 -0
  18. checkpoint-8236/special_tokens_map.json +37 -0
  19. checkpoint-8236/tokenizer.json +3 -0
  20. checkpoint-8236/tokenizer_config.json +66 -0
  21. checkpoint-8236/trainer_state.json +338 -0
  22. checkpoint-8236/training_args.bin +3 -0
  23. checkpoint-8236/vocab.txt +0 -0
  24. config.json +78 -0
  25. model.safetensors +3 -0
  26. special_tokens_map.json +37 -0
  27. tokenizer.json +3 -0
  28. tokenizer_config.json +66 -0
  29. training_args.bin +3 -0
  30. vocab.txt +0 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-7500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-8236/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-7500/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12",
26
+ "13": "LABEL_13",
27
+ "14": "LABEL_14",
28
+ "15": "LABEL_15",
29
+ "16": "LABEL_16",
30
+ "17": "LABEL_17",
31
+ "18": "LABEL_18",
32
+ "19": "LABEL_19",
33
+ "20": "LABEL_20"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_10": 10,
41
+ "LABEL_11": 11,
42
+ "LABEL_12": 12,
43
+ "LABEL_13": 13,
44
+ "LABEL_14": 14,
45
+ "LABEL_15": 15,
46
+ "LABEL_16": 16,
47
+ "LABEL_17": 17,
48
+ "LABEL_18": 18,
49
+ "LABEL_19": 19,
50
+ "LABEL_2": 2,
51
+ "LABEL_20": 20,
52
+ "LABEL_3": 3,
53
+ "LABEL_4": 4,
54
+ "LABEL_5": 5,
55
+ "LABEL_6": 6,
56
+ "LABEL_7": 7,
57
+ "LABEL_8": 8,
58
+ "LABEL_9": 9
59
+ },
60
+ "layer_norm_eps": 1e-12,
61
+ "max_position_embeddings": 512,
62
+ "model_type": "bert",
63
+ "num_attention_heads": 12,
64
+ "num_hidden_layers": 12,
65
+ "pad_token_id": 0,
66
+ "pooler_fc_size": 768,
67
+ "pooler_num_attention_heads": 12,
68
+ "pooler_num_fc_layers": 3,
69
+ "pooler_size_per_head": 128,
70
+ "pooler_type": "first_token_transform",
71
+ "position_embedding_type": "absolute",
72
+ "problem_type": "single_label_classification",
73
+ "torch_dtype": "float32",
74
+ "transformers_version": "4.52.4",
75
+ "type_vocab_size": 2,
76
+ "use_cache": true,
77
+ "vocab_size": 501153
78
+ }
checkpoint-7500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8d79d702599c2192e5b15515269df298de7479ff0c439862f99a481f490883
3
+ size 1883795932
checkpoint-7500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dee3c716ff6eb96535e390b377dbb720ed8ac39321619f61eb1ff7fb0c2dade
3
+ size 3767712058
checkpoint-7500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a0eaad9cbd70a4e1acc4256745f20f9b2d5dc8e282406c2caf0b8298568f3f1
3
+ size 14244
checkpoint-7500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:169c88efcd6ba472b0a671e6aa3f5138f864f1da5f2e2b84429033aa5df3fde7
3
+ size 1064
checkpoint-7500/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-7500/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d868657dd92b0a5a4d1c3a8580e44099f595c8ef7c95d0d48d4de01e5c1834
3
+ size 13632184
checkpoint-7500/tokenizer_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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
+ "max_length": 256,
52
+ "model_max_length": 256,
53
+ "never_split": null,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "[PAD]",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "[SEP]",
59
+ "stride": 0,
60
+ "strip_accents": null,
61
+ "tokenize_chinese_chars": true,
62
+ "tokenizer_class": "BertTokenizer",
63
+ "truncation_side": "right",
64
+ "truncation_strategy": "longest_first",
65
+ "unk_token": "[UNK]"
66
+ }
checkpoint-7500/trainer_state.json ADDED
@@ -0,0 +1,319 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 7500,
3
+ "best_metric": 0.7552966570626944,
4
+ "best_model_checkpoint": "./labse-Matryoshka-AuthId/checkpoint-7500",
5
+ "epoch": 3.642544924720738,
6
+ "eval_steps": 500,
7
+ "global_step": 7500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.24283632831471588,
14
+ "grad_norm": 8.226706504821777,
15
+ "learning_rate": 1.8788246721709567e-05,
16
+ "loss": 1.8844,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.24283632831471588,
21
+ "eval_accuracy": 0.580466682703873,
22
+ "eval_f1_macro": 0.4960676688683372,
23
+ "eval_loss": 1.5094239711761475,
24
+ "eval_precision_macro": 0.5214977084503927,
25
+ "eval_recall_macro": 0.5479464513669718,
26
+ "eval_runtime": 79.4803,
27
+ "eval_samples_per_second": 52.302,
28
+ "eval_steps_per_second": 3.271,
29
+ "step": 500
30
+ },
31
+ {
32
+ "epoch": 0.48567265662943176,
33
+ "grad_norm": 23.343076705932617,
34
+ "learning_rate": 1.757406508013599e-05,
35
+ "loss": 1.0439,
36
+ "step": 1000
37
+ },
38
+ {
39
+ "epoch": 0.48567265662943176,
40
+ "eval_accuracy": 0.6338705797450084,
41
+ "eval_f1_macro": 0.5443060410532249,
42
+ "eval_loss": 1.180512547492981,
43
+ "eval_precision_macro": 0.5964210887979737,
44
+ "eval_recall_macro": 0.5815396599629518,
45
+ "eval_runtime": 79.5018,
46
+ "eval_samples_per_second": 52.288,
47
+ "eval_steps_per_second": 3.27,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 0.7285089849441476,
52
+ "grad_norm": 22.333507537841797,
53
+ "learning_rate": 1.635988343856241e-05,
54
+ "loss": 0.7775,
55
+ "step": 1500
56
+ },
57
+ {
58
+ "epoch": 0.7285089849441476,
59
+ "eval_accuracy": 0.7168631224440702,
60
+ "eval_f1_macro": 0.6352859818957786,
61
+ "eval_loss": 1.000940203666687,
62
+ "eval_precision_macro": 0.6284925893229054,
63
+ "eval_recall_macro": 0.6892646842795946,
64
+ "eval_runtime": 79.7404,
65
+ "eval_samples_per_second": 52.132,
66
+ "eval_steps_per_second": 3.261,
67
+ "step": 1500
68
+ },
69
+ {
70
+ "epoch": 0.9713453132588635,
71
+ "grad_norm": 17.205595016479492,
72
+ "learning_rate": 1.514570179698883e-05,
73
+ "loss": 0.6235,
74
+ "step": 2000
75
+ },
76
+ {
77
+ "epoch": 0.9713453132588635,
78
+ "eval_accuracy": 0.7002646139042579,
79
+ "eval_f1_macro": 0.6444992633781246,
80
+ "eval_loss": 1.0062403678894043,
81
+ "eval_precision_macro": 0.6416324743101667,
82
+ "eval_recall_macro": 0.7175728403685042,
83
+ "eval_runtime": 79.8787,
84
+ "eval_samples_per_second": 52.041,
85
+ "eval_steps_per_second": 3.255,
86
+ "step": 2000
87
+ },
88
+ {
89
+ "epoch": 1.2141816415735793,
90
+ "grad_norm": 6.284836769104004,
91
+ "learning_rate": 1.393152015541525e-05,
92
+ "loss": 0.4443,
93
+ "step": 2500
94
+ },
95
+ {
96
+ "epoch": 1.2141816415735793,
97
+ "eval_accuracy": 0.752225162376714,
98
+ "eval_f1_macro": 0.7005112117395045,
99
+ "eval_loss": 0.8306922316551208,
100
+ "eval_precision_macro": 0.7030961323363835,
101
+ "eval_recall_macro": 0.7405526082434787,
102
+ "eval_runtime": 79.5711,
103
+ "eval_samples_per_second": 52.243,
104
+ "eval_steps_per_second": 3.268,
105
+ "step": 2500
106
+ },
107
+ {
108
+ "epoch": 1.4570179698882952,
109
+ "grad_norm": 14.860431671142578,
110
+ "learning_rate": 1.2717338513841673e-05,
111
+ "loss": 0.3917,
112
+ "step": 3000
113
+ },
114
+ {
115
+ "epoch": 1.4570179698882952,
116
+ "eval_accuracy": 0.776040413759923,
117
+ "eval_f1_macro": 0.7195032487137867,
118
+ "eval_loss": 0.7922475934028625,
119
+ "eval_precision_macro": 0.718432845056206,
120
+ "eval_recall_macro": 0.7476174763134192,
121
+ "eval_runtime": 79.7377,
122
+ "eval_samples_per_second": 52.133,
123
+ "eval_steps_per_second": 3.261,
124
+ "step": 3000
125
+ },
126
+ {
127
+ "epoch": 1.6998542982030111,
128
+ "grad_norm": 15.658327102661133,
129
+ "learning_rate": 1.1503156872268093e-05,
130
+ "loss": 0.3384,
131
+ "step": 3500
132
+ },
133
+ {
134
+ "epoch": 1.6998542982030111,
135
+ "eval_accuracy": 0.7914361318258359,
136
+ "eval_f1_macro": 0.7267579331806328,
137
+ "eval_loss": 0.7427302598953247,
138
+ "eval_precision_macro": 0.7315940928020874,
139
+ "eval_recall_macro": 0.7473775054197197,
140
+ "eval_runtime": 79.5326,
141
+ "eval_samples_per_second": 52.268,
142
+ "eval_steps_per_second": 3.269,
143
+ "step": 3500
144
+ },
145
+ {
146
+ "epoch": 1.942690626517727,
147
+ "grad_norm": 3.790079355239868,
148
+ "learning_rate": 1.0288975230694513e-05,
149
+ "loss": 0.3212,
150
+ "step": 4000
151
+ },
152
+ {
153
+ "epoch": 1.942690626517727,
154
+ "eval_accuracy": 0.7666586480635074,
155
+ "eval_f1_macro": 0.7040518310115823,
156
+ "eval_loss": 0.8302342891693115,
157
+ "eval_precision_macro": 0.7097429428181893,
158
+ "eval_recall_macro": 0.7427055724786205,
159
+ "eval_runtime": 79.7283,
160
+ "eval_samples_per_second": 52.14,
161
+ "eval_steps_per_second": 3.261,
162
+ "step": 4000
163
+ },
164
+ {
165
+ "epoch": 2.1855269548324427,
166
+ "grad_norm": 20.00322151184082,
167
+ "learning_rate": 9.074793589120935e-06,
168
+ "loss": 0.2072,
169
+ "step": 4500
170
+ },
171
+ {
172
+ "epoch": 2.1855269548324427,
173
+ "eval_accuracy": 0.7926389222997354,
174
+ "eval_f1_macro": 0.7306884775555181,
175
+ "eval_loss": 0.7662757039070129,
176
+ "eval_precision_macro": 0.7372020807956,
177
+ "eval_recall_macro": 0.7527073689440521,
178
+ "eval_runtime": 79.8142,
179
+ "eval_samples_per_second": 52.083,
180
+ "eval_steps_per_second": 3.258,
181
+ "step": 4500
182
+ },
183
+ {
184
+ "epoch": 2.4283632831471587,
185
+ "grad_norm": 9.991105079650879,
186
+ "learning_rate": 7.860611947547354e-06,
187
+ "loss": 0.1837,
188
+ "step": 5000
189
+ },
190
+ {
191
+ "epoch": 2.4283632831471587,
192
+ "eval_accuracy": 0.7887899927832571,
193
+ "eval_f1_macro": 0.7303342643678596,
194
+ "eval_loss": 0.8012056946754456,
195
+ "eval_precision_macro": 0.7383307287980656,
196
+ "eval_recall_macro": 0.749799051904019,
197
+ "eval_runtime": 79.4999,
198
+ "eval_samples_per_second": 52.289,
199
+ "eval_steps_per_second": 3.27,
200
+ "step": 5000
201
+ },
202
+ {
203
+ "epoch": 2.6711996114618746,
204
+ "grad_norm": 2.5781819820404053,
205
+ "learning_rate": 6.646430305973774e-06,
206
+ "loss": 0.1853,
207
+ "step": 5500
208
+ },
209
+ {
210
+ "epoch": 2.6711996114618746,
211
+ "eval_accuracy": 0.8169352898725042,
212
+ "eval_f1_macro": 0.7425975963793477,
213
+ "eval_loss": 0.7290380597114563,
214
+ "eval_precision_macro": 0.7490380424010595,
215
+ "eval_recall_macro": 0.7728571995465946,
216
+ "eval_runtime": 79.7501,
217
+ "eval_samples_per_second": 52.125,
218
+ "eval_steps_per_second": 3.26,
219
+ "step": 5500
220
+ },
221
+ {
222
+ "epoch": 2.9140359397765905,
223
+ "grad_norm": 13.812039375305176,
224
+ "learning_rate": 5.432248664400195e-06,
225
+ "loss": 0.1702,
226
+ "step": 6000
227
+ },
228
+ {
229
+ "epoch": 2.9140359397765905,
230
+ "eval_accuracy": 0.8025018041857108,
231
+ "eval_f1_macro": 0.7478693465335228,
232
+ "eval_loss": 0.7762283682823181,
233
+ "eval_precision_macro": 0.7494886922567287,
234
+ "eval_recall_macro": 0.7661448691705909,
235
+ "eval_runtime": 79.5684,
236
+ "eval_samples_per_second": 52.244,
237
+ "eval_steps_per_second": 3.268,
238
+ "step": 6000
239
+ },
240
+ {
241
+ "epoch": 3.1568722680913064,
242
+ "grad_norm": 19.965606689453125,
243
+ "learning_rate": 4.2180670228266156e-06,
244
+ "loss": 0.115,
245
+ "step": 6500
246
+ },
247
+ {
248
+ "epoch": 3.1568722680913064,
249
+ "eval_accuracy": 0.8085157565552081,
250
+ "eval_f1_macro": 0.7550956906548623,
251
+ "eval_loss": 0.8461021184921265,
252
+ "eval_precision_macro": 0.7547053436507176,
253
+ "eval_recall_macro": 0.7770605308609413,
254
+ "eval_runtime": 79.7407,
255
+ "eval_samples_per_second": 52.131,
256
+ "eval_steps_per_second": 3.261,
257
+ "step": 6500
258
+ },
259
+ {
260
+ "epoch": 3.3997085964060223,
261
+ "grad_norm": 5.473484039306641,
262
+ "learning_rate": 3.0038853812530354e-06,
263
+ "loss": 0.0881,
264
+ "step": 7000
265
+ },
266
+ {
267
+ "epoch": 3.3997085964060223,
268
+ "eval_accuracy": 0.8051479432282896,
269
+ "eval_f1_macro": 0.7518260599241406,
270
+ "eval_loss": 0.8820834755897522,
271
+ "eval_precision_macro": 0.7561690673733429,
272
+ "eval_recall_macro": 0.7634548535133201,
273
+ "eval_runtime": 79.7355,
274
+ "eval_samples_per_second": 52.135,
275
+ "eval_steps_per_second": 3.261,
276
+ "step": 7000
277
+ },
278
+ {
279
+ "epoch": 3.642544924720738,
280
+ "grad_norm": 0.03955981135368347,
281
+ "learning_rate": 1.789703739679456e-06,
282
+ "loss": 0.0854,
283
+ "step": 7500
284
+ },
285
+ {
286
+ "epoch": 3.642544924720738,
287
+ "eval_accuracy": 0.8171758479672842,
288
+ "eval_f1_macro": 0.7552966570626944,
289
+ "eval_loss": 0.8381013870239258,
290
+ "eval_precision_macro": 0.7568149477995186,
291
+ "eval_recall_macro": 0.7706908260368737,
292
+ "eval_runtime": 79.5261,
293
+ "eval_samples_per_second": 52.272,
294
+ "eval_steps_per_second": 3.269,
295
+ "step": 7500
296
+ }
297
+ ],
298
+ "logging_steps": 500,
299
+ "max_steps": 8236,
300
+ "num_input_tokens_seen": 0,
301
+ "num_train_epochs": 4,
302
+ "save_steps": 500,
303
+ "stateful_callbacks": {
304
+ "TrainerControl": {
305
+ "args": {
306
+ "should_epoch_stop": false,
307
+ "should_evaluate": false,
308
+ "should_log": false,
309
+ "should_save": true,
310
+ "should_training_stop": false
311
+ },
312
+ "attributes": {}
313
+ }
314
+ },
315
+ "total_flos": 1.5788172219388416e+16,
316
+ "train_batch_size": 16,
317
+ "trial_name": null,
318
+ "trial_params": null
319
+ }
checkpoint-7500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea67396e2e70da3680b12a1b662e3dd1c5a582e94f8467a623f4cdb0c3d71ae
3
+ size 5304
checkpoint-7500/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-8236/config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12",
26
+ "13": "LABEL_13",
27
+ "14": "LABEL_14",
28
+ "15": "LABEL_15",
29
+ "16": "LABEL_16",
30
+ "17": "LABEL_17",
31
+ "18": "LABEL_18",
32
+ "19": "LABEL_19",
33
+ "20": "LABEL_20"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_10": 10,
41
+ "LABEL_11": 11,
42
+ "LABEL_12": 12,
43
+ "LABEL_13": 13,
44
+ "LABEL_14": 14,
45
+ "LABEL_15": 15,
46
+ "LABEL_16": 16,
47
+ "LABEL_17": 17,
48
+ "LABEL_18": 18,
49
+ "LABEL_19": 19,
50
+ "LABEL_2": 2,
51
+ "LABEL_20": 20,
52
+ "LABEL_3": 3,
53
+ "LABEL_4": 4,
54
+ "LABEL_5": 5,
55
+ "LABEL_6": 6,
56
+ "LABEL_7": 7,
57
+ "LABEL_8": 8,
58
+ "LABEL_9": 9
59
+ },
60
+ "layer_norm_eps": 1e-12,
61
+ "max_position_embeddings": 512,
62
+ "model_type": "bert",
63
+ "num_attention_heads": 12,
64
+ "num_hidden_layers": 12,
65
+ "pad_token_id": 0,
66
+ "pooler_fc_size": 768,
67
+ "pooler_num_attention_heads": 12,
68
+ "pooler_num_fc_layers": 3,
69
+ "pooler_size_per_head": 128,
70
+ "pooler_type": "first_token_transform",
71
+ "position_embedding_type": "absolute",
72
+ "problem_type": "single_label_classification",
73
+ "torch_dtype": "float32",
74
+ "transformers_version": "4.52.4",
75
+ "type_vocab_size": 2,
76
+ "use_cache": true,
77
+ "vocab_size": 501153
78
+ }
checkpoint-8236/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885f9337978168bcfd02eb28417d352fd8ba3fb132845d80382af195cbca40fe
3
+ size 1883795932
checkpoint-8236/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:070586218f43065b0e2c63593f357186981547f10822db28eb7d14d814f4cf4f
3
+ size 3767712058
checkpoint-8236/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4c544b64bb1824b4cfc374f9f2408569ca375ee08972d4aaab9ddc84abb6d10
3
+ size 14244
checkpoint-8236/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c49c4c3f9280587c8ffc7eba095e0030369b0c09f7ff72035d62a66e48c3f2d2
3
+ size 1064
checkpoint-8236/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-8236/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d868657dd92b0a5a4d1c3a8580e44099f595c8ef7c95d0d48d4de01e5c1834
3
+ size 13632184
checkpoint-8236/tokenizer_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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
+ "max_length": 256,
52
+ "model_max_length": 256,
53
+ "never_split": null,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "[PAD]",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "[SEP]",
59
+ "stride": 0,
60
+ "strip_accents": null,
61
+ "tokenize_chinese_chars": true,
62
+ "tokenizer_class": "BertTokenizer",
63
+ "truncation_side": "right",
64
+ "truncation_strategy": "longest_first",
65
+ "unk_token": "[UNK]"
66
+ }
checkpoint-8236/trainer_state.json ADDED
@@ -0,0 +1,338 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 7500,
3
+ "best_metric": 0.7552966570626944,
4
+ "best_model_checkpoint": "./labse-Matryoshka-AuthId/checkpoint-7500",
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 8236,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.24283632831471588,
14
+ "grad_norm": 8.226706504821777,
15
+ "learning_rate": 1.8788246721709567e-05,
16
+ "loss": 1.8844,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.24283632831471588,
21
+ "eval_accuracy": 0.580466682703873,
22
+ "eval_f1_macro": 0.4960676688683372,
23
+ "eval_loss": 1.5094239711761475,
24
+ "eval_precision_macro": 0.5214977084503927,
25
+ "eval_recall_macro": 0.5479464513669718,
26
+ "eval_runtime": 79.4803,
27
+ "eval_samples_per_second": 52.302,
28
+ "eval_steps_per_second": 3.271,
29
+ "step": 500
30
+ },
31
+ {
32
+ "epoch": 0.48567265662943176,
33
+ "grad_norm": 23.343076705932617,
34
+ "learning_rate": 1.757406508013599e-05,
35
+ "loss": 1.0439,
36
+ "step": 1000
37
+ },
38
+ {
39
+ "epoch": 0.48567265662943176,
40
+ "eval_accuracy": 0.6338705797450084,
41
+ "eval_f1_macro": 0.5443060410532249,
42
+ "eval_loss": 1.180512547492981,
43
+ "eval_precision_macro": 0.5964210887979737,
44
+ "eval_recall_macro": 0.5815396599629518,
45
+ "eval_runtime": 79.5018,
46
+ "eval_samples_per_second": 52.288,
47
+ "eval_steps_per_second": 3.27,
48
+ "step": 1000
49
+ },
50
+ {
51
+ "epoch": 0.7285089849441476,
52
+ "grad_norm": 22.333507537841797,
53
+ "learning_rate": 1.635988343856241e-05,
54
+ "loss": 0.7775,
55
+ "step": 1500
56
+ },
57
+ {
58
+ "epoch": 0.7285089849441476,
59
+ "eval_accuracy": 0.7168631224440702,
60
+ "eval_f1_macro": 0.6352859818957786,
61
+ "eval_loss": 1.000940203666687,
62
+ "eval_precision_macro": 0.6284925893229054,
63
+ "eval_recall_macro": 0.6892646842795946,
64
+ "eval_runtime": 79.7404,
65
+ "eval_samples_per_second": 52.132,
66
+ "eval_steps_per_second": 3.261,
67
+ "step": 1500
68
+ },
69
+ {
70
+ "epoch": 0.9713453132588635,
71
+ "grad_norm": 17.205595016479492,
72
+ "learning_rate": 1.514570179698883e-05,
73
+ "loss": 0.6235,
74
+ "step": 2000
75
+ },
76
+ {
77
+ "epoch": 0.9713453132588635,
78
+ "eval_accuracy": 0.7002646139042579,
79
+ "eval_f1_macro": 0.6444992633781246,
80
+ "eval_loss": 1.0062403678894043,
81
+ "eval_precision_macro": 0.6416324743101667,
82
+ "eval_recall_macro": 0.7175728403685042,
83
+ "eval_runtime": 79.8787,
84
+ "eval_samples_per_second": 52.041,
85
+ "eval_steps_per_second": 3.255,
86
+ "step": 2000
87
+ },
88
+ {
89
+ "epoch": 1.2141816415735793,
90
+ "grad_norm": 6.284836769104004,
91
+ "learning_rate": 1.393152015541525e-05,
92
+ "loss": 0.4443,
93
+ "step": 2500
94
+ },
95
+ {
96
+ "epoch": 1.2141816415735793,
97
+ "eval_accuracy": 0.752225162376714,
98
+ "eval_f1_macro": 0.7005112117395045,
99
+ "eval_loss": 0.8306922316551208,
100
+ "eval_precision_macro": 0.7030961323363835,
101
+ "eval_recall_macro": 0.7405526082434787,
102
+ "eval_runtime": 79.5711,
103
+ "eval_samples_per_second": 52.243,
104
+ "eval_steps_per_second": 3.268,
105
+ "step": 2500
106
+ },
107
+ {
108
+ "epoch": 1.4570179698882952,
109
+ "grad_norm": 14.860431671142578,
110
+ "learning_rate": 1.2717338513841673e-05,
111
+ "loss": 0.3917,
112
+ "step": 3000
113
+ },
114
+ {
115
+ "epoch": 1.4570179698882952,
116
+ "eval_accuracy": 0.776040413759923,
117
+ "eval_f1_macro": 0.7195032487137867,
118
+ "eval_loss": 0.7922475934028625,
119
+ "eval_precision_macro": 0.718432845056206,
120
+ "eval_recall_macro": 0.7476174763134192,
121
+ "eval_runtime": 79.7377,
122
+ "eval_samples_per_second": 52.133,
123
+ "eval_steps_per_second": 3.261,
124
+ "step": 3000
125
+ },
126
+ {
127
+ "epoch": 1.6998542982030111,
128
+ "grad_norm": 15.658327102661133,
129
+ "learning_rate": 1.1503156872268093e-05,
130
+ "loss": 0.3384,
131
+ "step": 3500
132
+ },
133
+ {
134
+ "epoch": 1.6998542982030111,
135
+ "eval_accuracy": 0.7914361318258359,
136
+ "eval_f1_macro": 0.7267579331806328,
137
+ "eval_loss": 0.7427302598953247,
138
+ "eval_precision_macro": 0.7315940928020874,
139
+ "eval_recall_macro": 0.7473775054197197,
140
+ "eval_runtime": 79.5326,
141
+ "eval_samples_per_second": 52.268,
142
+ "eval_steps_per_second": 3.269,
143
+ "step": 3500
144
+ },
145
+ {
146
+ "epoch": 1.942690626517727,
147
+ "grad_norm": 3.790079355239868,
148
+ "learning_rate": 1.0288975230694513e-05,
149
+ "loss": 0.3212,
150
+ "step": 4000
151
+ },
152
+ {
153
+ "epoch": 1.942690626517727,
154
+ "eval_accuracy": 0.7666586480635074,
155
+ "eval_f1_macro": 0.7040518310115823,
156
+ "eval_loss": 0.8302342891693115,
157
+ "eval_precision_macro": 0.7097429428181893,
158
+ "eval_recall_macro": 0.7427055724786205,
159
+ "eval_runtime": 79.7283,
160
+ "eval_samples_per_second": 52.14,
161
+ "eval_steps_per_second": 3.261,
162
+ "step": 4000
163
+ },
164
+ {
165
+ "epoch": 2.1855269548324427,
166
+ "grad_norm": 20.00322151184082,
167
+ "learning_rate": 9.074793589120935e-06,
168
+ "loss": 0.2072,
169
+ "step": 4500
170
+ },
171
+ {
172
+ "epoch": 2.1855269548324427,
173
+ "eval_accuracy": 0.7926389222997354,
174
+ "eval_f1_macro": 0.7306884775555181,
175
+ "eval_loss": 0.7662757039070129,
176
+ "eval_precision_macro": 0.7372020807956,
177
+ "eval_recall_macro": 0.7527073689440521,
178
+ "eval_runtime": 79.8142,
179
+ "eval_samples_per_second": 52.083,
180
+ "eval_steps_per_second": 3.258,
181
+ "step": 4500
182
+ },
183
+ {
184
+ "epoch": 2.4283632831471587,
185
+ "grad_norm": 9.991105079650879,
186
+ "learning_rate": 7.860611947547354e-06,
187
+ "loss": 0.1837,
188
+ "step": 5000
189
+ },
190
+ {
191
+ "epoch": 2.4283632831471587,
192
+ "eval_accuracy": 0.7887899927832571,
193
+ "eval_f1_macro": 0.7303342643678596,
194
+ "eval_loss": 0.8012056946754456,
195
+ "eval_precision_macro": 0.7383307287980656,
196
+ "eval_recall_macro": 0.749799051904019,
197
+ "eval_runtime": 79.4999,
198
+ "eval_samples_per_second": 52.289,
199
+ "eval_steps_per_second": 3.27,
200
+ "step": 5000
201
+ },
202
+ {
203
+ "epoch": 2.6711996114618746,
204
+ "grad_norm": 2.5781819820404053,
205
+ "learning_rate": 6.646430305973774e-06,
206
+ "loss": 0.1853,
207
+ "step": 5500
208
+ },
209
+ {
210
+ "epoch": 2.6711996114618746,
211
+ "eval_accuracy": 0.8169352898725042,
212
+ "eval_f1_macro": 0.7425975963793477,
213
+ "eval_loss": 0.7290380597114563,
214
+ "eval_precision_macro": 0.7490380424010595,
215
+ "eval_recall_macro": 0.7728571995465946,
216
+ "eval_runtime": 79.7501,
217
+ "eval_samples_per_second": 52.125,
218
+ "eval_steps_per_second": 3.26,
219
+ "step": 5500
220
+ },
221
+ {
222
+ "epoch": 2.9140359397765905,
223
+ "grad_norm": 13.812039375305176,
224
+ "learning_rate": 5.432248664400195e-06,
225
+ "loss": 0.1702,
226
+ "step": 6000
227
+ },
228
+ {
229
+ "epoch": 2.9140359397765905,
230
+ "eval_accuracy": 0.8025018041857108,
231
+ "eval_f1_macro": 0.7478693465335228,
232
+ "eval_loss": 0.7762283682823181,
233
+ "eval_precision_macro": 0.7494886922567287,
234
+ "eval_recall_macro": 0.7661448691705909,
235
+ "eval_runtime": 79.5684,
236
+ "eval_samples_per_second": 52.244,
237
+ "eval_steps_per_second": 3.268,
238
+ "step": 6000
239
+ },
240
+ {
241
+ "epoch": 3.1568722680913064,
242
+ "grad_norm": 19.965606689453125,
243
+ "learning_rate": 4.2180670228266156e-06,
244
+ "loss": 0.115,
245
+ "step": 6500
246
+ },
247
+ {
248
+ "epoch": 3.1568722680913064,
249
+ "eval_accuracy": 0.8085157565552081,
250
+ "eval_f1_macro": 0.7550956906548623,
251
+ "eval_loss": 0.8461021184921265,
252
+ "eval_precision_macro": 0.7547053436507176,
253
+ "eval_recall_macro": 0.7770605308609413,
254
+ "eval_runtime": 79.7407,
255
+ "eval_samples_per_second": 52.131,
256
+ "eval_steps_per_second": 3.261,
257
+ "step": 6500
258
+ },
259
+ {
260
+ "epoch": 3.3997085964060223,
261
+ "grad_norm": 5.473484039306641,
262
+ "learning_rate": 3.0038853812530354e-06,
263
+ "loss": 0.0881,
264
+ "step": 7000
265
+ },
266
+ {
267
+ "epoch": 3.3997085964060223,
268
+ "eval_accuracy": 0.8051479432282896,
269
+ "eval_f1_macro": 0.7518260599241406,
270
+ "eval_loss": 0.8820834755897522,
271
+ "eval_precision_macro": 0.7561690673733429,
272
+ "eval_recall_macro": 0.7634548535133201,
273
+ "eval_runtime": 79.7355,
274
+ "eval_samples_per_second": 52.135,
275
+ "eval_steps_per_second": 3.261,
276
+ "step": 7000
277
+ },
278
+ {
279
+ "epoch": 3.642544924720738,
280
+ "grad_norm": 0.03955981135368347,
281
+ "learning_rate": 1.789703739679456e-06,
282
+ "loss": 0.0854,
283
+ "step": 7500
284
+ },
285
+ {
286
+ "epoch": 3.642544924720738,
287
+ "eval_accuracy": 0.8171758479672842,
288
+ "eval_f1_macro": 0.7552966570626944,
289
+ "eval_loss": 0.8381013870239258,
290
+ "eval_precision_macro": 0.7568149477995186,
291
+ "eval_recall_macro": 0.7706908260368737,
292
+ "eval_runtime": 79.5261,
293
+ "eval_samples_per_second": 52.272,
294
+ "eval_steps_per_second": 3.269,
295
+ "step": 7500
296
+ },
297
+ {
298
+ "epoch": 3.885381253035454,
299
+ "grad_norm": 6.264761447906494,
300
+ "learning_rate": 5.755220981058767e-07,
301
+ "loss": 0.0848,
302
+ "step": 8000
303
+ },
304
+ {
305
+ "epoch": 3.885381253035454,
306
+ "eval_accuracy": 0.8077940822708685,
307
+ "eval_f1_macro": 0.7527204408320765,
308
+ "eval_loss": 0.8696035742759705,
309
+ "eval_precision_macro": 0.7535730472048996,
310
+ "eval_recall_macro": 0.7700727790457579,
311
+ "eval_runtime": 79.6143,
312
+ "eval_samples_per_second": 52.214,
313
+ "eval_steps_per_second": 3.266,
314
+ "step": 8000
315
+ }
316
+ ],
317
+ "logging_steps": 500,
318
+ "max_steps": 8236,
319
+ "num_input_tokens_seen": 0,
320
+ "num_train_epochs": 4,
321
+ "save_steps": 500,
322
+ "stateful_callbacks": {
323
+ "TrainerControl": {
324
+ "args": {
325
+ "should_epoch_stop": false,
326
+ "should_evaluate": false,
327
+ "should_log": false,
328
+ "should_save": true,
329
+ "should_training_stop": true
330
+ },
331
+ "attributes": {}
332
+ }
333
+ },
334
+ "total_flos": 1.7337239662270464e+16,
335
+ "train_batch_size": 16,
336
+ "trial_name": null,
337
+ "trial_params": null
338
+ }
checkpoint-8236/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea67396e2e70da3680b12a1b662e3dd1c5a582e94f8467a623f4cdb0c3d71ae
3
+ size 5304
checkpoint-8236/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,78 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "directionality": "bidi",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8",
22
+ "9": "LABEL_9",
23
+ "10": "LABEL_10",
24
+ "11": "LABEL_11",
25
+ "12": "LABEL_12",
26
+ "13": "LABEL_13",
27
+ "14": "LABEL_14",
28
+ "15": "LABEL_15",
29
+ "16": "LABEL_16",
30
+ "17": "LABEL_17",
31
+ "18": "LABEL_18",
32
+ "19": "LABEL_19",
33
+ "20": "LABEL_20"
34
+ },
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_10": 10,
41
+ "LABEL_11": 11,
42
+ "LABEL_12": 12,
43
+ "LABEL_13": 13,
44
+ "LABEL_14": 14,
45
+ "LABEL_15": 15,
46
+ "LABEL_16": 16,
47
+ "LABEL_17": 17,
48
+ "LABEL_18": 18,
49
+ "LABEL_19": 19,
50
+ "LABEL_2": 2,
51
+ "LABEL_20": 20,
52
+ "LABEL_3": 3,
53
+ "LABEL_4": 4,
54
+ "LABEL_5": 5,
55
+ "LABEL_6": 6,
56
+ "LABEL_7": 7,
57
+ "LABEL_8": 8,
58
+ "LABEL_9": 9
59
+ },
60
+ "layer_norm_eps": 1e-12,
61
+ "max_position_embeddings": 512,
62
+ "model_type": "bert",
63
+ "num_attention_heads": 12,
64
+ "num_hidden_layers": 12,
65
+ "pad_token_id": 0,
66
+ "pooler_fc_size": 768,
67
+ "pooler_num_attention_heads": 12,
68
+ "pooler_num_fc_layers": 3,
69
+ "pooler_size_per_head": 128,
70
+ "pooler_type": "first_token_transform",
71
+ "position_embedding_type": "absolute",
72
+ "problem_type": "single_label_classification",
73
+ "torch_dtype": "float32",
74
+ "transformers_version": "4.52.4",
75
+ "type_vocab_size": 2,
76
+ "use_cache": true,
77
+ "vocab_size": 501153
78
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8d79d702599c2192e5b15515269df298de7479ff0c439862f99a481f490883
3
+ size 1883795932
special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94d868657dd92b0a5a4d1c3a8580e44099f595c8ef7c95d0d48d4de01e5c1834
3
+ size 13632184
tokenizer_config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
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
+ "max_length": 256,
52
+ "model_max_length": 256,
53
+ "never_split": null,
54
+ "pad_to_multiple_of": null,
55
+ "pad_token": "[PAD]",
56
+ "pad_token_type_id": 0,
57
+ "padding_side": "right",
58
+ "sep_token": "[SEP]",
59
+ "stride": 0,
60
+ "strip_accents": null,
61
+ "tokenize_chinese_chars": true,
62
+ "tokenizer_class": "BertTokenizer",
63
+ "truncation_side": "right",
64
+ "truncation_strategy": "longest_first",
65
+ "unk_token": "[UNK]"
66
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ea67396e2e70da3680b12a1b662e3dd1c5a582e94f8467a623f4cdb0c3d71ae
3
+ size 5304
vocab.txt ADDED
The diff for this file is too large to render. See raw diff