Hugging Face's logo

mdg-nlp
/
time-ner-bert-base-cased

Safetensors
bert
Model card Files
xet
Community
fahmidiqbal commited on
Commit
32c2d7b
·
verified ·
1 Parent(s): 3f245f5

Upload time-ner model

Browse files
Files changed (33) hide show
  1. $null +1 -0
  2. .gitattributes +5 -35
  3. checkpoint-5000/config.json +35 -0
  4. checkpoint-5000/model.safetensors +3 -0
  5. checkpoint-5000/optimizer.pt +3 -0
  6. checkpoint-5000/rng_state.pth +3 -0
  7. checkpoint-5000/scaler.pt +3 -0
  8. checkpoint-5000/scheduler.pt +3 -0
  9. checkpoint-5000/special_tokens_map.json +7 -0
  10. checkpoint-5000/tokenizer.json +0 -0
  11. checkpoint-5000/tokenizer_config.json +56 -0
  12. checkpoint-5000/trainer_state.json +734 -0
  13. checkpoint-5000/training_args.bin +3 -0
  14. checkpoint-5000/vocab.txt +0 -0
  15. checkpoint-5340/config.json +35 -0
  16. checkpoint-5340/model.safetensors +3 -0
  17. checkpoint-5340/optimizer.pt +3 -0
  18. checkpoint-5340/rng_state.pth +3 -0
  19. checkpoint-5340/scaler.pt +3 -0
  20. checkpoint-5340/scheduler.pt +3 -0
  21. checkpoint-5340/special_tokens_map.json +7 -0
  22. checkpoint-5340/tokenizer.json +0 -0
  23. checkpoint-5340/tokenizer_config.json +56 -0
  24. checkpoint-5340/trainer_state.json +776 -0
  25. checkpoint-5340/training_args.bin +3 -0
  26. checkpoint-5340/vocab.txt +0 -0
  27. config.json +35 -0
  28. model.safetensors +3 -0
  29. special_tokens_map.json +7 -0
  30. tokenizer.json +0 -0
  31. tokenizer_config.json +56 -0
  32. training_args.bin +3 -0
  33. vocab.txt +0 -0
$null ADDED
@@ -0,0 +1 @@
 
 
1
+ Could Not Find C:\Users\ASUS_GAMER\Desktop\time-ner\outputs\bert-base-cased-timeNER\scheduler.pt
.gitattributes CHANGED
@@ -1,35 +1,5 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ckpt filter=lfs diff=lfs merge=lfs -text
6
- *.ftz filter=lfs diff=lfs merge=lfs -text
7
- *.gz filter=lfs diff=lfs merge=lfs -text
8
- *.h5 filter=lfs diff=lfs merge=lfs -text
9
- *.joblib filter=lfs diff=lfs merge=lfs -text
10
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
- *.model filter=lfs diff=lfs merge=lfs -text
13
- *.msgpack filter=lfs diff=lfs merge=lfs -text
14
- *.npy filter=lfs diff=lfs merge=lfs -text
15
- *.npz filter=lfs diff=lfs merge=lfs -text
16
- *.onnx filter=lfs diff=lfs merge=lfs -text
17
- *.ot filter=lfs diff=lfs merge=lfs -text
18
- *.parquet filter=lfs diff=lfs merge=lfs -text
19
- *.pb filter=lfs diff=lfs merge=lfs -text
20
- *.pickle filter=lfs diff=lfs merge=lfs -text
21
- *.pkl filter=lfs diff=lfs merge=lfs -text
22
- *.pt filter=lfs diff=lfs merge=lfs -text
23
- *.pth filter=lfs diff=lfs merge=lfs -text
24
- *.rar filter=lfs diff=lfs merge=lfs -text
25
- *.safetensors filter=lfs diff=lfs merge=lfs -text
26
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
- *.tar.* filter=lfs diff=lfs merge=lfs -text
28
- *.tar filter=lfs diff=lfs merge=lfs -text
29
- *.tflite filter=lfs diff=lfs merge=lfs -text
30
- *.tgz filter=lfs diff=lfs merge=lfs -text
31
- *.wasm filter=lfs diff=lfs merge=lfs -text
32
- *.xz 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
 
1
+ *.bin filter=lfs diff=lfs merge=lfs -text
2
+ *.pt filter=lfs diff=lfs merge=lfs -text
3
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
4
+ checkpoint-5000/rng_state.pth filter=lfs diff=lfs merge=lfs -text
5
+ checkpoint-5340/rng_state.pth filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-5000/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
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": "O",
13
+ "1": "B-T",
14
+ "2": "I-T"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B-T": 1,
20
+ "I-T": 2,
21
+ "O": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.55.2",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 28996
35
+ }
checkpoint-5000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082f59240a5b52992f7d028f5c976f5680390ab665093d24f740d3b2ed272872
3
+ size 430911284
checkpoint-5000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:621acf3444e79ec3cf629cb36da0f7a5c5055aaf32d1f63131159dd0e3cd1fba
3
+ size 861942330
checkpoint-5000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb2a6688697724c5b13b57e4ec6ad0b483bbb746c8fb31eee359541380dae3a6
3
+ size 14244
checkpoint-5000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7fa7680b8343f94dbfa2a0f6c23d0480ab0ed845ccef7c32e37a1bee2b71440
3
+ size 988
checkpoint-5000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d20f174c85013c3b1345682cbec6cf88adfa60bf98f45bdd8f2d6dd8bb5567d1
3
+ size 1064
checkpoint-5000/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-5000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5000/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-5000/trainer_state.json ADDED
@@ -0,0 +1,734 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.808988764044944,
6
+ "eval_steps": 500,
7
+ "global_step": 5000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.028089887640449437,
14
+ "grad_norm": 1.1079061031341553,
15
+ "learning_rate": 7.165109034267913e-06,
16
+ "loss": 0.8082,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.056179775280898875,
21
+ "grad_norm": 0.5799519419670105,
22
+ "learning_rate": 1.4953271028037382e-05,
23
+ "loss": 0.1088,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.08426966292134831,
28
+ "grad_norm": 1.1547191143035889,
29
+ "learning_rate": 2.2741433021806856e-05,
30
+ "loss": 0.0414,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.11235955056179775,
35
+ "grad_norm": 0.6215643882751465,
36
+ "learning_rate": 3.0529595015576326e-05,
37
+ "loss": 0.0316,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.1404494382022472,
42
+ "grad_norm": 0.08635082095861435,
43
+ "learning_rate": 3.831775700934579e-05,
44
+ "loss": 0.0287,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.16853932584269662,
49
+ "grad_norm": 0.9524874091148376,
50
+ "learning_rate": 4.6105919003115266e-05,
51
+ "loss": 0.0221,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.19662921348314608,
56
+ "grad_norm": 0.05205271765589714,
57
+ "learning_rate": 4.975094640366607e-05,
58
+ "loss": 0.0276,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.2247191011235955,
63
+ "grad_norm": 0.24252551794052124,
64
+ "learning_rate": 4.925283921099821e-05,
65
+ "loss": 0.0284,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.25280898876404495,
70
+ "grad_norm": 0.3349544107913971,
71
+ "learning_rate": 4.8754732018330345e-05,
72
+ "loss": 0.023,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.2808988764044944,
77
+ "grad_norm": 0.4288809895515442,
78
+ "learning_rate": 4.825662482566248e-05,
79
+ "loss": 0.0317,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.3089887640449438,
84
+ "grad_norm": 0.6128108501434326,
85
+ "learning_rate": 4.775851763299462e-05,
86
+ "loss": 0.0227,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.33707865168539325,
91
+ "grad_norm": 0.21435250341892242,
92
+ "learning_rate": 4.7260410440326764e-05,
93
+ "loss": 0.0272,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.3651685393258427,
98
+ "grad_norm": 0.31150922179222107,
99
+ "learning_rate": 4.67623032476589e-05,
100
+ "loss": 0.0244,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.39325842696629215,
105
+ "grad_norm": 0.2189209759235382,
106
+ "learning_rate": 4.626419605499104e-05,
107
+ "loss": 0.0228,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.42134831460674155,
112
+ "grad_norm": 0.09890653192996979,
113
+ "learning_rate": 4.5766088862323175e-05,
114
+ "loss": 0.0205,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.449438202247191,
119
+ "grad_norm": 0.3555811643600464,
120
+ "learning_rate": 4.526798166965531e-05,
121
+ "loss": 0.0193,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.47752808988764045,
126
+ "grad_norm": 0.19844049215316772,
127
+ "learning_rate": 4.476987447698745e-05,
128
+ "loss": 0.0247,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.5056179775280899,
133
+ "grad_norm": 0.052936404943466187,
134
+ "learning_rate": 4.427176728431959e-05,
135
+ "loss": 0.0243,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.5337078651685393,
140
+ "grad_norm": 0.16083820164203644,
141
+ "learning_rate": 4.3773660091651724e-05,
142
+ "loss": 0.0267,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.5617977528089888,
147
+ "grad_norm": 0.27762746810913086,
148
+ "learning_rate": 4.327555289898386e-05,
149
+ "loss": 0.0191,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.5898876404494382,
154
+ "grad_norm": 0.21402454376220703,
155
+ "learning_rate": 4.2777445706316e-05,
156
+ "loss": 0.0213,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.6179775280898876,
161
+ "grad_norm": 0.990424394607544,
162
+ "learning_rate": 4.2279338513648136e-05,
163
+ "loss": 0.0214,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.6460674157303371,
168
+ "grad_norm": 0.22891901433467865,
169
+ "learning_rate": 4.178123132098028e-05,
170
+ "loss": 0.0199,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.6741573033707865,
175
+ "grad_norm": 0.14127930998802185,
176
+ "learning_rate": 4.128312412831242e-05,
177
+ "loss": 0.0237,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.702247191011236,
182
+ "grad_norm": 0.04946295917034149,
183
+ "learning_rate": 4.0785016935644554e-05,
184
+ "loss": 0.0215,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.7303370786516854,
189
+ "grad_norm": 0.8209590911865234,
190
+ "learning_rate": 4.028690974297669e-05,
191
+ "loss": 0.0203,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.7584269662921348,
196
+ "grad_norm": 0.17434939742088318,
197
+ "learning_rate": 3.978880255030883e-05,
198
+ "loss": 0.017,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.7865168539325843,
203
+ "grad_norm": 2.3930020332336426,
204
+ "learning_rate": 3.9290695357640966e-05,
205
+ "loss": 0.0212,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.8146067415730337,
210
+ "grad_norm": 0.08658076077699661,
211
+ "learning_rate": 3.87925881649731e-05,
212
+ "loss": 0.0263,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.8426966292134831,
217
+ "grad_norm": 0.06970521062612534,
218
+ "learning_rate": 3.829448097230524e-05,
219
+ "loss": 0.0215,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.8707865168539326,
224
+ "grad_norm": 0.7530669569969177,
225
+ "learning_rate": 3.779637377963738e-05,
226
+ "loss": 0.0263,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.898876404494382,
231
+ "grad_norm": 0.2610790729522705,
232
+ "learning_rate": 3.7298266586969514e-05,
233
+ "loss": 0.0195,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.9269662921348315,
238
+ "grad_norm": 0.3151768743991852,
239
+ "learning_rate": 3.680015939430165e-05,
240
+ "loss": 0.0223,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.9550561797752809,
245
+ "grad_norm": 0.31642162799835205,
246
+ "learning_rate": 3.6302052201633796e-05,
247
+ "loss": 0.0175,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.9831460674157303,
252
+ "grad_norm": 0.5880666971206665,
253
+ "learning_rate": 3.580394500896593e-05,
254
+ "loss": 0.0213,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 1.0112359550561798,
259
+ "grad_norm": 0.28274914622306824,
260
+ "learning_rate": 3.530583781629807e-05,
261
+ "loss": 0.0135,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 1.0393258426966292,
266
+ "grad_norm": 0.21516074240207672,
267
+ "learning_rate": 3.480773062363021e-05,
268
+ "loss": 0.0154,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 1.0674157303370786,
273
+ "grad_norm": 0.10146140307188034,
274
+ "learning_rate": 3.4309623430962344e-05,
275
+ "loss": 0.0105,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 1.095505617977528,
280
+ "grad_norm": 0.2809500992298126,
281
+ "learning_rate": 3.381151623829448e-05,
282
+ "loss": 0.0136,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 1.1235955056179776,
287
+ "grad_norm": 0.14375343918800354,
288
+ "learning_rate": 3.331340904562662e-05,
289
+ "loss": 0.0164,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 1.151685393258427,
294
+ "grad_norm": 0.5019508004188538,
295
+ "learning_rate": 3.2815301852958756e-05,
296
+ "loss": 0.0118,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 1.1797752808988764,
301
+ "grad_norm": 0.5104942917823792,
302
+ "learning_rate": 3.231719466029089e-05,
303
+ "loss": 0.015,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 1.2078651685393258,
308
+ "grad_norm": 0.016837913542985916,
309
+ "learning_rate": 3.181908746762303e-05,
310
+ "loss": 0.0145,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 1.2359550561797752,
315
+ "grad_norm": 0.024886703118681908,
316
+ "learning_rate": 3.132098027495517e-05,
317
+ "loss": 0.014,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 1.2640449438202248,
322
+ "grad_norm": 0.07716447114944458,
323
+ "learning_rate": 3.082287308228731e-05,
324
+ "loss": 0.0118,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 1.2921348314606742,
329
+ "grad_norm": 0.2997690737247467,
330
+ "learning_rate": 3.032476588961945e-05,
331
+ "loss": 0.0132,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 1.3202247191011236,
336
+ "grad_norm": 0.18653158843517303,
337
+ "learning_rate": 2.9826658696951586e-05,
338
+ "loss": 0.0165,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 1.348314606741573,
343
+ "grad_norm": 0.08433976769447327,
344
+ "learning_rate": 2.9328551504283723e-05,
345
+ "loss": 0.0129,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 1.3764044943820224,
350
+ "grad_norm": 0.05465363338589668,
351
+ "learning_rate": 2.883044431161586e-05,
352
+ "loss": 0.0158,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 1.404494382022472,
357
+ "grad_norm": 0.5007831454277039,
358
+ "learning_rate": 2.8332337118947998e-05,
359
+ "loss": 0.0111,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 1.4325842696629214,
364
+ "grad_norm": 0.3369932174682617,
365
+ "learning_rate": 2.7834229926280138e-05,
366
+ "loss": 0.018,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 1.4606741573033708,
371
+ "grad_norm": 0.4814421832561493,
372
+ "learning_rate": 2.7336122733612275e-05,
373
+ "loss": 0.011,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 1.4887640449438202,
378
+ "grad_norm": 0.2698827087879181,
379
+ "learning_rate": 2.6838015540944413e-05,
380
+ "loss": 0.0109,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 1.5168539325842696,
385
+ "grad_norm": 0.4240029454231262,
386
+ "learning_rate": 2.633990834827655e-05,
387
+ "loss": 0.0137,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 1.5449438202247192,
392
+ "grad_norm": 0.14388051629066467,
393
+ "learning_rate": 2.5841801155608687e-05,
394
+ "loss": 0.0116,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 1.5730337078651684,
399
+ "grad_norm": 0.02085546962916851,
400
+ "learning_rate": 2.5343693962940827e-05,
401
+ "loss": 0.0142,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 1.601123595505618,
406
+ "grad_norm": 0.05095446854829788,
407
+ "learning_rate": 2.4845586770272965e-05,
408
+ "loss": 0.0095,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 1.6292134831460674,
413
+ "grad_norm": 0.17238661646842957,
414
+ "learning_rate": 2.4347479577605102e-05,
415
+ "loss": 0.0166,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 1.6573033707865168,
420
+ "grad_norm": 0.46116310358047485,
421
+ "learning_rate": 2.3849372384937242e-05,
422
+ "loss": 0.0093,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 1.6853932584269664,
427
+ "grad_norm": 2.433911085128784,
428
+ "learning_rate": 2.335126519226938e-05,
429
+ "loss": 0.0154,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 1.7134831460674156,
434
+ "grad_norm": 0.05736437067389488,
435
+ "learning_rate": 2.2853157999601517e-05,
436
+ "loss": 0.016,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 1.7415730337078652,
441
+ "grad_norm": 0.06804224848747253,
442
+ "learning_rate": 2.2355050806933654e-05,
443
+ "loss": 0.0108,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 1.7696629213483146,
448
+ "grad_norm": 0.30779746174812317,
449
+ "learning_rate": 2.185694361426579e-05,
450
+ "loss": 0.0123,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 1.797752808988764,
455
+ "grad_norm": 0.30230316519737244,
456
+ "learning_rate": 2.135883642159793e-05,
457
+ "loss": 0.0133,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 1.8258426966292136,
462
+ "grad_norm": 0.16813495755195618,
463
+ "learning_rate": 2.086072922893007e-05,
464
+ "loss": 0.013,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 1.8539325842696628,
469
+ "grad_norm": 0.09787996113300323,
470
+ "learning_rate": 2.0362622036262206e-05,
471
+ "loss": 0.0182,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 1.8820224719101124,
476
+ "grad_norm": 0.14785389602184296,
477
+ "learning_rate": 1.9864514843594343e-05,
478
+ "loss": 0.0113,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 1.9101123595505618,
483
+ "grad_norm": 0.14845307171344757,
484
+ "learning_rate": 1.936640765092648e-05,
485
+ "loss": 0.0103,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 1.9382022471910112,
490
+ "grad_norm": 0.252806693315506,
491
+ "learning_rate": 1.8868300458258618e-05,
492
+ "loss": 0.0132,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 1.9662921348314608,
497
+ "grad_norm": 0.13823914527893066,
498
+ "learning_rate": 1.837019326559076e-05,
499
+ "loss": 0.0147,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 1.99438202247191,
504
+ "grad_norm": 0.012696351855993271,
505
+ "learning_rate": 1.7872086072922896e-05,
506
+ "loss": 0.0103,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 2.0224719101123596,
511
+ "grad_norm": 0.22270624339580536,
512
+ "learning_rate": 1.7373978880255033e-05,
513
+ "loss": 0.0072,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 2.050561797752809,
518
+ "grad_norm": 0.08390676230192184,
519
+ "learning_rate": 1.687587168758717e-05,
520
+ "loss": 0.0052,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 2.0786516853932584,
525
+ "grad_norm": 0.12281487137079239,
526
+ "learning_rate": 1.6377764494919307e-05,
527
+ "loss": 0.0051,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 2.106741573033708,
532
+ "grad_norm": 0.3707364797592163,
533
+ "learning_rate": 1.5879657302251448e-05,
534
+ "loss": 0.0065,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 2.134831460674157,
539
+ "grad_norm": 0.08561158180236816,
540
+ "learning_rate": 1.5381550109583585e-05,
541
+ "loss": 0.0061,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 2.162921348314607,
546
+ "grad_norm": 0.02789130248129368,
547
+ "learning_rate": 1.4883442916915722e-05,
548
+ "loss": 0.0057,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 2.191011235955056,
553
+ "grad_norm": 0.05514415353536606,
554
+ "learning_rate": 1.438533572424786e-05,
555
+ "loss": 0.0054,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 2.2191011235955056,
560
+ "grad_norm": 0.0021910604555159807,
561
+ "learning_rate": 1.3887228531579997e-05,
562
+ "loss": 0.0041,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 2.247191011235955,
567
+ "grad_norm": 0.0027703680098056793,
568
+ "learning_rate": 1.3389121338912134e-05,
569
+ "loss": 0.0082,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 2.2752808988764044,
574
+ "grad_norm": 0.147604838013649,
575
+ "learning_rate": 1.2891014146244274e-05,
576
+ "loss": 0.0082,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 2.303370786516854,
581
+ "grad_norm": 0.17855724692344666,
582
+ "learning_rate": 1.2392906953576412e-05,
583
+ "loss": 0.0064,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 2.331460674157303,
588
+ "grad_norm": 0.17660567164421082,
589
+ "learning_rate": 1.1894799760908549e-05,
590
+ "loss": 0.0059,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 2.359550561797753,
595
+ "grad_norm": 0.01138710230588913,
596
+ "learning_rate": 1.1396692568240686e-05,
597
+ "loss": 0.0069,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 2.3876404494382024,
602
+ "grad_norm": 0.6561909317970276,
603
+ "learning_rate": 1.0898585375572825e-05,
604
+ "loss": 0.0061,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 2.4157303370786516,
609
+ "grad_norm": 0.07312587648630142,
610
+ "learning_rate": 1.0400478182904962e-05,
611
+ "loss": 0.0064,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 2.443820224719101,
616
+ "grad_norm": 0.0237751342356205,
617
+ "learning_rate": 9.9023709902371e-06,
618
+ "loss": 0.0042,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 2.4719101123595504,
623
+ "grad_norm": 0.15219363570213318,
624
+ "learning_rate": 9.404263797569238e-06,
625
+ "loss": 0.0055,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 2.5,
630
+ "grad_norm": 0.009567302651703358,
631
+ "learning_rate": 8.906156604901375e-06,
632
+ "loss": 0.0052,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 2.5280898876404496,
637
+ "grad_norm": 0.09412640333175659,
638
+ "learning_rate": 8.408049412233512e-06,
639
+ "loss": 0.0054,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 2.556179775280899,
644
+ "grad_norm": 0.16591890156269073,
645
+ "learning_rate": 7.909942219565651e-06,
646
+ "loss": 0.0057,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 2.5842696629213484,
651
+ "grad_norm": 0.48482850193977356,
652
+ "learning_rate": 7.4118350268977886e-06,
653
+ "loss": 0.0087,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 2.6123595505617976,
658
+ "grad_norm": 0.43278753757476807,
659
+ "learning_rate": 6.9137278342299275e-06,
660
+ "loss": 0.0052,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 2.640449438202247,
665
+ "grad_norm": 0.26168298721313477,
666
+ "learning_rate": 6.415620641562065e-06,
667
+ "loss": 0.0049,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 2.668539325842697,
672
+ "grad_norm": 0.24148398637771606,
673
+ "learning_rate": 5.917513448894203e-06,
674
+ "loss": 0.0046,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 2.696629213483146,
679
+ "grad_norm": 0.3959837853908539,
680
+ "learning_rate": 5.41940625622634e-06,
681
+ "loss": 0.0072,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 2.7247191011235956,
686
+ "grad_norm": 0.4944019615650177,
687
+ "learning_rate": 4.921299063558478e-06,
688
+ "loss": 0.0044,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 2.752808988764045,
693
+ "grad_norm": 0.23829056322574615,
694
+ "learning_rate": 4.423191870890616e-06,
695
+ "loss": 0.0051,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 2.7808988764044944,
700
+ "grad_norm": 0.30201318860054016,
701
+ "learning_rate": 3.925084678222754e-06,
702
+ "loss": 0.006,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 2.808988764044944,
707
+ "grad_norm": 0.011093543842434883,
708
+ "learning_rate": 3.4269774855548912e-06,
709
+ "loss": 0.0044,
710
+ "step": 5000
711
+ }
712
+ ],
713
+ "logging_steps": 50,
714
+ "max_steps": 5340,
715
+ "num_input_tokens_seen": 0,
716
+ "num_train_epochs": 3,
717
+ "save_steps": 1000,
718
+ "stateful_callbacks": {
719
+ "TrainerControl": {
720
+ "args": {
721
+ "should_epoch_stop": false,
722
+ "should_evaluate": false,
723
+ "should_log": false,
724
+ "should_save": true,
725
+ "should_training_stop": false
726
+ },
727
+ "attributes": {}
728
+ }
729
+ },
730
+ "total_flos": 2513807761346352.0,
731
+ "train_batch_size": 16,
732
+ "trial_name": null,
733
+ "trial_params": null
734
+ }
checkpoint-5000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:294714db0ea3f4506c5f8a1f7cbff32000dc44762fc37d2c21d7f5de1fc2136c
3
+ size 5368
checkpoint-5000/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5340/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
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": "O",
13
+ "1": "B-T",
14
+ "2": "I-T"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B-T": 1,
20
+ "I-T": 2,
21
+ "O": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.55.2",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 28996
35
+ }
checkpoint-5340/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf94fabfbf186a48a92b67db00d0d3ed563161882a28173d297c898b386d0644
3
+ size 430911284
checkpoint-5340/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dc694aa4d8634560e1961c079e36987a89ad96687ec54395949abf3650dddb1
3
+ size 861942330
checkpoint-5340/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5db19aa59e5aefdedcbe7d1fdf32c4427f4a4573810fe22c9c7017f04f9911d9
3
+ size 14244
checkpoint-5340/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c68bb348f86036ea7b214c2a1c132a3ed462723973ce037d362e454939ac2186
3
+ size 988
checkpoint-5340/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e753724ba61dc77c6ef011aa0273751eca66623d89aaac70c145764e28b7596
3
+ size 1064
checkpoint-5340/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-5340/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-5340/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
checkpoint-5340/trainer_state.json ADDED
@@ -0,0 +1,776 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 5340,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.028089887640449437,
14
+ "grad_norm": 1.1079061031341553,
15
+ "learning_rate": 7.165109034267913e-06,
16
+ "loss": 0.8082,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.056179775280898875,
21
+ "grad_norm": 0.5799519419670105,
22
+ "learning_rate": 1.4953271028037382e-05,
23
+ "loss": 0.1088,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.08426966292134831,
28
+ "grad_norm": 1.1547191143035889,
29
+ "learning_rate": 2.2741433021806856e-05,
30
+ "loss": 0.0414,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 0.11235955056179775,
35
+ "grad_norm": 0.6215643882751465,
36
+ "learning_rate": 3.0529595015576326e-05,
37
+ "loss": 0.0316,
38
+ "step": 200
39
+ },
40
+ {
41
+ "epoch": 0.1404494382022472,
42
+ "grad_norm": 0.08635082095861435,
43
+ "learning_rate": 3.831775700934579e-05,
44
+ "loss": 0.0287,
45
+ "step": 250
46
+ },
47
+ {
48
+ "epoch": 0.16853932584269662,
49
+ "grad_norm": 0.9524874091148376,
50
+ "learning_rate": 4.6105919003115266e-05,
51
+ "loss": 0.0221,
52
+ "step": 300
53
+ },
54
+ {
55
+ "epoch": 0.19662921348314608,
56
+ "grad_norm": 0.05205271765589714,
57
+ "learning_rate": 4.975094640366607e-05,
58
+ "loss": 0.0276,
59
+ "step": 350
60
+ },
61
+ {
62
+ "epoch": 0.2247191011235955,
63
+ "grad_norm": 0.24252551794052124,
64
+ "learning_rate": 4.925283921099821e-05,
65
+ "loss": 0.0284,
66
+ "step": 400
67
+ },
68
+ {
69
+ "epoch": 0.25280898876404495,
70
+ "grad_norm": 0.3349544107913971,
71
+ "learning_rate": 4.8754732018330345e-05,
72
+ "loss": 0.023,
73
+ "step": 450
74
+ },
75
+ {
76
+ "epoch": 0.2808988764044944,
77
+ "grad_norm": 0.4288809895515442,
78
+ "learning_rate": 4.825662482566248e-05,
79
+ "loss": 0.0317,
80
+ "step": 500
81
+ },
82
+ {
83
+ "epoch": 0.3089887640449438,
84
+ "grad_norm": 0.6128108501434326,
85
+ "learning_rate": 4.775851763299462e-05,
86
+ "loss": 0.0227,
87
+ "step": 550
88
+ },
89
+ {
90
+ "epoch": 0.33707865168539325,
91
+ "grad_norm": 0.21435250341892242,
92
+ "learning_rate": 4.7260410440326764e-05,
93
+ "loss": 0.0272,
94
+ "step": 600
95
+ },
96
+ {
97
+ "epoch": 0.3651685393258427,
98
+ "grad_norm": 0.31150922179222107,
99
+ "learning_rate": 4.67623032476589e-05,
100
+ "loss": 0.0244,
101
+ "step": 650
102
+ },
103
+ {
104
+ "epoch": 0.39325842696629215,
105
+ "grad_norm": 0.2189209759235382,
106
+ "learning_rate": 4.626419605499104e-05,
107
+ "loss": 0.0228,
108
+ "step": 700
109
+ },
110
+ {
111
+ "epoch": 0.42134831460674155,
112
+ "grad_norm": 0.09890653192996979,
113
+ "learning_rate": 4.5766088862323175e-05,
114
+ "loss": 0.0205,
115
+ "step": 750
116
+ },
117
+ {
118
+ "epoch": 0.449438202247191,
119
+ "grad_norm": 0.3555811643600464,
120
+ "learning_rate": 4.526798166965531e-05,
121
+ "loss": 0.0193,
122
+ "step": 800
123
+ },
124
+ {
125
+ "epoch": 0.47752808988764045,
126
+ "grad_norm": 0.19844049215316772,
127
+ "learning_rate": 4.476987447698745e-05,
128
+ "loss": 0.0247,
129
+ "step": 850
130
+ },
131
+ {
132
+ "epoch": 0.5056179775280899,
133
+ "grad_norm": 0.052936404943466187,
134
+ "learning_rate": 4.427176728431959e-05,
135
+ "loss": 0.0243,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 0.5337078651685393,
140
+ "grad_norm": 0.16083820164203644,
141
+ "learning_rate": 4.3773660091651724e-05,
142
+ "loss": 0.0267,
143
+ "step": 950
144
+ },
145
+ {
146
+ "epoch": 0.5617977528089888,
147
+ "grad_norm": 0.27762746810913086,
148
+ "learning_rate": 4.327555289898386e-05,
149
+ "loss": 0.0191,
150
+ "step": 1000
151
+ },
152
+ {
153
+ "epoch": 0.5898876404494382,
154
+ "grad_norm": 0.21402454376220703,
155
+ "learning_rate": 4.2777445706316e-05,
156
+ "loss": 0.0213,
157
+ "step": 1050
158
+ },
159
+ {
160
+ "epoch": 0.6179775280898876,
161
+ "grad_norm": 0.990424394607544,
162
+ "learning_rate": 4.2279338513648136e-05,
163
+ "loss": 0.0214,
164
+ "step": 1100
165
+ },
166
+ {
167
+ "epoch": 0.6460674157303371,
168
+ "grad_norm": 0.22891901433467865,
169
+ "learning_rate": 4.178123132098028e-05,
170
+ "loss": 0.0199,
171
+ "step": 1150
172
+ },
173
+ {
174
+ "epoch": 0.6741573033707865,
175
+ "grad_norm": 0.14127930998802185,
176
+ "learning_rate": 4.128312412831242e-05,
177
+ "loss": 0.0237,
178
+ "step": 1200
179
+ },
180
+ {
181
+ "epoch": 0.702247191011236,
182
+ "grad_norm": 0.04946295917034149,
183
+ "learning_rate": 4.0785016935644554e-05,
184
+ "loss": 0.0215,
185
+ "step": 1250
186
+ },
187
+ {
188
+ "epoch": 0.7303370786516854,
189
+ "grad_norm": 0.8209590911865234,
190
+ "learning_rate": 4.028690974297669e-05,
191
+ "loss": 0.0203,
192
+ "step": 1300
193
+ },
194
+ {
195
+ "epoch": 0.7584269662921348,
196
+ "grad_norm": 0.17434939742088318,
197
+ "learning_rate": 3.978880255030883e-05,
198
+ "loss": 0.017,
199
+ "step": 1350
200
+ },
201
+ {
202
+ "epoch": 0.7865168539325843,
203
+ "grad_norm": 2.3930020332336426,
204
+ "learning_rate": 3.9290695357640966e-05,
205
+ "loss": 0.0212,
206
+ "step": 1400
207
+ },
208
+ {
209
+ "epoch": 0.8146067415730337,
210
+ "grad_norm": 0.08658076077699661,
211
+ "learning_rate": 3.87925881649731e-05,
212
+ "loss": 0.0263,
213
+ "step": 1450
214
+ },
215
+ {
216
+ "epoch": 0.8426966292134831,
217
+ "grad_norm": 0.06970521062612534,
218
+ "learning_rate": 3.829448097230524e-05,
219
+ "loss": 0.0215,
220
+ "step": 1500
221
+ },
222
+ {
223
+ "epoch": 0.8707865168539326,
224
+ "grad_norm": 0.7530669569969177,
225
+ "learning_rate": 3.779637377963738e-05,
226
+ "loss": 0.0263,
227
+ "step": 1550
228
+ },
229
+ {
230
+ "epoch": 0.898876404494382,
231
+ "grad_norm": 0.2610790729522705,
232
+ "learning_rate": 3.7298266586969514e-05,
233
+ "loss": 0.0195,
234
+ "step": 1600
235
+ },
236
+ {
237
+ "epoch": 0.9269662921348315,
238
+ "grad_norm": 0.3151768743991852,
239
+ "learning_rate": 3.680015939430165e-05,
240
+ "loss": 0.0223,
241
+ "step": 1650
242
+ },
243
+ {
244
+ "epoch": 0.9550561797752809,
245
+ "grad_norm": 0.31642162799835205,
246
+ "learning_rate": 3.6302052201633796e-05,
247
+ "loss": 0.0175,
248
+ "step": 1700
249
+ },
250
+ {
251
+ "epoch": 0.9831460674157303,
252
+ "grad_norm": 0.5880666971206665,
253
+ "learning_rate": 3.580394500896593e-05,
254
+ "loss": 0.0213,
255
+ "step": 1750
256
+ },
257
+ {
258
+ "epoch": 1.0112359550561798,
259
+ "grad_norm": 0.28274914622306824,
260
+ "learning_rate": 3.530583781629807e-05,
261
+ "loss": 0.0135,
262
+ "step": 1800
263
+ },
264
+ {
265
+ "epoch": 1.0393258426966292,
266
+ "grad_norm": 0.21516074240207672,
267
+ "learning_rate": 3.480773062363021e-05,
268
+ "loss": 0.0154,
269
+ "step": 1850
270
+ },
271
+ {
272
+ "epoch": 1.0674157303370786,
273
+ "grad_norm": 0.10146140307188034,
274
+ "learning_rate": 3.4309623430962344e-05,
275
+ "loss": 0.0105,
276
+ "step": 1900
277
+ },
278
+ {
279
+ "epoch": 1.095505617977528,
280
+ "grad_norm": 0.2809500992298126,
281
+ "learning_rate": 3.381151623829448e-05,
282
+ "loss": 0.0136,
283
+ "step": 1950
284
+ },
285
+ {
286
+ "epoch": 1.1235955056179776,
287
+ "grad_norm": 0.14375343918800354,
288
+ "learning_rate": 3.331340904562662e-05,
289
+ "loss": 0.0164,
290
+ "step": 2000
291
+ },
292
+ {
293
+ "epoch": 1.151685393258427,
294
+ "grad_norm": 0.5019508004188538,
295
+ "learning_rate": 3.2815301852958756e-05,
296
+ "loss": 0.0118,
297
+ "step": 2050
298
+ },
299
+ {
300
+ "epoch": 1.1797752808988764,
301
+ "grad_norm": 0.5104942917823792,
302
+ "learning_rate": 3.231719466029089e-05,
303
+ "loss": 0.015,
304
+ "step": 2100
305
+ },
306
+ {
307
+ "epoch": 1.2078651685393258,
308
+ "grad_norm": 0.016837913542985916,
309
+ "learning_rate": 3.181908746762303e-05,
310
+ "loss": 0.0145,
311
+ "step": 2150
312
+ },
313
+ {
314
+ "epoch": 1.2359550561797752,
315
+ "grad_norm": 0.024886703118681908,
316
+ "learning_rate": 3.132098027495517e-05,
317
+ "loss": 0.014,
318
+ "step": 2200
319
+ },
320
+ {
321
+ "epoch": 1.2640449438202248,
322
+ "grad_norm": 0.07716447114944458,
323
+ "learning_rate": 3.082287308228731e-05,
324
+ "loss": 0.0118,
325
+ "step": 2250
326
+ },
327
+ {
328
+ "epoch": 1.2921348314606742,
329
+ "grad_norm": 0.2997690737247467,
330
+ "learning_rate": 3.032476588961945e-05,
331
+ "loss": 0.0132,
332
+ "step": 2300
333
+ },
334
+ {
335
+ "epoch": 1.3202247191011236,
336
+ "grad_norm": 0.18653158843517303,
337
+ "learning_rate": 2.9826658696951586e-05,
338
+ "loss": 0.0165,
339
+ "step": 2350
340
+ },
341
+ {
342
+ "epoch": 1.348314606741573,
343
+ "grad_norm": 0.08433976769447327,
344
+ "learning_rate": 2.9328551504283723e-05,
345
+ "loss": 0.0129,
346
+ "step": 2400
347
+ },
348
+ {
349
+ "epoch": 1.3764044943820224,
350
+ "grad_norm": 0.05465363338589668,
351
+ "learning_rate": 2.883044431161586e-05,
352
+ "loss": 0.0158,
353
+ "step": 2450
354
+ },
355
+ {
356
+ "epoch": 1.404494382022472,
357
+ "grad_norm": 0.5007831454277039,
358
+ "learning_rate": 2.8332337118947998e-05,
359
+ "loss": 0.0111,
360
+ "step": 2500
361
+ },
362
+ {
363
+ "epoch": 1.4325842696629214,
364
+ "grad_norm": 0.3369932174682617,
365
+ "learning_rate": 2.7834229926280138e-05,
366
+ "loss": 0.018,
367
+ "step": 2550
368
+ },
369
+ {
370
+ "epoch": 1.4606741573033708,
371
+ "grad_norm": 0.4814421832561493,
372
+ "learning_rate": 2.7336122733612275e-05,
373
+ "loss": 0.011,
374
+ "step": 2600
375
+ },
376
+ {
377
+ "epoch": 1.4887640449438202,
378
+ "grad_norm": 0.2698827087879181,
379
+ "learning_rate": 2.6838015540944413e-05,
380
+ "loss": 0.0109,
381
+ "step": 2650
382
+ },
383
+ {
384
+ "epoch": 1.5168539325842696,
385
+ "grad_norm": 0.4240029454231262,
386
+ "learning_rate": 2.633990834827655e-05,
387
+ "loss": 0.0137,
388
+ "step": 2700
389
+ },
390
+ {
391
+ "epoch": 1.5449438202247192,
392
+ "grad_norm": 0.14388051629066467,
393
+ "learning_rate": 2.5841801155608687e-05,
394
+ "loss": 0.0116,
395
+ "step": 2750
396
+ },
397
+ {
398
+ "epoch": 1.5730337078651684,
399
+ "grad_norm": 0.02085546962916851,
400
+ "learning_rate": 2.5343693962940827e-05,
401
+ "loss": 0.0142,
402
+ "step": 2800
403
+ },
404
+ {
405
+ "epoch": 1.601123595505618,
406
+ "grad_norm": 0.05095446854829788,
407
+ "learning_rate": 2.4845586770272965e-05,
408
+ "loss": 0.0095,
409
+ "step": 2850
410
+ },
411
+ {
412
+ "epoch": 1.6292134831460674,
413
+ "grad_norm": 0.17238661646842957,
414
+ "learning_rate": 2.4347479577605102e-05,
415
+ "loss": 0.0166,
416
+ "step": 2900
417
+ },
418
+ {
419
+ "epoch": 1.6573033707865168,
420
+ "grad_norm": 0.46116310358047485,
421
+ "learning_rate": 2.3849372384937242e-05,
422
+ "loss": 0.0093,
423
+ "step": 2950
424
+ },
425
+ {
426
+ "epoch": 1.6853932584269664,
427
+ "grad_norm": 2.433911085128784,
428
+ "learning_rate": 2.335126519226938e-05,
429
+ "loss": 0.0154,
430
+ "step": 3000
431
+ },
432
+ {
433
+ "epoch": 1.7134831460674156,
434
+ "grad_norm": 0.05736437067389488,
435
+ "learning_rate": 2.2853157999601517e-05,
436
+ "loss": 0.016,
437
+ "step": 3050
438
+ },
439
+ {
440
+ "epoch": 1.7415730337078652,
441
+ "grad_norm": 0.06804224848747253,
442
+ "learning_rate": 2.2355050806933654e-05,
443
+ "loss": 0.0108,
444
+ "step": 3100
445
+ },
446
+ {
447
+ "epoch": 1.7696629213483146,
448
+ "grad_norm": 0.30779746174812317,
449
+ "learning_rate": 2.185694361426579e-05,
450
+ "loss": 0.0123,
451
+ "step": 3150
452
+ },
453
+ {
454
+ "epoch": 1.797752808988764,
455
+ "grad_norm": 0.30230316519737244,
456
+ "learning_rate": 2.135883642159793e-05,
457
+ "loss": 0.0133,
458
+ "step": 3200
459
+ },
460
+ {
461
+ "epoch": 1.8258426966292136,
462
+ "grad_norm": 0.16813495755195618,
463
+ "learning_rate": 2.086072922893007e-05,
464
+ "loss": 0.013,
465
+ "step": 3250
466
+ },
467
+ {
468
+ "epoch": 1.8539325842696628,
469
+ "grad_norm": 0.09787996113300323,
470
+ "learning_rate": 2.0362622036262206e-05,
471
+ "loss": 0.0182,
472
+ "step": 3300
473
+ },
474
+ {
475
+ "epoch": 1.8820224719101124,
476
+ "grad_norm": 0.14785389602184296,
477
+ "learning_rate": 1.9864514843594343e-05,
478
+ "loss": 0.0113,
479
+ "step": 3350
480
+ },
481
+ {
482
+ "epoch": 1.9101123595505618,
483
+ "grad_norm": 0.14845307171344757,
484
+ "learning_rate": 1.936640765092648e-05,
485
+ "loss": 0.0103,
486
+ "step": 3400
487
+ },
488
+ {
489
+ "epoch": 1.9382022471910112,
490
+ "grad_norm": 0.252806693315506,
491
+ "learning_rate": 1.8868300458258618e-05,
492
+ "loss": 0.0132,
493
+ "step": 3450
494
+ },
495
+ {
496
+ "epoch": 1.9662921348314608,
497
+ "grad_norm": 0.13823914527893066,
498
+ "learning_rate": 1.837019326559076e-05,
499
+ "loss": 0.0147,
500
+ "step": 3500
501
+ },
502
+ {
503
+ "epoch": 1.99438202247191,
504
+ "grad_norm": 0.012696351855993271,
505
+ "learning_rate": 1.7872086072922896e-05,
506
+ "loss": 0.0103,
507
+ "step": 3550
508
+ },
509
+ {
510
+ "epoch": 2.0224719101123596,
511
+ "grad_norm": 0.22270624339580536,
512
+ "learning_rate": 1.7373978880255033e-05,
513
+ "loss": 0.0072,
514
+ "step": 3600
515
+ },
516
+ {
517
+ "epoch": 2.050561797752809,
518
+ "grad_norm": 0.08390676230192184,
519
+ "learning_rate": 1.687587168758717e-05,
520
+ "loss": 0.0052,
521
+ "step": 3650
522
+ },
523
+ {
524
+ "epoch": 2.0786516853932584,
525
+ "grad_norm": 0.12281487137079239,
526
+ "learning_rate": 1.6377764494919307e-05,
527
+ "loss": 0.0051,
528
+ "step": 3700
529
+ },
530
+ {
531
+ "epoch": 2.106741573033708,
532
+ "grad_norm": 0.3707364797592163,
533
+ "learning_rate": 1.5879657302251448e-05,
534
+ "loss": 0.0065,
535
+ "step": 3750
536
+ },
537
+ {
538
+ "epoch": 2.134831460674157,
539
+ "grad_norm": 0.08561158180236816,
540
+ "learning_rate": 1.5381550109583585e-05,
541
+ "loss": 0.0061,
542
+ "step": 3800
543
+ },
544
+ {
545
+ "epoch": 2.162921348314607,
546
+ "grad_norm": 0.02789130248129368,
547
+ "learning_rate": 1.4883442916915722e-05,
548
+ "loss": 0.0057,
549
+ "step": 3850
550
+ },
551
+ {
552
+ "epoch": 2.191011235955056,
553
+ "grad_norm": 0.05514415353536606,
554
+ "learning_rate": 1.438533572424786e-05,
555
+ "loss": 0.0054,
556
+ "step": 3900
557
+ },
558
+ {
559
+ "epoch": 2.2191011235955056,
560
+ "grad_norm": 0.0021910604555159807,
561
+ "learning_rate": 1.3887228531579997e-05,
562
+ "loss": 0.0041,
563
+ "step": 3950
564
+ },
565
+ {
566
+ "epoch": 2.247191011235955,
567
+ "grad_norm": 0.0027703680098056793,
568
+ "learning_rate": 1.3389121338912134e-05,
569
+ "loss": 0.0082,
570
+ "step": 4000
571
+ },
572
+ {
573
+ "epoch": 2.2752808988764044,
574
+ "grad_norm": 0.147604838013649,
575
+ "learning_rate": 1.2891014146244274e-05,
576
+ "loss": 0.0082,
577
+ "step": 4050
578
+ },
579
+ {
580
+ "epoch": 2.303370786516854,
581
+ "grad_norm": 0.17855724692344666,
582
+ "learning_rate": 1.2392906953576412e-05,
583
+ "loss": 0.0064,
584
+ "step": 4100
585
+ },
586
+ {
587
+ "epoch": 2.331460674157303,
588
+ "grad_norm": 0.17660567164421082,
589
+ "learning_rate": 1.1894799760908549e-05,
590
+ "loss": 0.0059,
591
+ "step": 4150
592
+ },
593
+ {
594
+ "epoch": 2.359550561797753,
595
+ "grad_norm": 0.01138710230588913,
596
+ "learning_rate": 1.1396692568240686e-05,
597
+ "loss": 0.0069,
598
+ "step": 4200
599
+ },
600
+ {
601
+ "epoch": 2.3876404494382024,
602
+ "grad_norm": 0.6561909317970276,
603
+ "learning_rate": 1.0898585375572825e-05,
604
+ "loss": 0.0061,
605
+ "step": 4250
606
+ },
607
+ {
608
+ "epoch": 2.4157303370786516,
609
+ "grad_norm": 0.07312587648630142,
610
+ "learning_rate": 1.0400478182904962e-05,
611
+ "loss": 0.0064,
612
+ "step": 4300
613
+ },
614
+ {
615
+ "epoch": 2.443820224719101,
616
+ "grad_norm": 0.0237751342356205,
617
+ "learning_rate": 9.9023709902371e-06,
618
+ "loss": 0.0042,
619
+ "step": 4350
620
+ },
621
+ {
622
+ "epoch": 2.4719101123595504,
623
+ "grad_norm": 0.15219363570213318,
624
+ "learning_rate": 9.404263797569238e-06,
625
+ "loss": 0.0055,
626
+ "step": 4400
627
+ },
628
+ {
629
+ "epoch": 2.5,
630
+ "grad_norm": 0.009567302651703358,
631
+ "learning_rate": 8.906156604901375e-06,
632
+ "loss": 0.0052,
633
+ "step": 4450
634
+ },
635
+ {
636
+ "epoch": 2.5280898876404496,
637
+ "grad_norm": 0.09412640333175659,
638
+ "learning_rate": 8.408049412233512e-06,
639
+ "loss": 0.0054,
640
+ "step": 4500
641
+ },
642
+ {
643
+ "epoch": 2.556179775280899,
644
+ "grad_norm": 0.16591890156269073,
645
+ "learning_rate": 7.909942219565651e-06,
646
+ "loss": 0.0057,
647
+ "step": 4550
648
+ },
649
+ {
650
+ "epoch": 2.5842696629213484,
651
+ "grad_norm": 0.48482850193977356,
652
+ "learning_rate": 7.4118350268977886e-06,
653
+ "loss": 0.0087,
654
+ "step": 4600
655
+ },
656
+ {
657
+ "epoch": 2.6123595505617976,
658
+ "grad_norm": 0.43278753757476807,
659
+ "learning_rate": 6.9137278342299275e-06,
660
+ "loss": 0.0052,
661
+ "step": 4650
662
+ },
663
+ {
664
+ "epoch": 2.640449438202247,
665
+ "grad_norm": 0.26168298721313477,
666
+ "learning_rate": 6.415620641562065e-06,
667
+ "loss": 0.0049,
668
+ "step": 4700
669
+ },
670
+ {
671
+ "epoch": 2.668539325842697,
672
+ "grad_norm": 0.24148398637771606,
673
+ "learning_rate": 5.917513448894203e-06,
674
+ "loss": 0.0046,
675
+ "step": 4750
676
+ },
677
+ {
678
+ "epoch": 2.696629213483146,
679
+ "grad_norm": 0.3959837853908539,
680
+ "learning_rate": 5.41940625622634e-06,
681
+ "loss": 0.0072,
682
+ "step": 4800
683
+ },
684
+ {
685
+ "epoch": 2.7247191011235956,
686
+ "grad_norm": 0.4944019615650177,
687
+ "learning_rate": 4.921299063558478e-06,
688
+ "loss": 0.0044,
689
+ "step": 4850
690
+ },
691
+ {
692
+ "epoch": 2.752808988764045,
693
+ "grad_norm": 0.23829056322574615,
694
+ "learning_rate": 4.423191870890616e-06,
695
+ "loss": 0.0051,
696
+ "step": 4900
697
+ },
698
+ {
699
+ "epoch": 2.7808988764044944,
700
+ "grad_norm": 0.30201318860054016,
701
+ "learning_rate": 3.925084678222754e-06,
702
+ "loss": 0.006,
703
+ "step": 4950
704
+ },
705
+ {
706
+ "epoch": 2.808988764044944,
707
+ "grad_norm": 0.011093543842434883,
708
+ "learning_rate": 3.4269774855548912e-06,
709
+ "loss": 0.0044,
710
+ "step": 5000
711
+ },
712
+ {
713
+ "epoch": 2.837078651685393,
714
+ "grad_norm": 0.03844978287816048,
715
+ "learning_rate": 2.9288702928870293e-06,
716
+ "loss": 0.0056,
717
+ "step": 5050
718
+ },
719
+ {
720
+ "epoch": 2.865168539325843,
721
+ "grad_norm": 0.12920677661895752,
722
+ "learning_rate": 2.4307631002191673e-06,
723
+ "loss": 0.0038,
724
+ "step": 5100
725
+ },
726
+ {
727
+ "epoch": 2.893258426966292,
728
+ "grad_norm": 0.5641211867332458,
729
+ "learning_rate": 1.9326559075513053e-06,
730
+ "loss": 0.0051,
731
+ "step": 5150
732
+ },
733
+ {
734
+ "epoch": 2.9213483146067416,
735
+ "grad_norm": 0.4559594988822937,
736
+ "learning_rate": 1.434548714883443e-06,
737
+ "loss": 0.0071,
738
+ "step": 5200
739
+ },
740
+ {
741
+ "epoch": 2.949438202247191,
742
+ "grad_norm": 0.0500352717936039,
743
+ "learning_rate": 9.364415222155809e-07,
744
+ "loss": 0.0043,
745
+ "step": 5250
746
+ },
747
+ {
748
+ "epoch": 2.9775280898876404,
749
+ "grad_norm": 0.08150682598352432,
750
+ "learning_rate": 4.383343295477187e-07,
751
+ "loss": 0.0054,
752
+ "step": 5300
753
+ }
754
+ ],
755
+ "logging_steps": 50,
756
+ "max_steps": 5340,
757
+ "num_input_tokens_seen": 0,
758
+ "num_train_epochs": 3,
759
+ "save_steps": 1000,
760
+ "stateful_callbacks": {
761
+ "TrainerControl": {
762
+ "args": {
763
+ "should_epoch_stop": false,
764
+ "should_evaluate": false,
765
+ "should_log": false,
766
+ "should_save": true,
767
+ "should_training_stop": true
768
+ },
769
+ "attributes": {}
770
+ }
771
+ },
772
+ "total_flos": 2684581025476392.0,
773
+ "train_batch_size": 16,
774
+ "trial_name": null,
775
+ "trial_params": null
776
+ }
checkpoint-5340/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:294714db0ea3f4506c5f8a1f7cbff32000dc44762fc37d2c21d7f5de1fc2136c
3
+ size 5368
checkpoint-5340/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForTokenClassification"
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": "O",
13
+ "1": "B-T",
14
+ "2": "I-T"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "B-T": 1,
20
+ "I-T": 2,
21
+ "O": 0
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 512,
25
+ "model_type": "bert",
26
+ "num_attention_heads": 12,
27
+ "num_hidden_layers": 12,
28
+ "pad_token_id": 0,
29
+ "position_embedding_type": "absolute",
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.55.2",
32
+ "type_vocab_size": 2,
33
+ "use_cache": true,
34
+ "vocab_size": 28996
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf94fabfbf186a48a92b67db00d0d3ed563161882a28173d297c898b386d0644
3
+ size 430911284
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 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": false,
47
+ "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
49
+ "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "BertTokenizer",
55
+ "unk_token": "[UNK]"
56
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:294714db0ea3f4506c5f8a1f7cbff32000dc44762fc37d2c21d7f5de1fc2136c
3
+ size 5368
vocab.txt ADDED
The diff for this file is too large to render. See raw diff