wt3639 commited on
Commit
2318da8
1 Parent(s): 7d45e9c

Upload 20 files

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": true,
4
+ "pooling_mode_mean_tokens": false,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sentence-transformers
3
+ pipeline_tag: sentence-similarity
4
+ tags:
5
+ - sentence-transformers
6
+ - feature-extraction
7
+ - sentence-similarity
8
+
9
+ ---
10
+
11
+ # {MODEL_NAME}
12
+
13
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 1024 dimensional dense vector space and can be used for tasks like clustering or semantic search.
14
+
15
+ <!--- Describe your model here -->
16
+
17
+ ## Usage (Sentence-Transformers)
18
+
19
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
20
+
21
+ ```
22
+ pip install -U sentence-transformers
23
+ ```
24
+
25
+ Then you can use the model like this:
26
+
27
+ ```python
28
+ from sentence_transformers import SentenceTransformer
29
+ sentences = ["This is an example sentence", "Each sentence is converted"]
30
+
31
+ model = SentenceTransformer('{MODEL_NAME}')
32
+ embeddings = model.encode(sentences)
33
+ print(embeddings)
34
+ ```
35
+
36
+
37
+
38
+ ## Evaluation Results
39
+
40
+ <!--- Describe how your model was evaluated -->
41
+
42
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
43
+
44
+
45
+
46
+ ## Full Model Architecture
47
+ ```
48
+ SentenceTransformer(
49
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
50
+ (1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
51
+ (2): Normalize()
52
+ )
53
+ ```
54
+
55
+ ## Citing & Authors
56
+
57
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/hpcwork/vg380347/EduGBERT_nameskill_balanced_randneg/checkpoint-1000",
3
+ "architectures": [
4
+ "BertModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "classifier_dropout": null,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4096,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 16,
17
+ "num_hidden_layers": 24,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.34.1",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 31102
25
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.7.0",
4
+ "transformers": "4.34.1",
5
+ "pytorch": "2.2.0+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null
9
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12764615cf9ac84b1c8e7fd02da5431dd7fcace841b93fb40e49bfa95aa95573
3
+ size 1342988112
modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f205c08dd1a2f70396d5405753c76553b9ee1780139f357db42b0e5167c2f3aa
3
+ size 2677815201
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ee95ea14730bc3adbca5f22b51fcbb0001da2aa48cd7ffb8638607118cbb631
3
+ size 1343070054
rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b701e0dabd2d4ca2ededed626a0dc225f4d66a1cc04f5d208b403a703a87180
3
+ size 14960
rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01e438c15f3e81c46d9770b9f721a343311a583b9e4acd117c4330aeba3b0b8f
3
+ size 14960
rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d74e72cfd0e8b54cdc4d9bb8bbab62c7d64a5755427049a120fa683e197868c
3
+ size 14960
rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad5d0577dca223c12eb288b820ba774a386364f82fb3ae14187324ea29837b0
3
+ size 14960
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de8135331009ad2e046c06d44515654f339cf301c974ca002c4daf95ab69e2cc
3
+ size 1064
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 512,
3
+ "do_lower_case": false
4
+ }
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "101": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "102": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "103": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "104": {
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
+ "mask_token": "[MASK]",
49
+ "max_len": 512,
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": false,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
trainer_state.json ADDED
@@ -0,0 +1,619 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.474576271186441,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.08,
13
+ "learning_rate": 9.994067796610171e-06,
14
+ "loss": 2.3903,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 0.17,
19
+ "learning_rate": 9.986440677966102e-06,
20
+ "loss": 1.2215,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 0.25,
25
+ "learning_rate": 9.977966101694917e-06,
26
+ "loss": 1.1136,
27
+ "step": 30
28
+ },
29
+ {
30
+ "epoch": 0.34,
31
+ "learning_rate": 9.96949152542373e-06,
32
+ "loss": 1.1659,
33
+ "step": 40
34
+ },
35
+ {
36
+ "epoch": 0.42,
37
+ "learning_rate": 9.961016949152543e-06,
38
+ "loss": 0.9895,
39
+ "step": 50
40
+ },
41
+ {
42
+ "epoch": 0.51,
43
+ "learning_rate": 9.953389830508475e-06,
44
+ "loss": 1.2496,
45
+ "step": 60
46
+ },
47
+ {
48
+ "epoch": 0.59,
49
+ "learning_rate": 9.944915254237288e-06,
50
+ "loss": 1.058,
51
+ "step": 70
52
+ },
53
+ {
54
+ "epoch": 0.68,
55
+ "learning_rate": 9.936440677966102e-06,
56
+ "loss": 0.8977,
57
+ "step": 80
58
+ },
59
+ {
60
+ "epoch": 0.76,
61
+ "learning_rate": 9.927966101694915e-06,
62
+ "loss": 1.0084,
63
+ "step": 90
64
+ },
65
+ {
66
+ "epoch": 0.85,
67
+ "learning_rate": 9.91949152542373e-06,
68
+ "loss": 1.1805,
69
+ "step": 100
70
+ },
71
+ {
72
+ "epoch": 0.93,
73
+ "learning_rate": 9.911016949152543e-06,
74
+ "loss": 0.971,
75
+ "step": 110
76
+ },
77
+ {
78
+ "epoch": 1.02,
79
+ "learning_rate": 9.902542372881356e-06,
80
+ "loss": 0.8166,
81
+ "step": 120
82
+ },
83
+ {
84
+ "epoch": 1.1,
85
+ "learning_rate": 9.89406779661017e-06,
86
+ "loss": 0.713,
87
+ "step": 130
88
+ },
89
+ {
90
+ "epoch": 1.19,
91
+ "learning_rate": 9.885593220338984e-06,
92
+ "loss": 0.7842,
93
+ "step": 140
94
+ },
95
+ {
96
+ "epoch": 1.27,
97
+ "learning_rate": 9.877118644067798e-06,
98
+ "loss": 0.6229,
99
+ "step": 150
100
+ },
101
+ {
102
+ "epoch": 1.36,
103
+ "learning_rate": 9.86949152542373e-06,
104
+ "loss": 0.9259,
105
+ "step": 160
106
+ },
107
+ {
108
+ "epoch": 1.44,
109
+ "learning_rate": 9.861016949152544e-06,
110
+ "loss": 0.8035,
111
+ "step": 170
112
+ },
113
+ {
114
+ "epoch": 1.53,
115
+ "learning_rate": 9.852542372881356e-06,
116
+ "loss": 1.7852,
117
+ "step": 180
118
+ },
119
+ {
120
+ "epoch": 1.61,
121
+ "learning_rate": 9.844067796610171e-06,
122
+ "loss": 0.79,
123
+ "step": 190
124
+ },
125
+ {
126
+ "epoch": 1.69,
127
+ "learning_rate": 9.835593220338984e-06,
128
+ "loss": 0.8361,
129
+ "step": 200
130
+ },
131
+ {
132
+ "epoch": 1.78,
133
+ "learning_rate": 9.827118644067797e-06,
134
+ "loss": 0.789,
135
+ "step": 210
136
+ },
137
+ {
138
+ "epoch": 1.86,
139
+ "learning_rate": 9.818644067796612e-06,
140
+ "loss": 0.9851,
141
+ "step": 220
142
+ },
143
+ {
144
+ "epoch": 1.95,
145
+ "learning_rate": 9.810169491525425e-06,
146
+ "loss": 0.7422,
147
+ "step": 230
148
+ },
149
+ {
150
+ "epoch": 2.03,
151
+ "learning_rate": 9.801694915254238e-06,
152
+ "loss": 0.7643,
153
+ "step": 240
154
+ },
155
+ {
156
+ "epoch": 2.12,
157
+ "learning_rate": 9.79322033898305e-06,
158
+ "loss": 0.6639,
159
+ "step": 250
160
+ },
161
+ {
162
+ "epoch": 2.2,
163
+ "learning_rate": 9.784745762711865e-06,
164
+ "loss": 0.5698,
165
+ "step": 260
166
+ },
167
+ {
168
+ "epoch": 2.29,
169
+ "learning_rate": 9.776271186440678e-06,
170
+ "loss": 0.5661,
171
+ "step": 270
172
+ },
173
+ {
174
+ "epoch": 2.37,
175
+ "learning_rate": 9.767796610169491e-06,
176
+ "loss": 0.8881,
177
+ "step": 280
178
+ },
179
+ {
180
+ "epoch": 2.46,
181
+ "learning_rate": 9.759322033898306e-06,
182
+ "loss": 0.5563,
183
+ "step": 290
184
+ },
185
+ {
186
+ "epoch": 2.54,
187
+ "learning_rate": 9.750847457627119e-06,
188
+ "loss": 0.7705,
189
+ "step": 300
190
+ },
191
+ {
192
+ "epoch": 2.63,
193
+ "learning_rate": 9.742372881355932e-06,
194
+ "loss": 0.5988,
195
+ "step": 310
196
+ },
197
+ {
198
+ "epoch": 2.71,
199
+ "learning_rate": 9.733898305084747e-06,
200
+ "loss": 0.7516,
201
+ "step": 320
202
+ },
203
+ {
204
+ "epoch": 2.8,
205
+ "learning_rate": 9.72542372881356e-06,
206
+ "loss": 1.0188,
207
+ "step": 330
208
+ },
209
+ {
210
+ "epoch": 2.88,
211
+ "learning_rate": 9.717796610169492e-06,
212
+ "loss": 1.6122,
213
+ "step": 340
214
+ },
215
+ {
216
+ "epoch": 2.97,
217
+ "learning_rate": 9.709322033898307e-06,
218
+ "loss": 1.5343,
219
+ "step": 350
220
+ },
221
+ {
222
+ "epoch": 3.05,
223
+ "learning_rate": 9.70084745762712e-06,
224
+ "loss": 0.8529,
225
+ "step": 360
226
+ },
227
+ {
228
+ "epoch": 3.14,
229
+ "learning_rate": 9.692372881355932e-06,
230
+ "loss": 0.7866,
231
+ "step": 370
232
+ },
233
+ {
234
+ "epoch": 3.22,
235
+ "learning_rate": 9.683898305084747e-06,
236
+ "loss": 0.8368,
237
+ "step": 380
238
+ },
239
+ {
240
+ "epoch": 3.31,
241
+ "learning_rate": 9.67542372881356e-06,
242
+ "loss": 0.6965,
243
+ "step": 390
244
+ },
245
+ {
246
+ "epoch": 3.39,
247
+ "learning_rate": 9.666949152542375e-06,
248
+ "loss": 0.9716,
249
+ "step": 400
250
+ },
251
+ {
252
+ "epoch": 3.47,
253
+ "learning_rate": 9.659322033898307e-06,
254
+ "loss": 0.8647,
255
+ "step": 410
256
+ },
257
+ {
258
+ "epoch": 3.56,
259
+ "learning_rate": 9.65084745762712e-06,
260
+ "loss": 0.7379,
261
+ "step": 420
262
+ },
263
+ {
264
+ "epoch": 3.64,
265
+ "learning_rate": 9.642372881355933e-06,
266
+ "loss": 0.5591,
267
+ "step": 430
268
+ },
269
+ {
270
+ "epoch": 3.73,
271
+ "learning_rate": 9.633898305084746e-06,
272
+ "loss": 0.5949,
273
+ "step": 440
274
+ },
275
+ {
276
+ "epoch": 3.81,
277
+ "learning_rate": 9.62542372881356e-06,
278
+ "loss": 0.6818,
279
+ "step": 450
280
+ },
281
+ {
282
+ "epoch": 3.9,
283
+ "learning_rate": 9.616949152542374e-06,
284
+ "loss": 0.607,
285
+ "step": 460
286
+ },
287
+ {
288
+ "epoch": 3.98,
289
+ "learning_rate": 9.608474576271187e-06,
290
+ "loss": 0.6291,
291
+ "step": 470
292
+ },
293
+ {
294
+ "epoch": 4.07,
295
+ "learning_rate": 9.600000000000001e-06,
296
+ "loss": 0.3769,
297
+ "step": 480
298
+ },
299
+ {
300
+ "epoch": 4.15,
301
+ "learning_rate": 9.591525423728814e-06,
302
+ "loss": 0.5266,
303
+ "step": 490
304
+ },
305
+ {
306
+ "epoch": 4.24,
307
+ "learning_rate": 9.583050847457627e-06,
308
+ "loss": 0.6024,
309
+ "step": 500
310
+ },
311
+ {
312
+ "epoch": 4.32,
313
+ "learning_rate": 9.57457627118644e-06,
314
+ "loss": 0.5602,
315
+ "step": 510
316
+ },
317
+ {
318
+ "epoch": 4.41,
319
+ "learning_rate": 9.566101694915255e-06,
320
+ "loss": 0.6886,
321
+ "step": 520
322
+ },
323
+ {
324
+ "epoch": 4.49,
325
+ "learning_rate": 9.557627118644068e-06,
326
+ "loss": 0.6933,
327
+ "step": 530
328
+ },
329
+ {
330
+ "epoch": 4.58,
331
+ "learning_rate": 9.549152542372883e-06,
332
+ "loss": 0.4223,
333
+ "step": 540
334
+ },
335
+ {
336
+ "epoch": 4.66,
337
+ "learning_rate": 9.540677966101696e-06,
338
+ "loss": 0.4604,
339
+ "step": 550
340
+ },
341
+ {
342
+ "epoch": 4.75,
343
+ "learning_rate": 9.532203389830508e-06,
344
+ "loss": 0.3966,
345
+ "step": 560
346
+ },
347
+ {
348
+ "epoch": 4.83,
349
+ "learning_rate": 9.523728813559323e-06,
350
+ "loss": 0.4864,
351
+ "step": 570
352
+ },
353
+ {
354
+ "epoch": 4.92,
355
+ "learning_rate": 9.515254237288136e-06,
356
+ "loss": 0.6848,
357
+ "step": 580
358
+ },
359
+ {
360
+ "epoch": 5.0,
361
+ "learning_rate": 9.506779661016949e-06,
362
+ "loss": 0.488,
363
+ "step": 590
364
+ },
365
+ {
366
+ "epoch": 5.08,
367
+ "learning_rate": 9.498305084745764e-06,
368
+ "loss": 0.5127,
369
+ "step": 600
370
+ },
371
+ {
372
+ "epoch": 5.17,
373
+ "learning_rate": 9.489830508474577e-06,
374
+ "loss": 0.4368,
375
+ "step": 610
376
+ },
377
+ {
378
+ "epoch": 5.25,
379
+ "learning_rate": 9.481355932203391e-06,
380
+ "loss": 0.4431,
381
+ "step": 620
382
+ },
383
+ {
384
+ "epoch": 5.34,
385
+ "learning_rate": 9.472881355932204e-06,
386
+ "loss": 0.7604,
387
+ "step": 630
388
+ },
389
+ {
390
+ "epoch": 5.42,
391
+ "learning_rate": 9.464406779661017e-06,
392
+ "loss": 0.4196,
393
+ "step": 640
394
+ },
395
+ {
396
+ "epoch": 5.51,
397
+ "learning_rate": 9.455932203389832e-06,
398
+ "loss": 0.5376,
399
+ "step": 650
400
+ },
401
+ {
402
+ "epoch": 5.59,
403
+ "learning_rate": 9.447457627118645e-06,
404
+ "loss": 0.4184,
405
+ "step": 660
406
+ },
407
+ {
408
+ "epoch": 5.68,
409
+ "learning_rate": 9.43898305084746e-06,
410
+ "loss": 0.3217,
411
+ "step": 670
412
+ },
413
+ {
414
+ "epoch": 5.76,
415
+ "learning_rate": 9.430508474576273e-06,
416
+ "loss": 0.4748,
417
+ "step": 680
418
+ },
419
+ {
420
+ "epoch": 5.85,
421
+ "learning_rate": 9.422033898305086e-06,
422
+ "loss": 0.6145,
423
+ "step": 690
424
+ },
425
+ {
426
+ "epoch": 5.93,
427
+ "learning_rate": 9.413559322033899e-06,
428
+ "loss": 0.3761,
429
+ "step": 700
430
+ },
431
+ {
432
+ "epoch": 6.02,
433
+ "learning_rate": 9.405084745762713e-06,
434
+ "loss": 0.3156,
435
+ "step": 710
436
+ },
437
+ {
438
+ "epoch": 6.1,
439
+ "learning_rate": 9.396610169491526e-06,
440
+ "loss": 0.4638,
441
+ "step": 720
442
+ },
443
+ {
444
+ "epoch": 6.19,
445
+ "learning_rate": 9.38813559322034e-06,
446
+ "loss": 0.488,
447
+ "step": 730
448
+ },
449
+ {
450
+ "epoch": 6.27,
451
+ "learning_rate": 9.379661016949152e-06,
452
+ "loss": 0.5872,
453
+ "step": 740
454
+ },
455
+ {
456
+ "epoch": 6.36,
457
+ "learning_rate": 9.371186440677967e-06,
458
+ "loss": 0.5414,
459
+ "step": 750
460
+ },
461
+ {
462
+ "epoch": 6.44,
463
+ "learning_rate": 9.36271186440678e-06,
464
+ "loss": 0.3205,
465
+ "step": 760
466
+ },
467
+ {
468
+ "epoch": 6.53,
469
+ "learning_rate": 9.354237288135593e-06,
470
+ "loss": 0.4158,
471
+ "step": 770
472
+ },
473
+ {
474
+ "epoch": 6.61,
475
+ "learning_rate": 9.346610169491525e-06,
476
+ "loss": 0.3371,
477
+ "step": 780
478
+ },
479
+ {
480
+ "epoch": 6.69,
481
+ "learning_rate": 9.33813559322034e-06,
482
+ "loss": 0.4453,
483
+ "step": 790
484
+ },
485
+ {
486
+ "epoch": 6.78,
487
+ "learning_rate": 9.329661016949153e-06,
488
+ "loss": 0.4018,
489
+ "step": 800
490
+ },
491
+ {
492
+ "epoch": 6.86,
493
+ "learning_rate": 9.321186440677967e-06,
494
+ "loss": 0.4046,
495
+ "step": 810
496
+ },
497
+ {
498
+ "epoch": 6.95,
499
+ "learning_rate": 9.31271186440678e-06,
500
+ "loss": 0.438,
501
+ "step": 820
502
+ },
503
+ {
504
+ "epoch": 7.03,
505
+ "learning_rate": 9.304237288135593e-06,
506
+ "loss": 0.4067,
507
+ "step": 830
508
+ },
509
+ {
510
+ "epoch": 7.12,
511
+ "learning_rate": 9.295762711864408e-06,
512
+ "loss": 0.3016,
513
+ "step": 840
514
+ },
515
+ {
516
+ "epoch": 7.2,
517
+ "learning_rate": 9.287288135593221e-06,
518
+ "loss": 0.3699,
519
+ "step": 850
520
+ },
521
+ {
522
+ "epoch": 7.29,
523
+ "learning_rate": 9.278813559322036e-06,
524
+ "loss": 0.3857,
525
+ "step": 860
526
+ },
527
+ {
528
+ "epoch": 7.37,
529
+ "learning_rate": 9.270338983050849e-06,
530
+ "loss": 0.4237,
531
+ "step": 870
532
+ },
533
+ {
534
+ "epoch": 7.46,
535
+ "learning_rate": 9.261864406779662e-06,
536
+ "loss": 0.3207,
537
+ "step": 880
538
+ },
539
+ {
540
+ "epoch": 7.54,
541
+ "learning_rate": 9.253389830508476e-06,
542
+ "loss": 0.2815,
543
+ "step": 890
544
+ },
545
+ {
546
+ "epoch": 7.63,
547
+ "learning_rate": 9.24491525423729e-06,
548
+ "loss": 0.2975,
549
+ "step": 900
550
+ },
551
+ {
552
+ "epoch": 7.71,
553
+ "learning_rate": 9.236440677966102e-06,
554
+ "loss": 0.3149,
555
+ "step": 910
556
+ },
557
+ {
558
+ "epoch": 7.8,
559
+ "learning_rate": 9.227966101694917e-06,
560
+ "loss": 0.3816,
561
+ "step": 920
562
+ },
563
+ {
564
+ "epoch": 7.88,
565
+ "learning_rate": 9.21949152542373e-06,
566
+ "loss": 0.3822,
567
+ "step": 930
568
+ },
569
+ {
570
+ "epoch": 7.97,
571
+ "learning_rate": 9.211016949152543e-06,
572
+ "loss": 0.3699,
573
+ "step": 940
574
+ },
575
+ {
576
+ "epoch": 8.05,
577
+ "learning_rate": 9.202542372881356e-06,
578
+ "loss": 0.2304,
579
+ "step": 950
580
+ },
581
+ {
582
+ "epoch": 8.14,
583
+ "learning_rate": 9.19406779661017e-06,
584
+ "loss": 0.3732,
585
+ "step": 960
586
+ },
587
+ {
588
+ "epoch": 8.22,
589
+ "learning_rate": 9.185593220338984e-06,
590
+ "loss": 0.3458,
591
+ "step": 970
592
+ },
593
+ {
594
+ "epoch": 8.31,
595
+ "learning_rate": 9.177118644067797e-06,
596
+ "loss": 0.3233,
597
+ "step": 980
598
+ },
599
+ {
600
+ "epoch": 8.39,
601
+ "learning_rate": 9.168644067796611e-06,
602
+ "loss": 0.3938,
603
+ "step": 990
604
+ },
605
+ {
606
+ "epoch": 8.47,
607
+ "learning_rate": 9.160169491525424e-06,
608
+ "loss": 0.3358,
609
+ "step": 1000
610
+ }
611
+ ],
612
+ "logging_steps": 10,
613
+ "max_steps": 11800,
614
+ "num_train_epochs": 100,
615
+ "save_steps": 1000,
616
+ "total_flos": 0.0,
617
+ "trial_name": null,
618
+ "trial_params": null
619
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57a09e5f6331a10592ac6b6d12ddd1fda5539f30eedca8a311d494d942bed63b
3
+ size 4792
vocab.txt ADDED
The diff for this file is too large to render. See raw diff