Hugging Face's logo

Turkish-NLI
/
legal_nli_TR_V1

Sentence Similarity
sentence-transformers
Safetensors
Turkish
bert
feature-extraction
Generated from Trainer
dataset_size:202000
loss:SoftmaxLoss
Eval Results
text-embeddings-inference
Inference Endpoints
Model card Files Community
1
MesutDemirel commited on
Commit
8495761
•
1 Parent(s): 48e24d4

Model loaded

Browse files
Files changed (16) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +0 -0
  3. config.json +25 -0
  4. config_sentence_transformers.json +10 -0
  5. model.safetensors +3 -0
  6. modules.json +14 -0
  7. optimizer.pt +3 -0
  8. rng_state.pth +3 -0
  9. scheduler.pt +3 -0
  10. sentence_bert_config.json +4 -0
  11. special_tokens_map.json +37 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +65 -0
  14. trainer_state.json +333 -0
  15. training_args.bin +3 -0
  16. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
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 CHANGED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/calisma/checkpoint-1500",
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": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "layer_norm_eps": 1e-12,
14
+ "max_position_embeddings": 512,
15
+ "model_type": "bert",
16
+ "num_attention_heads": 12,
17
+ "num_hidden_layers": 12,
18
+ "pad_token_id": 0,
19
+ "position_embedding_type": "absolute",
20
+ "torch_dtype": "float32",
21
+ "transformers_version": "4.42.4",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 32000
25
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.0.1",
4
+ "transformers": "4.42.4",
5
+ "pytorch": "2.3.1+cu121"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": null
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d09bd3e69372be37be004f32ede469b09797649a5421eee6fabecc58b5cfc074
3
+ size 442491744
modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ ]
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68e34094347f680dacf33b99630f89d758785d58b71254ce94e1487780379600
3
+ size 880378810
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce904aa8117d75b39279a1f89ae0c6abf8aa06a462def857c3a5adeb68893458
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:558e869d13a69d104c504c0dc3b5003c34f3ba480fa99d5956887c409f09735a
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 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_len": 512,
50
+ "max_length": 512,
51
+ "model_max_length": 512,
52
+ "never_split": null,
53
+ "pad_to_multiple_of": null,
54
+ "pad_token": "[PAD]",
55
+ "pad_token_type_id": 0,
56
+ "padding_side": "right",
57
+ "sep_token": "[SEP]",
58
+ "stride": 0,
59
+ "strip_accents": null,
60
+ "tokenize_chinese_chars": true,
61
+ "tokenizer_class": "BertTokenizer",
62
+ "truncation_side": "right",
63
+ "truncation_strategy": "longest_first",
64
+ "unk_token": "[UNK]"
65
+ }
trainer_state.json ADDED
@@ -0,0 +1,333 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6313,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0792016473942658,
13
+ "grad_norm": 0.07919532805681229,
14
+ "learning_rate": 3.9556962025316456e-05,
15
+ "loss": 0.1311,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 0.0792016473942658,
20
+ "eval_loss": 0.014126550406217575,
21
+ "eval_runtime": 83.0348,
22
+ "eval_samples_per_second": 60.216,
23
+ "eval_steps_per_second": 1.891,
24
+ "eval_sts-dev_pearson_cosine": 0.1557480599999687,
25
+ "eval_sts-dev_pearson_dot": 0.13799264585261115,
26
+ "eval_sts-dev_pearson_euclidean": 0.18714752476831273,
27
+ "eval_sts-dev_pearson_manhattan": 0.18855989459573652,
28
+ "eval_sts-dev_pearson_max": 0.18855989459573652,
29
+ "eval_sts-dev_spearman_cosine": 0.20357424121861373,
30
+ "eval_sts-dev_spearman_dot": 0.14034776792350498,
31
+ "eval_sts-dev_spearman_euclidean": 0.21044421396782537,
32
+ "eval_sts-dev_spearman_manhattan": 0.21183531991746804,
33
+ "eval_sts-dev_spearman_max": 0.21183531991746804,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 0.1584032947885316,
38
+ "grad_norm": 0.012879022397100925,
39
+ "learning_rate": 4.677873613800388e-05,
40
+ "loss": 0.0203,
41
+ "step": 1000
42
+ },
43
+ {
44
+ "epoch": 0.1584032947885316,
45
+ "eval_loss": 0.015841394662857056,
46
+ "eval_runtime": 82.5774,
47
+ "eval_samples_per_second": 60.549,
48
+ "eval_steps_per_second": 1.901,
49
+ "eval_sts-dev_pearson_cosine": 0.16793876783774,
50
+ "eval_sts-dev_pearson_dot": 0.1481957278796634,
51
+ "eval_sts-dev_pearson_euclidean": 0.19722850814365245,
52
+ "eval_sts-dev_pearson_manhattan": 0.19617097331605537,
53
+ "eval_sts-dev_pearson_max": 0.19722850814365245,
54
+ "eval_sts-dev_spearman_cosine": 0.19966948583403588,
55
+ "eval_sts-dev_spearman_dot": 0.14869572921537724,
56
+ "eval_sts-dev_spearman_euclidean": 0.208144651870388,
57
+ "eval_sts-dev_spearman_manhattan": 0.20697988059772135,
58
+ "eval_sts-dev_spearman_max": 0.208144651870388,
59
+ "step": 1000
60
+ },
61
+ {
62
+ "epoch": 0.2376049421827974,
63
+ "grad_norm": 0.007155057042837143,
64
+ "learning_rate": 4.2378102446752334e-05,
65
+ "loss": 0.0174,
66
+ "step": 1500
67
+ },
68
+ {
69
+ "epoch": 0.2376049421827974,
70
+ "eval_loss": 0.01738722249865532,
71
+ "eval_runtime": 82.5636,
72
+ "eval_samples_per_second": 60.559,
73
+ "eval_steps_per_second": 1.902,
74
+ "eval_sts-dev_pearson_cosine": 0.13663702381510662,
75
+ "eval_sts-dev_pearson_dot": 0.11588852598989118,
76
+ "eval_sts-dev_pearson_euclidean": 0.16056667152911408,
77
+ "eval_sts-dev_pearson_manhattan": 0.15924268782656817,
78
+ "eval_sts-dev_pearson_max": 0.16056667152911408,
79
+ "eval_sts-dev_spearman_cosine": 0.16527466832006016,
80
+ "eval_sts-dev_spearman_dot": 0.10078185264794931,
81
+ "eval_sts-dev_spearman_euclidean": 0.1719215715191216,
82
+ "eval_sts-dev_spearman_manhattan": 0.170303502778187,
83
+ "eval_sts-dev_spearman_max": 0.1719215715191216,
84
+ "step": 1500
85
+ },
86
+ {
87
+ "epoch": 0.3168065895770632,
88
+ "grad_norm": 0.002368535613641143,
89
+ "learning_rate": 3.79774687555008e-05,
90
+ "loss": 0.0108,
91
+ "step": 2000
92
+ },
93
+ {
94
+ "epoch": 0.3168065895770632,
95
+ "eval_loss": 0.013646911829710007,
96
+ "eval_runtime": 83.1873,
97
+ "eval_samples_per_second": 60.105,
98
+ "eval_steps_per_second": 1.887,
99
+ "eval_sts-dev_pearson_cosine": 0.14207290429771552,
100
+ "eval_sts-dev_pearson_dot": 0.12219302310028649,
101
+ "eval_sts-dev_pearson_euclidean": 0.15249164642806468,
102
+ "eval_sts-dev_pearson_manhattan": 0.15099460310457263,
103
+ "eval_sts-dev_pearson_max": 0.15249164642806468,
104
+ "eval_sts-dev_spearman_cosine": 0.14567413155731176,
105
+ "eval_sts-dev_spearman_dot": 0.09939489795167657,
106
+ "eval_sts-dev_spearman_euclidean": 0.14960035136962835,
107
+ "eval_sts-dev_spearman_manhattan": 0.14872808741782187,
108
+ "eval_sts-dev_spearman_max": 0.14960035136962835,
109
+ "step": 2000
110
+ },
111
+ {
112
+ "epoch": 0.39600823697132903,
113
+ "grad_norm": 0.011403551325201988,
114
+ "learning_rate": 3.3576835064249254e-05,
115
+ "loss": 0.0121,
116
+ "step": 2500
117
+ },
118
+ {
119
+ "epoch": 0.39600823697132903,
120
+ "eval_loss": 0.015611983835697174,
121
+ "eval_runtime": 82.8829,
122
+ "eval_samples_per_second": 60.326,
123
+ "eval_steps_per_second": 1.894,
124
+ "eval_sts-dev_pearson_cosine": 0.1786266334873075,
125
+ "eval_sts-dev_pearson_dot": 0.16571459472812308,
126
+ "eval_sts-dev_pearson_euclidean": 0.19586188718253267,
127
+ "eval_sts-dev_pearson_manhattan": 0.19603778309890557,
128
+ "eval_sts-dev_pearson_max": 0.19603778309890557,
129
+ "eval_sts-dev_spearman_cosine": 0.20990140220242978,
130
+ "eval_sts-dev_spearman_dot": 0.1668269410484095,
131
+ "eval_sts-dev_spearman_euclidean": 0.21443661354146873,
132
+ "eval_sts-dev_spearman_manhattan": 0.21529338637929912,
133
+ "eval_sts-dev_spearman_max": 0.21529338637929912,
134
+ "step": 2500
135
+ },
136
+ {
137
+ "epoch": 0.4752098843655948,
138
+ "grad_norm": 0.004168146755546331,
139
+ "learning_rate": 2.9176201372997714e-05,
140
+ "loss": 0.0122,
141
+ "step": 3000
142
+ },
143
+ {
144
+ "epoch": 0.4752098843655948,
145
+ "eval_loss": 0.013952625915408134,
146
+ "eval_runtime": 82.7861,
147
+ "eval_samples_per_second": 60.397,
148
+ "eval_steps_per_second": 1.896,
149
+ "eval_sts-dev_pearson_cosine": 0.16089480397614714,
150
+ "eval_sts-dev_pearson_dot": 0.14333252395560012,
151
+ "eval_sts-dev_pearson_euclidean": 0.17458568236482797,
152
+ "eval_sts-dev_pearson_manhattan": 0.1736800184097837,
153
+ "eval_sts-dev_pearson_max": 0.17458568236482797,
154
+ "eval_sts-dev_spearman_cosine": 0.17227083866593193,
155
+ "eval_sts-dev_spearman_dot": 0.12781779851368713,
156
+ "eval_sts-dev_spearman_euclidean": 0.17703810710585532,
157
+ "eval_sts-dev_spearman_manhattan": 0.17557253669161538,
158
+ "eval_sts-dev_spearman_max": 0.17703810710585532,
159
+ "step": 3000
160
+ },
161
+ {
162
+ "epoch": 0.5544115317598606,
163
+ "grad_norm": 0.004282405134290457,
164
+ "learning_rate": 2.4775567681746174e-05,
165
+ "loss": 0.0125,
166
+ "step": 3500
167
+ },
168
+ {
169
+ "epoch": 0.5544115317598606,
170
+ "eval_loss": 0.011783541180193424,
171
+ "eval_runtime": 82.8159,
172
+ "eval_samples_per_second": 60.375,
173
+ "eval_steps_per_second": 1.896,
174
+ "eval_sts-dev_pearson_cosine": 0.18448919166260044,
175
+ "eval_sts-dev_pearson_dot": 0.17905699568214264,
176
+ "eval_sts-dev_pearson_euclidean": 0.20624063360858977,
177
+ "eval_sts-dev_pearson_manhattan": 0.205619351099398,
178
+ "eval_sts-dev_pearson_max": 0.20624063360858977,
179
+ "eval_sts-dev_spearman_cosine": 0.22476168122019577,
180
+ "eval_sts-dev_spearman_dot": 0.19305224567026316,
181
+ "eval_sts-dev_spearman_euclidean": 0.2268539691521332,
182
+ "eval_sts-dev_spearman_manhattan": 0.2268021523901189,
183
+ "eval_sts-dev_spearman_max": 0.2268539691521332,
184
+ "step": 3500
185
+ },
186
+ {
187
+ "epoch": 0.6336131791541264,
188
+ "grad_norm": 0.016134686768054962,
189
+ "learning_rate": 2.0374933990494634e-05,
190
+ "loss": 0.0079,
191
+ "step": 4000
192
+ },
193
+ {
194
+ "epoch": 0.6336131791541264,
195
+ "eval_loss": 0.011526196263730526,
196
+ "eval_runtime": 83.1812,
197
+ "eval_samples_per_second": 60.11,
198
+ "eval_steps_per_second": 1.887,
199
+ "eval_sts-dev_pearson_cosine": 0.16979017817169434,
200
+ "eval_sts-dev_pearson_dot": 0.16329193511035556,
201
+ "eval_sts-dev_pearson_euclidean": 0.2041557241070686,
202
+ "eval_sts-dev_pearson_manhattan": 0.20415667390135622,
203
+ "eval_sts-dev_pearson_max": 0.20415667390135622,
204
+ "eval_sts-dev_spearman_cosine": 0.23370816253094054,
205
+ "eval_sts-dev_spearman_dot": 0.19110938133669397,
206
+ "eval_sts-dev_spearman_euclidean": 0.23731458674719166,
207
+ "eval_sts-dev_spearman_manhattan": 0.2363744330684564,
208
+ "eval_sts-dev_spearman_max": 0.23731458674719166,
209
+ "step": 4000
210
+ },
211
+ {
212
+ "epoch": 0.7128148265483922,
213
+ "grad_norm": 0.10654988884925842,
214
+ "learning_rate": 1.5983101566625593e-05,
215
+ "loss": 0.0093,
216
+ "step": 4500
217
+ },
218
+ {
219
+ "epoch": 0.7128148265483922,
220
+ "eval_loss": 0.01042733620852232,
221
+ "eval_runtime": 82.4696,
222
+ "eval_samples_per_second": 60.628,
223
+ "eval_steps_per_second": 1.904,
224
+ "eval_sts-dev_pearson_cosine": 0.16883832363197002,
225
+ "eval_sts-dev_pearson_dot": 0.16172877878537467,
226
+ "eval_sts-dev_pearson_euclidean": 0.20343671061551505,
227
+ "eval_sts-dev_pearson_manhattan": 0.20269317144225543,
228
+ "eval_sts-dev_pearson_max": 0.20343671061551505,
229
+ "eval_sts-dev_spearman_cosine": 0.23314123864913222,
230
+ "eval_sts-dev_spearman_dot": 0.19029123486315452,
231
+ "eval_sts-dev_spearman_euclidean": 0.23747745874658102,
232
+ "eval_sts-dev_spearman_manhattan": 0.23681371095402073,
233
+ "eval_sts-dev_spearman_max": 0.23747745874658102,
234
+ "step": 4500
235
+ },
236
+ {
237
+ "epoch": 0.7920164739426581,
238
+ "grad_norm": 0.0034745726734399796,
239
+ "learning_rate": 1.1582467875374054e-05,
240
+ "loss": 0.0071,
241
+ "step": 5000
242
+ },
243
+ {
244
+ "epoch": 0.7920164739426581,
245
+ "eval_loss": 0.010719917714595795,
246
+ "eval_runtime": 82.5902,
247
+ "eval_samples_per_second": 60.54,
248
+ "eval_steps_per_second": 1.901,
249
+ "eval_sts-dev_pearson_cosine": 0.19565242771314767,
250
+ "eval_sts-dev_pearson_dot": 0.18923012649171922,
251
+ "eval_sts-dev_pearson_euclidean": 0.2278768429358364,
252
+ "eval_sts-dev_pearson_manhattan": 0.22768897126347665,
253
+ "eval_sts-dev_pearson_max": 0.2278768429358364,
254
+ "eval_sts-dev_spearman_cosine": 0.24240094548214325,
255
+ "eval_sts-dev_spearman_dot": 0.21284981986619678,
256
+ "eval_sts-dev_spearman_euclidean": 0.24732163285243935,
257
+ "eval_sts-dev_spearman_manhattan": 0.24736929658665446,
258
+ "eval_sts-dev_spearman_max": 0.24736929658665446,
259
+ "step": 5000
260
+ },
261
+ {
262
+ "epoch": 0.8712181213369238,
263
+ "grad_norm": 0.004818719811737537,
264
+ "learning_rate": 7.181834184122514e-06,
265
+ "loss": 0.0041,
266
+ "step": 5500
267
+ },
268
+ {
269
+ "epoch": 0.8712181213369238,
270
+ "eval_loss": 0.009991911239922047,
271
+ "eval_runtime": 82.1637,
272
+ "eval_samples_per_second": 60.854,
273
+ "eval_steps_per_second": 1.911,
274
+ "eval_sts-dev_pearson_cosine": 0.1892693811813182,
275
+ "eval_sts-dev_pearson_dot": 0.18290497740650222,
276
+ "eval_sts-dev_pearson_euclidean": 0.22463164519842746,
277
+ "eval_sts-dev_pearson_manhattan": 0.22460268853676083,
278
+ "eval_sts-dev_pearson_max": 0.22463164519842746,
279
+ "eval_sts-dev_spearman_cosine": 0.24628027091826607,
280
+ "eval_sts-dev_spearman_dot": 0.21127633301239485,
281
+ "eval_sts-dev_spearman_euclidean": 0.251238048387475,
282
+ "eval_sts-dev_spearman_manhattan": 0.2518403299451181,
283
+ "eval_sts-dev_spearman_max": 0.2518403299451181,
284
+ "step": 5500
285
+ },
286
+ {
287
+ "epoch": 0.9504197687311896,
288
+ "grad_norm": 0.012634661048650742,
289
+ "learning_rate": 2.7812004928709737e-06,
290
+ "loss": 0.0069,
291
+ "step": 6000
292
+ },
293
+ {
294
+ "epoch": 0.9504197687311896,
295
+ "eval_loss": 0.009837556630373001,
296
+ "eval_runtime": 83.3155,
297
+ "eval_samples_per_second": 60.013,
298
+ "eval_steps_per_second": 1.884,
299
+ "eval_sts-dev_pearson_cosine": 0.19373258731869963,
300
+ "eval_sts-dev_pearson_dot": 0.18775862207030505,
301
+ "eval_sts-dev_pearson_euclidean": 0.22537635202224982,
302
+ "eval_sts-dev_pearson_manhattan": 0.2245827911400446,
303
+ "eval_sts-dev_pearson_max": 0.22537635202224982,
304
+ "eval_sts-dev_spearman_cosine": 0.24307341815427166,
305
+ "eval_sts-dev_spearman_dot": 0.2124049530103558,
306
+ "eval_sts-dev_spearman_euclidean": 0.24695143686545143,
307
+ "eval_sts-dev_spearman_manhattan": 0.2468102784042943,
308
+ "eval_sts-dev_spearman_max": 0.24695143686545143,
309
+ "step": 6000
310
+ }
311
+ ],
312
+ "logging_steps": 500,
313
+ "max_steps": 6313,
314
+ "num_input_tokens_seen": 0,
315
+ "num_train_epochs": 1,
316
+ "save_steps": 500,
317
+ "stateful_callbacks": {
318
+ "TrainerControl": {
319
+ "args": {
320
+ "should_epoch_stop": false,
321
+ "should_evaluate": false,
322
+ "should_log": false,
323
+ "should_save": true,
324
+ "should_training_stop": true
325
+ },
326
+ "attributes": {}
327
+ }
328
+ },
329
+ "total_flos": 0.0,
330
+ "train_batch_size": 32,
331
+ "trial_name": null,
332
+ "trial_params": null
333
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49cd29a3f4634cde346f934be256bc249299b11b2a06ac368e70856ff7be6b50
3
+ size 5496
vocab.txt ADDED
The diff for this file is too large to render. See raw diff