Upload 7 files
Browse files- config.json +48 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- trainer_state.json +394 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "LazarusNLP/simcse-indobert-base",
|
3 |
+
"_num_labels": 5,
|
4 |
+
"architectures": [
|
5 |
+
"BertForCL"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"directionality": "bidi",
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "LABEL_0",
|
16 |
+
"1": "LABEL_1",
|
17 |
+
"2": "LABEL_2",
|
18 |
+
"3": "LABEL_3",
|
19 |
+
"4": "LABEL_4"
|
20 |
+
},
|
21 |
+
"initializer_range": 0.02,
|
22 |
+
"intermediate_size": 3072,
|
23 |
+
"label2id": {
|
24 |
+
"LABEL_0": 0,
|
25 |
+
"LABEL_1": 1,
|
26 |
+
"LABEL_2": 2,
|
27 |
+
"LABEL_3": 3,
|
28 |
+
"LABEL_4": 4
|
29 |
+
},
|
30 |
+
"layer_norm_eps": 1e-12,
|
31 |
+
"max_position_embeddings": 512,
|
32 |
+
"model_type": "bert",
|
33 |
+
"num_attention_heads": 12,
|
34 |
+
"num_hidden_layers": 12,
|
35 |
+
"output_past": true,
|
36 |
+
"pad_token_id": 0,
|
37 |
+
"pooler_fc_size": 768,
|
38 |
+
"pooler_num_attention_heads": 12,
|
39 |
+
"pooler_num_fc_layers": 3,
|
40 |
+
"pooler_size_per_head": 128,
|
41 |
+
"pooler_type": "first_token_transform",
|
42 |
+
"position_embedding_type": "absolute",
|
43 |
+
"torch_dtype": "float32",
|
44 |
+
"transformers_version": "4.2.1",
|
45 |
+
"type_vocab_size": 2,
|
46 |
+
"use_cache": true,
|
47 |
+
"vocab_size": 30521
|
48 |
+
}
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:716dc1e0ecc72a21dbd30ffe1fd356459acf297f912f907fb9e68170a0514ebf
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "clean_up_tokenization_spaces": true, "do_basic_tokenize": true, "model_max_length": 1000000000000000019884624838656, "never_split": null, "tokenizer_class": "BertTokenizer", "special_tokens_map_file": "/home/ifti001/.cache/huggingface/transformers/7cc9f436cefa78ab595ac4e5b35da41475c4703c7dfa70ca087711ea68d89a2f.7da70648c6cb9951e284c9685f9ba7ae083dd59ed1d6d84bdfc0584a4ea94b6d", "name_or_path": "LazarusNLP/simcse-indobert-base"}
|
trainer_state.json
ADDED
@@ -0,0 +1,394 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5689655172413793,
|
3 |
+
"best_model_checkpoint": "result/unsup/simcse-indobert-fact-FakeCLSTrain-precise",
|
4 |
+
"epoch": 1.4229249011857708,
|
5 |
+
"global_step": 360,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.08,
|
12 |
+
"eval_CR": 73.51,
|
13 |
+
"eval_FakeCLSDev": 0.9859484777517564,
|
14 |
+
"eval_FakeCLSTest": 0.5161290322580645,
|
15 |
+
"eval_FakeCLSTrain": 0.47105788423153694,
|
16 |
+
"eval_FakePairs": -0.0655808472434033,
|
17 |
+
"eval_FakePairsNLI": 61.47,
|
18 |
+
"eval_MPQA": 77.42,
|
19 |
+
"eval_MR": 62.27,
|
20 |
+
"eval_MRPC": 69.77,
|
21 |
+
"eval_SST2": 69.5,
|
22 |
+
"eval_SUBJ": 83.28,
|
23 |
+
"eval_TREC": 63.68,
|
24 |
+
"eval_avg_sts": 0.615711473961408,
|
25 |
+
"eval_avg_transfer": 71.34714285714286,
|
26 |
+
"eval_sickr_spearman": 0.5665051314046887,
|
27 |
+
"eval_stsb_indo": 0.33437727467476286,
|
28 |
+
"eval_stsb_spearman": 0.6649178165181273,
|
29 |
+
"step": 20
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.16,
|
33 |
+
"eval_CR": 72.68,
|
34 |
+
"eval_FakeCLSDev": 0.9851767388825542,
|
35 |
+
"eval_FakeCLSTest": 0.4231433506044905,
|
36 |
+
"eval_FakeCLSTrain": 0.5489130434782609,
|
37 |
+
"eval_FakePairs": -0.04097804462346638,
|
38 |
+
"eval_FakePairsNLI": 61.0,
|
39 |
+
"eval_MPQA": 77.55,
|
40 |
+
"eval_MR": 61.07,
|
41 |
+
"eval_MRPC": 69.36,
|
42 |
+
"eval_SST2": 69.61,
|
43 |
+
"eval_SUBJ": 82.67,
|
44 |
+
"eval_TREC": 64.01,
|
45 |
+
"eval_avg_sts": 0.6012550116719224,
|
46 |
+
"eval_avg_transfer": 70.99285714285715,
|
47 |
+
"eval_sickr_spearman": 0.5668606095864323,
|
48 |
+
"eval_stsb_indo": 0.3166064743127013,
|
49 |
+
"eval_stsb_spearman": 0.6356494137574127,
|
50 |
+
"step": 40
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.24,
|
54 |
+
"eval_CR": 73.47,
|
55 |
+
"eval_FakeCLSDev": 0.9851598173515982,
|
56 |
+
"eval_FakeCLSTest": 0.49099099099099097,
|
57 |
+
"eval_FakeCLSTrain": 0.5536723163841808,
|
58 |
+
"eval_FakePairs": -0.03922070157918517,
|
59 |
+
"eval_FakePairsNLI": 61.62,
|
60 |
+
"eval_MPQA": 77.38,
|
61 |
+
"eval_MR": 62.28,
|
62 |
+
"eval_MRPC": 69.77,
|
63 |
+
"eval_SST2": 68.69,
|
64 |
+
"eval_SUBJ": 83.33,
|
65 |
+
"eval_TREC": 64.75,
|
66 |
+
"eval_avg_sts": 0.608615640622381,
|
67 |
+
"eval_avg_transfer": 71.38142857142857,
|
68 |
+
"eval_sickr_spearman": 0.5717063713483206,
|
69 |
+
"eval_stsb_indo": 0.3395385317873131,
|
70 |
+
"eval_stsb_spearman": 0.6455249098964414,
|
71 |
+
"step": 60
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.32,
|
75 |
+
"eval_CR": 73.54,
|
76 |
+
"eval_FakeCLSDev": 0.9851598173515982,
|
77 |
+
"eval_FakeCLSTest": 0.4665271966527197,
|
78 |
+
"eval_FakeCLSTrain": 0.56,
|
79 |
+
"eval_FakePairs": -0.058711233524849485,
|
80 |
+
"eval_FakePairsNLI": 60.53,
|
81 |
+
"eval_MPQA": 77.36,
|
82 |
+
"eval_MR": 62.75,
|
83 |
+
"eval_MRPC": 69.97,
|
84 |
+
"eval_SST2": 69.95,
|
85 |
+
"eval_SUBJ": 83.69,
|
86 |
+
"eval_TREC": 64.69,
|
87 |
+
"eval_avg_sts": 0.6091550301498823,
|
88 |
+
"eval_avg_transfer": 71.70714285714287,
|
89 |
+
"eval_sickr_spearman": 0.5691681677928235,
|
90 |
+
"eval_stsb_indo": 0.35668523348337833,
|
91 |
+
"eval_stsb_spearman": 0.6491418925069411,
|
92 |
+
"step": 80
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.4,
|
96 |
+
"eval_CR": 72.86,
|
97 |
+
"eval_FakeCLSDev": 0.9851767388825542,
|
98 |
+
"eval_FakeCLSTest": 0.43423423423423424,
|
99 |
+
"eval_FakeCLSTrain": 0.5497237569060773,
|
100 |
+
"eval_FakePairs": -0.06198628192555537,
|
101 |
+
"eval_FakePairsNLI": 63.34,
|
102 |
+
"eval_MPQA": 77.43,
|
103 |
+
"eval_MR": 62.37,
|
104 |
+
"eval_MRPC": 70.02,
|
105 |
+
"eval_SST2": 69.72,
|
106 |
+
"eval_SUBJ": 83.97,
|
107 |
+
"eval_TREC": 62.91,
|
108 |
+
"eval_avg_sts": 0.6086202878060443,
|
109 |
+
"eval_avg_transfer": 71.32571428571428,
|
110 |
+
"eval_sickr_spearman": 0.5628235474794574,
|
111 |
+
"eval_stsb_indo": 0.3583996091555714,
|
112 |
+
"eval_stsb_spearman": 0.6544170281326311,
|
113 |
+
"step": 100
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.47,
|
117 |
+
"eval_CR": 73.16,
|
118 |
+
"eval_FakeCLSDev": 0.9851767388825542,
|
119 |
+
"eval_FakeCLSTest": 0.43783783783783786,
|
120 |
+
"eval_FakeCLSTrain": 0.5668604651162791,
|
121 |
+
"eval_FakePairs": -0.061826523466984355,
|
122 |
+
"eval_FakePairsNLI": 63.03,
|
123 |
+
"eval_MPQA": 77.29,
|
124 |
+
"eval_MR": 62.36,
|
125 |
+
"eval_MRPC": 70.27,
|
126 |
+
"eval_SST2": 67.89,
|
127 |
+
"eval_SUBJ": 83.77,
|
128 |
+
"eval_TREC": 64.22,
|
129 |
+
"eval_avg_sts": 0.6163408060409252,
|
130 |
+
"eval_avg_transfer": 71.27999999999999,
|
131 |
+
"eval_sickr_spearman": 0.5696943965401795,
|
132 |
+
"eval_stsb_indo": 0.3670526673661317,
|
133 |
+
"eval_stsb_spearman": 0.6629872155416708,
|
134 |
+
"step": 120
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.55,
|
138 |
+
"eval_CR": 73.07,
|
139 |
+
"eval_FakeCLSDev": 0.9851767388825542,
|
140 |
+
"eval_FakeCLSTest": 0.41919191919191917,
|
141 |
+
"eval_FakeCLSTrain": 0.556497175141243,
|
142 |
+
"eval_FakePairs": -0.06653939799482943,
|
143 |
+
"eval_FakePairsNLI": 70.2,
|
144 |
+
"eval_MPQA": 77.45,
|
145 |
+
"eval_MR": 62.45,
|
146 |
+
"eval_MRPC": 69.9,
|
147 |
+
"eval_SST2": 68.46,
|
148 |
+
"eval_SUBJ": 83.58,
|
149 |
+
"eval_TREC": 63.08,
|
150 |
+
"eval_avg_sts": 0.6153345841426848,
|
151 |
+
"eval_avg_transfer": 71.14142857142856,
|
152 |
+
"eval_sickr_spearman": 0.5701103458786335,
|
153 |
+
"eval_stsb_indo": 0.3509797527191032,
|
154 |
+
"eval_stsb_spearman": 0.6605588224067361,
|
155 |
+
"step": 140
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.63,
|
159 |
+
"eval_CR": 73.5,
|
160 |
+
"eval_FakeCLSDev": 0.9851598173515982,
|
161 |
+
"eval_FakeCLSTest": 0.4753747323340471,
|
162 |
+
"eval_FakeCLSTrain": 0.5612535612535613,
|
163 |
+
"eval_FakePairs": -0.0680571033512541,
|
164 |
+
"eval_FakePairsNLI": 65.83,
|
165 |
+
"eval_MPQA": 77.08,
|
166 |
+
"eval_MR": 62.5,
|
167 |
+
"eval_MRPC": 69.8,
|
168 |
+
"eval_SST2": 69.5,
|
169 |
+
"eval_SUBJ": 83.92,
|
170 |
+
"eval_TREC": 63.7,
|
171 |
+
"eval_avg_sts": 0.6138085030907702,
|
172 |
+
"eval_avg_transfer": 71.42857142857143,
|
173 |
+
"eval_sickr_spearman": 0.5714391262999188,
|
174 |
+
"eval_stsb_indo": 0.35272703771997466,
|
175 |
+
"eval_stsb_spearman": 0.6561778798816216,
|
176 |
+
"step": 160
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.71,
|
180 |
+
"eval_CR": 72.79,
|
181 |
+
"eval_FakeCLSDev": 0.9851513420902341,
|
182 |
+
"eval_FakeCLSTest": 0.49417249417249415,
|
183 |
+
"eval_FakeCLSTrain": 0.5285359801488834,
|
184 |
+
"eval_FakePairs": -0.06949492947839328,
|
185 |
+
"eval_FakePairsNLI": 62.71,
|
186 |
+
"eval_MPQA": 76.76,
|
187 |
+
"eval_MR": 62.73,
|
188 |
+
"eval_MRPC": 70.02,
|
189 |
+
"eval_SST2": 68.58,
|
190 |
+
"eval_SUBJ": 84.43,
|
191 |
+
"eval_TREC": 62.42,
|
192 |
+
"eval_avg_sts": 0.6196401183056581,
|
193 |
+
"eval_avg_transfer": 71.10428571428572,
|
194 |
+
"eval_sickr_spearman": 0.5703694256397907,
|
195 |
+
"eval_stsb_indo": 0.36643910488045184,
|
196 |
+
"eval_stsb_spearman": 0.6689108109715255,
|
197 |
+
"step": 180
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 0.79,
|
201 |
+
"eval_CR": 72.87,
|
202 |
+
"eval_FakeCLSDev": 0.9851767388825542,
|
203 |
+
"eval_FakeCLSTest": 0.44014732965009207,
|
204 |
+
"eval_FakeCLSTrain": 0.5657142857142857,
|
205 |
+
"eval_FakePairs": -0.07093275560553244,
|
206 |
+
"eval_FakePairsNLI": 62.56,
|
207 |
+
"eval_MPQA": 76.85,
|
208 |
+
"eval_MR": 62.55,
|
209 |
+
"eval_MRPC": 70.34,
|
210 |
+
"eval_SST2": 66.28,
|
211 |
+
"eval_SUBJ": 83.69,
|
212 |
+
"eval_TREC": 62.9,
|
213 |
+
"eval_avg_sts": 0.6117092253437233,
|
214 |
+
"eval_avg_transfer": 70.78285714285714,
|
215 |
+
"eval_sickr_spearman": 0.562769224303731,
|
216 |
+
"eval_stsb_indo": 0.37225410713674706,
|
217 |
+
"eval_stsb_spearman": 0.6606492263837157,
|
218 |
+
"step": 200
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.87,
|
222 |
+
"eval_CR": 72.81,
|
223 |
+
"eval_FakeCLSDev": 0.9851598173515982,
|
224 |
+
"eval_FakeCLSTest": 0.4673684210526316,
|
225 |
+
"eval_FakeCLSTrain": 0.547945205479452,
|
226 |
+
"eval_FakePairs": -0.054158117455575444,
|
227 |
+
"eval_FakePairsNLI": 63.65,
|
228 |
+
"eval_MPQA": 77.75,
|
229 |
+
"eval_MR": 62.64,
|
230 |
+
"eval_MRPC": 70.29,
|
231 |
+
"eval_SST2": 69.38,
|
232 |
+
"eval_SUBJ": 83.87,
|
233 |
+
"eval_TREC": 63.48,
|
234 |
+
"eval_avg_sts": 0.6109666311280921,
|
235 |
+
"eval_avg_transfer": 71.46000000000001,
|
236 |
+
"eval_sickr_spearman": 0.5690365625748831,
|
237 |
+
"eval_stsb_indo": 0.359153644946237,
|
238 |
+
"eval_stsb_spearman": 0.652896699681301,
|
239 |
+
"step": 220
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.95,
|
243 |
+
"eval_CR": 73.15,
|
244 |
+
"eval_FakeCLSDev": 0.9851767388825542,
|
245 |
+
"eval_FakeCLSTest": 0.42757417102966844,
|
246 |
+
"eval_FakeCLSTrain": 0.5528455284552846,
|
247 |
+
"eval_FakePairs": -0.044652489170599816,
|
248 |
+
"eval_FakePairsNLI": 60.69,
|
249 |
+
"eval_MPQA": 77.47,
|
250 |
+
"eval_MR": 62.17,
|
251 |
+
"eval_MRPC": 70.34,
|
252 |
+
"eval_SST2": 67.09,
|
253 |
+
"eval_SUBJ": 83.56,
|
254 |
+
"eval_TREC": 62.33,
|
255 |
+
"eval_avg_sts": 0.6128236398775047,
|
256 |
+
"eval_avg_transfer": 70.87285714285714,
|
257 |
+
"eval_sickr_spearman": 0.5620660489786768,
|
258 |
+
"eval_stsb_indo": 0.3265208518275815,
|
259 |
+
"eval_stsb_spearman": 0.6635812307763325,
|
260 |
+
"step": 240
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.03,
|
264 |
+
"eval_CR": 73.03,
|
265 |
+
"eval_FakeCLSDev": 0.9851513420902341,
|
266 |
+
"eval_FakeCLSTest": 0.4306306306306306,
|
267 |
+
"eval_FakeCLSTrain": 0.5597667638483965,
|
268 |
+
"eval_FakePairs": -0.05024404074786382,
|
269 |
+
"eval_FakePairsNLI": 61.62,
|
270 |
+
"eval_MPQA": 77.18,
|
271 |
+
"eval_MR": 61.87,
|
272 |
+
"eval_MRPC": 70.0,
|
273 |
+
"eval_SST2": 67.43,
|
274 |
+
"eval_SUBJ": 83.27,
|
275 |
+
"eval_TREC": 62.67,
|
276 |
+
"eval_avg_sts": 0.6131921270133698,
|
277 |
+
"eval_avg_transfer": 70.77857142857144,
|
278 |
+
"eval_sickr_spearman": 0.5614766113018284,
|
279 |
+
"eval_stsb_indo": 0.3244277933781677,
|
280 |
+
"eval_stsb_spearman": 0.6649076427249111,
|
281 |
+
"step": 260
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.11,
|
285 |
+
"eval_CR": 73.01,
|
286 |
+
"eval_FakeCLSDev": 0.9861030689056167,
|
287 |
+
"eval_FakeCLSTest": 0.5215189873417722,
|
288 |
+
"eval_FakeCLSTrain": 0.5498652291105122,
|
289 |
+
"eval_FakePairs": -0.04281527160708269,
|
290 |
+
"eval_FakePairsNLI": 60.53,
|
291 |
+
"eval_MPQA": 77.48,
|
292 |
+
"eval_MR": 61.83,
|
293 |
+
"eval_MRPC": 69.9,
|
294 |
+
"eval_SST2": 69.27,
|
295 |
+
"eval_SUBJ": 82.46,
|
296 |
+
"eval_TREC": 63.98,
|
297 |
+
"eval_avg_sts": 0.6053801581830358,
|
298 |
+
"eval_avg_transfer": 71.13285714285715,
|
299 |
+
"eval_sickr_spearman": 0.5599164170338142,
|
300 |
+
"eval_stsb_indo": 0.3103923440865193,
|
301 |
+
"eval_stsb_spearman": 0.6508438993322574,
|
302 |
+
"step": 280
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.19,
|
306 |
+
"eval_CR": 72.83,
|
307 |
+
"eval_FakeCLSDev": 0.9856073690270581,
|
308 |
+
"eval_FakeCLSTest": 0.516209476309227,
|
309 |
+
"eval_FakeCLSTrain": 0.5464190981432361,
|
310 |
+
"eval_FakePairs": -0.020449082697090434,
|
311 |
+
"eval_FakePairsNLI": 60.53,
|
312 |
+
"eval_MPQA": 77.52,
|
313 |
+
"eval_MR": 61.56,
|
314 |
+
"eval_MRPC": 69.9,
|
315 |
+
"eval_SST2": 68.23,
|
316 |
+
"eval_SUBJ": 82.49,
|
317 |
+
"eval_TREC": 64.05,
|
318 |
+
"eval_avg_sts": 0.5997509995903676,
|
319 |
+
"eval_avg_transfer": 70.94000000000001,
|
320 |
+
"eval_sickr_spearman": 0.5583291812556904,
|
321 |
+
"eval_stsb_indo": 0.2918589228675973,
|
322 |
+
"eval_stsb_spearman": 0.6411728179250447,
|
323 |
+
"step": 300
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.26,
|
327 |
+
"eval_CR": 72.67,
|
328 |
+
"eval_FakeCLSDev": 0.9851936218678815,
|
329 |
+
"eval_FakeCLSTest": 0.5277777777777778,
|
330 |
+
"eval_FakeCLSTrain": 0.5513513513513514,
|
331 |
+
"eval_FakePairs": -0.0066299760306972886,
|
332 |
+
"eval_FakePairsNLI": 60.53,
|
333 |
+
"eval_MPQA": 77.09,
|
334 |
+
"eval_MR": 62.07,
|
335 |
+
"eval_MRPC": 70.22,
|
336 |
+
"eval_SST2": 68.0,
|
337 |
+
"eval_SUBJ": 82.45,
|
338 |
+
"eval_TREC": 64.58,
|
339 |
+
"eval_avg_sts": 0.6007609352858567,
|
340 |
+
"eval_avg_transfer": 71.01142857142857,
|
341 |
+
"eval_sickr_spearman": 0.5664013842255825,
|
342 |
+
"eval_stsb_indo": 0.3162610592900211,
|
343 |
+
"eval_stsb_spearman": 0.6351204863461308,
|
344 |
+
"step": 320
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.34,
|
348 |
+
"eval_CR": 72.99,
|
349 |
+
"eval_FakeCLSDev": 0.993006993006993,
|
350 |
+
"eval_FakeCLSTest": 0.30303030303030304,
|
351 |
+
"eval_FakeCLSTrain": 0.5580110497237569,
|
352 |
+
"eval_FakePairs": -0.02212654651208613,
|
353 |
+
"eval_FakePairsNLI": 63.03,
|
354 |
+
"eval_MPQA": 77.68,
|
355 |
+
"eval_MR": 62.61,
|
356 |
+
"eval_MRPC": 69.87,
|
357 |
+
"eval_SST2": 68.23,
|
358 |
+
"eval_SUBJ": 83.02,
|
359 |
+
"eval_TREC": 65.72,
|
360 |
+
"eval_avg_sts": 0.6010452523806686,
|
361 |
+
"eval_avg_transfer": 71.44571428571429,
|
362 |
+
"eval_sickr_spearman": 0.5730101275657566,
|
363 |
+
"eval_stsb_indo": 0.33175461948179213,
|
364 |
+
"eval_stsb_spearman": 0.6290803771955807,
|
365 |
+
"step": 340
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 1.42,
|
369 |
+
"eval_CR": 72.46,
|
370 |
+
"eval_FakeCLSDev": 1.0,
|
371 |
+
"eval_FakeCLSTest": 0.0,
|
372 |
+
"eval_FakeCLSTrain": 0.5689655172413793,
|
373 |
+
"eval_FakePairs": -0.022206425741371643,
|
374 |
+
"eval_FakePairsNLI": 60.53,
|
375 |
+
"eval_MPQA": 77.87,
|
376 |
+
"eval_MR": 62.74,
|
377 |
+
"eval_MRPC": 70.34,
|
378 |
+
"eval_SST2": 68.81,
|
379 |
+
"eval_SUBJ": 83.4,
|
380 |
+
"eval_TREC": 66.23,
|
381 |
+
"eval_avg_sts": 0.6023165873556424,
|
382 |
+
"eval_avg_transfer": 71.69285714285715,
|
383 |
+
"eval_sickr_spearman": 0.5723746280626291,
|
384 |
+
"eval_stsb_indo": 0.3481165947946874,
|
385 |
+
"eval_stsb_spearman": 0.6322585466486558,
|
386 |
+
"step": 360
|
387 |
+
}
|
388 |
+
],
|
389 |
+
"max_steps": 759,
|
390 |
+
"num_train_epochs": 3,
|
391 |
+
"total_flos": 0,
|
392 |
+
"trial_name": null,
|
393 |
+
"trial_params": null
|
394 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e969a9bcd5202996e59fe2250ba8e1b43ade28b87a1e1d2c08ccbd2f4e07f394
|
3 |
+
size 2808
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|