Hugging Face's logo

Detomo
/
cl-nagoya-sup-simcse-ja-for-standard-name-v1_1

Sentence Similarity
sentence-transformers
Safetensors
bert
feature-extraction
Generated from Trainer
dataset_size:8788
loss:BatchAllTripletLoss
text-embeddings-inference
Model card Files
xet
Community
dtm-hoinv commited on
Commit
155fb32
·
verified ·
1 Parent(s): 224732d

Add new SentenceTransformer model

Browse files
Files changed (11) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +768 -0
  3. config.json +25 -0
  4. config_sentence_transformers.json +10 -0
  5. model.safetensors +3 -0
  6. modules.json +14 -0
  7. sentence_bert_config.json +4 -0
  8. special_tokens_map.json +7 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +67 -0
  11. vocab.txt +0 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
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 +1,768 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - sentence-transformers
4
+ - sentence-similarity
5
+ - feature-extraction
6
+ - generated_from_trainer
7
+ - dataset_size:8788
8
+ - loss:BatchAllTripletLoss
9
+ base_model: cl-nagoya/sup-simcse-ja-base
10
+ widget:
11
+ - source_sentence: 科目：ユニット及びその他。名称：ピクチャーレールA。
12
+ sentences:
13
+ - 科目：ユニット及びその他。名称：床ゴムチップ舗装。
14
+ - 科目：ユニット及びその他。名称：講堂スピーカー戸。
15
+ - 科目：ユニット及びその他。名称：C7三槽シンク。
16
+ - source_sentence: 科目：ユニット及びその他。名称：A-#小児プレイルームアート。
17
+ sentences:
18
+ - 科目：ユニット及びその他。名称：F-#階ひまわり学級職員室ミニキッチン。
19
+ - 科目：ユニット及びその他。名称：連絡通路梁用バトントラス。
20
+ - 科目：ユニット及びその他。名称：体育館サブバレーボールコートライン。
21
+ - source_sentence: 科目：ユニット及びその他。名称：厨房カウンター。
22
+ sentences:
23
+ - 科目：コンクリート。名称：地上部暑中コンクリート。
24
+ - 科目：コンクリート。名称：免震EXP.J用充填コンクリート。
25
+ - 科目：コンクリート。名称：基礎コンクリート。
26
+ - source_sentence: 科目：ユニット及びその他。名称：1F電話コーナーカウンター。
27
+ sentences:
28
+ - 科目：ユニット及びその他。名称：1・2階男子・女子更衣室カーテンレール。
29
+ - 科目：コンクリート。名称：鉄筋コンクリート（免震下部）。
30
+ - 科目：タイル。名称：EXP.J上床磁器質タイルA。
31
+ - source_sentence: 科目：ユニット及びその他。名称：4F透析室カウンター。
32
+ sentences:
33
+ - 科目：ユニット及びその他。名称：2F初療1、2カウンター。
34
+ - 科目：ユニット及びその他。名称：5Fファミリールームカウンター。
35
+ - 科目：ユニット及びその他。名称：9Fスタッフステーション1カウンター。
36
+ pipeline_tag: sentence-similarity
37
+ library_name: sentence-transformers
38
+ ---
39
+
40
+ # SentenceTransformer based on cl-nagoya/sup-simcse-ja-base
41
+
42
+ This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [cl-nagoya/sup-simcse-ja-base](https://huggingface.co/cl-nagoya/sup-simcse-ja-base). It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
43
+
44
+ ## Model Details
45
+
46
+ ### Model Description
47
+ - **Model Type:** Sentence Transformer
48
+ - **Base model:** [cl-nagoya/sup-simcse-ja-base](https://huggingface.co/cl-nagoya/sup-simcse-ja-base) <!-- at revision d7315d93baf2c20fffa2b6845330049963509f79 -->
49
+ - **Maximum Sequence Length:** 512 tokens
50
+ - **Output Dimensionality:** 768 dimensions
51
+ - **Similarity Function:** Cosine Similarity
52
+ <!-- - **Training Dataset:** Unknown -->
53
+ <!-- - **Language:** Unknown -->
54
+ <!-- - **License:** Unknown -->
55
+
56
+ ### Model Sources
57
+
58
+ - **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
59
+ - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
60
+ - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
61
+
62
+ ### Full Model Architecture
63
+
64
+ ```
65
+ SentenceTransformer(
66
+ (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
67
+ (1): Pooling({'word_embedding_dimension': 768, '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})
68
+ )
69
+ ```
70
+
71
+ ## Usage
72
+
73
+ ### Direct Usage (Sentence Transformers)
74
+
75
+ First install the Sentence Transformers library:
76
+
77
+ ```bash
78
+ pip install -U sentence-transformers
79
+ ```
80
+
81
+ Then you can load this model and run inference.
82
+ ```python
83
+ from sentence_transformers import SentenceTransformer
84
+
85
+ # Download from the 🤗 Hub
86
+ model = SentenceTransformer("Detomo/cl-nagoya-sup-simcse-ja-for-standard-name-v1_1")
87
+ # Run inference
88
+ sentences = [
89
+ '科目：ユニット及びその他。名称：4F透析室カウンター。',
90
+ '科目：ユニット及びその他。名称：2F初療1、2カウンター。',
91
+ '科目：ユニット及びその他。名称：9Fスタッフステーション1カウンター。',
92
+ ]
93
+ embeddings = model.encode(sentences)
94
+ print(embeddings.shape)
95
+ # [3, 768]
96
+
97
+ # Get the similarity scores for the embeddings
98
+ similarities = model.similarity(embeddings, embeddings)
99
+ print(similarities.shape)
100
+ # [3, 3]
101
+ ```
102
+
103
+ <!--
104
+ ### Direct Usage (Transformers)
105
+
106
+ <details><summary>Click to see the direct usage in Transformers</summary>
107
+
108
+ </details>
109
+ -->
110
+
111
+ <!--
112
+ ### Downstream Usage (Sentence Transformers)
113
+
114
+ You can finetune this model on your own dataset.
115
+
116
+ <details><summary>Click to expand</summary>
117
+
118
+ </details>
119
+ -->
120
+
121
+ <!--
122
+ ### Out-of-Scope Use
123
+
124
+ *List how the model may foreseeably be misused and address what users ought not to do with the model.*
125
+ -->
126
+
127
+ <!--
128
+ ## Bias, Risks and Limitations
129
+
130
+ *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
131
+ -->
132
+
133
+ <!--
134
+ ### Recommendations
135
+
136
+ *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
137
+ -->
138
+
139
+ ## Training Details
140
+
141
+ ### Training Dataset
142
+
143
+ #### Unnamed Dataset
144
+
145
+
146
+ * Size: 8,788 training samples
147
+ * Columns: <code>sentence</code> and <code>label</code>
148
+ * Approximate statistics based on the first 1000 samples:
149
+ | | sentence | label |
150
+ |:--------|:-----------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
151
+ | type | string | int |
152
+ | details | <ul><li>min: 13 tokens</li><li>mean: 23.19 tokens</li><li>max: 41 tokens</li></ul> | <ul><li>0: ~0.20%</li><li>1: ~0.30%</li><li>2: ~0.30%</li><li>3: ~0.30%</li><li>4: ~0.20%</li><li>5: ~0.20%</li><li>6: ~0.20%</li><li>7: ~0.20%</li><li>8: ~0.30%</li><li>9: ~0.30%</li><li>10: ~0.20%</li><li>11: ~0.20%</li><li>12: ~0.20%</li><li>13: ~0.20%</li><li>14: ~0.20%</li><li>15: ~0.20%</li><li>16: ~0.40%</li><li>17: ~0.20%</li><li>18: ~0.20%</li><li>19: ~0.20%</li><li>20: ~0.20%</li><li>21: ~0.20%</li><li>22: ~0.20%</li><li>23: ~0.20%</li><li>24: ~0.20%</li><li>25: ~0.20%</li><li>26: ~0.20%</li><li>27: ~0.20%</li><li>28: ~0.20%</li><li>29: ~0.20%</li><li>30: ~0.20%</li><li>31: ~0.20%</li><li>32: ~0.20%</li><li>33: ~0.20%</li><li>34: ~0.20%</li><li>35: ~0.20%</li><li>36: ~0.20%</li><li>37: ~0.20%</li><li>38: ~0.20%</li><li>39: ~0.20%</li><li>40: ~0.20%</li><li>41: ~0.20%</li><li>42: ~0.60%</li><li>43: ~0.70%</li><li>44: ~0.20%</li><li>45: ~0.30%</li><li>46: ~0.20%</li><li>47: ~0.20%</li><li>48: ~0.30%</li><li>49: ~0.20%</li><li>50: ~0.20%</li><li>51: ~0.20%</li><li>52: ~0.20%</li><li>53: ~0.30%</li><li>54: ~0.40%</li><li>55: ~0.30%</li><li>56: ~0.20%</li><li>57: ~0.20%</li><li>58: ~0.20%</li><li>59: ~0.20%</li><li>60: ~0.20%</li><li>61: ~0.30%</li><li>62: ~0.20%</li><li>63: ~0.20%</li><li>64: ~0.20%</li><li>65: ~0.20%</li><li>66: ~0.40%</li><li>67: ~0.40%</li><li>68: ~0.20%</li><li>69: ~0.60%</li><li>70: ~0.20%</li><li>71: ~0.20%</li><li>72: ~0.20%</li><li>73: ~0.20%</li><li>74: ~0.20%</li><li>75: ~0.30%</li><li>76: ~0.20%</li><li>77: ~0.40%</li><li>78: ~0.20%</li><li>79: ~0.20%</li><li>80: ~0.50%</li><li>81: ~0.30%</li><li>82: ~0.60%</li><li>83: ~0.20%</li><li>84: ~0.30%</li><li>85: ~0.20%</li><li>86: ~0.20%</li><li>87: ~0.20%</li><li>88: ~0.20%</li><li>89: ~1.10%</li><li>90: ~1.70%</li><li>91: ~2.20%</li><li>92: ~0.50%</li><li>93: ~0.20%</li><li>94: ~0.20%</li><li>95: ~1.60%</li><li>96: ~0.20%</li><li>97: ~0.20%</li><li>98: ~0.20%</li><li>99: ~0.20%</li><li>100: ~0.30%</li><li>101: ~1.70%</li><li>102: ~0.20%</li><li>103: ~0.20%</li><li>104: ~0.40%</li><li>105: ~0.40%</li><li>106: ~0.20%</li><li>107: ~0.20%</li><li>108: ~0.20%</li><li>109: ~1.10%</li><li>110: ~0.20%</li><li>111: ~0.40%</li><li>112: ~0.50%</li><li>113: ~0.20%</li><li>114: ~0.20%</li><li>115: ~0.20%</li><li>116: ~0.20%</li><li>117: ~0.50%</li><li>118: ~0.20%</li><li>119: ~0.20%</li><li>120: ~0.20%</li><li>121: ~0.20%</li><li>122: ~0.20%</li><li>123: ~0.20%</li><li>124: ~0.30%</li><li>125: ~0.20%</li><li>126: ~0.20%</li><li>127: ~0.20%</li><li>128: ~0.40%</li><li>129: ~0.20%</li><li>130: ~0.20%</li><li>131: ~0.20%</li><li>132: ~0.20%</li><li>133: ~0.20%</li><li>134: ~0.20%</li><li>135: ~0.20%</li><li>136: ~0.20%</li><li>137: ~0.20%</li><li>138: ~0.30%</li><li>139: ~0.20%</li><li>140: ~0.30%</li><li>141: ~0.30%</li><li>142: ~0.20%</li><li>143: ~0.20%</li><li>144: ~0.20%</li><li>145: ~0.20%</li><li>146: ~0.20%</li><li>147: ~0.20%</li><li>148: ~0.20%</li><li>149: ~0.20%</li><li>150: ~0.20%</li><li>151: ~0.20%</li><li>152: ~0.20%</li><li>153: ~0.20%</li><li>154: ~0.20%</li><li>155: ~0.20%</li><li>156: ~0.60%</li><li>157: ~0.20%</li><li>158: ~1.50%</li><li>159: ~0.20%</li><li>160: ~0.20%</li><li>161: ~0.20%</li><li>162: ~0.20%</li><li>163: ~0.50%</li><li>164: ~0.20%</li><li>165: ~0.20%</li><li>166: ~0.20%</li><li>167: ~0.20%</li><li>168: ~0.20%</li><li>169: ~0.30%</li><li>170: ~0.30%</li><li>171: ~0.20%</li><li>172: ~0.20%</li><li>173: ~1.30%</li><li>174: ~0.20%</li><li>175: ~0.20%</li><li>176: ~0.20%</li><li>177: ~0.20%</li><li>178: ~0.60%</li><li>179: ~0.20%</li><li>180: ~0.20%</li><li>181: ~0.20%</li><li>182: ~0.20%</li><li>183: ~0.20%</li><li>184: ~0.20%</li><li>185: ~0.30%</li><li>186: ~0.20%</li><li>187: ~0.20%</li><li>188: ~0.30%</li><li>189: ~0.20%</li><li>190: ~0.90%</li><li>191: ~0.30%</li><li>192: ~0.30%</li><li>193: ~0.20%</li><li>194: ~0.30%</li><li>195: ~0.20%</li><li>196: ~0.80%</li><li>197: ~0.20%</li><li>198: ~0.20%</li><li>199: ~0.30%</li><li>200: ~0.20%</li><li>201: ~0.20%</li><li>202: ~0.20%</li><li>203: ~0.20%</li><li>204: ~0.20%</li><li>205: ~1.20%</li><li>206: ~0.40%</li><li>207: ~0.20%</li><li>208: ~0.20%</li><li>209: ~0.20%</li><li>210: ~0.20%</li><li>211: ~0.30%</li><li>212: ~0.20%</li><li>213: ~0.80%</li><li>214: ~0.30%</li><li>215: ~0.20%</li><li>216: ~1.10%</li><li>217: ~0.30%</li><li>218: ~0.20%</li><li>219: ~0.20%</li><li>220: ~0.20%</li><li>221: ~0.20%</li><li>222: ~0.20%</li><li>223: ~0.20%</li><li>224: ~0.20%</li><li>225: ~0.30%</li><li>226: ~0.20%</li><li>227: ~0.90%</li><li>228: ~4.70%</li><li>229: ~0.20%</li><li>230: ~0.20%</li><li>231: ~0.20%</li><li>232: ~0.70%</li><li>233: ~0.20%</li><li>234: ~0.80%</li><li>235: ~0.20%</li><li>236: ~0.40%</li><li>237: ~0.30%</li><li>238: ~0.40%</li><li>239: ~0.20%</li><li>240: ~0.30%</li><li>241: ~0.50%</li><li>242: ~0.30%</li><li>243: ~0.20%</li><li>244: ~0.20%</li><li>245: ~0.30%</li><li>246: ~0.30%</li><li>247: ~0.30%</li><li>248: ~0.60%</li><li>249: ~0.20%</li><li>250: ~0.20%</li><li>251: ~0.20%</li><li>252: ~0.30%</li><li>253: ~0.30%</li><li>254: ~1.90%</li><li>255: ~0.20%</li><li>256: ~0.20%</li><li>257: ~0.20%</li><li>258: ~0.20%</li><li>259: ~0.20%</li><li>260: ~0.50%</li><li>261: ~0.20%</li><li>262: ~0.30%</li><li>263: ~0.20%</li><li>264: ~0.20%</li><li>265: ~1.00%</li><li>266: ~0.20%</li><li>267: ~0.20%</li><li>268: ~0.20%</li><li>269: ~0.40%</li><li>270: ~0.20%</li><li>271: ~0.20%</li><li>272: ~0.20%</li><li>273: ~0.20%</li><li>274: ~0.20%</li><li>275: ~0.20%</li><li>276: ~0.20%</li><li>277: ~3.70%</li><li>278: ~0.20%</li><li>279: ~0.40%</li><li>280: ~0.20%</li><li>281: ~0.20%</li><li>282: ~0.90%</li><li>283: ~0.40%</li><li>284: ~0.20%</li><li>285: ~2.30%</li><li>286: ~0.30%</li><li>287: ~0.20%</li><li>288: ~0.30%</li><li>289: ~0.60%</li></ul> |
153
+ * Samples:
154
+ | sentence | label |
155
+ |:----------------------------------------|:---------------|
156
+ | <code>科目：コンクリート。名称：免震基礎天端グラウト注入。</code> | <code>0</code> |
157
+ | <code>科目：コンクリート。名称：免震基礎天端グラウト注入。</code> | <code>0</code> |
158
+ | <code>科目：コンクリート。名称：コンクリートポンプ圧送。</code> | <code>1</code> |
159
+ * Loss: [<code>BatchAllTripletLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#batchalltripletloss)
160
+
161
+ ### Training Hyperparameters
162
+ #### Non-Default Hyperparameters
163
+
164
+ - `per_device_train_batch_size`: 256
165
+ - `per_device_eval_batch_size`: 256
166
+ - `learning_rate`: 1e-05
167
+ - `weight_decay`: 0.01
168
+ - `num_train_epochs`: 250
169
+ - `warmup_ratio`: 0.1
170
+ - `fp16`: True
171
+ - `batch_sampler`: group_by_label
172
+
173
+ #### All Hyperparameters
174
+ <details><summary>Click to expand</summary>
175
+
176
+ - `overwrite_output_dir`: False
177
+ - `do_predict`: False
178
+ - `eval_strategy`: no
179
+ - `prediction_loss_only`: True
180
+ - `per_device_train_batch_size`: 256
181
+ - `per_device_eval_batch_size`: 256
182
+ - `per_gpu_train_batch_size`: None
183
+ - `per_gpu_eval_batch_size`: None
184
+ - `gradient_accumulation_steps`: 1
185
+ - `eval_accumulation_steps`: None
186
+ - `torch_empty_cache_steps`: None
187
+ - `learning_rate`: 1e-05
188
+ - `weight_decay`: 0.01
189
+ - `adam_beta1`: 0.9
190
+ - `adam_beta2`: 0.999
191
+ - `adam_epsilon`: 1e-08
192
+ - `max_grad_norm`: 1.0
193
+ - `num_train_epochs`: 250
194
+ - `max_steps`: -1
195
+ - `lr_scheduler_type`: linear
196
+ - `lr_scheduler_kwargs`: {}
197
+ - `warmup_ratio`: 0.1
198
+ - `warmup_steps`: 0
199
+ - `log_level`: passive
200
+ - `log_level_replica`: warning
201
+ - `log_on_each_node`: True
202
+ - `logging_nan_inf_filter`: True
203
+ - `save_safetensors`: True
204
+ - `save_on_each_node`: False
205
+ - `save_only_model`: False
206
+ - `restore_callback_states_from_checkpoint`: False
207
+ - `no_cuda`: False
208
+ - `use_cpu`: False
209
+ - `use_mps_device`: False
210
+ - `seed`: 42
211
+ - `data_seed`: None
212
+ - `jit_mode_eval`: False
213
+ - `use_ipex`: False
214
+ - `bf16`: False
215
+ - `fp16`: True
216
+ - `fp16_opt_level`: O1
217
+ - `half_precision_backend`: auto
218
+ - `bf16_full_eval`: False
219
+ - `fp16_full_eval`: False
220
+ - `tf32`: None
221
+ - `local_rank`: 0
222
+ - `ddp_backend`: None
223
+ - `tpu_num_cores`: None
224
+ - `tpu_metrics_debug`: False
225
+ - `debug`: []
226
+ - `dataloader_drop_last`: False
227
+ - `dataloader_num_workers`: 0
228
+ - `dataloader_prefetch_factor`: None
229
+ - `past_index`: -1
230
+ - `disable_tqdm`: False
231
+ - `remove_unused_columns`: True
232
+ - `label_names`: None
233
+ - `load_best_model_at_end`: False
234
+ - `ignore_data_skip`: False
235
+ - `fsdp`: []
236
+ - `fsdp_min_num_params`: 0
237
+ - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
238
+ - `fsdp_transformer_layer_cls_to_wrap`: None
239
+ - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
240
+ - `deepspeed`: None
241
+ - `label_smoothing_factor`: 0.0
242
+ - `optim`: adamw_torch
243
+ - `optim_args`: None
244
+ - `adafactor`: False
245
+ - `group_by_length`: False
246
+ - `length_column_name`: length
247
+ - `ddp_find_unused_parameters`: None
248
+ - `ddp_bucket_cap_mb`: None
249
+ - `ddp_broadcast_buffers`: False
250
+ - `dataloader_pin_memory`: True
251
+ - `dataloader_persistent_workers`: False
252
+ - `skip_memory_metrics`: True
253
+ - `use_legacy_prediction_loop`: False
254
+ - `push_to_hub`: False
255
+ - `resume_from_checkpoint`: None
256
+ - `hub_model_id`: None
257
+ - `hub_strategy`: every_save
258
+ - `hub_private_repo`: None
259
+ - `hub_always_push`: False
260
+ - `gradient_checkpointing`: False
261
+ - `gradient_checkpointing_kwargs`: None
262
+ - `include_inputs_for_metrics`: False
263
+ - `include_for_metrics`: []
264
+ - `eval_do_concat_batches`: True
265
+ - `fp16_backend`: auto
266
+ - `push_to_hub_model_id`: None
267
+ - `push_to_hub_organization`: None
268
+ - `mp_parameters`:
269
+ - `auto_find_batch_size`: False
270
+ - `full_determinism`: False
271
+ - `torchdynamo`: None
272
+ - `ray_scope`: last
273
+ - `ddp_timeout`: 1800
274
+ - `torch_compile`: False
275
+ - `torch_compile_backend`: None
276
+ - `torch_compile_mode`: None
277
+ - `dispatch_batches`: None
278
+ - `split_batches`: None
279
+ - `include_tokens_per_second`: False
280
+ - `include_num_input_tokens_seen`: False
281
+ - `neftune_noise_alpha`: None
282
+ - `optim_target_modules`: None
283
+ - `batch_eval_metrics`: False
284
+ - `eval_on_start`: False
285
+ - `use_liger_kernel`: False
286
+ - `eval_use_gather_object`: False
287
+ - `average_tokens_across_devices`: False
288
+ - `prompts`: None
289
+ - `batch_sampler`: group_by_label
290
+ - `multi_dataset_batch_sampler`: proportional
291
+
292
+ </details>
293
+
294
+ ### Training Logs
295
+ <details><summary>Click to expand</summary>
296
+
297
+ | Epoch | Step | Training Loss |
298
+ |:--------:|:----:|:-------------:|
299
+ | 0.5714 | 20 | 0.787 |
300
+ | 1.2 | 40 | 0.7827 |
301
+ | 1.7714 | 60 | 0.7361 |
302
+ | 2.4 | 80 | 0.6798 |
303
+ | 3.0286 | 100 | 0.6569 |
304
+ | 3.6 | 120 | 0.6669 |
305
+ | 4.2286 | 140 | 0.6163 |
306
+ | 4.8 | 160 | 0.6277 |
307
+ | 5.4286 | 180 | 0.6449 |
308
+ | 6.0571 | 200 | 0.6135 |
309
+ | 6.6286 | 220 | 0.6445 |
310
+ | 7.2571 | 240 | 0.6572 |
311
+ | 7.8286 | 260 | 0.6268 |
312
+ | 8.4571 | 280 | 0.6034 |
313
+ | 9.0857 | 300 | 0.5598 |
314
+ | 9.6571 | 320 | 0.5801 |
315
+ | 10.2857 | 340 | 0.5471 |
316
+ | 10.8571 | 360 | 0.6579 |
317
+ | 11.4857 | 380 | 0.6059 |
318
+ | 12.1143 | 400 | 0.5715 |
319
+ | 12.6857 | 420 | 0.5986 |
320
+ | 13.3143 | 440 | 0.5601 |
321
+ | 13.8857 | 460 | 0.5547 |
322
+ | 14.5143 | 480 | 0.5642 |
323
+ | 15.1429 | 500 | 0.697 |
324
+ | 15.7143 | 520 | 0.5688 |
325
+ | 16.3429 | 540 | 0.5736 |
326
+ | 16.9143 | 560 | 0.5088 |
327
+ | 17.5429 | 580 | 0.5677 |
328
+ | 18.1714 | 600 | 0.6028 |
329
+ | 18.7429 | 620 | 0.5674 |
330
+ | 19.3714 | 640 | 0.5665 |
331
+ | 19.9429 | 660 | 0.6289 |
332
+ | 20.5714 | 680 | 0.5456 |
333
+ | 21.2 | 700 | 0.4944 |
334
+ | 21.7714 | 720 | 0.5712 |
335
+ | 22.4 | 740 | 0.6106 |
336
+ | 23.0286 | 760 | 0.5209 |
337
+ | 23.6 | 780 | 0.5236 |
338
+ | 24.2286 | 800 | 0.6091 |
339
+ | 24.8 | 820 | 0.6678 |
340
+ | 25.4286 | 840 | 0.4693 |
341
+ | 26.0571 | 860 | 0.4582 |
342
+ | 26.6286 | 880 | 0.5627 |
343
+ | 27.2571 | 900 | 0.5525 |
344
+ | 27.8286 | 920 | 0.503 |
345
+ | 28.4571 | 940 | 0.4801 |
346
+ | 29.0857 | 960 | 0.5039 |
347
+ | 29.6571 | 980 | 0.5049 |
348
+ | 30.2857 | 1000 | 0.595 |
349
+ | 30.8571 | 1020 | 0.4733 |
350
+ | 31.4857 | 1040 | 0.5804 |
351
+ | 32.1143 | 1060 | 0.4101 |
352
+ | 32.6857 | 1080 | 0.4311 |
353
+ | 33.3143 | 1100 | 0.4746 |
354
+ | 33.8857 | 1120 | 0.4964 |
355
+ | 34.5143 | 1140 | 0.4436 |
356
+ | 35.1429 | 1160 | 0.6351 |
357
+ | 35.7143 | 1180 | 0.5267 |
358
+ | 36.3429 | 1200 | 0.4685 |
359
+ | 36.9143 | 1220 | 0.4201 |
360
+ | 37.5429 | 1240 | 0.4256 |
361
+ | 38.1714 | 1260 | 0.5543 |
362
+ | 38.7429 | 1280 | 0.5176 |
363
+ | 39.3714 | 1300 | 0.4328 |
364
+ | 39.9429 | 1320 | 0.4746 |
365
+ | 40.5714 | 1340 | 0.4768 |
366
+ | 41.2 | 1360 | 0.4663 |
367
+ | 41.7714 | 1380 | 0.4729 |
368
+ | 42.4 | 1400 | 0.4141 |
369
+ | 43.0286 | 1420 | 0.3195 |
370
+ | 43.6 | 1440 | 0.3789 |
371
+ | 44.2286 | 1460 | 0.4032 |
372
+ | 44.8 | 1480 | 0.443 |
373
+ | 45.4286 | 1500 | 0.4116 |
374
+ | 46.0571 | 1520 | 0.4951 |
375
+ | 46.6286 | 1540 | 0.3845 |
376
+ | 47.2571 | 1560 | 0.3461 |
377
+ | 47.8286 | 1580 | 0.4754 |
378
+ | 48.4571 | 1600 | 0.5583 |
379
+ | 49.0857 | 1620 | 0.4282 |
380
+ | 49.6571 | 1640 | 0.436 |
381
+ | 50.2857 | 1660 | 0.4097 |
382
+ | 50.8571 | 1680 | 0.4642 |
383
+ | 51.4857 | 1700 | 0.3243 |
384
+ | 52.1143 | 1720 | 0.4395 |
385
+ | 52.6857 | 1740 | 0.3672 |
386
+ | 53.3143 | 1760 | 0.4781 |
387
+ | 53.8857 | 1780 | 0.5362 |
388
+ | 54.5143 | 1800 | 0.4401 |
389
+ | 55.1429 | 1820 | 0.4313 |
390
+ | 55.7143 | 1840 | 0.2751 |
391
+ | 56.3429 | 1860 | 0.331 |
392
+ | 56.9143 | 1880 | 0.4325 |
393
+ | 57.5429 | 1900 | 0.2995 |
394
+ | 58.1714 | 1920 | 0.4159 |
395
+ | 58.7429 | 1940 | 0.5603 |
396
+ | 59.3714 | 1960 | 0.4575 |
397
+ | 59.9429 | 1980 | 0.4677 |
398
+ | 60.5714 | 2000 | 0.4653 |
399
+ | 61.2 | 2020 | 0.3098 |
400
+ | 61.7714 | 2040 | 0.3188 |
401
+ | 62.4 | 2060 | 0.3769 |
402
+ | 63.0286 | 2080 | 0.2902 |
403
+ | 63.6 | 2100 | 0.4064 |
404
+ | 64.2286 | 2120 | 0.3663 |
405
+ | 64.8 | 2140 | 0.3184 |
406
+ | 65.4286 | 2160 | 0.4874 |
407
+ | 66.0571 | 2180 | 0.4094 |
408
+ | 66.6286 | 2200 | 0.4261 |
409
+ | 67.2571 | 2220 | 0.3808 |
410
+ | 67.8286 | 2240 | 0.2991 |
411
+ | 68.4571 | 2260 | 0.3242 |
412
+ | 69.0857 | 2280 | 0.2582 |
413
+ | 69.6571 | 2300 | 0.3806 |
414
+ | 70.2857 | 2320 | 0.3573 |
415
+ | 70.8571 | 2340 | 0.3183 |
416
+ | 71.4857 | 2360 | 0.4043 |
417
+ | 72.1143 | 2380 | 0.4266 |
418
+ | 72.6857 | 2400 | 0.5612 |
419
+ | 73.3143 | 2420 | 0.3476 |
420
+ | 73.8857 | 2440 | 0.3018 |
421
+ | 74.5143 | 2460 | 0.2952 |
422
+ | 75.1429 | 2480 | 0.2633 |
423
+ | 75.7143 | 2500 | 0.3564 |
424
+ | 76.3429 | 2520 | 0.2283 |
425
+ | 76.9143 | 2540 | 0.3615 |
426
+ | 77.5429 | 2560 | 0.2174 |
427
+ | 78.1714 | 2580 | 0.3049 |
428
+ | 78.7429 | 2600 | 0.2838 |
429
+ | 79.3714 | 2620 | 0.3191 |
430
+ | 79.9429 | 2640 | 0.2529 |
431
+ | 80.5714 | 2660 | 0.3192 |
432
+ | 81.2 | 2680 | 0.5119 |
433
+ | 81.7714 | 2700 | 0.2459 |
434
+ | 82.4 | 2720 | 0.4136 |
435
+ | 83.0286 | 2740 | 0.3266 |
436
+ | 83.6 | 2760 | 0.2863 |
437
+ | 84.2286 | 2780 | 0.3563 |
438
+ | 84.8 | 2800 | 0.2605 |
439
+ | 85.4286 | 2820 | 0.254 |
440
+ | 86.0571 | 2840 | 0.2252 |
441
+ | 86.6286 | 2860 | 0.3191 |
442
+ | 87.2571 | 2880 | 0.3074 |
443
+ | 87.8286 | 2900 | 0.274 |
444
+ | 88.4571 | 2920 | 0.3864 |
445
+ | 89.0857 | 2940 | 0.3206 |
446
+ | 89.6571 | 2960 | 0.2752 |
447
+ | 90.2857 | 2980 | 0.2033 |
448
+ | 90.8571 | 3000 | 0.3979 |
449
+ | 91.4857 | 3020 | 0.4327 |
450
+ | 92.1143 | 3040 | 0.1999 |
451
+ | 92.6857 | 3060 | 0.3939 |
452
+ | 93.3143 | 3080 | 0.2733 |
453
+ | 93.8857 | 3100 | 0.4334 |
454
+ | 94.5143 | 3120 | 0.3726 |
455
+ | 95.1429 | 3140 | 0.2567 |
456
+ | 95.7143 | 3160 | 0.258 |
457
+ | 96.3429 | 3180 | 0.1805 |
458
+ | 96.9143 | 3200 | 0.3244 |
459
+ | 97.5429 | 3220 | 0.2038 |
460
+ | 98.1714 | 3240 | 0.2689 |
461
+ | 98.7429 | 3260 | 0.433 |
462
+ | 99.3714 | 3280 | 0.1587 |
463
+ | 99.9429 | 3300 | 0.3088 |
464
+ | 100.5714 | 3320 | 0.3049 |
465
+ | 101.2 | 3340 | 0.335 |
466
+ | 101.7714 | 3360 | 0.2688 |
467
+ | 102.4 | 3380 | 0.359 |
468
+ | 103.0286 | 3400 | 0.2512 |
469
+ | 103.6 | 3420 | 0.2818 |
470
+ | 104.2286 | 3440 | 0.3606 |
471
+ | 104.8 | 3460 | 0.3254 |
472
+ | 105.4286 | 3480 | 0.2487 |
473
+ | 106.0571 | 3500 | 0.2184 |
474
+ | 106.6286 | 3520 | 0.2897 |
475
+ | 107.2571 | 3540 | 0.2849 |
476
+ | 107.8286 | 3560 | 0.362 |
477
+ | 108.4571 | 3580 | 0.2418 |
478
+ | 109.0857 | 3600 | 0.1498 |
479
+ | 109.6571 | 3620 | 0.2566 |
480
+ | 110.2857 | 3640 | 0.1181 |
481
+ | 110.8571 | 3660 | 0.3675 |
482
+ | 111.4857 | 3680 | 0.2722 |
483
+ | 112.1143 | 3700 | 0.3779 |
484
+ | 112.6857 | 3720 | 0.3882 |
485
+ | 113.3143 | 3740 | 0.1941 |
486
+ | 113.8857 | 3760 | 0.2281 |
487
+ | 114.5143 | 3780 | 0.2079 |
488
+ | 115.1429 | 3800 | 0.3443 |
489
+ | 115.7143 | 3820 | 0.2763 |
490
+ | 116.3429 | 3840 | 0.2331 |
491
+ | 116.9143 | 3860 | 0.2093 |
492
+ | 117.5429 | 3880 | 0.2439 |
493
+ | 118.1714 | 3900 | 0.1312 |
494
+ | 118.7429 | 3920 | 0.1098 |
495
+ | 119.3714 | 3940 | 0.2295 |
496
+ | 119.9429 | 3960 | 0.2501 |
497
+ | 120.5714 | 3980 | 0.3522 |
498
+ | 121.2 | 4000 | 0.3293 |
499
+ | 121.7714 | 4020 | 0.1698 |
500
+ | 122.4 | 4040 | 0.3992 |
501
+ | 123.0286 | 4060 | 0.1931 |
502
+ | 123.6 | 4080 | 0.1755 |
503
+ | 124.2286 | 4100 | 0.3408 |
504
+ | 124.8 | 4120 | 0.2337 |
505
+ | 125.4286 | 4140 | 0.2121 |
506
+ | 126.0571 | 4160 | 0.1628 |
507
+ | 126.6286 | 4180 | 0.2455 |
508
+ | 127.2571 | 4200 | 0.3342 |
509
+ | 127.8286 | 4220 | 0.1725 |
510
+ | 128.4571 | 4240 | 0.3714 |
511
+ | 129.0857 | 4260 | 0.2775 |
512
+ | 129.6571 | 4280 | 0.1764 |
513
+ | 130.2857 | 4300 | 0.1863 |
514
+ | 130.8571 | 4320 | 0.276 |
515
+ | 131.4857 | 4340 | 0.2006 |
516
+ | 132.1143 | 4360 | 0.2099 |
517
+ | 132.6857 | 4380 | 0.2397 |
518
+ | 133.3143 | 4400 | 0.223 |
519
+ | 133.8857 | 4420 | 0.1321 |
520
+ | 134.5143 | 4440 | 0.2499 |
521
+ | 135.1429 | 4460 | 0.2107 |
522
+ | 135.7143 | 4480 | 0.2374 |
523
+ | 136.3429 | 4500 | 0.2589 |
524
+ | 136.9143 | 4520 | 0.2382 |
525
+ | 137.5429 | 4540 | 0.1058 |
526
+ | 138.1714 | 4560 | 0.2519 |
527
+ | 138.7429 | 4580 | 0.23 |
528
+ | 139.3714 | 4600 | 0.2031 |
529
+ | 139.9429 | 4620 | 0.2424 |
530
+ | 140.5714 | 4640 | 0.1312 |
531
+ | 141.2 | 4660 | 0.1787 |
532
+ | 141.7714 | 4680 | 0.2445 |
533
+ | 142.4 | 4700 | 0.1948 |
534
+ | 143.0286 | 4720 | 0.2601 |
535
+ | 143.6 | 4740 | 0.1906 |
536
+ | 144.2286 | 4760 | 0.35 |
537
+ | 144.8 | 4780 | 0.1674 |
538
+ | 145.4286 | 4800 | 0.2339 |
539
+ | 146.0571 | 4820 | 0.2151 |
540
+ | 146.6286 | 4840 | 0.1986 |
541
+ | 147.2571 | 4860 | 0.1608 |
542
+ | 147.8286 | 4880 | 0.2729 |
543
+ | 148.4571 | 4900 | 0.1555 |
544
+ | 149.0857 | 4920 | 0.1536 |
545
+ | 149.6571 | 4940 | 0.1245 |
546
+ | 150.2857 | 4960 | 0.2635 |
547
+ | 150.8571 | 4980 | 0.1628 |
548
+ | 151.4857 | 5000 | 0.1869 |
549
+ | 152.1143 | 5020 | 0.2142 |
550
+ | 152.6857 | 5040 | 0.1867 |
551
+ | 153.3143 | 5060 | 0.2361 |
552
+ | 153.8857 | 5080 | 0.1811 |
553
+ | 154.5143 | 5100 | 0.4071 |
554
+ | 155.1429 | 5120 | 0.2499 |
555
+ | 155.7143 | 5140 | 0.2398 |
556
+ | 156.3429 | 5160 | 0.1486 |
557
+ | 156.9143 | 5180 | 0.1683 |
558
+ | 157.5429 | 5200 | 0.1434 |
559
+ | 158.1714 | 5220 | 0.1731 |
560
+ | 158.7429 | 5240 | 0.1674 |
561
+ | 159.3714 | 5260 | 0.1085 |
562
+ | 159.9429 | 5280 | 0.2573 |
563
+ | 160.5714 | 5300 | 0.1937 |
564
+ | 161.2 | 5320 | 0.0806 |
565
+ | 161.7714 | 5340 | 0.1411 |
566
+ | 162.4 | 5360 | 0.1603 |
567
+ | 163.0286 | 5380 | 0.1787 |
568
+ | 163.6 | 5400 | 0.2099 |
569
+ | 164.2286 | 5420 | 0.2676 |
570
+ | 164.8 | 5440 | 0.2658 |
571
+ | 165.4286 | 5460 | 0.2632 |
572
+ | 166.0571 | 5480 | 0.1839 |
573
+ | 166.6286 | 5500 | 0.2524 |
574
+ | 167.2571 | 5520 | 0.2018 |
575
+ | 167.8286 | 5540 | 0.2955 |
576
+ | 168.4571 | 5560 | 0.209 |
577
+ | 169.0857 | 5580 | 0.1999 |
578
+ | 169.6571 | 5600 | 0.2836 |
579
+ | 170.2857 | 5620 | 0.1559 |
580
+ | 170.8571 | 5640 | 0.2746 |
581
+ | 171.4857 | 5660 | 0.1939 |
582
+ | 172.1143 | 5680 | 0.1561 |
583
+ | 172.6857 | 5700 | 0.0935 |
584
+ | 173.3143 | 5720 | 0.1927 |
585
+ | 173.8857 | 5740 | 0.3022 |
586
+ | 174.5143 | 5760 | 0.2068 |
587
+ | 175.1429 | 5780 | 0.1384 |
588
+ | 175.7143 | 5800 | 0.086 |
589
+ | 176.3429 | 5820 | 0.1181 |
590
+ | 176.9143 | 5840 | 0.3145 |
591
+ | 177.5429 | 5860 | 0.0974 |
592
+ | 178.1714 | 5880 | 0.1891 |
593
+ | 178.7429 | 5900 | 0.1788 |
594
+ | 179.3714 | 5920 | 0.1954 |
595
+ | 179.9429 | 5940 | 0.1342 |
596
+ | 180.5714 | 5960 | 0.0936 |
597
+ | 181.2 | 5980 | 0.3109 |
598
+ | 181.7714 | 6000 | 0.1879 |
599
+ | 182.4 | 6020 | 0.0798 |
600
+ | 183.0286 | 6040 | 0.097 |
601
+ | 183.6 | 6060 | 0.0835 |
602
+ | 184.2286 | 6080 | 0.0931 |
603
+ | 184.8 | 6100 | 0.1377 |
604
+ | 185.4286 | 6120 | 0.1239 |
605
+ | 186.0571 | 6140 | 0.0307 |
606
+ | 186.6286 | 6160 | 0.1962 |
607
+ | 187.2571 | 6180 | 0.242 |
608
+ | 187.8286 | 6200 | 0.0886 |
609
+ | 188.4571 | 6220 | 0.2103 |
610
+ | 189.0857 | 6240 | 0.0746 |
611
+ | 189.6571 | 6260 | 0.1191 |
612
+ | 190.2857 | 6280 | 0.2356 |
613
+ | 190.8571 | 6300 | 0.2015 |
614
+ | 191.4857 | 6320 | 0.1728 |
615
+ | 192.1143 | 6340 | 0.1624 |
616
+ | 192.6857 | 6360 | 0.2528 |
617
+ | 193.3143 | 6380 | 0.0759 |
618
+ | 193.8857 | 6400 | 0.2138 |
619
+ | 194.5143 | 6420 | 0.1544 |
620
+ | 195.1429 | 6440 | 0.2444 |
621
+ | 195.7143 | 6460 | 0.1896 |
622
+ | 196.3429 | 6480 | 0.1646 |
623
+ | 196.9143 | 6500 | 0.1305 |
624
+ | 197.5429 | 6520 | 0.1379 |
625
+ | 198.1714 | 6540 | 0.1845 |
626
+ | 198.7429 | 6560 | 0.1997 |
627
+ | 199.3714 | 6580 | 0.2049 |
628
+ | 199.9429 | 6600 | 0.2891 |
629
+ | 200.5714 | 6620 | 0.1718 |
630
+ | 201.2 | 6640 | 0.1449 |
631
+ | 201.7714 | 6660 | 0.2096 |
632
+ | 202.4 | 6680 | 0.1056 |
633
+ | 203.0286 | 6700 | 0.0862 |
634
+ | 203.6 | 6720 | 0.0914 |
635
+ | 204.2286 | 6740 | 0.2433 |
636
+ | 204.8 | 6760 | 0.146 |
637
+ | 205.4286 | 6780 | 0.2099 |
638
+ | 206.0571 | 6800 | 0.0877 |
639
+ | 206.6286 | 6820 | 0.1194 |
640
+ | 207.2571 | 6840 | 0.069 |
641
+ | 207.8286 | 6860 | 0.0742 |
642
+ | 208.4571 | 6880 | 0.2773 |
643
+ | 209.0857 | 6900 | 0.1762 |
644
+ | 209.6571 | 6920 | 0.1573 |
645
+ | 210.2857 | 6940 | 0.0922 |
646
+ | 210.8571 | 6960 | 0.1366 |
647
+ | 211.4857 | 6980 | 0.0746 |
648
+ | 212.1143 | 7000 | 0.2004 |
649
+ | 212.6857 | 7020 | 0.0922 |
650
+ | 213.3143 | 7040 | 0.0662 |
651
+ | 213.8857 | 7060 | 0.1828 |
652
+ | 214.5143 | 7080 | 0.1202 |
653
+ | 215.1429 | 7100 | 0.1388 |
654
+ | 215.7143 | 7120 | 0.0638 |
655
+ | 216.3429 | 7140 | 0.2259 |
656
+ | 216.9143 | 7160 | 0.1219 |
657
+ | 217.5429 | 7180 | 0.1599 |
658
+ | 218.1714 | 7200 | 0.2424 |
659
+ | 218.7429 | 7220 | 0.149 |
660
+ | 219.3714 | 7240 | 0.272 |
661
+ | 219.9429 | 7260 | 0.1051 |
662
+ | 220.5714 | 7280 | 0.2117 |
663
+ | 221.2 | 7300 | 0.1466 |
664
+ | 221.7714 | 7320 | 0.1155 |
665
+ | 222.4 | 7340 | 0.2247 |
666
+ | 223.0286 | 7360 | 0.096 |
667
+ | 223.6 | 7380 | 0.0566 |
668
+ | 224.2286 | 7400 | 0.2404 |
669
+ | 224.8 | 7420 | 0.1684 |
670
+ | 225.4286 | 7440 | 0.0927 |
671
+ | 226.0571 | 7460 | 0.1746 |
672
+ | 226.6286 | 7480 | 0.13 |
673
+ | 227.2571 | 7500 | 0.1027 |
674
+ | 227.8286 | 7520 | 0.1359 |
675
+ | 228.4571 | 7540 | 0.0937 |
676
+ | 229.0857 | 7560 | 0.1378 |
677
+ | 229.6571 | 7580 | 0.0458 |
678
+ | 230.2857 | 7600 | 0.0766 |
679
+ | 230.8571 | 7620 | 0.0896 |
680
+ | 231.4857 | 7640 | 0.1541 |
681
+ | 232.1143 | 7660 | 0.1464 |
682
+ | 232.6857 | 7680 | 0.1427 |
683
+ | 233.3143 | 7700 | 0.2471 |
684
+ | 233.8857 | 7720 | 0.1636 |
685
+ | 234.5143 | 7740 | 0.1601 |
686
+ | 235.1429 | 7760 | 0.1583 |
687
+ | 235.7143 | 7780 | 0.1473 |
688
+ | 236.3429 | 7800 | 0.1211 |
689
+ | 236.9143 | 7820 | 0.1582 |
690
+ | 237.5429 | 7840 | 0.1083 |
691
+ | 238.1714 | 7860 | 0.2014 |
692
+ | 238.7429 | 7880 | 0.0981 |
693
+ | 239.3714 | 7900 | 0.2449 |
694
+ | 239.9429 | 7920 | 0.1142 |
695
+ | 240.5714 | 7940 | 0.1177 |
696
+ | 241.2 | 7960 | 0.1241 |
697
+ | 241.7714 | 7980 | 0.2778 |
698
+ | 242.4 | 8000 | 0.1066 |
699
+ | 243.0286 | 8020 | 0.0867 |
700
+ | 243.6 | 8040 | 0.156 |
701
+ | 244.2286 | 8060 | 0.1413 |
702
+ | 244.8 | 8080 | 0.0598 |
703
+ | 245.4286 | 8100 | 0.1206 |
704
+ | 246.0571 | 8120 | 0.1883 |
705
+ | 246.6286 | 8140 | 0.1245 |
706
+ | 247.2571 | 8160 | 0.0949 |
707
+ | 247.8286 | 8180 | 0.1096 |
708
+ | 248.4571 | 8200 | 0.1567 |
709
+ | 249.0857 | 8220 | 0.065 |
710
+ | 249.6571 | 8240 | 0.1075 |
711
+
712
+ </details>
713
+
714
+ ### Framework Versions
715
+ - Python: 3.11.11
716
+ - Sentence Transformers: 3.3.1
717
+ - Transformers: 4.48.3
718
+ - PyTorch: 2.5.1+cu124
719
+ - Accelerate: 1.3.0
720
+ - Datasets: 3.3.2
721
+ - Tokenizers: 0.21.0
722
+
723
+ ## Citation
724
+
725
+ ### BibTeX
726
+
727
+ #### Sentence Transformers
728
+ ```bibtex
729
+ @inproceedings{reimers-2019-sentence-bert,
730
+ title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
731
+ author = "Reimers, Nils and Gurevych, Iryna",
732
+ booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
733
+ month = "11",
734
+ year = "2019",
735
+ publisher = "Association for Computational Linguistics",
736
+ url = "https://arxiv.org/abs/1908.10084",
737
+ }
738
+ ```
739
+
740
+ #### BatchAllTripletLoss
741
+ ```bibtex
742
+ @misc{hermans2017defense,
743
+ title={In Defense of the Triplet Loss for Person Re-Identification},
744
+ author={Alexander Hermans and Lucas Beyer and Bastian Leibe},
745
+ year={2017},
746
+ eprint={1703.07737},
747
+ archivePrefix={arXiv},
748
+ primaryClass={cs.CV}
749
+ }
750
+ ```
751
+
752
+ <!--
753
+ ## Glossary
754
+
755
+ *Clearly define terms in order to be accessible across audiences.*
756
+ -->
757
+
758
+ <!--
759
+ ## Model Card Authors
760
+
761
+ *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
762
+ -->
763
+
764
+ <!--
765
+ ## Model Card Contact
766
+
767
+ *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
768
+ -->
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cl-nagoya/sup-simcse-ja-base",
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": "4.48.3",
22
+ "type_vocab_size": 2,
23
+ "use_cache": true,
24
+ "vocab_size": 32768
25
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.48.3",
5
+ "pytorch": "2.5.1+cu124"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b34777f10626d2c1bb546159872a3d7f6da77cbe0ec8fba4ceba436e88a931
3
+ size 444851048
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
+ ]
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 +1,7 @@
 
 
 
 
 
 
 
 
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 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "do_subword_tokenize": true,
49
+ "do_word_tokenize": true,
50
+ "extra_special_tokens": {},
51
+ "jumanpp_kwargs": null,
52
+ "mask_token": "[MASK]",
53
+ "mecab_kwargs": {
54
+ "mecab_dic": "unidic_lite"
55
+ },
56
+ "model_max_length": 512,
57
+ "never_split": null,
58
+ "pad_token": "[PAD]",
59
+ "sep_token": "[SEP]",
60
+ "strip_accents": null,
61
+ "subword_tokenizer_type": "wordpiece",
62
+ "sudachi_kwargs": null,
63
+ "tokenize_chinese_chars": true,
64
+ "tokenizer_class": "BertTokenizer",
65
+ "unk_token": "[UNK]",
66
+ "word_tokenizer_type": "mecab"
67
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff