Add new SentenceTransformer model.
Browse files- README.md +531 -164
- checkpoint-84/1_Pooling/config.json +10 -0
- checkpoint-84/README.md +567 -0
- checkpoint-84/added_tokens.json +3 -0
- checkpoint-84/config.json +33 -0
- checkpoint-84/config_sentence_transformers.json +10 -0
- checkpoint-84/model.safetensors +3 -0
- checkpoint-84/modules.json +14 -0
- checkpoint-84/optimizer.pt +3 -0
- checkpoint-84/rng_state.pth +3 -0
- checkpoint-84/scheduler.pt +3 -0
- checkpoint-84/sentence_bert_config.json +4 -0
- checkpoint-84/special_tokens_map.json +15 -0
- checkpoint-84/spm.model +3 -0
- checkpoint-84/tokenizer.json +0 -0
- checkpoint-84/tokenizer_config.json +65 -0
- checkpoint-84/trainer_state.json +733 -0
- checkpoint-84/training_args.bin +3 -0
- checkpoint-90/1_Pooling/config.json +10 -0
- checkpoint-90/README.md +568 -0
- checkpoint-90/added_tokens.json +3 -0
- checkpoint-90/config.json +33 -0
- checkpoint-90/config_sentence_transformers.json +10 -0
- checkpoint-90/model.safetensors +3 -0
- checkpoint-90/modules.json +14 -0
- checkpoint-90/optimizer.pt +3 -0
- checkpoint-90/rng_state.pth +3 -0
- checkpoint-90/scheduler.pt +3 -0
- checkpoint-90/sentence_bert_config.json +4 -0
- checkpoint-90/special_tokens_map.json +15 -0
- checkpoint-90/spm.model +3 -0
- checkpoint-90/tokenizer.json +0 -0
- checkpoint-90/tokenizer_config.json +65 -0
- checkpoint-90/trainer_state.json +783 -0
- checkpoint-90/training_args.bin +3 -0
- model.safetensors +1 -1
- runs/Sep17_23-02-23_default/events.out.tfevents.1726614145.default.7803.0 +3 -0
README.md
CHANGED
|
@@ -1,201 +1,568 @@
|
|
| 1 |
---
|
| 2 |
base_model: colorfulscoop/sbert-base-ja
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
-
#
|
| 9 |
-
|
| 10 |
-
<!-- Provide a quick summary of what the model is/does. -->
|
| 11 |
-
|
| 12 |
|
|
|
|
| 13 |
|
| 14 |
## Model Details
|
| 15 |
|
| 16 |
### Model Description
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
-
|
| 19 |
-
|
| 20 |
-
Generates similarity embeddings
|
| 21 |
-
|
| 22 |
-
- **Developed by:** [More Information Needed]
|
| 23 |
-
- **Funded by [optional]:** [More Information Needed]
|
| 24 |
-
- **Shared by [optional]:** [More Information Needed]
|
| 25 |
-
- **Model type:** [More Information Needed]
|
| 26 |
-
- **Language(s) (NLP):** ja
|
| 27 |
-
- **License:** cc-by-sa-4.0
|
| 28 |
-
- **Finetuned from model [optional]:** colorfulscoop/sbert-base-ja
|
| 29 |
-
|
| 30 |
-
### Model Sources [optional]
|
| 31 |
-
|
| 32 |
-
<!-- Provide the basic links for the model. -->
|
| 33 |
-
|
| 34 |
-
- **Repository:** [More Information Needed]
|
| 35 |
-
- **Paper [optional]:** [More Information Needed]
|
| 36 |
-
- **Demo [optional]:** [More Information Needed]
|
| 37 |
-
|
| 38 |
-
## Uses
|
| 39 |
-
|
| 40 |
-
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 41 |
|
| 42 |
-
|
|
|
|
|
|
|
| 43 |
|
| 44 |
-
|
| 45 |
|
| 46 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 47 |
|
| 48 |
-
|
| 49 |
|
| 50 |
-
|
| 51 |
|
| 52 |
-
|
| 53 |
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
[More Information Needed]
|
| 59 |
|
| 60 |
-
|
|
|
|
|
|
|
| 61 |
|
| 62 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
|
| 64 |
-
|
| 65 |
-
|
| 66 |
-
|
|
|
|
|
|
|
| 67 |
|
| 68 |
-
<!--
|
|
|
|
| 69 |
|
| 70 |
-
|
| 71 |
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
Use the code below to get started with the model.
|
| 75 |
-
|
| 76 |
-
[More Information Needed]
|
| 77 |
-
|
| 78 |
-
## Training Details
|
| 79 |
|
| 80 |
-
|
|
|
|
| 81 |
|
| 82 |
-
|
| 83 |
|
| 84 |
-
|
| 85 |
|
| 86 |
-
|
|
|
|
| 87 |
|
| 88 |
-
<!--
|
| 89 |
-
|
| 90 |
-
#### Preprocessing [optional]
|
| 91 |
-
|
| 92 |
-
[More Information Needed]
|
| 93 |
-
|
| 94 |
-
|
| 95 |
-
#### Training Hyperparameters
|
| 96 |
-
|
| 97 |
-
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 98 |
-
|
| 99 |
-
#### Speeds, Sizes, Times [optional]
|
| 100 |
-
|
| 101 |
-
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 102 |
|
| 103 |
-
|
|
|
|
| 104 |
|
| 105 |
## Evaluation
|
| 106 |
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
|
| 122 |
-
|
| 123 |
-
|
| 124 |
-
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
|
| 128 |
-
|
| 129 |
-
|
| 130 |
-
|
| 131 |
-
|
| 132 |
-
|
| 133 |
-
|
| 134 |
-
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
|
| 144 |
-
|
| 145 |
-
|
| 146 |
-
|
| 147 |
-
|
| 148 |
-
|
| 149 |
-
|
| 150 |
-
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
|
| 159 |
-
[More Information Needed]
|
| 160 |
-
|
| 161 |
-
### Compute Infrastructure
|
| 162 |
-
|
| 163 |
-
[More Information Needed]
|
| 164 |
-
|
| 165 |
-
#### Hardware
|
| 166 |
-
|
| 167 |
-
[More Information Needed]
|
| 168 |
-
|
| 169 |
-
#### Software
|
| 170 |
-
|
| 171 |
-
[More Information Needed]
|
| 172 |
-
|
| 173 |
-
## Citation [optional]
|
| 174 |
-
|
| 175 |
-
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 176 |
-
|
| 177 |
-
**BibTeX:**
|
| 178 |
-
|
| 179 |
-
[More Information Needed]
|
| 180 |
-
|
| 181 |
-
**APA:**
|
| 182 |
-
|
| 183 |
-
[More Information Needed]
|
| 184 |
-
|
| 185 |
-
## Glossary [optional]
|
| 186 |
-
|
| 187 |
-
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 188 |
-
|
| 189 |
-
[More Information Needed]
|
| 190 |
-
|
| 191 |
-
## More Information [optional]
|
| 192 |
-
|
| 193 |
-
[More Information Needed]
|
| 194 |
|
| 195 |
-
|
|
|
|
| 196 |
|
| 197 |
-
|
| 198 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 199 |
## Model Card Contact
|
| 200 |
|
| 201 |
-
|
|
|
|
|
|
| 1 |
---
|
| 2 |
base_model: colorfulscoop/sbert-base-ja
|
| 3 |
+
library_name: sentence-transformers
|
| 4 |
+
metrics:
|
| 5 |
+
- cosine_accuracy
|
| 6 |
+
- cosine_accuracy_threshold
|
| 7 |
+
- cosine_f1
|
| 8 |
+
- cosine_f1_threshold
|
| 9 |
+
- cosine_precision
|
| 10 |
+
- cosine_recall
|
| 11 |
+
- cosine_ap
|
| 12 |
+
- dot_accuracy
|
| 13 |
+
- dot_accuracy_threshold
|
| 14 |
+
- dot_f1
|
| 15 |
+
- dot_f1_threshold
|
| 16 |
+
- dot_precision
|
| 17 |
+
- dot_recall
|
| 18 |
+
- dot_ap
|
| 19 |
+
- manhattan_accuracy
|
| 20 |
+
- manhattan_accuracy_threshold
|
| 21 |
+
- manhattan_f1
|
| 22 |
+
- manhattan_f1_threshold
|
| 23 |
+
- manhattan_precision
|
| 24 |
+
- manhattan_recall
|
| 25 |
+
- manhattan_ap
|
| 26 |
+
- euclidean_accuracy
|
| 27 |
+
- euclidean_accuracy_threshold
|
| 28 |
+
- euclidean_f1
|
| 29 |
+
- euclidean_f1_threshold
|
| 30 |
+
- euclidean_precision
|
| 31 |
+
- euclidean_recall
|
| 32 |
+
- euclidean_ap
|
| 33 |
+
- max_accuracy
|
| 34 |
+
- max_accuracy_threshold
|
| 35 |
+
- max_f1
|
| 36 |
+
- max_f1_threshold
|
| 37 |
+
- max_precision
|
| 38 |
+
- max_recall
|
| 39 |
+
- max_ap
|
| 40 |
+
pipeline_tag: sentence-similarity
|
| 41 |
+
tags:
|
| 42 |
+
- sentence-transformers
|
| 43 |
+
- sentence-similarity
|
| 44 |
+
- feature-extraction
|
| 45 |
+
- generated_from_trainer
|
| 46 |
+
- dataset_size:53
|
| 47 |
+
- loss:CosineSimilarityLoss
|
| 48 |
+
widget:
|
| 49 |
+
- source_sentence: 黒い タイル の 本当に すてきな カウンター の 前 と 後ろ で 働く 人々 。
|
| 50 |
+
sentences:
|
| 51 |
+
- 男性 は バレエ に 参加 して い ます 。
|
| 52 |
+
- 岩 の 上 に 座って いる 二 人
|
| 53 |
+
- 人々 は 宝石 店 で 働いて い ます 。
|
| 54 |
+
- source_sentence: 少年 は 木 の 切り株 に 座って い ます 。
|
| 55 |
+
sentences:
|
| 56 |
+
- ストリート ワーカー は 保護 具 を 着用 して い ませ ん 。
|
| 57 |
+
- 芝生 の エリア で 数 匹 の 犬 が 交流 し ます 。
|
| 58 |
+
- 木 を 切り 倒した 後 、 木 の 切り株 に 座って いる 少年 。
|
| 59 |
+
- source_sentence: 岩 の 多い 景色 を 見て 二 人
|
| 60 |
+
sentences:
|
| 61 |
+
- 何 か を 見て いる 二 人 が い ます 。
|
| 62 |
+
- 誰 か が 肖像 画 を 描いて い ます 。
|
| 63 |
+
- バイカー は 足 を 使って 自転車 を さらに 進め ます 。
|
| 64 |
+
model-index:
|
| 65 |
+
- name: SentenceTransformer based on colorfulscoop/sbert-base-ja
|
| 66 |
+
results:
|
| 67 |
+
- task:
|
| 68 |
+
type: binary-classification
|
| 69 |
+
name: Binary Classification
|
| 70 |
+
dataset:
|
| 71 |
+
name: custom arc semantics data jp
|
| 72 |
+
type: custom-arc-semantics-data-jp
|
| 73 |
+
metrics:
|
| 74 |
+
- type: cosine_accuracy
|
| 75 |
+
value: 0.6363636363636364
|
| 76 |
+
name: Cosine Accuracy
|
| 77 |
+
- type: cosine_accuracy_threshold
|
| 78 |
+
value: 0.3379952907562256
|
| 79 |
+
name: Cosine Accuracy Threshold
|
| 80 |
+
- type: cosine_f1
|
| 81 |
+
value: 0.7777777777777777
|
| 82 |
+
name: Cosine F1
|
| 83 |
+
- type: cosine_f1_threshold
|
| 84 |
+
value: 0.3379952907562256
|
| 85 |
+
name: Cosine F1 Threshold
|
| 86 |
+
- type: cosine_precision
|
| 87 |
+
value: 0.7
|
| 88 |
+
name: Cosine Precision
|
| 89 |
+
- type: cosine_recall
|
| 90 |
+
value: 0.875
|
| 91 |
+
name: Cosine Recall
|
| 92 |
+
- type: cosine_ap
|
| 93 |
+
value: 0.619629329004329
|
| 94 |
+
name: Cosine Ap
|
| 95 |
+
- type: dot_accuracy
|
| 96 |
+
value: 0.6363636363636364
|
| 97 |
+
name: Dot Accuracy
|
| 98 |
+
- type: dot_accuracy_threshold
|
| 99 |
+
value: 187.5118865966797
|
| 100 |
+
name: Dot Accuracy Threshold
|
| 101 |
+
- type: dot_f1
|
| 102 |
+
value: 0.7777777777777777
|
| 103 |
+
name: Dot F1
|
| 104 |
+
- type: dot_f1_threshold
|
| 105 |
+
value: 187.5118865966797
|
| 106 |
+
name: Dot F1 Threshold
|
| 107 |
+
- type: dot_precision
|
| 108 |
+
value: 0.7
|
| 109 |
+
name: Dot Precision
|
| 110 |
+
- type: dot_recall
|
| 111 |
+
value: 0.875
|
| 112 |
+
name: Dot Recall
|
| 113 |
+
- type: dot_ap
|
| 114 |
+
value: 0.6946293290043289
|
| 115 |
+
name: Dot Ap
|
| 116 |
+
- type: manhattan_accuracy
|
| 117 |
+
value: 0.6363636363636364
|
| 118 |
+
name: Manhattan Accuracy
|
| 119 |
+
- type: manhattan_accuracy_threshold
|
| 120 |
+
value: 598.9317626953125
|
| 121 |
+
name: Manhattan Accuracy Threshold
|
| 122 |
+
- type: manhattan_f1
|
| 123 |
+
value: 0.7777777777777777
|
| 124 |
+
name: Manhattan F1
|
| 125 |
+
- type: manhattan_f1_threshold
|
| 126 |
+
value: 598.9317626953125
|
| 127 |
+
name: Manhattan F1 Threshold
|
| 128 |
+
- type: manhattan_precision
|
| 129 |
+
value: 0.7
|
| 130 |
+
name: Manhattan Precision
|
| 131 |
+
- type: manhattan_recall
|
| 132 |
+
value: 0.875
|
| 133 |
+
name: Manhattan Recall
|
| 134 |
+
- type: manhattan_ap
|
| 135 |
+
value: 0.619629329004329
|
| 136 |
+
name: Manhattan Ap
|
| 137 |
+
- type: euclidean_accuracy
|
| 138 |
+
value: 0.6363636363636364
|
| 139 |
+
name: Euclidean Accuracy
|
| 140 |
+
- type: euclidean_accuracy_threshold
|
| 141 |
+
value: 27.118305206298828
|
| 142 |
+
name: Euclidean Accuracy Threshold
|
| 143 |
+
- type: euclidean_f1
|
| 144 |
+
value: 0.7777777777777777
|
| 145 |
+
name: Euclidean F1
|
| 146 |
+
- type: euclidean_f1_threshold
|
| 147 |
+
value: 27.118305206298828
|
| 148 |
+
name: Euclidean F1 Threshold
|
| 149 |
+
- type: euclidean_precision
|
| 150 |
+
value: 0.7
|
| 151 |
+
name: Euclidean Precision
|
| 152 |
+
- type: euclidean_recall
|
| 153 |
+
value: 0.875
|
| 154 |
+
name: Euclidean Recall
|
| 155 |
+
- type: euclidean_ap
|
| 156 |
+
value: 0.619629329004329
|
| 157 |
+
name: Euclidean Ap
|
| 158 |
+
- type: max_accuracy
|
| 159 |
+
value: 0.6363636363636364
|
| 160 |
+
name: Max Accuracy
|
| 161 |
+
- type: max_accuracy_threshold
|
| 162 |
+
value: 598.9317626953125
|
| 163 |
+
name: Max Accuracy Threshold
|
| 164 |
+
- type: max_f1
|
| 165 |
+
value: 0.7777777777777777
|
| 166 |
+
name: Max F1
|
| 167 |
+
- type: max_f1_threshold
|
| 168 |
+
value: 598.9317626953125
|
| 169 |
+
name: Max F1 Threshold
|
| 170 |
+
- type: max_precision
|
| 171 |
+
value: 0.7
|
| 172 |
+
name: Max Precision
|
| 173 |
+
- type: max_recall
|
| 174 |
+
value: 0.875
|
| 175 |
+
name: Max Recall
|
| 176 |
+
- type: max_ap
|
| 177 |
+
value: 0.6946293290043289
|
| 178 |
+
name: Max Ap
|
| 179 |
---
|
| 180 |
|
| 181 |
+
# SentenceTransformer based on colorfulscoop/sbert-base-ja
|
|
|
|
|
|
|
|
|
|
| 182 |
|
| 183 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) on the csv dataset. 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.
|
| 184 |
|
| 185 |
## Model Details
|
| 186 |
|
| 187 |
### Model Description
|
| 188 |
+
- **Model Type:** Sentence Transformer
|
| 189 |
+
- **Base model:** [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) <!-- at revision ecb8a98cd5176719ff7ab0d770a27420118732cf -->
|
| 190 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 191 |
+
- **Output Dimensionality:** 768 tokens
|
| 192 |
+
- **Similarity Function:** Cosine Similarity
|
| 193 |
+
- **Training Dataset:**
|
| 194 |
+
- csv
|
| 195 |
+
<!-- - **Language:** Unknown -->
|
| 196 |
+
<!-- - **License:** Unknown -->
|
| 197 |
|
| 198 |
+
### Model Sources
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 199 |
|
| 200 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 201 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 202 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 203 |
|
| 204 |
+
### Full Model Architecture
|
| 205 |
|
| 206 |
+
```
|
| 207 |
+
SentenceTransformer(
|
| 208 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
| 209 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
| 210 |
+
)
|
| 211 |
+
```
|
| 212 |
|
| 213 |
+
## Usage
|
| 214 |
|
| 215 |
+
### Direct Usage (Sentence Transformers)
|
| 216 |
|
| 217 |
+
First install the Sentence Transformers library:
|
| 218 |
|
| 219 |
+
```bash
|
| 220 |
+
pip install -U sentence-transformers
|
| 221 |
+
```
|
|
|
|
|
|
|
| 222 |
|
| 223 |
+
Then you can load this model and run inference.
|
| 224 |
+
```python
|
| 225 |
+
from sentence_transformers import SentenceTransformer
|
| 226 |
|
| 227 |
+
# Download from the 🤗 Hub
|
| 228 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 229 |
+
# Run inference
|
| 230 |
+
sentences = [
|
| 231 |
+
'岩 の 多い 景色 を 見て 二 人',
|
| 232 |
+
'何 か を 見て いる 二 人 が い ます 。',
|
| 233 |
+
'誰 か が 肖像 画 を 描いて い ます 。',
|
| 234 |
+
]
|
| 235 |
+
embeddings = model.encode(sentences)
|
| 236 |
+
print(embeddings.shape)
|
| 237 |
+
# [3, 768]
|
| 238 |
|
| 239 |
+
# Get the similarity scores for the embeddings
|
| 240 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 241 |
+
print(similarities.shape)
|
| 242 |
+
# [3, 3]
|
| 243 |
+
```
|
| 244 |
|
| 245 |
+
<!--
|
| 246 |
+
### Direct Usage (Transformers)
|
| 247 |
|
| 248 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 249 |
|
| 250 |
+
</details>
|
| 251 |
+
-->
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
|
| 253 |
+
<!--
|
| 254 |
+
### Downstream Usage (Sentence Transformers)
|
| 255 |
|
| 256 |
+
You can finetune this model on your own dataset.
|
| 257 |
|
| 258 |
+
<details><summary>Click to expand</summary>
|
| 259 |
|
| 260 |
+
</details>
|
| 261 |
+
-->
|
| 262 |
|
| 263 |
+
<!--
|
| 264 |
+
### Out-of-Scope Use
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 265 |
|
| 266 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 267 |
+
-->
|
| 268 |
|
| 269 |
## Evaluation
|
| 270 |
|
| 271 |
+
### Metrics
|
| 272 |
+
|
| 273 |
+
#### Binary Classification
|
| 274 |
+
* Dataset: `custom-arc-semantics-data-jp`
|
| 275 |
+
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
|
| 276 |
+
|
| 277 |
+
| Metric | Value |
|
| 278 |
+
|:-----------------------------|:-----------|
|
| 279 |
+
| cosine_accuracy | 0.6364 |
|
| 280 |
+
| cosine_accuracy_threshold | 0.338 |
|
| 281 |
+
| cosine_f1 | 0.7778 |
|
| 282 |
+
| cosine_f1_threshold | 0.338 |
|
| 283 |
+
| cosine_precision | 0.7 |
|
| 284 |
+
| cosine_recall | 0.875 |
|
| 285 |
+
| cosine_ap | 0.6196 |
|
| 286 |
+
| dot_accuracy | 0.6364 |
|
| 287 |
+
| dot_accuracy_threshold | 187.5119 |
|
| 288 |
+
| dot_f1 | 0.7778 |
|
| 289 |
+
| dot_f1_threshold | 187.5119 |
|
| 290 |
+
| dot_precision | 0.7 |
|
| 291 |
+
| dot_recall | 0.875 |
|
| 292 |
+
| dot_ap | 0.6946 |
|
| 293 |
+
| manhattan_accuracy | 0.6364 |
|
| 294 |
+
| manhattan_accuracy_threshold | 598.9318 |
|
| 295 |
+
| manhattan_f1 | 0.7778 |
|
| 296 |
+
| manhattan_f1_threshold | 598.9318 |
|
| 297 |
+
| manhattan_precision | 0.7 |
|
| 298 |
+
| manhattan_recall | 0.875 |
|
| 299 |
+
| manhattan_ap | 0.6196 |
|
| 300 |
+
| euclidean_accuracy | 0.6364 |
|
| 301 |
+
| euclidean_accuracy_threshold | 27.1183 |
|
| 302 |
+
| euclidean_f1 | 0.7778 |
|
| 303 |
+
| euclidean_f1_threshold | 27.1183 |
|
| 304 |
+
| euclidean_precision | 0.7 |
|
| 305 |
+
| euclidean_recall | 0.875 |
|
| 306 |
+
| euclidean_ap | 0.6196 |
|
| 307 |
+
| max_accuracy | 0.6364 |
|
| 308 |
+
| max_accuracy_threshold | 598.9318 |
|
| 309 |
+
| max_f1 | 0.7778 |
|
| 310 |
+
| max_f1_threshold | 598.9318 |
|
| 311 |
+
| max_precision | 0.7 |
|
| 312 |
+
| max_recall | 0.875 |
|
| 313 |
+
| **max_ap** | **0.6946** |
|
| 314 |
+
|
| 315 |
+
<!--
|
| 316 |
+
## Bias, Risks and Limitations
|
| 317 |
+
|
| 318 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 319 |
+
-->
|
| 320 |
+
|
| 321 |
+
<!--
|
| 322 |
+
### Recommendations
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 323 |
|
| 324 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 325 |
+
-->
|
| 326 |
|
| 327 |
+
## Training Details
|
| 328 |
|
| 329 |
+
### Training Dataset
|
| 330 |
+
|
| 331 |
+
#### csv
|
| 332 |
+
|
| 333 |
+
* Dataset: csv
|
| 334 |
+
* Size: 53 training samples
|
| 335 |
+
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 336 |
+
* Approximate statistics based on the first 53 samples:
|
| 337 |
+
| | text1 | text2 | label |
|
| 338 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
|
| 339 |
+
| type | string | string | int |
|
| 340 |
+
| details | <ul><li>min: 14 tokens</li><li>mean: 35.36 tokens</li><li>max: 79 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 21.33 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>0: ~38.10%</li><li>1: ~61.90%</li></ul> |
|
| 341 |
+
* Samples:
|
| 342 |
+
| text1 | text2 | label |
|
| 343 |
+
|:---------------------------------------------------------------------------------------|:----------------------------------------------------------|:---------------|
|
| 344 |
+
| <code>薄紫 色 の ドレス と 明るい ホット ピンク の 靴 を 着た 女性 が 、 水 と コーヒー を 飲んで テーブル に 座って い ます 。</code> | <code>ブラインド デート の 女性 が 座って 、 デート が 現れる の を 待ち ます 。</code> | <code>1</code> |
|
| 345 |
+
| <code>トラック を 自転車 で 走る 人々 の グループ 。</code> | <code>自転車 の 挑戦 に 勝とう と する 人々 の グループ 。</code> | <code>1</code> |
|
| 346 |
+
| <code>野球 の 試合 中 に 基地 を 走る 野球 選手 の シャープリー 。</code> | <code>Ｓｈａｒｐ ｌｅｙ は ゲーム で プレイ して い ます 。</code> | <code>0</code> |
|
| 347 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 348 |
+
```json
|
| 349 |
+
{
|
| 350 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
| 351 |
+
}
|
| 352 |
+
```
|
| 353 |
+
|
| 354 |
+
### Evaluation Dataset
|
| 355 |
+
|
| 356 |
+
#### csv
|
| 357 |
+
|
| 358 |
+
* Dataset: csv
|
| 359 |
+
* Size: 53 evaluation samples
|
| 360 |
+
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 361 |
+
* Approximate statistics based on the first 53 samples:
|
| 362 |
+
| | text1 | text2 | label |
|
| 363 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
|
| 364 |
+
| type | string | string | int |
|
| 365 |
+
| details | <ul><li>min: 19 tokens</li><li>mean: 39.64 tokens</li><li>max: 84 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 25.27 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>0: ~27.27%</li><li>1: ~72.73%</li></ul> |
|
| 366 |
+
* Samples:
|
| 367 |
+
| text1 | text2 | label |
|
| 368 |
+
|:----------------------------------------------------------------------------------------------------------|:------------------------------------------------|:---------------|
|
| 369 |
+
| <code>岩 の 多い 景色 を 見て 二 人</code> | <code>何 か を 見て いる 二 人 が い ます 。</code> | <code>0</code> |
|
| 370 |
+
| <code>白い ヘルメット と オレンジ色 の シャツ 、 ジーンズ 、 白い トラック と オレンジ色 の パイロン の 前 に 反射 ジャケット を 着た 金髪 の ストリート ワーカー 。</code> | <code>ストリート ワーカー は 保護 具 を 着用 して い ませ ん 。</code> | <code>1</code> |
|
| 371 |
+
| <code>白い 帽子 を かぶった 女性 が 、 鮮やかな 色 の 岩 の 風景 を 描いて い ます 。 岩 層 自体 が 背景 に 見え ます 。</code> | <code>誰 か が 肖像 画 を 描いて い ます 。</code> | <code>1</code> |
|
| 372 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 373 |
+
```json
|
| 374 |
+
{
|
| 375 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
| 376 |
+
}
|
| 377 |
+
```
|
| 378 |
+
|
| 379 |
+
### Training Hyperparameters
|
| 380 |
+
#### Non-Default Hyperparameters
|
| 381 |
+
|
| 382 |
+
- `eval_strategy`: epoch
|
| 383 |
+
- `learning_rate`: 2e-05
|
| 384 |
+
- `num_train_epochs`: 15
|
| 385 |
+
- `warmup_ratio`: 0.4
|
| 386 |
+
- `fp16`: True
|
| 387 |
+
- `batch_sampler`: no_duplicates
|
| 388 |
+
|
| 389 |
+
#### All Hyperparameters
|
| 390 |
+
<details><summary>Click to expand</summary>
|
| 391 |
+
|
| 392 |
+
- `overwrite_output_dir`: False
|
| 393 |
+
- `do_predict`: False
|
| 394 |
+
- `eval_strategy`: epoch
|
| 395 |
+
- `prediction_loss_only`: True
|
| 396 |
+
- `per_device_train_batch_size`: 8
|
| 397 |
+
- `per_device_eval_batch_size`: 8
|
| 398 |
+
- `per_gpu_train_batch_size`: None
|
| 399 |
+
- `per_gpu_eval_batch_size`: None
|
| 400 |
+
- `gradient_accumulation_steps`: 1
|
| 401 |
+
- `eval_accumulation_steps`: None
|
| 402 |
+
- `torch_empty_cache_steps`: None
|
| 403 |
+
- `learning_rate`: 2e-05
|
| 404 |
+
- `weight_decay`: 0.0
|
| 405 |
+
- `adam_beta1`: 0.9
|
| 406 |
+
- `adam_beta2`: 0.999
|
| 407 |
+
- `adam_epsilon`: 1e-08
|
| 408 |
+
- `max_grad_norm`: 1.0
|
| 409 |
+
- `num_train_epochs`: 15
|
| 410 |
+
- `max_steps`: -1
|
| 411 |
+
- `lr_scheduler_type`: linear
|
| 412 |
+
- `lr_scheduler_kwargs`: {}
|
| 413 |
+
- `warmup_ratio`: 0.4
|
| 414 |
+
- `warmup_steps`: 0
|
| 415 |
+
- `log_level`: passive
|
| 416 |
+
- `log_level_replica`: warning
|
| 417 |
+
- `log_on_each_node`: True
|
| 418 |
+
- `logging_nan_inf_filter`: True
|
| 419 |
+
- `save_safetensors`: True
|
| 420 |
+
- `save_on_each_node`: False
|
| 421 |
+
- `save_only_model`: False
|
| 422 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 423 |
+
- `no_cuda`: False
|
| 424 |
+
- `use_cpu`: False
|
| 425 |
+
- `use_mps_device`: False
|
| 426 |
+
- `seed`: 42
|
| 427 |
+
- `data_seed`: None
|
| 428 |
+
- `jit_mode_eval`: False
|
| 429 |
+
- `use_ipex`: False
|
| 430 |
+
- `bf16`: False
|
| 431 |
+
- `fp16`: True
|
| 432 |
+
- `fp16_opt_level`: O1
|
| 433 |
+
- `half_precision_backend`: auto
|
| 434 |
+
- `bf16_full_eval`: False
|
| 435 |
+
- `fp16_full_eval`: False
|
| 436 |
+
- `tf32`: None
|
| 437 |
+
- `local_rank`: 0
|
| 438 |
+
- `ddp_backend`: None
|
| 439 |
+
- `tpu_num_cores`: None
|
| 440 |
+
- `tpu_metrics_debug`: False
|
| 441 |
+
- `debug`: []
|
| 442 |
+
- `dataloader_drop_last`: False
|
| 443 |
+
- `dataloader_num_workers`: 0
|
| 444 |
+
- `dataloader_prefetch_factor`: None
|
| 445 |
+
- `past_index`: -1
|
| 446 |
+
- `disable_tqdm`: False
|
| 447 |
+
- `remove_unused_columns`: True
|
| 448 |
+
- `label_names`: None
|
| 449 |
+
- `load_best_model_at_end`: False
|
| 450 |
+
- `ignore_data_skip`: False
|
| 451 |
+
- `fsdp`: []
|
| 452 |
+
- `fsdp_min_num_params`: 0
|
| 453 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 454 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 455 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 456 |
+
- `deepspeed`: None
|
| 457 |
+
- `label_smoothing_factor`: 0.0
|
| 458 |
+
- `optim`: adamw_torch
|
| 459 |
+
- `optim_args`: None
|
| 460 |
+
- `adafactor`: False
|
| 461 |
+
- `group_by_length`: False
|
| 462 |
+
- `length_column_name`: length
|
| 463 |
+
- `ddp_find_unused_parameters`: None
|
| 464 |
+
- `ddp_bucket_cap_mb`: None
|
| 465 |
+
- `ddp_broadcast_buffers`: False
|
| 466 |
+
- `dataloader_pin_memory`: True
|
| 467 |
+
- `dataloader_persistent_workers`: False
|
| 468 |
+
- `skip_memory_metrics`: True
|
| 469 |
+
- `use_legacy_prediction_loop`: False
|
| 470 |
+
- `push_to_hub`: False
|
| 471 |
+
- `resume_from_checkpoint`: None
|
| 472 |
+
- `hub_model_id`: None
|
| 473 |
+
- `hub_strategy`: every_save
|
| 474 |
+
- `hub_private_repo`: False
|
| 475 |
+
- `hub_always_push`: False
|
| 476 |
+
- `gradient_checkpointing`: False
|
| 477 |
+
- `gradient_checkpointing_kwargs`: None
|
| 478 |
+
- `include_inputs_for_metrics`: False
|
| 479 |
+
- `eval_do_concat_batches`: True
|
| 480 |
+
- `fp16_backend`: auto
|
| 481 |
+
- `push_to_hub_model_id`: None
|
| 482 |
+
- `push_to_hub_organization`: None
|
| 483 |
+
- `mp_parameters`:
|
| 484 |
+
- `auto_find_batch_size`: False
|
| 485 |
+
- `full_determinism`: False
|
| 486 |
+
- `torchdynamo`: None
|
| 487 |
+
- `ray_scope`: last
|
| 488 |
+
- `ddp_timeout`: 1800
|
| 489 |
+
- `torch_compile`: False
|
| 490 |
+
- `torch_compile_backend`: None
|
| 491 |
+
- `torch_compile_mode`: None
|
| 492 |
+
- `dispatch_batches`: None
|
| 493 |
+
- `split_batches`: None
|
| 494 |
+
- `include_tokens_per_second`: False
|
| 495 |
+
- `include_num_input_tokens_seen`: False
|
| 496 |
+
- `neftune_noise_alpha`: None
|
| 497 |
+
- `optim_target_modules`: None
|
| 498 |
+
- `batch_eval_metrics`: False
|
| 499 |
+
- `eval_on_start`: False
|
| 500 |
+
- `eval_use_gather_object`: False
|
| 501 |
+
- `batch_sampler`: no_duplicates
|
| 502 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 503 |
+
|
| 504 |
+
</details>
|
| 505 |
+
|
| 506 |
+
### Training Logs
|
| 507 |
+
| Epoch | Step | Training Loss | loss | custom-arc-semantics-data-jp_max_ap |
|
| 508 |
+
|:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
|
| 509 |
+
| 1.0 | 6 | 0.2963 | 0.3111 | 0.6821 |
|
| 510 |
+
| 2.0 | 12 | 0.2833 | 0.3096 | 0.7238 |
|
| 511 |
+
| 3.0 | 18 | 0.2568 | 0.3050 | 0.7238 |
|
| 512 |
+
| 4.0 | 24 | 0.2177 | 0.2958 | 0.7238 |
|
| 513 |
+
| 5.0 | 30 | 0.1797 | 0.2826 | 0.6946 |
|
| 514 |
+
| 6.0 | 36 | 0.1419 | 0.2765 | 0.6509 |
|
| 515 |
+
| 7.0 | 42 | 0.1057 | 0.2954 | 0.6509 |
|
| 516 |
+
| 8.0 | 48 | 0.0815 | 0.3165 | 0.6509 |
|
| 517 |
+
| 9.0 | 54 | 0.0664 | 0.3199 | 0.6509 |
|
| 518 |
+
| 10.0 | 60 | 0.0497 | 0.3140 | 0.6509 |
|
| 519 |
+
| 11.0 | 66 | 0.0402 | 0.3081 | 0.6321 |
|
| 520 |
+
| 12.0 | 72 | 0.0346 | 0.3072 | 0.6946 |
|
| 521 |
+
| 13.0 | 78 | 0.0293 | 0.3066 | 0.6946 |
|
| 522 |
+
| 14.0 | 84 | 0.0302 | 0.3076 | 0.6946 |
|
| 523 |
+
| 15.0 | 90 | 0.0287 | 0.3078 | 0.6946 |
|
| 524 |
+
|
| 525 |
+
|
| 526 |
+
### Framework Versions
|
| 527 |
+
- Python: 3.10.14
|
| 528 |
+
- Sentence Transformers: 3.1.0
|
| 529 |
+
- Transformers: 4.44.2
|
| 530 |
+
- PyTorch: 2.4.1+cu121
|
| 531 |
+
- Accelerate: 0.34.2
|
| 532 |
+
- Datasets: 2.20.0
|
| 533 |
+
- Tokenizers: 0.19.1
|
| 534 |
+
|
| 535 |
+
## Citation
|
| 536 |
+
|
| 537 |
+
### BibTeX
|
| 538 |
+
|
| 539 |
+
#### Sentence Transformers
|
| 540 |
+
```bibtex
|
| 541 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 542 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 543 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 544 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 545 |
+
month = "11",
|
| 546 |
+
year = "2019",
|
| 547 |
+
publisher = "Association for Computational Linguistics",
|
| 548 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 549 |
+
}
|
| 550 |
+
```
|
| 551 |
+
|
| 552 |
+
<!--
|
| 553 |
+
## Glossary
|
| 554 |
+
|
| 555 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 556 |
+
-->
|
| 557 |
+
|
| 558 |
+
<!--
|
| 559 |
+
## Model Card Authors
|
| 560 |
+
|
| 561 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 562 |
+
-->
|
| 563 |
+
|
| 564 |
+
<!--
|
| 565 |
## Model Card Contact
|
| 566 |
|
| 567 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 568 |
+
-->
|
checkpoint-84/1_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 |
+
}
|
checkpoint-84/README.md
ADDED
|
@@ -0,0 +1,567 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: colorfulscoop/sbert-base-ja
|
| 3 |
+
library_name: sentence-transformers
|
| 4 |
+
metrics:
|
| 5 |
+
- cosine_accuracy
|
| 6 |
+
- cosine_accuracy_threshold
|
| 7 |
+
- cosine_f1
|
| 8 |
+
- cosine_f1_threshold
|
| 9 |
+
- cosine_precision
|
| 10 |
+
- cosine_recall
|
| 11 |
+
- cosine_ap
|
| 12 |
+
- dot_accuracy
|
| 13 |
+
- dot_accuracy_threshold
|
| 14 |
+
- dot_f1
|
| 15 |
+
- dot_f1_threshold
|
| 16 |
+
- dot_precision
|
| 17 |
+
- dot_recall
|
| 18 |
+
- dot_ap
|
| 19 |
+
- manhattan_accuracy
|
| 20 |
+
- manhattan_accuracy_threshold
|
| 21 |
+
- manhattan_f1
|
| 22 |
+
- manhattan_f1_threshold
|
| 23 |
+
- manhattan_precision
|
| 24 |
+
- manhattan_recall
|
| 25 |
+
- manhattan_ap
|
| 26 |
+
- euclidean_accuracy
|
| 27 |
+
- euclidean_accuracy_threshold
|
| 28 |
+
- euclidean_f1
|
| 29 |
+
- euclidean_f1_threshold
|
| 30 |
+
- euclidean_precision
|
| 31 |
+
- euclidean_recall
|
| 32 |
+
- euclidean_ap
|
| 33 |
+
- max_accuracy
|
| 34 |
+
- max_accuracy_threshold
|
| 35 |
+
- max_f1
|
| 36 |
+
- max_f1_threshold
|
| 37 |
+
- max_precision
|
| 38 |
+
- max_recall
|
| 39 |
+
- max_ap
|
| 40 |
+
pipeline_tag: sentence-similarity
|
| 41 |
+
tags:
|
| 42 |
+
- sentence-transformers
|
| 43 |
+
- sentence-similarity
|
| 44 |
+
- feature-extraction
|
| 45 |
+
- generated_from_trainer
|
| 46 |
+
- dataset_size:53
|
| 47 |
+
- loss:CosineSimilarityLoss
|
| 48 |
+
widget:
|
| 49 |
+
- source_sentence: 黒い タイル の 本当に すてきな カウンター の 前 と 後ろ で 働く 人々 。
|
| 50 |
+
sentences:
|
| 51 |
+
- 男性 は バレエ に 参加 して い ます 。
|
| 52 |
+
- 岩 の 上 に 座って いる 二 人
|
| 53 |
+
- 人々 は 宝石 店 で 働いて い ます 。
|
| 54 |
+
- source_sentence: 少年 は 木 の 切り株 に 座って い ます 。
|
| 55 |
+
sentences:
|
| 56 |
+
- ストリート ワーカー は 保護 具 を 着用 して い ませ ん 。
|
| 57 |
+
- 芝生 の エリア で 数 匹 の 犬 が 交流 し ます 。
|
| 58 |
+
- 木 を 切り 倒した 後 、 木 の 切り株 に 座って いる 少年 。
|
| 59 |
+
- source_sentence: 岩 の 多い 景色 を 見て 二 人
|
| 60 |
+
sentences:
|
| 61 |
+
- 何 か を 見て いる 二 人 が い ます 。
|
| 62 |
+
- 誰 か が 肖像 画 を 描いて い ます 。
|
| 63 |
+
- バイカー は 足 を 使って 自転車 を さらに 進め ます 。
|
| 64 |
+
model-index:
|
| 65 |
+
- name: SentenceTransformer based on colorfulscoop/sbert-base-ja
|
| 66 |
+
results:
|
| 67 |
+
- task:
|
| 68 |
+
type: binary-classification
|
| 69 |
+
name: Binary Classification
|
| 70 |
+
dataset:
|
| 71 |
+
name: custom arc semantics data jp
|
| 72 |
+
type: custom-arc-semantics-data-jp
|
| 73 |
+
metrics:
|
| 74 |
+
- type: cosine_accuracy
|
| 75 |
+
value: 0.6363636363636364
|
| 76 |
+
name: Cosine Accuracy
|
| 77 |
+
- type: cosine_accuracy_threshold
|
| 78 |
+
value: 0.3385917544364929
|
| 79 |
+
name: Cosine Accuracy Threshold
|
| 80 |
+
- type: cosine_f1
|
| 81 |
+
value: 0.7777777777777777
|
| 82 |
+
name: Cosine F1
|
| 83 |
+
- type: cosine_f1_threshold
|
| 84 |
+
value: 0.3385917544364929
|
| 85 |
+
name: Cosine F1 Threshold
|
| 86 |
+
- type: cosine_precision
|
| 87 |
+
value: 0.7
|
| 88 |
+
name: Cosine Precision
|
| 89 |
+
- type: cosine_recall
|
| 90 |
+
value: 0.875
|
| 91 |
+
name: Cosine Recall
|
| 92 |
+
- type: cosine_ap
|
| 93 |
+
value: 0.619629329004329
|
| 94 |
+
name: Cosine Ap
|
| 95 |
+
- type: dot_accuracy
|
| 96 |
+
value: 0.6363636363636364
|
| 97 |
+
name: Dot Accuracy
|
| 98 |
+
- type: dot_accuracy_threshold
|
| 99 |
+
value: 187.77444458007812
|
| 100 |
+
name: Dot Accuracy Threshold
|
| 101 |
+
- type: dot_f1
|
| 102 |
+
value: 0.7777777777777777
|
| 103 |
+
name: Dot F1
|
| 104 |
+
- type: dot_f1_threshold
|
| 105 |
+
value: 187.77444458007812
|
| 106 |
+
name: Dot F1 Threshold
|
| 107 |
+
- type: dot_precision
|
| 108 |
+
value: 0.7
|
| 109 |
+
name: Dot Precision
|
| 110 |
+
- type: dot_recall
|
| 111 |
+
value: 0.875
|
| 112 |
+
name: Dot Recall
|
| 113 |
+
- type: dot_ap
|
| 114 |
+
value: 0.6946293290043289
|
| 115 |
+
name: Dot Ap
|
| 116 |
+
- type: manhattan_accuracy
|
| 117 |
+
value: 0.6363636363636364
|
| 118 |
+
name: Manhattan Accuracy
|
| 119 |
+
- type: manhattan_accuracy_threshold
|
| 120 |
+
value: 598.5726318359375
|
| 121 |
+
name: Manhattan Accuracy Threshold
|
| 122 |
+
- type: manhattan_f1
|
| 123 |
+
value: 0.7777777777777777
|
| 124 |
+
name: Manhattan F1
|
| 125 |
+
- type: manhattan_f1_threshold
|
| 126 |
+
value: 598.5726318359375
|
| 127 |
+
name: Manhattan F1 Threshold
|
| 128 |
+
- type: manhattan_precision
|
| 129 |
+
value: 0.7
|
| 130 |
+
name: Manhattan Precision
|
| 131 |
+
- type: manhattan_recall
|
| 132 |
+
value: 0.875
|
| 133 |
+
name: Manhattan Recall
|
| 134 |
+
- type: manhattan_ap
|
| 135 |
+
value: 0.619629329004329
|
| 136 |
+
name: Manhattan Ap
|
| 137 |
+
- type: euclidean_accuracy
|
| 138 |
+
value: 0.6363636363636364
|
| 139 |
+
name: Euclidean Accuracy
|
| 140 |
+
- type: euclidean_accuracy_threshold
|
| 141 |
+
value: 27.100971221923828
|
| 142 |
+
name: Euclidean Accuracy Threshold
|
| 143 |
+
- type: euclidean_f1
|
| 144 |
+
value: 0.7777777777777777
|
| 145 |
+
name: Euclidean F1
|
| 146 |
+
- type: euclidean_f1_threshold
|
| 147 |
+
value: 27.100971221923828
|
| 148 |
+
name: Euclidean F1 Threshold
|
| 149 |
+
- type: euclidean_precision
|
| 150 |
+
value: 0.7
|
| 151 |
+
name: Euclidean Precision
|
| 152 |
+
- type: euclidean_recall
|
| 153 |
+
value: 0.875
|
| 154 |
+
name: Euclidean Recall
|
| 155 |
+
- type: euclidean_ap
|
| 156 |
+
value: 0.619629329004329
|
| 157 |
+
name: Euclidean Ap
|
| 158 |
+
- type: max_accuracy
|
| 159 |
+
value: 0.6363636363636364
|
| 160 |
+
name: Max Accuracy
|
| 161 |
+
- type: max_accuracy_threshold
|
| 162 |
+
value: 598.5726318359375
|
| 163 |
+
name: Max Accuracy Threshold
|
| 164 |
+
- type: max_f1
|
| 165 |
+
value: 0.7777777777777777
|
| 166 |
+
name: Max F1
|
| 167 |
+
- type: max_f1_threshold
|
| 168 |
+
value: 598.5726318359375
|
| 169 |
+
name: Max F1 Threshold
|
| 170 |
+
- type: max_precision
|
| 171 |
+
value: 0.7
|
| 172 |
+
name: Max Precision
|
| 173 |
+
- type: max_recall
|
| 174 |
+
value: 0.875
|
| 175 |
+
name: Max Recall
|
| 176 |
+
- type: max_ap
|
| 177 |
+
value: 0.6946293290043289
|
| 178 |
+
name: Max Ap
|
| 179 |
+
---
|
| 180 |
+
|
| 181 |
+
# SentenceTransformer based on colorfulscoop/sbert-base-ja
|
| 182 |
+
|
| 183 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) on the csv dataset. 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.
|
| 184 |
+
|
| 185 |
+
## Model Details
|
| 186 |
+
|
| 187 |
+
### Model Description
|
| 188 |
+
- **Model Type:** Sentence Transformer
|
| 189 |
+
- **Base model:** [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) <!-- at revision ecb8a98cd5176719ff7ab0d770a27420118732cf -->
|
| 190 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 191 |
+
- **Output Dimensionality:** 768 tokens
|
| 192 |
+
- **Similarity Function:** Cosine Similarity
|
| 193 |
+
- **Training Dataset:**
|
| 194 |
+
- csv
|
| 195 |
+
<!-- - **Language:** Unknown -->
|
| 196 |
+
<!-- - **License:** Unknown -->
|
| 197 |
+
|
| 198 |
+
### Model Sources
|
| 199 |
+
|
| 200 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 201 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 202 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 203 |
+
|
| 204 |
+
### Full Model Architecture
|
| 205 |
+
|
| 206 |
+
```
|
| 207 |
+
SentenceTransformer(
|
| 208 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
| 209 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
| 210 |
+
)
|
| 211 |
+
```
|
| 212 |
+
|
| 213 |
+
## Usage
|
| 214 |
+
|
| 215 |
+
### Direct Usage (Sentence Transformers)
|
| 216 |
+
|
| 217 |
+
First install the Sentence Transformers library:
|
| 218 |
+
|
| 219 |
+
```bash
|
| 220 |
+
pip install -U sentence-transformers
|
| 221 |
+
```
|
| 222 |
+
|
| 223 |
+
Then you can load this model and run inference.
|
| 224 |
+
```python
|
| 225 |
+
from sentence_transformers import SentenceTransformer
|
| 226 |
+
|
| 227 |
+
# Download from the 🤗 Hub
|
| 228 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 229 |
+
# Run inference
|
| 230 |
+
sentences = [
|
| 231 |
+
'岩 の 多い 景色 を 見て 二 人',
|
| 232 |
+
'何 か を 見て いる 二 人 が い ます 。',
|
| 233 |
+
'誰 か が 肖像 画 を 描いて い ます 。',
|
| 234 |
+
]
|
| 235 |
+
embeddings = model.encode(sentences)
|
| 236 |
+
print(embeddings.shape)
|
| 237 |
+
# [3, 768]
|
| 238 |
+
|
| 239 |
+
# Get the similarity scores for the embeddings
|
| 240 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 241 |
+
print(similarities.shape)
|
| 242 |
+
# [3, 3]
|
| 243 |
+
```
|
| 244 |
+
|
| 245 |
+
<!--
|
| 246 |
+
### Direct Usage (Transformers)
|
| 247 |
+
|
| 248 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 249 |
+
|
| 250 |
+
</details>
|
| 251 |
+
-->
|
| 252 |
+
|
| 253 |
+
<!--
|
| 254 |
+
### Downstream Usage (Sentence Transformers)
|
| 255 |
+
|
| 256 |
+
You can finetune this model on your own dataset.
|
| 257 |
+
|
| 258 |
+
<details><summary>Click to expand</summary>
|
| 259 |
+
|
| 260 |
+
</details>
|
| 261 |
+
-->
|
| 262 |
+
|
| 263 |
+
<!--
|
| 264 |
+
### Out-of-Scope Use
|
| 265 |
+
|
| 266 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 267 |
+
-->
|
| 268 |
+
|
| 269 |
+
## Evaluation
|
| 270 |
+
|
| 271 |
+
### Metrics
|
| 272 |
+
|
| 273 |
+
#### Binary Classification
|
| 274 |
+
* Dataset: `custom-arc-semantics-data-jp`
|
| 275 |
+
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
|
| 276 |
+
|
| 277 |
+
| Metric | Value |
|
| 278 |
+
|:-----------------------------|:-----------|
|
| 279 |
+
| cosine_accuracy | 0.6364 |
|
| 280 |
+
| cosine_accuracy_threshold | 0.3386 |
|
| 281 |
+
| cosine_f1 | 0.7778 |
|
| 282 |
+
| cosine_f1_threshold | 0.3386 |
|
| 283 |
+
| cosine_precision | 0.7 |
|
| 284 |
+
| cosine_recall | 0.875 |
|
| 285 |
+
| cosine_ap | 0.6196 |
|
| 286 |
+
| dot_accuracy | 0.6364 |
|
| 287 |
+
| dot_accuracy_threshold | 187.7744 |
|
| 288 |
+
| dot_f1 | 0.7778 |
|
| 289 |
+
| dot_f1_threshold | 187.7744 |
|
| 290 |
+
| dot_precision | 0.7 |
|
| 291 |
+
| dot_recall | 0.875 |
|
| 292 |
+
| dot_ap | 0.6946 |
|
| 293 |
+
| manhattan_accuracy | 0.6364 |
|
| 294 |
+
| manhattan_accuracy_threshold | 598.5726 |
|
| 295 |
+
| manhattan_f1 | 0.7778 |
|
| 296 |
+
| manhattan_f1_threshold | 598.5726 |
|
| 297 |
+
| manhattan_precision | 0.7 |
|
| 298 |
+
| manhattan_recall | 0.875 |
|
| 299 |
+
| manhattan_ap | 0.6196 |
|
| 300 |
+
| euclidean_accuracy | 0.6364 |
|
| 301 |
+
| euclidean_accuracy_threshold | 27.101 |
|
| 302 |
+
| euclidean_f1 | 0.7778 |
|
| 303 |
+
| euclidean_f1_threshold | 27.101 |
|
| 304 |
+
| euclidean_precision | 0.7 |
|
| 305 |
+
| euclidean_recall | 0.875 |
|
| 306 |
+
| euclidean_ap | 0.6196 |
|
| 307 |
+
| max_accuracy | 0.6364 |
|
| 308 |
+
| max_accuracy_threshold | 598.5726 |
|
| 309 |
+
| max_f1 | 0.7778 |
|
| 310 |
+
| max_f1_threshold | 598.5726 |
|
| 311 |
+
| max_precision | 0.7 |
|
| 312 |
+
| max_recall | 0.875 |
|
| 313 |
+
| **max_ap** | **0.6946** |
|
| 314 |
+
|
| 315 |
+
<!--
|
| 316 |
+
## Bias, Risks and Limitations
|
| 317 |
+
|
| 318 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 319 |
+
-->
|
| 320 |
+
|
| 321 |
+
<!--
|
| 322 |
+
### Recommendations
|
| 323 |
+
|
| 324 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 325 |
+
-->
|
| 326 |
+
|
| 327 |
+
## Training Details
|
| 328 |
+
|
| 329 |
+
### Training Dataset
|
| 330 |
+
|
| 331 |
+
#### csv
|
| 332 |
+
|
| 333 |
+
* Dataset: csv
|
| 334 |
+
* Size: 53 training samples
|
| 335 |
+
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 336 |
+
* Approximate statistics based on the first 53 samples:
|
| 337 |
+
| | text1 | text2 | label |
|
| 338 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
|
| 339 |
+
| type | string | string | int |
|
| 340 |
+
| details | <ul><li>min: 14 tokens</li><li>mean: 35.36 tokens</li><li>max: 79 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 21.33 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>0: ~38.10%</li><li>1: ~61.90%</li></ul> |
|
| 341 |
+
* Samples:
|
| 342 |
+
| text1 | text2 | label |
|
| 343 |
+
|:---------------------------------------------------------------------------------------|:----------------------------------------------------------|:---------------|
|
| 344 |
+
| <code>薄紫 色 の ドレス と 明るい ホット ピンク の 靴 を 着た 女性 が 、 水 と コーヒー を 飲んで テーブル に 座って い ます 。</code> | <code>ブラインド デート の 女性 が 座って 、 デート が 現れる の を 待ち ます 。</code> | <code>1</code> |
|
| 345 |
+
| <code>トラック を 自転車 で 走る 人々 の グループ 。</code> | <code>自転車 の 挑戦 に 勝とう と する 人々 の グループ 。</code> | <code>1</code> |
|
| 346 |
+
| <code>野球 の 試合 中 に 基地 を 走る 野球 選手 の シャープリー 。</code> | <code>Ｓｈａｒｐ ｌｅｙ は ゲーム で プレイ して い ます 。</code> | <code>0</code> |
|
| 347 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 348 |
+
```json
|
| 349 |
+
{
|
| 350 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
| 351 |
+
}
|
| 352 |
+
```
|
| 353 |
+
|
| 354 |
+
### Evaluation Dataset
|
| 355 |
+
|
| 356 |
+
#### csv
|
| 357 |
+
|
| 358 |
+
* Dataset: csv
|
| 359 |
+
* Size: 53 evaluation samples
|
| 360 |
+
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 361 |
+
* Approximate statistics based on the first 53 samples:
|
| 362 |
+
| | text1 | text2 | label |
|
| 363 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
|
| 364 |
+
| type | string | string | int |
|
| 365 |
+
| details | <ul><li>min: 19 tokens</li><li>mean: 39.64 tokens</li><li>max: 84 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 25.27 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>0: ~27.27%</li><li>1: ~72.73%</li></ul> |
|
| 366 |
+
* Samples:
|
| 367 |
+
| text1 | text2 | label |
|
| 368 |
+
|:----------------------------------------------------------------------------------------------------------|:------------------------------------------------|:---------------|
|
| 369 |
+
| <code>岩 の 多い 景色 を 見て 二 人</code> | <code>何 か を 見て いる 二 人 が い ます 。</code> | <code>0</code> |
|
| 370 |
+
| <code>白い ヘルメット と オレンジ色 の シャツ 、 ジーンズ 、 白い トラック と オレンジ色 の パイロン の 前 に 反射 ジャケット を 着た 金髪 の ストリート ワーカー 。</code> | <code>ストリート ワーカー は 保護 具 を 着用 して い ませ ん 。</code> | <code>1</code> |
|
| 371 |
+
| <code>白い 帽子 を かぶった 女�� が 、 鮮やかな 色 の 岩 の 風景 を 描いて い ます 。 岩 層 自体 が 背景 に 見え ます 。</code> | <code>誰 か が 肖像 画 を 描いて い ます 。</code> | <code>1</code> |
|
| 372 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 373 |
+
```json
|
| 374 |
+
{
|
| 375 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
| 376 |
+
}
|
| 377 |
+
```
|
| 378 |
+
|
| 379 |
+
### Training Hyperparameters
|
| 380 |
+
#### Non-Default Hyperparameters
|
| 381 |
+
|
| 382 |
+
- `eval_strategy`: epoch
|
| 383 |
+
- `learning_rate`: 2e-05
|
| 384 |
+
- `num_train_epochs`: 15
|
| 385 |
+
- `warmup_ratio`: 0.4
|
| 386 |
+
- `fp16`: True
|
| 387 |
+
- `batch_sampler`: no_duplicates
|
| 388 |
+
|
| 389 |
+
#### All Hyperparameters
|
| 390 |
+
<details><summary>Click to expand</summary>
|
| 391 |
+
|
| 392 |
+
- `overwrite_output_dir`: False
|
| 393 |
+
- `do_predict`: False
|
| 394 |
+
- `eval_strategy`: epoch
|
| 395 |
+
- `prediction_loss_only`: True
|
| 396 |
+
- `per_device_train_batch_size`: 8
|
| 397 |
+
- `per_device_eval_batch_size`: 8
|
| 398 |
+
- `per_gpu_train_batch_size`: None
|
| 399 |
+
- `per_gpu_eval_batch_size`: None
|
| 400 |
+
- `gradient_accumulation_steps`: 1
|
| 401 |
+
- `eval_accumulation_steps`: None
|
| 402 |
+
- `torch_empty_cache_steps`: None
|
| 403 |
+
- `learning_rate`: 2e-05
|
| 404 |
+
- `weight_decay`: 0.0
|
| 405 |
+
- `adam_beta1`: 0.9
|
| 406 |
+
- `adam_beta2`: 0.999
|
| 407 |
+
- `adam_epsilon`: 1e-08
|
| 408 |
+
- `max_grad_norm`: 1.0
|
| 409 |
+
- `num_train_epochs`: 15
|
| 410 |
+
- `max_steps`: -1
|
| 411 |
+
- `lr_scheduler_type`: linear
|
| 412 |
+
- `lr_scheduler_kwargs`: {}
|
| 413 |
+
- `warmup_ratio`: 0.4
|
| 414 |
+
- `warmup_steps`: 0
|
| 415 |
+
- `log_level`: passive
|
| 416 |
+
- `log_level_replica`: warning
|
| 417 |
+
- `log_on_each_node`: True
|
| 418 |
+
- `logging_nan_inf_filter`: True
|
| 419 |
+
- `save_safetensors`: True
|
| 420 |
+
- `save_on_each_node`: False
|
| 421 |
+
- `save_only_model`: False
|
| 422 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 423 |
+
- `no_cuda`: False
|
| 424 |
+
- `use_cpu`: False
|
| 425 |
+
- `use_mps_device`: False
|
| 426 |
+
- `seed`: 42
|
| 427 |
+
- `data_seed`: None
|
| 428 |
+
- `jit_mode_eval`: False
|
| 429 |
+
- `use_ipex`: False
|
| 430 |
+
- `bf16`: False
|
| 431 |
+
- `fp16`: True
|
| 432 |
+
- `fp16_opt_level`: O1
|
| 433 |
+
- `half_precision_backend`: auto
|
| 434 |
+
- `bf16_full_eval`: False
|
| 435 |
+
- `fp16_full_eval`: False
|
| 436 |
+
- `tf32`: None
|
| 437 |
+
- `local_rank`: 0
|
| 438 |
+
- `ddp_backend`: None
|
| 439 |
+
- `tpu_num_cores`: None
|
| 440 |
+
- `tpu_metrics_debug`: False
|
| 441 |
+
- `debug`: []
|
| 442 |
+
- `dataloader_drop_last`: False
|
| 443 |
+
- `dataloader_num_workers`: 0
|
| 444 |
+
- `dataloader_prefetch_factor`: None
|
| 445 |
+
- `past_index`: -1
|
| 446 |
+
- `disable_tqdm`: False
|
| 447 |
+
- `remove_unused_columns`: True
|
| 448 |
+
- `label_names`: None
|
| 449 |
+
- `load_best_model_at_end`: False
|
| 450 |
+
- `ignore_data_skip`: False
|
| 451 |
+
- `fsdp`: []
|
| 452 |
+
- `fsdp_min_num_params`: 0
|
| 453 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 454 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 455 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 456 |
+
- `deepspeed`: None
|
| 457 |
+
- `label_smoothing_factor`: 0.0
|
| 458 |
+
- `optim`: adamw_torch
|
| 459 |
+
- `optim_args`: None
|
| 460 |
+
- `adafactor`: False
|
| 461 |
+
- `group_by_length`: False
|
| 462 |
+
- `length_column_name`: length
|
| 463 |
+
- `ddp_find_unused_parameters`: None
|
| 464 |
+
- `ddp_bucket_cap_mb`: None
|
| 465 |
+
- `ddp_broadcast_buffers`: False
|
| 466 |
+
- `dataloader_pin_memory`: True
|
| 467 |
+
- `dataloader_persistent_workers`: False
|
| 468 |
+
- `skip_memory_metrics`: True
|
| 469 |
+
- `use_legacy_prediction_loop`: False
|
| 470 |
+
- `push_to_hub`: False
|
| 471 |
+
- `resume_from_checkpoint`: None
|
| 472 |
+
- `hub_model_id`: None
|
| 473 |
+
- `hub_strategy`: every_save
|
| 474 |
+
- `hub_private_repo`: False
|
| 475 |
+
- `hub_always_push`: False
|
| 476 |
+
- `gradient_checkpointing`: False
|
| 477 |
+
- `gradient_checkpointing_kwargs`: None
|
| 478 |
+
- `include_inputs_for_metrics`: False
|
| 479 |
+
- `eval_do_concat_batches`: True
|
| 480 |
+
- `fp16_backend`: auto
|
| 481 |
+
- `push_to_hub_model_id`: None
|
| 482 |
+
- `push_to_hub_organization`: None
|
| 483 |
+
- `mp_parameters`:
|
| 484 |
+
- `auto_find_batch_size`: False
|
| 485 |
+
- `full_determinism`: False
|
| 486 |
+
- `torchdynamo`: None
|
| 487 |
+
- `ray_scope`: last
|
| 488 |
+
- `ddp_timeout`: 1800
|
| 489 |
+
- `torch_compile`: False
|
| 490 |
+
- `torch_compile_backend`: None
|
| 491 |
+
- `torch_compile_mode`: None
|
| 492 |
+
- `dispatch_batches`: None
|
| 493 |
+
- `split_batches`: None
|
| 494 |
+
- `include_tokens_per_second`: False
|
| 495 |
+
- `include_num_input_tokens_seen`: False
|
| 496 |
+
- `neftune_noise_alpha`: None
|
| 497 |
+
- `optim_target_modules`: None
|
| 498 |
+
- `batch_eval_metrics`: False
|
| 499 |
+
- `eval_on_start`: False
|
| 500 |
+
- `eval_use_gather_object`: False
|
| 501 |
+
- `batch_sampler`: no_duplicates
|
| 502 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 503 |
+
|
| 504 |
+
</details>
|
| 505 |
+
|
| 506 |
+
### Training Logs
|
| 507 |
+
| Epoch | Step | Training Loss | loss | custom-arc-semantics-data-jp_max_ap |
|
| 508 |
+
|:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
|
| 509 |
+
| 1.0 | 6 | 0.2963 | 0.3111 | 0.6821 |
|
| 510 |
+
| 2.0 | 12 | 0.2833 | 0.3096 | 0.7238 |
|
| 511 |
+
| 3.0 | 18 | 0.2568 | 0.3050 | 0.7238 |
|
| 512 |
+
| 4.0 | 24 | 0.2177 | 0.2958 | 0.7238 |
|
| 513 |
+
| 5.0 | 30 | 0.1797 | 0.2826 | 0.6946 |
|
| 514 |
+
| 6.0 | 36 | 0.1419 | 0.2765 | 0.6509 |
|
| 515 |
+
| 7.0 | 42 | 0.1057 | 0.2954 | 0.6509 |
|
| 516 |
+
| 8.0 | 48 | 0.0815 | 0.3165 | 0.6509 |
|
| 517 |
+
| 9.0 | 54 | 0.0664 | 0.3199 | 0.6509 |
|
| 518 |
+
| 10.0 | 60 | 0.0497 | 0.3140 | 0.6509 |
|
| 519 |
+
| 11.0 | 66 | 0.0402 | 0.3081 | 0.6321 |
|
| 520 |
+
| 12.0 | 72 | 0.0346 | 0.3072 | 0.6946 |
|
| 521 |
+
| 13.0 | 78 | 0.0293 | 0.3066 | 0.6946 |
|
| 522 |
+
| 14.0 | 84 | 0.0302 | 0.3076 | 0.6946 |
|
| 523 |
+
|
| 524 |
+
|
| 525 |
+
### Framework Versions
|
| 526 |
+
- Python: 3.10.14
|
| 527 |
+
- Sentence Transformers: 3.1.0
|
| 528 |
+
- Transformers: 4.44.2
|
| 529 |
+
- PyTorch: 2.4.1+cu121
|
| 530 |
+
- Accelerate: 0.34.2
|
| 531 |
+
- Datasets: 2.20.0
|
| 532 |
+
- Tokenizers: 0.19.1
|
| 533 |
+
|
| 534 |
+
## Citation
|
| 535 |
+
|
| 536 |
+
### BibTeX
|
| 537 |
+
|
| 538 |
+
#### Sentence Transformers
|
| 539 |
+
```bibtex
|
| 540 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 541 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 542 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 543 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 544 |
+
month = "11",
|
| 545 |
+
year = "2019",
|
| 546 |
+
publisher = "Association for Computational Linguistics",
|
| 547 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 548 |
+
}
|
| 549 |
+
```
|
| 550 |
+
|
| 551 |
+
<!--
|
| 552 |
+
## Glossary
|
| 553 |
+
|
| 554 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 555 |
+
-->
|
| 556 |
+
|
| 557 |
+
<!--
|
| 558 |
+
## Model Card Authors
|
| 559 |
+
|
| 560 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 561 |
+
-->
|
| 562 |
+
|
| 563 |
+
<!--
|
| 564 |
+
## Model Card Contact
|
| 565 |
+
|
| 566 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 567 |
+
-->
|
checkpoint-84/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
checkpoint-84/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "colorfulscoop/sbert-base-ja",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"cls_token_id": 2,
|
| 10 |
+
"eos_token_id": 3,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"layer_norm_eps": 1e-12,
|
| 18 |
+
"mask_token_id": 4,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"sep_token_id": 3,
|
| 26 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.44.2",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"unk_token_id": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32000
|
| 33 |
+
}
|
checkpoint-84/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.1.0",
|
| 4 |
+
"transformers": "4.44.2",
|
| 5 |
+
"pytorch": "2.4.1+cu121"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
checkpoint-84/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acdaff3103689cfe56522b5c693c4884f7abd661e30524b824e4ce2622bee97d
|
| 3 |
+
size 442491744
|
checkpoint-84/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 |
+
]
|
checkpoint-84/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31fdb32066d6a1b6dfcd1d2137aaa7f4f1bf9ba01e4ff596ccd06bf3a2a9ed59
|
| 3 |
+
size 880373306
|
checkpoint-84/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:940e4e36bcd8649ee1c10f895113f68d5e3153f4e3b24afa600e353656344e9a
|
| 3 |
+
size 13990
|
checkpoint-84/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c507b81b350b717234ee637a426e683f613d7a7fe5d535f96e8991005b154ddf
|
| 3 |
+
size 1064
|
checkpoint-84/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-84/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "<unk>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
checkpoint-84/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6467857b4b0c77ded9bac7ad2fb5c16eb64e17e417ce46624dacac2bbb404fc
|
| 3 |
+
size 802713
|
checkpoint-84/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-84/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": true,
|
| 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": false
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"32000": {
|
| 44 |
+
"content": "[PAD]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "[CLS]",
|
| 53 |
+
"clean_up_tokenization_spaces": true,
|
| 54 |
+
"cls_token": "[CLS]",
|
| 55 |
+
"do_lower_case": false,
|
| 56 |
+
"eos_token": "[SEP]",
|
| 57 |
+
"mask_token": "[MASK]",
|
| 58 |
+
"model_max_length": 512,
|
| 59 |
+
"pad_token": "<pad>",
|
| 60 |
+
"sep_token": "[SEP]",
|
| 61 |
+
"sp_model_kwargs": {},
|
| 62 |
+
"split_by_punct": false,
|
| 63 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 64 |
+
"unk_token": "<unk>"
|
| 65 |
+
}
|
checkpoint-84/trainer_state.json
ADDED
|
@@ -0,0 +1,733 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 14.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 84,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 4.725662708282471,
|
| 14 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 15 |
+
"loss": 0.2963,
|
| 16 |
+
"step": 6
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 21 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.30786412954330444,
|
| 22 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.682129329004329,
|
| 23 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 24 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.30786412954330444,
|
| 25 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 26 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 27 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 28 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 172.38189697265625,
|
| 29 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.682129329004329,
|
| 30 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 31 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 172.38189697265625,
|
| 32 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 33 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 34 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 35 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.785310745239258,
|
| 36 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.682129329004329,
|
| 37 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 38 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.785310745239258,
|
| 39 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 40 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 41 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 42 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 612.4951171875,
|
| 43 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.6612959956709956,
|
| 44 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 45 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 612.4951171875,
|
| 46 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 47 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 48 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 49 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 612.4951171875,
|
| 50 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.682129329004329,
|
| 51 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 52 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 612.4951171875,
|
| 53 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 54 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 55 |
+
"eval_loss": 0.3111322224140167,
|
| 56 |
+
"eval_runtime": 6.0296,
|
| 57 |
+
"eval_samples_per_second": 1.824,
|
| 58 |
+
"eval_steps_per_second": 0.332,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"grad_norm": 4.223657608032227,
|
| 64 |
+
"learning_rate": 6.666666666666667e-06,
|
| 65 |
+
"loss": 0.2833,
|
| 66 |
+
"step": 12
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.0,
|
| 70 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 71 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3102341890335083,
|
| 72 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.7237959956709956,
|
| 73 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 74 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3102341890335083,
|
| 75 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 76 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 77 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 78 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 173.5974578857422,
|
| 79 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.682129329004329,
|
| 80 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 81 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 173.5974578857422,
|
| 82 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 83 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 84 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 85 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.73798179626465,
|
| 86 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.7237959956709956,
|
| 87 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 88 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.73798179626465,
|
| 89 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 90 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 91 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 92 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 610.9443359375,
|
| 93 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.7237959956709956,
|
| 94 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 95 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 610.9443359375,
|
| 96 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 97 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 98 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 99 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 610.9443359375,
|
| 100 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.7237959956709956,
|
| 101 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 102 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 610.9443359375,
|
| 103 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 104 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 105 |
+
"eval_loss": 0.309558629989624,
|
| 106 |
+
"eval_runtime": 5.9488,
|
| 107 |
+
"eval_samples_per_second": 1.849,
|
| 108 |
+
"eval_steps_per_second": 0.336,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 3.0,
|
| 113 |
+
"grad_norm": 3.3170320987701416,
|
| 114 |
+
"learning_rate": 1e-05,
|
| 115 |
+
"loss": 0.2568,
|
| 116 |
+
"step": 18
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.0,
|
| 120 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 121 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3211533725261688,
|
| 122 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.7237959956709956,
|
| 123 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 124 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3211533725261688,
|
| 125 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 126 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 127 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 128 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 179.75201416015625,
|
| 129 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.7237959956709956,
|
| 130 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 131 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 179.75201416015625,
|
| 132 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 133 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 134 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 135 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.536266326904297,
|
| 136 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.7237959956709956,
|
| 137 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 138 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.536266326904297,
|
| 139 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 140 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 141 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 142 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 605.5822143554688,
|
| 143 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.7237959956709956,
|
| 144 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 145 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 605.5822143554688,
|
| 146 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 147 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 148 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 149 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 605.5822143554688,
|
| 150 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.7237959956709956,
|
| 151 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 152 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 605.5822143554688,
|
| 153 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 154 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 155 |
+
"eval_loss": 0.304984450340271,
|
| 156 |
+
"eval_runtime": 7.2979,
|
| 157 |
+
"eval_samples_per_second": 1.507,
|
| 158 |
+
"eval_steps_per_second": 0.274,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.0,
|
| 163 |
+
"grad_norm": 2.2900643348693848,
|
| 164 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 165 |
+
"loss": 0.2177,
|
| 166 |
+
"step": 24
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 4.0,
|
| 170 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 171 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3480110168457031,
|
| 172 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.7237959956709956,
|
| 173 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 174 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3480110168457031,
|
| 175 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 176 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 177 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 178 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 195.35403442382812,
|
| 179 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.7237959956709956,
|
| 180 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 181 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 195.35403442382812,
|
| 182 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 183 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 184 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 185 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.041318893432617,
|
| 186 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.682129329004329,
|
| 187 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 188 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.041318893432617,
|
| 189 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 190 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 191 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 192 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 593.150634765625,
|
| 193 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.682129329004329,
|
| 194 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 195 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 593.150634765625,
|
| 196 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 197 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 198 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 199 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 593.150634765625,
|
| 200 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.7237959956709956,
|
| 201 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 202 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 593.150634765625,
|
| 203 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 204 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 205 |
+
"eval_loss": 0.29575565457344055,
|
| 206 |
+
"eval_runtime": 6.0903,
|
| 207 |
+
"eval_samples_per_second": 1.806,
|
| 208 |
+
"eval_steps_per_second": 0.328,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.0,
|
| 213 |
+
"grad_norm": 1.5022671222686768,
|
| 214 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 215 |
+
"loss": 0.1797,
|
| 216 |
+
"step": 30
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.0,
|
| 220 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 221 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3965001106262207,
|
| 222 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.682129329004329,
|
| 223 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 224 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3965001106262207,
|
| 225 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 226 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 227 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 228 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 223.7809295654297,
|
| 229 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.6946293290043289,
|
| 230 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 231 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 223.7809295654297,
|
| 232 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 233 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 234 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 235 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 26.097108840942383,
|
| 236 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.682129329004329,
|
| 237 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 238 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 26.097108840942383,
|
| 239 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 240 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 241 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 242 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 570.329345703125,
|
| 243 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.682129329004329,
|
| 244 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 245 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 570.329345703125,
|
| 246 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 247 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 248 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 249 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 570.329345703125,
|
| 250 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.6946293290043289,
|
| 251 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 252 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 570.329345703125,
|
| 253 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 254 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 255 |
+
"eval_loss": 0.28263404965400696,
|
| 256 |
+
"eval_runtime": 6.0031,
|
| 257 |
+
"eval_samples_per_second": 1.832,
|
| 258 |
+
"eval_steps_per_second": 0.333,
|
| 259 |
+
"step": 30
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 6.0,
|
| 263 |
+
"grad_norm": 0.6781304478645325,
|
| 264 |
+
"learning_rate": 2e-05,
|
| 265 |
+
"loss": 0.1419,
|
| 266 |
+
"step": 36
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.0,
|
| 270 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 271 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.43997177481651306,
|
| 272 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.6321293290043289,
|
| 273 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 274 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.43997177481651306,
|
| 275 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 276 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 277 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 278 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 249.57528686523438,
|
| 279 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.650879329004329,
|
| 280 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 281 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 249.57528686523438,
|
| 282 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 283 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 284 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 285 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 25.200597763061523,
|
| 286 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.6321293290043289,
|
| 287 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 288 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 25.200597763061523,
|
| 289 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 290 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 291 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 292 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 550.5452880859375,
|
| 293 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.6321293290043289,
|
| 294 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 295 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 550.5452880859375,
|
| 296 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 297 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 298 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 299 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 550.5452880859375,
|
| 300 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.650879329004329,
|
| 301 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 302 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 550.5452880859375,
|
| 303 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 304 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 305 |
+
"eval_loss": 0.276452898979187,
|
| 306 |
+
"eval_runtime": 5.4943,
|
| 307 |
+
"eval_samples_per_second": 2.002,
|
| 308 |
+
"eval_steps_per_second": 0.364,
|
| 309 |
+
"step": 36
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.0,
|
| 313 |
+
"grad_norm": 0.4487136900424957,
|
| 314 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 315 |
+
"loss": 0.1057,
|
| 316 |
+
"step": 42
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 7.0,
|
| 320 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 321 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.37805190682411194,
|
| 322 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.6321293290043289,
|
| 323 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 324 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.37805190682411194,
|
| 325 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 326 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 327 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 328 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 211.4693603515625,
|
| 329 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.650879329004329,
|
| 330 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 331 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 211.4693603515625,
|
| 332 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 333 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 334 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 335 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 26.396636962890625,
|
| 336 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.6321293290043289,
|
| 337 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 338 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 26.396636962890625,
|
| 339 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 340 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 341 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 342 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 582.5875244140625,
|
| 343 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.6321293290043289,
|
| 344 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 345 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 582.5875244140625,
|
| 346 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 347 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 348 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 349 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 582.5875244140625,
|
| 350 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.650879329004329,
|
| 351 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 352 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 582.5875244140625,
|
| 353 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 354 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 355 |
+
"eval_loss": 0.295420378446579,
|
| 356 |
+
"eval_runtime": 6.1313,
|
| 357 |
+
"eval_samples_per_second": 1.794,
|
| 358 |
+
"eval_steps_per_second": 0.326,
|
| 359 |
+
"step": 42
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 8.0,
|
| 363 |
+
"grad_norm": 0.16805221140384674,
|
| 364 |
+
"learning_rate": 1.555555555555556e-05,
|
| 365 |
+
"loss": 0.0815,
|
| 366 |
+
"step": 48
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.0,
|
| 370 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 371 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.31827351450920105,
|
| 372 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.6321293290043289,
|
| 373 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 374 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.31827351450920105,
|
| 375 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 376 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 377 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 378 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 178.09083557128906,
|
| 379 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.650879329004329,
|
| 380 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 381 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 178.09083557128906,
|
| 382 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 383 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 384 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 385 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.63851547241211,
|
| 386 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.6321293290043289,
|
| 387 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 388 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.63851547241211,
|
| 389 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 390 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 391 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 392 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 612.4237060546875,
|
| 393 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.6321293290043289,
|
| 394 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 395 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 612.4237060546875,
|
| 396 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 397 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 398 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 399 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 612.4237060546875,
|
| 400 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.650879329004329,
|
| 401 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 402 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 612.4237060546875,
|
| 403 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 404 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 405 |
+
"eval_loss": 0.3164561986923218,
|
| 406 |
+
"eval_runtime": 6.5067,
|
| 407 |
+
"eval_samples_per_second": 1.691,
|
| 408 |
+
"eval_steps_per_second": 0.307,
|
| 409 |
+
"step": 48
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 9.0,
|
| 413 |
+
"grad_norm": 0.16789764165878296,
|
| 414 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 415 |
+
"loss": 0.0664,
|
| 416 |
+
"step": 54
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 9.0,
|
| 420 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 421 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.30298155546188354,
|
| 422 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.6321293290043289,
|
| 423 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 424 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.30298155546188354,
|
| 425 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 426 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 427 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 428 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 169.24606323242188,
|
| 429 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.650879329004329,
|
| 430 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 431 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 169.24606323242188,
|
| 432 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 433 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 434 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 435 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.91897964477539,
|
| 436 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 437 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 438 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.91897964477539,
|
| 439 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 440 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 441 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 442 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 618.7899169921875,
|
| 443 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 444 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 445 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 618.7899169921875,
|
| 446 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 447 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 448 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 449 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 618.7899169921875,
|
| 450 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.650879329004329,
|
| 451 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 452 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 618.7899169921875,
|
| 453 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 454 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 455 |
+
"eval_loss": 0.31994009017944336,
|
| 456 |
+
"eval_runtime": 6.8319,
|
| 457 |
+
"eval_samples_per_second": 1.61,
|
| 458 |
+
"eval_steps_per_second": 0.293,
|
| 459 |
+
"step": 54
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.0,
|
| 463 |
+
"grad_norm": 0.1519097536802292,
|
| 464 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 465 |
+
"loss": 0.0497,
|
| 466 |
+
"step": 60
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 10.0,
|
| 470 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 471 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.31682828068733215,
|
| 472 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.6321293290043289,
|
| 473 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 474 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.31682828068733215,
|
| 475 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 476 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 477 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 478 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 176.45004272460938,
|
| 479 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.650879329004329,
|
| 480 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 481 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 176.45004272460938,
|
| 482 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 483 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 484 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 485 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.598316192626953,
|
| 486 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 487 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 488 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.598316192626953,
|
| 489 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 490 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 491 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 492 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 611.2236328125,
|
| 493 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 494 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 495 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 611.2236328125,
|
| 496 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 497 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 498 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 499 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 611.2236328125,
|
| 500 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.650879329004329,
|
| 501 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 502 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 611.2236328125,
|
| 503 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 504 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 505 |
+
"eval_loss": 0.31398141384124756,
|
| 506 |
+
"eval_runtime": 6.4168,
|
| 507 |
+
"eval_samples_per_second": 1.714,
|
| 508 |
+
"eval_steps_per_second": 0.312,
|
| 509 |
+
"step": 60
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 11.0,
|
| 513 |
+
"grad_norm": 0.17287826538085938,
|
| 514 |
+
"learning_rate": 8.888888888888888e-06,
|
| 515 |
+
"loss": 0.0402,
|
| 516 |
+
"step": 66
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 11.0,
|
| 520 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 521 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.33553600311279297,
|
| 522 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.619629329004329,
|
| 523 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 524 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.33553600311279297,
|
| 525 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 526 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 527 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 528 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 186.30569458007812,
|
| 529 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.6321293290043289,
|
| 530 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 531 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 186.30569458007812,
|
| 532 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 533 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 534 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 535 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.178071975708008,
|
| 536 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 537 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 538 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.178071975708008,
|
| 539 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 540 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 541 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 542 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 601.0965576171875,
|
| 543 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 544 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 545 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 601.0965576171875,
|
| 546 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 547 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 548 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 549 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 601.0965576171875,
|
| 550 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.6321293290043289,
|
| 551 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 552 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 601.0965576171875,
|
| 553 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 554 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 555 |
+
"eval_loss": 0.3081442415714264,
|
| 556 |
+
"eval_runtime": 6.4435,
|
| 557 |
+
"eval_samples_per_second": 1.707,
|
| 558 |
+
"eval_steps_per_second": 0.31,
|
| 559 |
+
"step": 66
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 12.0,
|
| 563 |
+
"grad_norm": 0.1389617770910263,
|
| 564 |
+
"learning_rate": 6.666666666666667e-06,
|
| 565 |
+
"loss": 0.0346,
|
| 566 |
+
"step": 72
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 12.0,
|
| 570 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 571 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3391532003879547,
|
| 572 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.619629329004329,
|
| 573 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 574 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3391532003879547,
|
| 575 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 576 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 577 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 578 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 187.9766082763672,
|
| 579 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.6946293290043289,
|
| 580 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 581 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 187.9766082763672,
|
| 582 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 583 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 584 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 585 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.080123901367188,
|
| 586 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 587 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 588 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.080123901367188,
|
| 589 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 590 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 591 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 592 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 598.4072265625,
|
| 593 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 594 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 595 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 598.4072265625,
|
| 596 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 597 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 598 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 599 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 598.4072265625,
|
| 600 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.6946293290043289,
|
| 601 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 602 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 598.4072265625,
|
| 603 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 604 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 605 |
+
"eval_loss": 0.30722811818122864,
|
| 606 |
+
"eval_runtime": 6.555,
|
| 607 |
+
"eval_samples_per_second": 1.678,
|
| 608 |
+
"eval_steps_per_second": 0.305,
|
| 609 |
+
"step": 72
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.0,
|
| 613 |
+
"grad_norm": 0.10099858045578003,
|
| 614 |
+
"learning_rate": 4.444444444444444e-06,
|
| 615 |
+
"loss": 0.0293,
|
| 616 |
+
"step": 78
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 13.0,
|
| 620 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 621 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.34109100699424744,
|
| 622 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.619629329004329,
|
| 623 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 624 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.34109100699424744,
|
| 625 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 626 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 627 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 628 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 189.05935668945312,
|
| 629 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.6946293290043289,
|
| 630 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 631 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 189.05935668945312,
|
| 632 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 633 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 634 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 635 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.041587829589844,
|
| 636 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 637 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 638 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.041587829589844,
|
| 639 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 640 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 641 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 642 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 597.2989501953125,
|
| 643 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 644 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 645 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 597.2989501953125,
|
| 646 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 647 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 648 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 649 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 597.2989501953125,
|
| 650 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.6946293290043289,
|
| 651 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 652 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 597.2989501953125,
|
| 653 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 654 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 655 |
+
"eval_loss": 0.30660775303840637,
|
| 656 |
+
"eval_runtime": 5.9875,
|
| 657 |
+
"eval_samples_per_second": 1.837,
|
| 658 |
+
"eval_steps_per_second": 0.334,
|
| 659 |
+
"step": 78
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 14.0,
|
| 663 |
+
"grad_norm": 0.12931989133358002,
|
| 664 |
+
"learning_rate": 2.222222222222222e-06,
|
| 665 |
+
"loss": 0.0302,
|
| 666 |
+
"step": 84
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 14.0,
|
| 670 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 671 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3385917544364929,
|
| 672 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.619629329004329,
|
| 673 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 674 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3385917544364929,
|
| 675 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 676 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 677 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 678 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 187.77444458007812,
|
| 679 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.6946293290043289,
|
| 680 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 681 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 187.77444458007812,
|
| 682 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 683 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 684 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 685 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.100971221923828,
|
| 686 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 687 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 688 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.100971221923828,
|
| 689 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 690 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 691 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 692 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 598.5726318359375,
|
| 693 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 694 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 695 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 598.5726318359375,
|
| 696 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 697 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 698 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 699 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 598.5726318359375,
|
| 700 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.6946293290043289,
|
| 701 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 702 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 598.5726318359375,
|
| 703 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 704 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 705 |
+
"eval_loss": 0.30758312344551086,
|
| 706 |
+
"eval_runtime": 5.1895,
|
| 707 |
+
"eval_samples_per_second": 2.12,
|
| 708 |
+
"eval_steps_per_second": 0.385,
|
| 709 |
+
"step": 84
|
| 710 |
+
}
|
| 711 |
+
],
|
| 712 |
+
"logging_steps": 500,
|
| 713 |
+
"max_steps": 90,
|
| 714 |
+
"num_input_tokens_seen": 0,
|
| 715 |
+
"num_train_epochs": 15,
|
| 716 |
+
"save_steps": 100,
|
| 717 |
+
"stateful_callbacks": {
|
| 718 |
+
"TrainerControl": {
|
| 719 |
+
"args": {
|
| 720 |
+
"should_epoch_stop": false,
|
| 721 |
+
"should_evaluate": false,
|
| 722 |
+
"should_log": false,
|
| 723 |
+
"should_save": true,
|
| 724 |
+
"should_training_stop": false
|
| 725 |
+
},
|
| 726 |
+
"attributes": {}
|
| 727 |
+
}
|
| 728 |
+
},
|
| 729 |
+
"total_flos": 0.0,
|
| 730 |
+
"train_batch_size": 8,
|
| 731 |
+
"trial_name": null,
|
| 732 |
+
"trial_params": null
|
| 733 |
+
}
|
checkpoint-84/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab31a2f266552701315e4b4912e7ee4f071025a38324aa7dab7a38f1da2132a2
|
| 3 |
+
size 5432
|
checkpoint-90/1_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 |
+
}
|
checkpoint-90/README.md
ADDED
|
@@ -0,0 +1,568 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: colorfulscoop/sbert-base-ja
|
| 3 |
+
library_name: sentence-transformers
|
| 4 |
+
metrics:
|
| 5 |
+
- cosine_accuracy
|
| 6 |
+
- cosine_accuracy_threshold
|
| 7 |
+
- cosine_f1
|
| 8 |
+
- cosine_f1_threshold
|
| 9 |
+
- cosine_precision
|
| 10 |
+
- cosine_recall
|
| 11 |
+
- cosine_ap
|
| 12 |
+
- dot_accuracy
|
| 13 |
+
- dot_accuracy_threshold
|
| 14 |
+
- dot_f1
|
| 15 |
+
- dot_f1_threshold
|
| 16 |
+
- dot_precision
|
| 17 |
+
- dot_recall
|
| 18 |
+
- dot_ap
|
| 19 |
+
- manhattan_accuracy
|
| 20 |
+
- manhattan_accuracy_threshold
|
| 21 |
+
- manhattan_f1
|
| 22 |
+
- manhattan_f1_threshold
|
| 23 |
+
- manhattan_precision
|
| 24 |
+
- manhattan_recall
|
| 25 |
+
- manhattan_ap
|
| 26 |
+
- euclidean_accuracy
|
| 27 |
+
- euclidean_accuracy_threshold
|
| 28 |
+
- euclidean_f1
|
| 29 |
+
- euclidean_f1_threshold
|
| 30 |
+
- euclidean_precision
|
| 31 |
+
- euclidean_recall
|
| 32 |
+
- euclidean_ap
|
| 33 |
+
- max_accuracy
|
| 34 |
+
- max_accuracy_threshold
|
| 35 |
+
- max_f1
|
| 36 |
+
- max_f1_threshold
|
| 37 |
+
- max_precision
|
| 38 |
+
- max_recall
|
| 39 |
+
- max_ap
|
| 40 |
+
pipeline_tag: sentence-similarity
|
| 41 |
+
tags:
|
| 42 |
+
- sentence-transformers
|
| 43 |
+
- sentence-similarity
|
| 44 |
+
- feature-extraction
|
| 45 |
+
- generated_from_trainer
|
| 46 |
+
- dataset_size:53
|
| 47 |
+
- loss:CosineSimilarityLoss
|
| 48 |
+
widget:
|
| 49 |
+
- source_sentence: 黒い タイル の 本当に すてきな カウンター の 前 と 後ろ で 働く 人々 。
|
| 50 |
+
sentences:
|
| 51 |
+
- 男性 は バレエ に 参加 して い ます 。
|
| 52 |
+
- 岩 の 上 に 座って いる 二 人
|
| 53 |
+
- 人々 は 宝石 店 で 働いて い ます 。
|
| 54 |
+
- source_sentence: 少年 は 木 の 切り株 に 座って い ます 。
|
| 55 |
+
sentences:
|
| 56 |
+
- ストリート ワーカー は 保護 具 を 着用 して い ませ ん 。
|
| 57 |
+
- 芝生 の エリア で 数 匹 の 犬 が 交流 し ます 。
|
| 58 |
+
- 木 を 切り 倒した 後 、 木 の 切り株 に 座って いる 少年 。
|
| 59 |
+
- source_sentence: 岩 の 多い 景色 を 見て 二 人
|
| 60 |
+
sentences:
|
| 61 |
+
- 何 か を 見て いる 二 人 が い ます 。
|
| 62 |
+
- 誰 か が 肖像 画 を 描いて い ます 。
|
| 63 |
+
- バイカー は 足 を 使って 自転車 を さらに 進め ます 。
|
| 64 |
+
model-index:
|
| 65 |
+
- name: SentenceTransformer based on colorfulscoop/sbert-base-ja
|
| 66 |
+
results:
|
| 67 |
+
- task:
|
| 68 |
+
type: binary-classification
|
| 69 |
+
name: Binary Classification
|
| 70 |
+
dataset:
|
| 71 |
+
name: custom arc semantics data jp
|
| 72 |
+
type: custom-arc-semantics-data-jp
|
| 73 |
+
metrics:
|
| 74 |
+
- type: cosine_accuracy
|
| 75 |
+
value: 0.6363636363636364
|
| 76 |
+
name: Cosine Accuracy
|
| 77 |
+
- type: cosine_accuracy_threshold
|
| 78 |
+
value: 0.3379952907562256
|
| 79 |
+
name: Cosine Accuracy Threshold
|
| 80 |
+
- type: cosine_f1
|
| 81 |
+
value: 0.7777777777777777
|
| 82 |
+
name: Cosine F1
|
| 83 |
+
- type: cosine_f1_threshold
|
| 84 |
+
value: 0.3379952907562256
|
| 85 |
+
name: Cosine F1 Threshold
|
| 86 |
+
- type: cosine_precision
|
| 87 |
+
value: 0.7
|
| 88 |
+
name: Cosine Precision
|
| 89 |
+
- type: cosine_recall
|
| 90 |
+
value: 0.875
|
| 91 |
+
name: Cosine Recall
|
| 92 |
+
- type: cosine_ap
|
| 93 |
+
value: 0.619629329004329
|
| 94 |
+
name: Cosine Ap
|
| 95 |
+
- type: dot_accuracy
|
| 96 |
+
value: 0.6363636363636364
|
| 97 |
+
name: Dot Accuracy
|
| 98 |
+
- type: dot_accuracy_threshold
|
| 99 |
+
value: 187.5118865966797
|
| 100 |
+
name: Dot Accuracy Threshold
|
| 101 |
+
- type: dot_f1
|
| 102 |
+
value: 0.7777777777777777
|
| 103 |
+
name: Dot F1
|
| 104 |
+
- type: dot_f1_threshold
|
| 105 |
+
value: 187.5118865966797
|
| 106 |
+
name: Dot F1 Threshold
|
| 107 |
+
- type: dot_precision
|
| 108 |
+
value: 0.7
|
| 109 |
+
name: Dot Precision
|
| 110 |
+
- type: dot_recall
|
| 111 |
+
value: 0.875
|
| 112 |
+
name: Dot Recall
|
| 113 |
+
- type: dot_ap
|
| 114 |
+
value: 0.6946293290043289
|
| 115 |
+
name: Dot Ap
|
| 116 |
+
- type: manhattan_accuracy
|
| 117 |
+
value: 0.6363636363636364
|
| 118 |
+
name: Manhattan Accuracy
|
| 119 |
+
- type: manhattan_accuracy_threshold
|
| 120 |
+
value: 598.9317626953125
|
| 121 |
+
name: Manhattan Accuracy Threshold
|
| 122 |
+
- type: manhattan_f1
|
| 123 |
+
value: 0.7777777777777777
|
| 124 |
+
name: Manhattan F1
|
| 125 |
+
- type: manhattan_f1_threshold
|
| 126 |
+
value: 598.9317626953125
|
| 127 |
+
name: Manhattan F1 Threshold
|
| 128 |
+
- type: manhattan_precision
|
| 129 |
+
value: 0.7
|
| 130 |
+
name: Manhattan Precision
|
| 131 |
+
- type: manhattan_recall
|
| 132 |
+
value: 0.875
|
| 133 |
+
name: Manhattan Recall
|
| 134 |
+
- type: manhattan_ap
|
| 135 |
+
value: 0.619629329004329
|
| 136 |
+
name: Manhattan Ap
|
| 137 |
+
- type: euclidean_accuracy
|
| 138 |
+
value: 0.6363636363636364
|
| 139 |
+
name: Euclidean Accuracy
|
| 140 |
+
- type: euclidean_accuracy_threshold
|
| 141 |
+
value: 27.118305206298828
|
| 142 |
+
name: Euclidean Accuracy Threshold
|
| 143 |
+
- type: euclidean_f1
|
| 144 |
+
value: 0.7777777777777777
|
| 145 |
+
name: Euclidean F1
|
| 146 |
+
- type: euclidean_f1_threshold
|
| 147 |
+
value: 27.118305206298828
|
| 148 |
+
name: Euclidean F1 Threshold
|
| 149 |
+
- type: euclidean_precision
|
| 150 |
+
value: 0.7
|
| 151 |
+
name: Euclidean Precision
|
| 152 |
+
- type: euclidean_recall
|
| 153 |
+
value: 0.875
|
| 154 |
+
name: Euclidean Recall
|
| 155 |
+
- type: euclidean_ap
|
| 156 |
+
value: 0.619629329004329
|
| 157 |
+
name: Euclidean Ap
|
| 158 |
+
- type: max_accuracy
|
| 159 |
+
value: 0.6363636363636364
|
| 160 |
+
name: Max Accuracy
|
| 161 |
+
- type: max_accuracy_threshold
|
| 162 |
+
value: 598.9317626953125
|
| 163 |
+
name: Max Accuracy Threshold
|
| 164 |
+
- type: max_f1
|
| 165 |
+
value: 0.7777777777777777
|
| 166 |
+
name: Max F1
|
| 167 |
+
- type: max_f1_threshold
|
| 168 |
+
value: 598.9317626953125
|
| 169 |
+
name: Max F1 Threshold
|
| 170 |
+
- type: max_precision
|
| 171 |
+
value: 0.7
|
| 172 |
+
name: Max Precision
|
| 173 |
+
- type: max_recall
|
| 174 |
+
value: 0.875
|
| 175 |
+
name: Max Recall
|
| 176 |
+
- type: max_ap
|
| 177 |
+
value: 0.6946293290043289
|
| 178 |
+
name: Max Ap
|
| 179 |
+
---
|
| 180 |
+
|
| 181 |
+
# SentenceTransformer based on colorfulscoop/sbert-base-ja
|
| 182 |
+
|
| 183 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) on the csv dataset. 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.
|
| 184 |
+
|
| 185 |
+
## Model Details
|
| 186 |
+
|
| 187 |
+
### Model Description
|
| 188 |
+
- **Model Type:** Sentence Transformer
|
| 189 |
+
- **Base model:** [colorfulscoop/sbert-base-ja](https://huggingface.co/colorfulscoop/sbert-base-ja) <!-- at revision ecb8a98cd5176719ff7ab0d770a27420118732cf -->
|
| 190 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 191 |
+
- **Output Dimensionality:** 768 tokens
|
| 192 |
+
- **Similarity Function:** Cosine Similarity
|
| 193 |
+
- **Training Dataset:**
|
| 194 |
+
- csv
|
| 195 |
+
<!-- - **Language:** Unknown -->
|
| 196 |
+
<!-- - **License:** Unknown -->
|
| 197 |
+
|
| 198 |
+
### Model Sources
|
| 199 |
+
|
| 200 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 201 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 202 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 203 |
+
|
| 204 |
+
### Full Model Architecture
|
| 205 |
+
|
| 206 |
+
```
|
| 207 |
+
SentenceTransformer(
|
| 208 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: BertModel
|
| 209 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
| 210 |
+
)
|
| 211 |
+
```
|
| 212 |
+
|
| 213 |
+
## Usage
|
| 214 |
+
|
| 215 |
+
### Direct Usage (Sentence Transformers)
|
| 216 |
+
|
| 217 |
+
First install the Sentence Transformers library:
|
| 218 |
+
|
| 219 |
+
```bash
|
| 220 |
+
pip install -U sentence-transformers
|
| 221 |
+
```
|
| 222 |
+
|
| 223 |
+
Then you can load this model and run inference.
|
| 224 |
+
```python
|
| 225 |
+
from sentence_transformers import SentenceTransformer
|
| 226 |
+
|
| 227 |
+
# Download from the 🤗 Hub
|
| 228 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 229 |
+
# Run inference
|
| 230 |
+
sentences = [
|
| 231 |
+
'岩 の 多い 景色 を 見て 二 人',
|
| 232 |
+
'何 か を 見て いる 二 人 が い ます 。',
|
| 233 |
+
'誰 か が 肖像 画 を 描いて い ます 。',
|
| 234 |
+
]
|
| 235 |
+
embeddings = model.encode(sentences)
|
| 236 |
+
print(embeddings.shape)
|
| 237 |
+
# [3, 768]
|
| 238 |
+
|
| 239 |
+
# Get the similarity scores for the embeddings
|
| 240 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 241 |
+
print(similarities.shape)
|
| 242 |
+
# [3, 3]
|
| 243 |
+
```
|
| 244 |
+
|
| 245 |
+
<!--
|
| 246 |
+
### Direct Usage (Transformers)
|
| 247 |
+
|
| 248 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 249 |
+
|
| 250 |
+
</details>
|
| 251 |
+
-->
|
| 252 |
+
|
| 253 |
+
<!--
|
| 254 |
+
### Downstream Usage (Sentence Transformers)
|
| 255 |
+
|
| 256 |
+
You can finetune this model on your own dataset.
|
| 257 |
+
|
| 258 |
+
<details><summary>Click to expand</summary>
|
| 259 |
+
|
| 260 |
+
</details>
|
| 261 |
+
-->
|
| 262 |
+
|
| 263 |
+
<!--
|
| 264 |
+
### Out-of-Scope Use
|
| 265 |
+
|
| 266 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 267 |
+
-->
|
| 268 |
+
|
| 269 |
+
## Evaluation
|
| 270 |
+
|
| 271 |
+
### Metrics
|
| 272 |
+
|
| 273 |
+
#### Binary Classification
|
| 274 |
+
* Dataset: `custom-arc-semantics-data-jp`
|
| 275 |
+
* Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator)
|
| 276 |
+
|
| 277 |
+
| Metric | Value |
|
| 278 |
+
|:-----------------------------|:-----------|
|
| 279 |
+
| cosine_accuracy | 0.6364 |
|
| 280 |
+
| cosine_accuracy_threshold | 0.338 |
|
| 281 |
+
| cosine_f1 | 0.7778 |
|
| 282 |
+
| cosine_f1_threshold | 0.338 |
|
| 283 |
+
| cosine_precision | 0.7 |
|
| 284 |
+
| cosine_recall | 0.875 |
|
| 285 |
+
| cosine_ap | 0.6196 |
|
| 286 |
+
| dot_accuracy | 0.6364 |
|
| 287 |
+
| dot_accuracy_threshold | 187.5119 |
|
| 288 |
+
| dot_f1 | 0.7778 |
|
| 289 |
+
| dot_f1_threshold | 187.5119 |
|
| 290 |
+
| dot_precision | 0.7 |
|
| 291 |
+
| dot_recall | 0.875 |
|
| 292 |
+
| dot_ap | 0.6946 |
|
| 293 |
+
| manhattan_accuracy | 0.6364 |
|
| 294 |
+
| manhattan_accuracy_threshold | 598.9318 |
|
| 295 |
+
| manhattan_f1 | 0.7778 |
|
| 296 |
+
| manhattan_f1_threshold | 598.9318 |
|
| 297 |
+
| manhattan_precision | 0.7 |
|
| 298 |
+
| manhattan_recall | 0.875 |
|
| 299 |
+
| manhattan_ap | 0.6196 |
|
| 300 |
+
| euclidean_accuracy | 0.6364 |
|
| 301 |
+
| euclidean_accuracy_threshold | 27.1183 |
|
| 302 |
+
| euclidean_f1 | 0.7778 |
|
| 303 |
+
| euclidean_f1_threshold | 27.1183 |
|
| 304 |
+
| euclidean_precision | 0.7 |
|
| 305 |
+
| euclidean_recall | 0.875 |
|
| 306 |
+
| euclidean_ap | 0.6196 |
|
| 307 |
+
| max_accuracy | 0.6364 |
|
| 308 |
+
| max_accuracy_threshold | 598.9318 |
|
| 309 |
+
| max_f1 | 0.7778 |
|
| 310 |
+
| max_f1_threshold | 598.9318 |
|
| 311 |
+
| max_precision | 0.7 |
|
| 312 |
+
| max_recall | 0.875 |
|
| 313 |
+
| **max_ap** | **0.6946** |
|
| 314 |
+
|
| 315 |
+
<!--
|
| 316 |
+
## Bias, Risks and Limitations
|
| 317 |
+
|
| 318 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 319 |
+
-->
|
| 320 |
+
|
| 321 |
+
<!--
|
| 322 |
+
### Recommendations
|
| 323 |
+
|
| 324 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 325 |
+
-->
|
| 326 |
+
|
| 327 |
+
## Training Details
|
| 328 |
+
|
| 329 |
+
### Training Dataset
|
| 330 |
+
|
| 331 |
+
#### csv
|
| 332 |
+
|
| 333 |
+
* Dataset: csv
|
| 334 |
+
* Size: 53 training samples
|
| 335 |
+
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 336 |
+
* Approximate statistics based on the first 53 samples:
|
| 337 |
+
| | text1 | text2 | label |
|
| 338 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
|
| 339 |
+
| type | string | string | int |
|
| 340 |
+
| details | <ul><li>min: 14 tokens</li><li>mean: 35.36 tokens</li><li>max: 79 tokens</li></ul> | <ul><li>min: 11 tokens</li><li>mean: 21.33 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>0: ~38.10%</li><li>1: ~61.90%</li></ul> |
|
| 341 |
+
* Samples:
|
| 342 |
+
| text1 | text2 | label |
|
| 343 |
+
|:---------------------------------------------------------------------------------------|:----------------------------------------------------------|:---------------|
|
| 344 |
+
| <code>薄紫 色 の ドレス と 明るい ホット ピンク の 靴 を 着た 女性 が 、 水 と コーヒー を 飲んで テーブル に 座って い ます 。</code> | <code>ブラインド デート の 女性 が 座って 、 デート が 現れる の を 待ち ます 。</code> | <code>1</code> |
|
| 345 |
+
| <code>トラック を 自転車 で 走る 人々 の グループ 。</code> | <code>自転車 の 挑戦 に 勝とう と する 人々 の グループ 。</code> | <code>1</code> |
|
| 346 |
+
| <code>野球 の 試合 中 に 基地 を 走る 野球 選手 の シャープリー 。</code> | <code>Ｓｈａｒｐ ｌｅｙ は ゲーム で プレイ して い ます 。</code> | <code>0</code> |
|
| 347 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 348 |
+
```json
|
| 349 |
+
{
|
| 350 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
| 351 |
+
}
|
| 352 |
+
```
|
| 353 |
+
|
| 354 |
+
### Evaluation Dataset
|
| 355 |
+
|
| 356 |
+
#### csv
|
| 357 |
+
|
| 358 |
+
* Dataset: csv
|
| 359 |
+
* Size: 53 evaluation samples
|
| 360 |
+
* Columns: <code>text1</code>, <code>text2</code>, and <code>label</code>
|
| 361 |
+
* Approximate statistics based on the first 53 samples:
|
| 362 |
+
| | text1 | text2 | label |
|
| 363 |
+
|:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------|:------------------------------------------------|
|
| 364 |
+
| type | string | string | int |
|
| 365 |
+
| details | <ul><li>min: 19 tokens</li><li>mean: 39.64 tokens</li><li>max: 84 tokens</li></ul> | <ul><li>min: 19 tokens</li><li>mean: 25.27 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>0: ~27.27%</li><li>1: ~72.73%</li></ul> |
|
| 366 |
+
* Samples:
|
| 367 |
+
| text1 | text2 | label |
|
| 368 |
+
|:----------------------------------------------------------------------------------------------------------|:------------------------------------------------|:---------------|
|
| 369 |
+
| <code>岩 の 多い 景色 を 見て 二 人</code> | <code>何 か を 見て いる 二 人 が い ます 。</code> | <code>0</code> |
|
| 370 |
+
| <code>白い ヘルメット と オレンジ色 の シャツ 、 ジーンズ 、 白い トラック と オレンジ色 の パイロン の 前 に 反射 ジャケット を 着た 金髪 の ストリート ワーカー 。</code> | <code>ストリート ワーカー は 保護 具 を 着用 して い ませ ん 。</code> | <code>1</code> |
|
| 371 |
+
| <code>白い 帽子 を かぶった 女性 が 、 鮮やかな 色 の 岩 の 風景 を 描いて い ます 。 岩 層 自体 が 背景 に 見え ます 。</code> | <code>誰 か が 肖像 画 を 描いて い ます 。</code> | <code>1</code> |
|
| 372 |
+
* Loss: [<code>CosineSimilarityLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#cosinesimilarityloss) with these parameters:
|
| 373 |
+
```json
|
| 374 |
+
{
|
| 375 |
+
"loss_fct": "torch.nn.modules.loss.MSELoss"
|
| 376 |
+
}
|
| 377 |
+
```
|
| 378 |
+
|
| 379 |
+
### Training Hyperparameters
|
| 380 |
+
#### Non-Default Hyperparameters
|
| 381 |
+
|
| 382 |
+
- `eval_strategy`: epoch
|
| 383 |
+
- `learning_rate`: 2e-05
|
| 384 |
+
- `num_train_epochs`: 15
|
| 385 |
+
- `warmup_ratio`: 0.4
|
| 386 |
+
- `fp16`: True
|
| 387 |
+
- `batch_sampler`: no_duplicates
|
| 388 |
+
|
| 389 |
+
#### All Hyperparameters
|
| 390 |
+
<details><summary>Click to expand</summary>
|
| 391 |
+
|
| 392 |
+
- `overwrite_output_dir`: False
|
| 393 |
+
- `do_predict`: False
|
| 394 |
+
- `eval_strategy`: epoch
|
| 395 |
+
- `prediction_loss_only`: True
|
| 396 |
+
- `per_device_train_batch_size`: 8
|
| 397 |
+
- `per_device_eval_batch_size`: 8
|
| 398 |
+
- `per_gpu_train_batch_size`: None
|
| 399 |
+
- `per_gpu_eval_batch_size`: None
|
| 400 |
+
- `gradient_accumulation_steps`: 1
|
| 401 |
+
- `eval_accumulation_steps`: None
|
| 402 |
+
- `torch_empty_cache_steps`: None
|
| 403 |
+
- `learning_rate`: 2e-05
|
| 404 |
+
- `weight_decay`: 0.0
|
| 405 |
+
- `adam_beta1`: 0.9
|
| 406 |
+
- `adam_beta2`: 0.999
|
| 407 |
+
- `adam_epsilon`: 1e-08
|
| 408 |
+
- `max_grad_norm`: 1.0
|
| 409 |
+
- `num_train_epochs`: 15
|
| 410 |
+
- `max_steps`: -1
|
| 411 |
+
- `lr_scheduler_type`: linear
|
| 412 |
+
- `lr_scheduler_kwargs`: {}
|
| 413 |
+
- `warmup_ratio`: 0.4
|
| 414 |
+
- `warmup_steps`: 0
|
| 415 |
+
- `log_level`: passive
|
| 416 |
+
- `log_level_replica`: warning
|
| 417 |
+
- `log_on_each_node`: True
|
| 418 |
+
- `logging_nan_inf_filter`: True
|
| 419 |
+
- `save_safetensors`: True
|
| 420 |
+
- `save_on_each_node`: False
|
| 421 |
+
- `save_only_model`: False
|
| 422 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 423 |
+
- `no_cuda`: False
|
| 424 |
+
- `use_cpu`: False
|
| 425 |
+
- `use_mps_device`: False
|
| 426 |
+
- `seed`: 42
|
| 427 |
+
- `data_seed`: None
|
| 428 |
+
- `jit_mode_eval`: False
|
| 429 |
+
- `use_ipex`: False
|
| 430 |
+
- `bf16`: False
|
| 431 |
+
- `fp16`: True
|
| 432 |
+
- `fp16_opt_level`: O1
|
| 433 |
+
- `half_precision_backend`: auto
|
| 434 |
+
- `bf16_full_eval`: False
|
| 435 |
+
- `fp16_full_eval`: False
|
| 436 |
+
- `tf32`: None
|
| 437 |
+
- `local_rank`: 0
|
| 438 |
+
- `ddp_backend`: None
|
| 439 |
+
- `tpu_num_cores`: None
|
| 440 |
+
- `tpu_metrics_debug`: False
|
| 441 |
+
- `debug`: []
|
| 442 |
+
- `dataloader_drop_last`: False
|
| 443 |
+
- `dataloader_num_workers`: 0
|
| 444 |
+
- `dataloader_prefetch_factor`: None
|
| 445 |
+
- `past_index`: -1
|
| 446 |
+
- `disable_tqdm`: False
|
| 447 |
+
- `remove_unused_columns`: True
|
| 448 |
+
- `label_names`: None
|
| 449 |
+
- `load_best_model_at_end`: False
|
| 450 |
+
- `ignore_data_skip`: False
|
| 451 |
+
- `fsdp`: []
|
| 452 |
+
- `fsdp_min_num_params`: 0
|
| 453 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 454 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 455 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 456 |
+
- `deepspeed`: None
|
| 457 |
+
- `label_smoothing_factor`: 0.0
|
| 458 |
+
- `optim`: adamw_torch
|
| 459 |
+
- `optim_args`: None
|
| 460 |
+
- `adafactor`: False
|
| 461 |
+
- `group_by_length`: False
|
| 462 |
+
- `length_column_name`: length
|
| 463 |
+
- `ddp_find_unused_parameters`: None
|
| 464 |
+
- `ddp_bucket_cap_mb`: None
|
| 465 |
+
- `ddp_broadcast_buffers`: False
|
| 466 |
+
- `dataloader_pin_memory`: True
|
| 467 |
+
- `dataloader_persistent_workers`: False
|
| 468 |
+
- `skip_memory_metrics`: True
|
| 469 |
+
- `use_legacy_prediction_loop`: False
|
| 470 |
+
- `push_to_hub`: False
|
| 471 |
+
- `resume_from_checkpoint`: None
|
| 472 |
+
- `hub_model_id`: None
|
| 473 |
+
- `hub_strategy`: every_save
|
| 474 |
+
- `hub_private_repo`: False
|
| 475 |
+
- `hub_always_push`: False
|
| 476 |
+
- `gradient_checkpointing`: False
|
| 477 |
+
- `gradient_checkpointing_kwargs`: None
|
| 478 |
+
- `include_inputs_for_metrics`: False
|
| 479 |
+
- `eval_do_concat_batches`: True
|
| 480 |
+
- `fp16_backend`: auto
|
| 481 |
+
- `push_to_hub_model_id`: None
|
| 482 |
+
- `push_to_hub_organization`: None
|
| 483 |
+
- `mp_parameters`:
|
| 484 |
+
- `auto_find_batch_size`: False
|
| 485 |
+
- `full_determinism`: False
|
| 486 |
+
- `torchdynamo`: None
|
| 487 |
+
- `ray_scope`: last
|
| 488 |
+
- `ddp_timeout`: 1800
|
| 489 |
+
- `torch_compile`: False
|
| 490 |
+
- `torch_compile_backend`: None
|
| 491 |
+
- `torch_compile_mode`: None
|
| 492 |
+
- `dispatch_batches`: None
|
| 493 |
+
- `split_batches`: None
|
| 494 |
+
- `include_tokens_per_second`: False
|
| 495 |
+
- `include_num_input_tokens_seen`: False
|
| 496 |
+
- `neftune_noise_alpha`: None
|
| 497 |
+
- `optim_target_modules`: None
|
| 498 |
+
- `batch_eval_metrics`: False
|
| 499 |
+
- `eval_on_start`: False
|
| 500 |
+
- `eval_use_gather_object`: False
|
| 501 |
+
- `batch_sampler`: no_duplicates
|
| 502 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 503 |
+
|
| 504 |
+
</details>
|
| 505 |
+
|
| 506 |
+
### Training Logs
|
| 507 |
+
| Epoch | Step | Training Loss | loss | custom-arc-semantics-data-jp_max_ap |
|
| 508 |
+
|:-----:|:----:|:-------------:|:------:|:-----------------------------------:|
|
| 509 |
+
| 1.0 | 6 | 0.2963 | 0.3111 | 0.6821 |
|
| 510 |
+
| 2.0 | 12 | 0.2833 | 0.3096 | 0.7238 |
|
| 511 |
+
| 3.0 | 18 | 0.2568 | 0.3050 | 0.7238 |
|
| 512 |
+
| 4.0 | 24 | 0.2177 | 0.2958 | 0.7238 |
|
| 513 |
+
| 5.0 | 30 | 0.1797 | 0.2826 | 0.6946 |
|
| 514 |
+
| 6.0 | 36 | 0.1419 | 0.2765 | 0.6509 |
|
| 515 |
+
| 7.0 | 42 | 0.1057 | 0.2954 | 0.6509 |
|
| 516 |
+
| 8.0 | 48 | 0.0815 | 0.3165 | 0.6509 |
|
| 517 |
+
| 9.0 | 54 | 0.0664 | 0.3199 | 0.6509 |
|
| 518 |
+
| 10.0 | 60 | 0.0497 | 0.3140 | 0.6509 |
|
| 519 |
+
| 11.0 | 66 | 0.0402 | 0.3081 | 0.6321 |
|
| 520 |
+
| 12.0 | 72 | 0.0346 | 0.3072 | 0.6946 |
|
| 521 |
+
| 13.0 | 78 | 0.0293 | 0.3066 | 0.6946 |
|
| 522 |
+
| 14.0 | 84 | 0.0302 | 0.3076 | 0.6946 |
|
| 523 |
+
| 15.0 | 90 | 0.0287 | 0.3078 | 0.6946 |
|
| 524 |
+
|
| 525 |
+
|
| 526 |
+
### Framework Versions
|
| 527 |
+
- Python: 3.10.14
|
| 528 |
+
- Sentence Transformers: 3.1.0
|
| 529 |
+
- Transformers: 4.44.2
|
| 530 |
+
- PyTorch: 2.4.1+cu121
|
| 531 |
+
- Accelerate: 0.34.2
|
| 532 |
+
- Datasets: 2.20.0
|
| 533 |
+
- Tokenizers: 0.19.1
|
| 534 |
+
|
| 535 |
+
## Citation
|
| 536 |
+
|
| 537 |
+
### BibTeX
|
| 538 |
+
|
| 539 |
+
#### Sentence Transformers
|
| 540 |
+
```bibtex
|
| 541 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 542 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 543 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 544 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 545 |
+
month = "11",
|
| 546 |
+
year = "2019",
|
| 547 |
+
publisher = "Association for Computational Linguistics",
|
| 548 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 549 |
+
}
|
| 550 |
+
```
|
| 551 |
+
|
| 552 |
+
<!--
|
| 553 |
+
## Glossary
|
| 554 |
+
|
| 555 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 556 |
+
-->
|
| 557 |
+
|
| 558 |
+
<!--
|
| 559 |
+
## Model Card Authors
|
| 560 |
+
|
| 561 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 562 |
+
-->
|
| 563 |
+
|
| 564 |
+
<!--
|
| 565 |
+
## Model Card Contact
|
| 566 |
+
|
| 567 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 568 |
+
-->
|
checkpoint-90/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[PAD]": 32000
|
| 3 |
+
}
|
checkpoint-90/config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "colorfulscoop/sbert-base-ja",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertModel"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 2,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"cls_token_id": 2,
|
| 10 |
+
"eos_token_id": 3,
|
| 11 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.1,
|
| 14 |
+
"hidden_size": 768,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 3072,
|
| 17 |
+
"layer_norm_eps": 1e-12,
|
| 18 |
+
"mask_token_id": 4,
|
| 19 |
+
"max_position_embeddings": 512,
|
| 20 |
+
"model_type": "bert",
|
| 21 |
+
"num_attention_heads": 12,
|
| 22 |
+
"num_hidden_layers": 12,
|
| 23 |
+
"pad_token_id": 0,
|
| 24 |
+
"position_embedding_type": "absolute",
|
| 25 |
+
"sep_token_id": 3,
|
| 26 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 27 |
+
"torch_dtype": "float32",
|
| 28 |
+
"transformers_version": "4.44.2",
|
| 29 |
+
"type_vocab_size": 2,
|
| 30 |
+
"unk_token_id": 1,
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32000
|
| 33 |
+
}
|
checkpoint-90/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "3.1.0",
|
| 4 |
+
"transformers": "4.44.2",
|
| 5 |
+
"pytorch": "2.4.1+cu121"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": null
|
| 10 |
+
}
|
checkpoint-90/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e0ff31c3d5bd7da51b33521fe7ca57947f6379f6774871921947f2b3c0fd144
|
| 3 |
+
size 442491744
|
checkpoint-90/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 |
+
]
|
checkpoint-90/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33aececa3c5b2a6ff6f0d03cf3bb050e10b0b7be7626b8be54687506609d8655
|
| 3 |
+
size 880373306
|
checkpoint-90/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c8748dd673781ab2b020389825797b25f224be5f5c52a9b7cae9b0934ec6cb1
|
| 3 |
+
size 13990
|
checkpoint-90/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:639b21ab22113e656504cfe845f1fadd6b4f71536a4a4212c5d649f9fc63dce3
|
| 3 |
+
size 1064
|
checkpoint-90/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-90/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "<unk>",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
+
}
|
checkpoint-90/spm.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6467857b4b0c77ded9bac7ad2fb5c16eb64e17e417ce46624dacac2bbb404fc
|
| 3 |
+
size 802713
|
checkpoint-90/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-90/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": true,
|
| 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": false
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"32000": {
|
| 44 |
+
"content": "[PAD]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
}
|
| 51 |
+
},
|
| 52 |
+
"bos_token": "[CLS]",
|
| 53 |
+
"clean_up_tokenization_spaces": true,
|
| 54 |
+
"cls_token": "[CLS]",
|
| 55 |
+
"do_lower_case": false,
|
| 56 |
+
"eos_token": "[SEP]",
|
| 57 |
+
"mask_token": "[MASK]",
|
| 58 |
+
"model_max_length": 512,
|
| 59 |
+
"pad_token": "<pad>",
|
| 60 |
+
"sep_token": "[SEP]",
|
| 61 |
+
"sp_model_kwargs": {},
|
| 62 |
+
"split_by_punct": false,
|
| 63 |
+
"tokenizer_class": "DebertaV2Tokenizer",
|
| 64 |
+
"unk_token": "<unk>"
|
| 65 |
+
}
|
checkpoint-90/trainer_state.json
ADDED
|
@@ -0,0 +1,783 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 90,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"grad_norm": 4.725662708282471,
|
| 14 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 15 |
+
"loss": 0.2963,
|
| 16 |
+
"step": 6
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.0,
|
| 20 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 21 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.30786412954330444,
|
| 22 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.682129329004329,
|
| 23 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 24 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.30786412954330444,
|
| 25 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 26 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 27 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 28 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 172.38189697265625,
|
| 29 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.682129329004329,
|
| 30 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 31 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 172.38189697265625,
|
| 32 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 33 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 34 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 35 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.785310745239258,
|
| 36 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.682129329004329,
|
| 37 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 38 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.785310745239258,
|
| 39 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 40 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 41 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 42 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 612.4951171875,
|
| 43 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.6612959956709956,
|
| 44 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 45 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 612.4951171875,
|
| 46 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 47 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 48 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 49 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 612.4951171875,
|
| 50 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.682129329004329,
|
| 51 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 52 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 612.4951171875,
|
| 53 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 54 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 55 |
+
"eval_loss": 0.3111322224140167,
|
| 56 |
+
"eval_runtime": 6.0296,
|
| 57 |
+
"eval_samples_per_second": 1.824,
|
| 58 |
+
"eval_steps_per_second": 0.332,
|
| 59 |
+
"step": 6
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"grad_norm": 4.223657608032227,
|
| 64 |
+
"learning_rate": 6.666666666666667e-06,
|
| 65 |
+
"loss": 0.2833,
|
| 66 |
+
"step": 12
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 2.0,
|
| 70 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 71 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3102341890335083,
|
| 72 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.7237959956709956,
|
| 73 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 74 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3102341890335083,
|
| 75 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 76 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 77 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 78 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 173.5974578857422,
|
| 79 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.682129329004329,
|
| 80 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 81 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 173.5974578857422,
|
| 82 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 83 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 84 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 85 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.73798179626465,
|
| 86 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.7237959956709956,
|
| 87 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 88 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.73798179626465,
|
| 89 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 90 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 91 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 92 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 610.9443359375,
|
| 93 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.7237959956709956,
|
| 94 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 95 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 610.9443359375,
|
| 96 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 97 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 98 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 99 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 610.9443359375,
|
| 100 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.7237959956709956,
|
| 101 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 102 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 610.9443359375,
|
| 103 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 104 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 105 |
+
"eval_loss": 0.309558629989624,
|
| 106 |
+
"eval_runtime": 5.9488,
|
| 107 |
+
"eval_samples_per_second": 1.849,
|
| 108 |
+
"eval_steps_per_second": 0.336,
|
| 109 |
+
"step": 12
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 3.0,
|
| 113 |
+
"grad_norm": 3.3170320987701416,
|
| 114 |
+
"learning_rate": 1e-05,
|
| 115 |
+
"loss": 0.2568,
|
| 116 |
+
"step": 18
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 3.0,
|
| 120 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 121 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3211533725261688,
|
| 122 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.7237959956709956,
|
| 123 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 124 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3211533725261688,
|
| 125 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 126 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 127 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 128 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 179.75201416015625,
|
| 129 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.7237959956709956,
|
| 130 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 131 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 179.75201416015625,
|
| 132 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 133 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 134 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 135 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.536266326904297,
|
| 136 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.7237959956709956,
|
| 137 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 138 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.536266326904297,
|
| 139 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 140 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 141 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 142 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 605.5822143554688,
|
| 143 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.7237959956709956,
|
| 144 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 145 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 605.5822143554688,
|
| 146 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 147 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 148 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 149 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 605.5822143554688,
|
| 150 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.7237959956709956,
|
| 151 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 152 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 605.5822143554688,
|
| 153 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 154 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 155 |
+
"eval_loss": 0.304984450340271,
|
| 156 |
+
"eval_runtime": 7.2979,
|
| 157 |
+
"eval_samples_per_second": 1.507,
|
| 158 |
+
"eval_steps_per_second": 0.274,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.0,
|
| 163 |
+
"grad_norm": 2.2900643348693848,
|
| 164 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 165 |
+
"loss": 0.2177,
|
| 166 |
+
"step": 24
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 4.0,
|
| 170 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 171 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3480110168457031,
|
| 172 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.7237959956709956,
|
| 173 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 174 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3480110168457031,
|
| 175 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 176 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 177 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 178 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 195.35403442382812,
|
| 179 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.7237959956709956,
|
| 180 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 181 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 195.35403442382812,
|
| 182 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 183 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 184 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 185 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.041318893432617,
|
| 186 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.682129329004329,
|
| 187 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 188 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.041318893432617,
|
| 189 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 190 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 191 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 192 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 593.150634765625,
|
| 193 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.682129329004329,
|
| 194 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 195 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 593.150634765625,
|
| 196 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 197 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 198 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 199 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 593.150634765625,
|
| 200 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.7237959956709956,
|
| 201 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 202 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 593.150634765625,
|
| 203 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 204 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 205 |
+
"eval_loss": 0.29575565457344055,
|
| 206 |
+
"eval_runtime": 6.0903,
|
| 207 |
+
"eval_samples_per_second": 1.806,
|
| 208 |
+
"eval_steps_per_second": 0.328,
|
| 209 |
+
"step": 24
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 5.0,
|
| 213 |
+
"grad_norm": 1.5022671222686768,
|
| 214 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 215 |
+
"loss": 0.1797,
|
| 216 |
+
"step": 30
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 5.0,
|
| 220 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 221 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3965001106262207,
|
| 222 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.682129329004329,
|
| 223 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 224 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3965001106262207,
|
| 225 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 226 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 227 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 228 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 223.7809295654297,
|
| 229 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.6946293290043289,
|
| 230 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 231 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 223.7809295654297,
|
| 232 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 233 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 234 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 235 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 26.097108840942383,
|
| 236 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.682129329004329,
|
| 237 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 238 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 26.097108840942383,
|
| 239 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 240 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 241 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 242 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 570.329345703125,
|
| 243 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.682129329004329,
|
| 244 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 245 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 570.329345703125,
|
| 246 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 247 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 248 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 249 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 570.329345703125,
|
| 250 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.6946293290043289,
|
| 251 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 252 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 570.329345703125,
|
| 253 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 254 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 255 |
+
"eval_loss": 0.28263404965400696,
|
| 256 |
+
"eval_runtime": 6.0031,
|
| 257 |
+
"eval_samples_per_second": 1.832,
|
| 258 |
+
"eval_steps_per_second": 0.333,
|
| 259 |
+
"step": 30
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 6.0,
|
| 263 |
+
"grad_norm": 0.6781304478645325,
|
| 264 |
+
"learning_rate": 2e-05,
|
| 265 |
+
"loss": 0.1419,
|
| 266 |
+
"step": 36
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 6.0,
|
| 270 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 271 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.43997177481651306,
|
| 272 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.6321293290043289,
|
| 273 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 274 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.43997177481651306,
|
| 275 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 276 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 277 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 278 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 249.57528686523438,
|
| 279 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.650879329004329,
|
| 280 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 281 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 249.57528686523438,
|
| 282 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 283 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 284 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 285 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 25.200597763061523,
|
| 286 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.6321293290043289,
|
| 287 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 288 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 25.200597763061523,
|
| 289 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 290 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 291 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 292 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 550.5452880859375,
|
| 293 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.6321293290043289,
|
| 294 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 295 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 550.5452880859375,
|
| 296 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 297 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 298 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 299 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 550.5452880859375,
|
| 300 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.650879329004329,
|
| 301 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 302 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 550.5452880859375,
|
| 303 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 304 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 305 |
+
"eval_loss": 0.276452898979187,
|
| 306 |
+
"eval_runtime": 5.4943,
|
| 307 |
+
"eval_samples_per_second": 2.002,
|
| 308 |
+
"eval_steps_per_second": 0.364,
|
| 309 |
+
"step": 36
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.0,
|
| 313 |
+
"grad_norm": 0.4487136900424957,
|
| 314 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 315 |
+
"loss": 0.1057,
|
| 316 |
+
"step": 42
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 7.0,
|
| 320 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 321 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.37805190682411194,
|
| 322 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.6321293290043289,
|
| 323 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 324 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.37805190682411194,
|
| 325 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 326 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 327 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 328 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 211.4693603515625,
|
| 329 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.650879329004329,
|
| 330 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 331 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 211.4693603515625,
|
| 332 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 333 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 334 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 335 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 26.396636962890625,
|
| 336 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.6321293290043289,
|
| 337 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 338 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 26.396636962890625,
|
| 339 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 340 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 341 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 342 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 582.5875244140625,
|
| 343 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.6321293290043289,
|
| 344 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 345 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 582.5875244140625,
|
| 346 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 347 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 348 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 349 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 582.5875244140625,
|
| 350 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.650879329004329,
|
| 351 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 352 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 582.5875244140625,
|
| 353 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 354 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 355 |
+
"eval_loss": 0.295420378446579,
|
| 356 |
+
"eval_runtime": 6.1313,
|
| 357 |
+
"eval_samples_per_second": 1.794,
|
| 358 |
+
"eval_steps_per_second": 0.326,
|
| 359 |
+
"step": 42
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 8.0,
|
| 363 |
+
"grad_norm": 0.16805221140384674,
|
| 364 |
+
"learning_rate": 1.555555555555556e-05,
|
| 365 |
+
"loss": 0.0815,
|
| 366 |
+
"step": 48
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.0,
|
| 370 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 371 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.31827351450920105,
|
| 372 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.6321293290043289,
|
| 373 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 374 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.31827351450920105,
|
| 375 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 376 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 377 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 378 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 178.09083557128906,
|
| 379 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.650879329004329,
|
| 380 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 381 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 178.09083557128906,
|
| 382 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 383 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 384 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 385 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.63851547241211,
|
| 386 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.6321293290043289,
|
| 387 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 388 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.63851547241211,
|
| 389 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 390 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 391 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 392 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 612.4237060546875,
|
| 393 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.6321293290043289,
|
| 394 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 395 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 612.4237060546875,
|
| 396 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 397 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 398 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 399 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 612.4237060546875,
|
| 400 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.650879329004329,
|
| 401 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 402 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 612.4237060546875,
|
| 403 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 404 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 405 |
+
"eval_loss": 0.3164561986923218,
|
| 406 |
+
"eval_runtime": 6.5067,
|
| 407 |
+
"eval_samples_per_second": 1.691,
|
| 408 |
+
"eval_steps_per_second": 0.307,
|
| 409 |
+
"step": 48
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 9.0,
|
| 413 |
+
"grad_norm": 0.16789764165878296,
|
| 414 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 415 |
+
"loss": 0.0664,
|
| 416 |
+
"step": 54
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 9.0,
|
| 420 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 421 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.30298155546188354,
|
| 422 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.6321293290043289,
|
| 423 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 424 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.30298155546188354,
|
| 425 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 426 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 427 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 428 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 169.24606323242188,
|
| 429 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.650879329004329,
|
| 430 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 431 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 169.24606323242188,
|
| 432 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 433 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 434 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 435 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.91897964477539,
|
| 436 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 437 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 438 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.91897964477539,
|
| 439 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 440 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 441 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 442 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 618.7899169921875,
|
| 443 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 444 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 445 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 618.7899169921875,
|
| 446 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 447 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 448 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 449 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 618.7899169921875,
|
| 450 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.650879329004329,
|
| 451 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 452 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 618.7899169921875,
|
| 453 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 454 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 455 |
+
"eval_loss": 0.31994009017944336,
|
| 456 |
+
"eval_runtime": 6.8319,
|
| 457 |
+
"eval_samples_per_second": 1.61,
|
| 458 |
+
"eval_steps_per_second": 0.293,
|
| 459 |
+
"step": 54
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.0,
|
| 463 |
+
"grad_norm": 0.1519097536802292,
|
| 464 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 465 |
+
"loss": 0.0497,
|
| 466 |
+
"step": 60
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 10.0,
|
| 470 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 471 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.31682828068733215,
|
| 472 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.6321293290043289,
|
| 473 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 474 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.31682828068733215,
|
| 475 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 476 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 477 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 478 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 176.45004272460938,
|
| 479 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.650879329004329,
|
| 480 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 481 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 176.45004272460938,
|
| 482 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 483 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 484 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 485 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.598316192626953,
|
| 486 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 487 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 488 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.598316192626953,
|
| 489 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 490 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 491 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 492 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 611.2236328125,
|
| 493 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 494 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 495 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 611.2236328125,
|
| 496 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 497 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 498 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 499 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 611.2236328125,
|
| 500 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.650879329004329,
|
| 501 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 502 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 611.2236328125,
|
| 503 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 504 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 505 |
+
"eval_loss": 0.31398141384124756,
|
| 506 |
+
"eval_runtime": 6.4168,
|
| 507 |
+
"eval_samples_per_second": 1.714,
|
| 508 |
+
"eval_steps_per_second": 0.312,
|
| 509 |
+
"step": 60
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 11.0,
|
| 513 |
+
"grad_norm": 0.17287826538085938,
|
| 514 |
+
"learning_rate": 8.888888888888888e-06,
|
| 515 |
+
"loss": 0.0402,
|
| 516 |
+
"step": 66
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 11.0,
|
| 520 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 521 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.33553600311279297,
|
| 522 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.619629329004329,
|
| 523 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 524 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.33553600311279297,
|
| 525 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 526 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 527 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 528 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 186.30569458007812,
|
| 529 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.6321293290043289,
|
| 530 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 531 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 186.30569458007812,
|
| 532 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 533 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 534 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 535 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.178071975708008,
|
| 536 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 537 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 538 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.178071975708008,
|
| 539 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 540 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 541 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 542 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 601.0965576171875,
|
| 543 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 544 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 545 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 601.0965576171875,
|
| 546 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 547 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 548 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 549 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 601.0965576171875,
|
| 550 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.6321293290043289,
|
| 551 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 552 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 601.0965576171875,
|
| 553 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 554 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 555 |
+
"eval_loss": 0.3081442415714264,
|
| 556 |
+
"eval_runtime": 6.4435,
|
| 557 |
+
"eval_samples_per_second": 1.707,
|
| 558 |
+
"eval_steps_per_second": 0.31,
|
| 559 |
+
"step": 66
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 12.0,
|
| 563 |
+
"grad_norm": 0.1389617770910263,
|
| 564 |
+
"learning_rate": 6.666666666666667e-06,
|
| 565 |
+
"loss": 0.0346,
|
| 566 |
+
"step": 72
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 12.0,
|
| 570 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 571 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3391532003879547,
|
| 572 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.619629329004329,
|
| 573 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 574 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3391532003879547,
|
| 575 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 576 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 577 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 578 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 187.9766082763672,
|
| 579 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.6946293290043289,
|
| 580 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 581 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 187.9766082763672,
|
| 582 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 583 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 584 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 585 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.080123901367188,
|
| 586 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 587 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 588 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.080123901367188,
|
| 589 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 590 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 591 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 592 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 598.4072265625,
|
| 593 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 594 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 595 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 598.4072265625,
|
| 596 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 597 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 598 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 599 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 598.4072265625,
|
| 600 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.6946293290043289,
|
| 601 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 602 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 598.4072265625,
|
| 603 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 604 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 605 |
+
"eval_loss": 0.30722811818122864,
|
| 606 |
+
"eval_runtime": 6.555,
|
| 607 |
+
"eval_samples_per_second": 1.678,
|
| 608 |
+
"eval_steps_per_second": 0.305,
|
| 609 |
+
"step": 72
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.0,
|
| 613 |
+
"grad_norm": 0.10099858045578003,
|
| 614 |
+
"learning_rate": 4.444444444444444e-06,
|
| 615 |
+
"loss": 0.0293,
|
| 616 |
+
"step": 78
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 13.0,
|
| 620 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 621 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.34109100699424744,
|
| 622 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.619629329004329,
|
| 623 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 624 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.34109100699424744,
|
| 625 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 626 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 627 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 628 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 189.05935668945312,
|
| 629 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.6946293290043289,
|
| 630 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 631 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 189.05935668945312,
|
| 632 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 633 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 634 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 635 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.041587829589844,
|
| 636 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 637 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 638 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.041587829589844,
|
| 639 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 640 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 641 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 642 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 597.2989501953125,
|
| 643 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 644 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 645 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 597.2989501953125,
|
| 646 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 647 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 648 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 649 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 597.2989501953125,
|
| 650 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.6946293290043289,
|
| 651 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 652 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 597.2989501953125,
|
| 653 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 654 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 655 |
+
"eval_loss": 0.30660775303840637,
|
| 656 |
+
"eval_runtime": 5.9875,
|
| 657 |
+
"eval_samples_per_second": 1.837,
|
| 658 |
+
"eval_steps_per_second": 0.334,
|
| 659 |
+
"step": 78
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 14.0,
|
| 663 |
+
"grad_norm": 0.12931989133358002,
|
| 664 |
+
"learning_rate": 2.222222222222222e-06,
|
| 665 |
+
"loss": 0.0302,
|
| 666 |
+
"step": 84
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 14.0,
|
| 670 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 671 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3385917544364929,
|
| 672 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.619629329004329,
|
| 673 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 674 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3385917544364929,
|
| 675 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 676 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 677 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 678 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 187.77444458007812,
|
| 679 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.6946293290043289,
|
| 680 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 681 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 187.77444458007812,
|
| 682 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 683 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 684 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 685 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.100971221923828,
|
| 686 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 687 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 688 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.100971221923828,
|
| 689 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 690 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 691 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 692 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 598.5726318359375,
|
| 693 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 694 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 695 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 598.5726318359375,
|
| 696 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 697 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 698 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 699 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 598.5726318359375,
|
| 700 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.6946293290043289,
|
| 701 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 702 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 598.5726318359375,
|
| 703 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 704 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 705 |
+
"eval_loss": 0.30758312344551086,
|
| 706 |
+
"eval_runtime": 5.1895,
|
| 707 |
+
"eval_samples_per_second": 2.12,
|
| 708 |
+
"eval_steps_per_second": 0.385,
|
| 709 |
+
"step": 84
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 15.0,
|
| 713 |
+
"grad_norm": 0.16915012896060944,
|
| 714 |
+
"learning_rate": 0.0,
|
| 715 |
+
"loss": 0.0287,
|
| 716 |
+
"step": 90
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 15.0,
|
| 720 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy": 0.6363636363636364,
|
| 721 |
+
"eval_custom-arc-semantics-data-jp_cosine_accuracy_threshold": 0.3379952907562256,
|
| 722 |
+
"eval_custom-arc-semantics-data-jp_cosine_ap": 0.619629329004329,
|
| 723 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1": 0.7777777777777777,
|
| 724 |
+
"eval_custom-arc-semantics-data-jp_cosine_f1_threshold": 0.3379952907562256,
|
| 725 |
+
"eval_custom-arc-semantics-data-jp_cosine_precision": 0.7,
|
| 726 |
+
"eval_custom-arc-semantics-data-jp_cosine_recall": 0.875,
|
| 727 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy": 0.6363636363636364,
|
| 728 |
+
"eval_custom-arc-semantics-data-jp_dot_accuracy_threshold": 187.5118865966797,
|
| 729 |
+
"eval_custom-arc-semantics-data-jp_dot_ap": 0.6946293290043289,
|
| 730 |
+
"eval_custom-arc-semantics-data-jp_dot_f1": 0.7777777777777777,
|
| 731 |
+
"eval_custom-arc-semantics-data-jp_dot_f1_threshold": 187.5118865966797,
|
| 732 |
+
"eval_custom-arc-semantics-data-jp_dot_precision": 0.7,
|
| 733 |
+
"eval_custom-arc-semantics-data-jp_dot_recall": 0.875,
|
| 734 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy": 0.6363636363636364,
|
| 735 |
+
"eval_custom-arc-semantics-data-jp_euclidean_accuracy_threshold": 27.118305206298828,
|
| 736 |
+
"eval_custom-arc-semantics-data-jp_euclidean_ap": 0.619629329004329,
|
| 737 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1": 0.7777777777777777,
|
| 738 |
+
"eval_custom-arc-semantics-data-jp_euclidean_f1_threshold": 27.118305206298828,
|
| 739 |
+
"eval_custom-arc-semantics-data-jp_euclidean_precision": 0.7,
|
| 740 |
+
"eval_custom-arc-semantics-data-jp_euclidean_recall": 0.875,
|
| 741 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy": 0.6363636363636364,
|
| 742 |
+
"eval_custom-arc-semantics-data-jp_manhattan_accuracy_threshold": 598.9317626953125,
|
| 743 |
+
"eval_custom-arc-semantics-data-jp_manhattan_ap": 0.619629329004329,
|
| 744 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1": 0.7777777777777777,
|
| 745 |
+
"eval_custom-arc-semantics-data-jp_manhattan_f1_threshold": 598.9317626953125,
|
| 746 |
+
"eval_custom-arc-semantics-data-jp_manhattan_precision": 0.7,
|
| 747 |
+
"eval_custom-arc-semantics-data-jp_manhattan_recall": 0.875,
|
| 748 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy": 0.6363636363636364,
|
| 749 |
+
"eval_custom-arc-semantics-data-jp_max_accuracy_threshold": 598.9317626953125,
|
| 750 |
+
"eval_custom-arc-semantics-data-jp_max_ap": 0.6946293290043289,
|
| 751 |
+
"eval_custom-arc-semantics-data-jp_max_f1": 0.7777777777777777,
|
| 752 |
+
"eval_custom-arc-semantics-data-jp_max_f1_threshold": 598.9317626953125,
|
| 753 |
+
"eval_custom-arc-semantics-data-jp_max_precision": 0.7,
|
| 754 |
+
"eval_custom-arc-semantics-data-jp_max_recall": 0.875,
|
| 755 |
+
"eval_loss": 0.3078480362892151,
|
| 756 |
+
"eval_runtime": 5.9867,
|
| 757 |
+
"eval_samples_per_second": 1.837,
|
| 758 |
+
"eval_steps_per_second": 0.334,
|
| 759 |
+
"step": 90
|
| 760 |
+
}
|
| 761 |
+
],
|
| 762 |
+
"logging_steps": 500,
|
| 763 |
+
"max_steps": 90,
|
| 764 |
+
"num_input_tokens_seen": 0,
|
| 765 |
+
"num_train_epochs": 15,
|
| 766 |
+
"save_steps": 100,
|
| 767 |
+
"stateful_callbacks": {
|
| 768 |
+
"TrainerControl": {
|
| 769 |
+
"args": {
|
| 770 |
+
"should_epoch_stop": false,
|
| 771 |
+
"should_evaluate": false,
|
| 772 |
+
"should_log": false,
|
| 773 |
+
"should_save": true,
|
| 774 |
+
"should_training_stop": true
|
| 775 |
+
},
|
| 776 |
+
"attributes": {}
|
| 777 |
+
}
|
| 778 |
+
},
|
| 779 |
+
"total_flos": 0.0,
|
| 780 |
+
"train_batch_size": 8,
|
| 781 |
+
"trial_name": null,
|
| 782 |
+
"trial_params": null
|
| 783 |
+
}
|
checkpoint-90/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab31a2f266552701315e4b4912e7ee4f071025a38324aa7dab7a38f1da2132a2
|
| 3 |
+
size 5432
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 442491744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e0ff31c3d5bd7da51b33521fe7ca57947f6379f6774871921947f2b3c0fd144
|
| 3 |
size 442491744
|
runs/Sep17_23-02-23_default/events.out.tfevents.1726614145.default.7803.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c339034682b5e521c8749560c861365c786d6ffe4f02868b8606e2b94c04d49
|
| 3 |
+
size 57493
|