Add files using upload-large-folder tool
Browse files- checkpoint-4000/1_Pooling/config.json +10 -0
- checkpoint-4000/config.json +27 -0
- checkpoint-4000/config_sentence_transformers.json +10 -0
- checkpoint-4000/model.safetensors +3 -0
- checkpoint-4000/optimizer.pt +3 -0
- checkpoint-4000/rng_state.pth +3 -0
- checkpoint-4000/scaler.pt +3 -0
- checkpoint-4000/scheduler.pt +3 -0
- checkpoint-4000/sentence_bert_config.json +4 -0
- checkpoint-4000/special_tokens_map.json +51 -0
- checkpoint-4000/tokenizer_config.json +56 -0
- checkpoint-4000/trainer_state.json +0 -0
- checkpoint-4000/training_args.bin +3 -0
- checkpoint-4200/1_Pooling/config.json +10 -0
- checkpoint-4200/README.md +1438 -0
- checkpoint-4200/model.safetensors +3 -0
- checkpoint-4200/modules.json +20 -0
- checkpoint-4200/optimizer.pt +3 -0
- checkpoint-4200/rng_state.pth +3 -0
- checkpoint-4200/scaler.pt +3 -0
- checkpoint-4200/scheduler.pt +3 -0
- checkpoint-4200/sentence_bert_config.json +4 -0
- checkpoint-4200/sentencepiece.bpe.model +3 -0
- checkpoint-4200/training_args.bin +3 -0
- checkpoint-4400/config.json +27 -0
- checkpoint-4400/model.safetensors +3 -0
- checkpoint-4400/modules.json +20 -0
- checkpoint-4400/optimizer.pt +3 -0
- checkpoint-4400/scaler.pt +3 -0
- checkpoint-4400/scheduler.pt +3 -0
- checkpoint-4400/trainer_state.json +0 -0
- checkpoint-4400/training_args.bin +3 -0
- checkpoint-4600/model.safetensors +3 -0
- checkpoint-4600/optimizer.pt +3 -0
- checkpoint-4600/sentencepiece.bpe.model +3 -0
- checkpoint-4600/special_tokens_map.json +51 -0
- checkpoint-4800/1_Pooling/config.json +10 -0
- checkpoint-4800/model.safetensors +3 -0
- checkpoint-4800/optimizer.pt +3 -0
- checkpoint-4800/rng_state.pth +3 -0
- checkpoint-4800/scaler.pt +3 -0
- checkpoint-4800/sentencepiece.bpe.model +3 -0
- checkpoint-4800/training_args.bin +3 -0
checkpoint-4000/1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 1024,
|
| 3 |
+
"pooling_mode_cls_token": true,
|
| 4 |
+
"pooling_mode_mean_tokens": false,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
checkpoint-4000/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4096,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 8194,
|
| 16 |
+
"model_type": "xlm-roberta",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"output_past": true,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.51.2",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 250002
|
| 27 |
+
}
|
checkpoint-4000/config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"__version__": {
|
| 3 |
+
"sentence_transformers": "4.1.0",
|
| 4 |
+
"transformers": "4.51.2",
|
| 5 |
+
"pytorch": "2.6.0+cu124"
|
| 6 |
+
},
|
| 7 |
+
"prompts": {},
|
| 8 |
+
"default_prompt_name": null,
|
| 9 |
+
"similarity_fn_name": "cosine"
|
| 10 |
+
}
|
checkpoint-4000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e396a37e5acc679024a9fc8c8cddae538f7cf082d5682d004c44cf494e226f69
|
| 3 |
+
size 2271064456
|
checkpoint-4000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f99efc690de9364ab3597a63d4ecd7e827d9b9ac9541a5cd91510bccd5027f02
|
| 3 |
+
size 4533972937
|
checkpoint-4000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3efbf048b90dbf88fbe7c3e5343d8f5b231ce2f762e746e6dc52ad13d65a600
|
| 3 |
+
size 15958
|
checkpoint-4000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60386f0725c4fe780fb345fd957860c14c74f3535df8dbe1242c6c681a5d255b
|
| 3 |
+
size 988
|
checkpoint-4000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:067bf8b23f4d6fd97b4d2f83930a64c8500ad6e476ffd0437ac9124a04eee854
|
| 3 |
+
size 1064
|
checkpoint-4000/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-4000/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-4000/tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<pad>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"250001": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": true,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
+
"model_max_length": 8192,
|
| 51 |
+
"pad_token": "<pad>",
|
| 52 |
+
"sep_token": "</s>",
|
| 53 |
+
"sp_model_kwargs": {},
|
| 54 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
checkpoint-4000/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-4000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a948c4f5667f6700da28d0d70c0c6f024b018ee933ba85d5cc9de9d626dadca
|
| 3 |
+
size 5624
|
checkpoint-4200/1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 1024,
|
| 3 |
+
"pooling_mode_cls_token": true,
|
| 4 |
+
"pooling_mode_mean_tokens": false,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
checkpoint-4200/README.md
ADDED
|
@@ -0,0 +1,1438 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- sentence-transformers
|
| 4 |
+
- sentence-similarity
|
| 5 |
+
- feature-extraction
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
- dataset_size:124788
|
| 8 |
+
- loss:GISTEmbedLoss
|
| 9 |
+
base_model: BAAI/bge-m3
|
| 10 |
+
widget:
|
| 11 |
+
- source_sentence: 其他机械、设备和有形货物租赁服务代表
|
| 12 |
+
sentences:
|
| 13 |
+
- 其他机械和设备租赁服务工作人员
|
| 14 |
+
- 电子和电信设备及零部件物流经理
|
| 15 |
+
- 工业主厨
|
| 16 |
+
- source_sentence: 公交车司机
|
| 17 |
+
sentences:
|
| 18 |
+
- 表演灯光设计师
|
| 19 |
+
- 乙烯基地板安装工
|
| 20 |
+
- 国际巴士司机
|
| 21 |
+
- source_sentence: online communication manager
|
| 22 |
+
sentences:
|
| 23 |
+
- trades union official
|
| 24 |
+
- social media manager
|
| 25 |
+
- budget manager
|
| 26 |
+
- source_sentence: Projektmanagerin
|
| 27 |
+
sentences:
|
| 28 |
+
- Projektmanager/Projektmanagerin
|
| 29 |
+
- Category-Manager
|
| 30 |
+
- Infanterist
|
| 31 |
+
- source_sentence: Volksvertreter
|
| 32 |
+
sentences:
|
| 33 |
+
- Parlamentarier
|
| 34 |
+
- Oberbürgermeister
|
| 35 |
+
- Konsul
|
| 36 |
+
pipeline_tag: sentence-similarity
|
| 37 |
+
library_name: sentence-transformers
|
| 38 |
+
metrics:
|
| 39 |
+
- cosine_accuracy@1
|
| 40 |
+
- cosine_accuracy@20
|
| 41 |
+
- cosine_accuracy@50
|
| 42 |
+
- cosine_accuracy@100
|
| 43 |
+
- cosine_accuracy@150
|
| 44 |
+
- cosine_accuracy@200
|
| 45 |
+
- cosine_precision@1
|
| 46 |
+
- cosine_precision@20
|
| 47 |
+
- cosine_precision@50
|
| 48 |
+
- cosine_precision@100
|
| 49 |
+
- cosine_precision@150
|
| 50 |
+
- cosine_precision@200
|
| 51 |
+
- cosine_recall@1
|
| 52 |
+
- cosine_recall@20
|
| 53 |
+
- cosine_recall@50
|
| 54 |
+
- cosine_recall@100
|
| 55 |
+
- cosine_recall@150
|
| 56 |
+
- cosine_recall@200
|
| 57 |
+
- cosine_ndcg@1
|
| 58 |
+
- cosine_ndcg@20
|
| 59 |
+
- cosine_ndcg@50
|
| 60 |
+
- cosine_ndcg@100
|
| 61 |
+
- cosine_ndcg@150
|
| 62 |
+
- cosine_ndcg@200
|
| 63 |
+
- cosine_mrr@1
|
| 64 |
+
- cosine_mrr@20
|
| 65 |
+
- cosine_mrr@50
|
| 66 |
+
- cosine_mrr@100
|
| 67 |
+
- cosine_mrr@150
|
| 68 |
+
- cosine_mrr@200
|
| 69 |
+
- cosine_map@1
|
| 70 |
+
- cosine_map@20
|
| 71 |
+
- cosine_map@50
|
| 72 |
+
- cosine_map@100
|
| 73 |
+
- cosine_map@150
|
| 74 |
+
- cosine_map@200
|
| 75 |
+
- cosine_map@500
|
| 76 |
+
model-index:
|
| 77 |
+
- name: SentenceTransformer based on BAAI/bge-m3
|
| 78 |
+
results:
|
| 79 |
+
- task:
|
| 80 |
+
type: information-retrieval
|
| 81 |
+
name: Information Retrieval
|
| 82 |
+
dataset:
|
| 83 |
+
name: full en
|
| 84 |
+
type: full_en
|
| 85 |
+
metrics:
|
| 86 |
+
- type: cosine_accuracy@1
|
| 87 |
+
value: 0.6571428571428571
|
| 88 |
+
name: Cosine Accuracy@1
|
| 89 |
+
- type: cosine_accuracy@20
|
| 90 |
+
value: 0.9904761904761905
|
| 91 |
+
name: Cosine Accuracy@20
|
| 92 |
+
- type: cosine_accuracy@50
|
| 93 |
+
value: 0.9904761904761905
|
| 94 |
+
name: Cosine Accuracy@50
|
| 95 |
+
- type: cosine_accuracy@100
|
| 96 |
+
value: 0.9904761904761905
|
| 97 |
+
name: Cosine Accuracy@100
|
| 98 |
+
- type: cosine_accuracy@150
|
| 99 |
+
value: 0.9904761904761905
|
| 100 |
+
name: Cosine Accuracy@150
|
| 101 |
+
- type: cosine_accuracy@200
|
| 102 |
+
value: 0.9904761904761905
|
| 103 |
+
name: Cosine Accuracy@200
|
| 104 |
+
- type: cosine_precision@1
|
| 105 |
+
value: 0.6571428571428571
|
| 106 |
+
name: Cosine Precision@1
|
| 107 |
+
- type: cosine_precision@20
|
| 108 |
+
value: 0.5042857142857142
|
| 109 |
+
name: Cosine Precision@20
|
| 110 |
+
- type: cosine_precision@50
|
| 111 |
+
value: 0.30342857142857144
|
| 112 |
+
name: Cosine Precision@50
|
| 113 |
+
- type: cosine_precision@100
|
| 114 |
+
value: 0.18485714285714283
|
| 115 |
+
name: Cosine Precision@100
|
| 116 |
+
- type: cosine_precision@150
|
| 117 |
+
value: 0.13161904761904764
|
| 118 |
+
name: Cosine Precision@150
|
| 119 |
+
- type: cosine_precision@200
|
| 120 |
+
value: 0.1020952380952381
|
| 121 |
+
name: Cosine Precision@200
|
| 122 |
+
- type: cosine_recall@1
|
| 123 |
+
value: 0.06749696615971254
|
| 124 |
+
name: Cosine Recall@1
|
| 125 |
+
- type: cosine_recall@20
|
| 126 |
+
value: 0.5373072040835736
|
| 127 |
+
name: Cosine Recall@20
|
| 128 |
+
- type: cosine_recall@50
|
| 129 |
+
value: 0.7066915041490871
|
| 130 |
+
name: Cosine Recall@50
|
| 131 |
+
- type: cosine_recall@100
|
| 132 |
+
value: 0.8223255763807351
|
| 133 |
+
name: Cosine Recall@100
|
| 134 |
+
- type: cosine_recall@150
|
| 135 |
+
value: 0.8681298207585033
|
| 136 |
+
name: Cosine Recall@150
|
| 137 |
+
- type: cosine_recall@200
|
| 138 |
+
value: 0.8939381871513931
|
| 139 |
+
name: Cosine Recall@200
|
| 140 |
+
- type: cosine_ndcg@1
|
| 141 |
+
value: 0.6571428571428571
|
| 142 |
+
name: Cosine Ndcg@1
|
| 143 |
+
- type: cosine_ndcg@20
|
| 144 |
+
value: 0.6828242233504754
|
| 145 |
+
name: Cosine Ndcg@20
|
| 146 |
+
- type: cosine_ndcg@50
|
| 147 |
+
value: 0.6934957075565445
|
| 148 |
+
name: Cosine Ndcg@50
|
| 149 |
+
- type: cosine_ndcg@100
|
| 150 |
+
value: 0.7508237653332346
|
| 151 |
+
name: Cosine Ndcg@100
|
| 152 |
+
- type: cosine_ndcg@150
|
| 153 |
+
value: 0.7708996755918012
|
| 154 |
+
name: Cosine Ndcg@150
|
| 155 |
+
- type: cosine_ndcg@200
|
| 156 |
+
value: 0.7810547976165594
|
| 157 |
+
name: Cosine Ndcg@200
|
| 158 |
+
- type: cosine_mrr@1
|
| 159 |
+
value: 0.6571428571428571
|
| 160 |
+
name: Cosine Mrr@1
|
| 161 |
+
- type: cosine_mrr@20
|
| 162 |
+
value: 0.8050793650793651
|
| 163 |
+
name: Cosine Mrr@20
|
| 164 |
+
- type: cosine_mrr@50
|
| 165 |
+
value: 0.8050793650793651
|
| 166 |
+
name: Cosine Mrr@50
|
| 167 |
+
- type: cosine_mrr@100
|
| 168 |
+
value: 0.8050793650793651
|
| 169 |
+
name: Cosine Mrr@100
|
| 170 |
+
- type: cosine_mrr@150
|
| 171 |
+
value: 0.8050793650793651
|
| 172 |
+
name: Cosine Mrr@150
|
| 173 |
+
- type: cosine_mrr@200
|
| 174 |
+
value: 0.8050793650793651
|
| 175 |
+
name: Cosine Mrr@200
|
| 176 |
+
- type: cosine_map@1
|
| 177 |
+
value: 0.6571428571428571
|
| 178 |
+
name: Cosine Map@1
|
| 179 |
+
- type: cosine_map@20
|
| 180 |
+
value: 0.5403780248322398
|
| 181 |
+
name: Cosine Map@20
|
| 182 |
+
- type: cosine_map@50
|
| 183 |
+
value: 0.5246924299662313
|
| 184 |
+
name: Cosine Map@50
|
| 185 |
+
- type: cosine_map@100
|
| 186 |
+
value: 0.5574701928996357
|
| 187 |
+
name: Cosine Map@100
|
| 188 |
+
- type: cosine_map@150
|
| 189 |
+
value: 0.5657362210212612
|
| 190 |
+
name: Cosine Map@150
|
| 191 |
+
- type: cosine_map@200
|
| 192 |
+
value: 0.5689495406824301
|
| 193 |
+
name: Cosine Map@200
|
| 194 |
+
- type: cosine_map@500
|
| 195 |
+
value: 0.5740394717933254
|
| 196 |
+
name: Cosine Map@500
|
| 197 |
+
- task:
|
| 198 |
+
type: information-retrieval
|
| 199 |
+
name: Information Retrieval
|
| 200 |
+
dataset:
|
| 201 |
+
name: full es
|
| 202 |
+
type: full_es
|
| 203 |
+
metrics:
|
| 204 |
+
- type: cosine_accuracy@1
|
| 205 |
+
value: 0.11351351351351352
|
| 206 |
+
name: Cosine Accuracy@1
|
| 207 |
+
- type: cosine_accuracy@20
|
| 208 |
+
value: 1.0
|
| 209 |
+
name: Cosine Accuracy@20
|
| 210 |
+
- type: cosine_accuracy@50
|
| 211 |
+
value: 1.0
|
| 212 |
+
name: Cosine Accuracy@50
|
| 213 |
+
- type: cosine_accuracy@100
|
| 214 |
+
value: 1.0
|
| 215 |
+
name: Cosine Accuracy@100
|
| 216 |
+
- type: cosine_accuracy@150
|
| 217 |
+
value: 1.0
|
| 218 |
+
name: Cosine Accuracy@150
|
| 219 |
+
- type: cosine_accuracy@200
|
| 220 |
+
value: 1.0
|
| 221 |
+
name: Cosine Accuracy@200
|
| 222 |
+
- type: cosine_precision@1
|
| 223 |
+
value: 0.11351351351351352
|
| 224 |
+
name: Cosine Precision@1
|
| 225 |
+
- type: cosine_precision@20
|
| 226 |
+
value: 0.5678378378378378
|
| 227 |
+
name: Cosine Precision@20
|
| 228 |
+
- type: cosine_precision@50
|
| 229 |
+
value: 0.38616216216216215
|
| 230 |
+
name: Cosine Precision@50
|
| 231 |
+
- type: cosine_precision@100
|
| 232 |
+
value: 0.24956756756756757
|
| 233 |
+
name: Cosine Precision@100
|
| 234 |
+
- type: cosine_precision@150
|
| 235 |
+
value: 0.18836036036036036
|
| 236 |
+
name: Cosine Precision@150
|
| 237 |
+
- type: cosine_precision@200
|
| 238 |
+
value: 0.14981081081081082
|
| 239 |
+
name: Cosine Precision@200
|
| 240 |
+
- type: cosine_recall@1
|
| 241 |
+
value: 0.0035155918996302815
|
| 242 |
+
name: Cosine Recall@1
|
| 243 |
+
- type: cosine_recall@20
|
| 244 |
+
value: 0.37836142042267473
|
| 245 |
+
name: Cosine Recall@20
|
| 246 |
+
- type: cosine_recall@50
|
| 247 |
+
value: 0.5571586783455559
|
| 248 |
+
name: Cosine Recall@50
|
| 249 |
+
- type: cosine_recall@100
|
| 250 |
+
value: 0.6675392853403386
|
| 251 |
+
name: Cosine Recall@100
|
| 252 |
+
- type: cosine_recall@150
|
| 253 |
+
value: 0.7304539075934318
|
| 254 |
+
name: Cosine Recall@150
|
| 255 |
+
- type: cosine_recall@200
|
| 256 |
+
value: 0.762368065923207
|
| 257 |
+
name: Cosine Recall@200
|
| 258 |
+
- type: cosine_ndcg@1
|
| 259 |
+
value: 0.11351351351351352
|
| 260 |
+
name: Cosine Ndcg@1
|
| 261 |
+
- type: cosine_ndcg@20
|
| 262 |
+
value: 0.6138712223781554
|
| 263 |
+
name: Cosine Ndcg@20
|
| 264 |
+
- type: cosine_ndcg@50
|
| 265 |
+
value: 0.5860105244597086
|
| 266 |
+
name: Cosine Ndcg@50
|
| 267 |
+
- type: cosine_ndcg@100
|
| 268 |
+
value: 0.612222606218991
|
| 269 |
+
name: Cosine Ndcg@100
|
| 270 |
+
- type: cosine_ndcg@150
|
| 271 |
+
value: 0.6445206608822607
|
| 272 |
+
name: Cosine Ndcg@150
|
| 273 |
+
- type: cosine_ndcg@200
|
| 274 |
+
value: 0.6607643472995034
|
| 275 |
+
name: Cosine Ndcg@200
|
| 276 |
+
- type: cosine_mrr@1
|
| 277 |
+
value: 0.11351351351351352
|
| 278 |
+
name: Cosine Mrr@1
|
| 279 |
+
- type: cosine_mrr@20
|
| 280 |
+
value: 0.5536036036036036
|
| 281 |
+
name: Cosine Mrr@20
|
| 282 |
+
- type: cosine_mrr@50
|
| 283 |
+
value: 0.5536036036036036
|
| 284 |
+
name: Cosine Mrr@50
|
| 285 |
+
- type: cosine_mrr@100
|
| 286 |
+
value: 0.5536036036036036
|
| 287 |
+
name: Cosine Mrr@100
|
| 288 |
+
- type: cosine_mrr@150
|
| 289 |
+
value: 0.5536036036036036
|
| 290 |
+
name: Cosine Mrr@150
|
| 291 |
+
- type: cosine_mrr@200
|
| 292 |
+
value: 0.5536036036036036
|
| 293 |
+
name: Cosine Mrr@200
|
| 294 |
+
- type: cosine_map@1
|
| 295 |
+
value: 0.11351351351351352
|
| 296 |
+
name: Cosine Map@1
|
| 297 |
+
- type: cosine_map@20
|
| 298 |
+
value: 0.48205571119205054
|
| 299 |
+
name: Cosine Map@20
|
| 300 |
+
- type: cosine_map@50
|
| 301 |
+
value: 0.426066001253444
|
| 302 |
+
name: Cosine Map@50
|
| 303 |
+
- type: cosine_map@100
|
| 304 |
+
value: 0.4286297248227863
|
| 305 |
+
name: Cosine Map@100
|
| 306 |
+
- type: cosine_map@150
|
| 307 |
+
value: 0.44367730975701125
|
| 308 |
+
name: Cosine Map@150
|
| 309 |
+
- type: cosine_map@200
|
| 310 |
+
value: 0.45055470203697434
|
| 311 |
+
name: Cosine Map@200
|
| 312 |
+
- type: cosine_map@500
|
| 313 |
+
value: 0.4632014183024849
|
| 314 |
+
name: Cosine Map@500
|
| 315 |
+
- task:
|
| 316 |
+
type: information-retrieval
|
| 317 |
+
name: Information Retrieval
|
| 318 |
+
dataset:
|
| 319 |
+
name: full de
|
| 320 |
+
type: full_de
|
| 321 |
+
metrics:
|
| 322 |
+
- type: cosine_accuracy@1
|
| 323 |
+
value: 0.2955665024630542
|
| 324 |
+
name: Cosine Accuracy@1
|
| 325 |
+
- type: cosine_accuracy@20
|
| 326 |
+
value: 0.9802955665024631
|
| 327 |
+
name: Cosine Accuracy@20
|
| 328 |
+
- type: cosine_accuracy@50
|
| 329 |
+
value: 0.9852216748768473
|
| 330 |
+
name: Cosine Accuracy@50
|
| 331 |
+
- type: cosine_accuracy@100
|
| 332 |
+
value: 0.9852216748768473
|
| 333 |
+
name: Cosine Accuracy@100
|
| 334 |
+
- type: cosine_accuracy@150
|
| 335 |
+
value: 0.9901477832512315
|
| 336 |
+
name: Cosine Accuracy@150
|
| 337 |
+
- type: cosine_accuracy@200
|
| 338 |
+
value: 0.9901477832512315
|
| 339 |
+
name: Cosine Accuracy@200
|
| 340 |
+
- type: cosine_precision@1
|
| 341 |
+
value: 0.2955665024630542
|
| 342 |
+
name: Cosine Precision@1
|
| 343 |
+
- type: cosine_precision@20
|
| 344 |
+
value: 0.5391625615763547
|
| 345 |
+
name: Cosine Precision@20
|
| 346 |
+
- type: cosine_precision@50
|
| 347 |
+
value: 0.3801970443349754
|
| 348 |
+
name: Cosine Precision@50
|
| 349 |
+
- type: cosine_precision@100
|
| 350 |
+
value: 0.2476847290640394
|
| 351 |
+
name: Cosine Precision@100
|
| 352 |
+
- type: cosine_precision@150
|
| 353 |
+
value: 0.18568144499178982
|
| 354 |
+
name: Cosine Precision@150
|
| 355 |
+
- type: cosine_precision@200
|
| 356 |
+
value: 0.14891625615763546
|
| 357 |
+
name: Cosine Precision@200
|
| 358 |
+
- type: cosine_recall@1
|
| 359 |
+
value: 0.01108543831680986
|
| 360 |
+
name: Cosine Recall@1
|
| 361 |
+
- type: cosine_recall@20
|
| 362 |
+
value: 0.3399387209539555
|
| 363 |
+
name: Cosine Recall@20
|
| 364 |
+
- type: cosine_recall@50
|
| 365 |
+
value: 0.5308580040187325
|
| 366 |
+
name: Cosine Recall@50
|
| 367 |
+
- type: cosine_recall@100
|
| 368 |
+
value: 0.6430327898382845
|
| 369 |
+
name: Cosine Recall@100
|
| 370 |
+
- type: cosine_recall@150
|
| 371 |
+
value: 0.7043523082318627
|
| 372 |
+
name: Cosine Recall@150
|
| 373 |
+
- type: cosine_recall@200
|
| 374 |
+
value: 0.7435945575564449
|
| 375 |
+
name: Cosine Recall@200
|
| 376 |
+
- type: cosine_ndcg@1
|
| 377 |
+
value: 0.2955665024630542
|
| 378 |
+
name: Cosine Ndcg@1
|
| 379 |
+
- type: cosine_ndcg@20
|
| 380 |
+
value: 0.5620736680453444
|
| 381 |
+
name: Cosine Ndcg@20
|
| 382 |
+
- type: cosine_ndcg@50
|
| 383 |
+
value: 0.5486209217219633
|
| 384 |
+
name: Cosine Ndcg@50
|
| 385 |
+
- type: cosine_ndcg@100
|
| 386 |
+
value: 0.5742560822304251
|
| 387 |
+
name: Cosine Ndcg@100
|
| 388 |
+
- type: cosine_ndcg@150
|
| 389 |
+
value: 0.6059775924816383
|
| 390 |
+
name: Cosine Ndcg@150
|
| 391 |
+
- type: cosine_ndcg@200
|
| 392 |
+
value: 0.6254063201510274
|
| 393 |
+
name: Cosine Ndcg@200
|
| 394 |
+
- type: cosine_mrr@1
|
| 395 |
+
value: 0.2955665024630542
|
| 396 |
+
name: Cosine Mrr@1
|
| 397 |
+
- type: cosine_mrr@20
|
| 398 |
+
value: 0.5138789918346562
|
| 399 |
+
name: Cosine Mrr@20
|
| 400 |
+
- type: cosine_mrr@50
|
| 401 |
+
value: 0.5140086262655611
|
| 402 |
+
name: Cosine Mrr@50
|
| 403 |
+
- type: cosine_mrr@100
|
| 404 |
+
value: 0.5140086262655611
|
| 405 |
+
name: Cosine Mrr@100
|
| 406 |
+
- type: cosine_mrr@150
|
| 407 |
+
value: 0.5140546646615833
|
| 408 |
+
name: Cosine Mrr@150
|
| 409 |
+
- type: cosine_mrr@200
|
| 410 |
+
value: 0.5140546646615833
|
| 411 |
+
name: Cosine Mrr@200
|
| 412 |
+
- type: cosine_map@1
|
| 413 |
+
value: 0.2955665024630542
|
| 414 |
+
name: Cosine Map@1
|
| 415 |
+
- type: cosine_map@20
|
| 416 |
+
value: 0.42010224651188977
|
| 417 |
+
name: Cosine Map@20
|
| 418 |
+
- type: cosine_map@50
|
| 419 |
+
value: 0.37517744419195703
|
| 420 |
+
name: Cosine Map@50
|
| 421 |
+
- type: cosine_map@100
|
| 422 |
+
value: 0.3784520844424068
|
| 423 |
+
name: Cosine Map@100
|
| 424 |
+
- type: cosine_map@150
|
| 425 |
+
value: 0.3928983602214202
|
| 426 |
+
name: Cosine Map@150
|
| 427 |
+
- type: cosine_map@200
|
| 428 |
+
value: 0.40049621656562834
|
| 429 |
+
name: Cosine Map@200
|
| 430 |
+
- type: cosine_map@500
|
| 431 |
+
value: 0.4142041780241764
|
| 432 |
+
name: Cosine Map@500
|
| 433 |
+
- task:
|
| 434 |
+
type: information-retrieval
|
| 435 |
+
name: Information Retrieval
|
| 436 |
+
dataset:
|
| 437 |
+
name: full zh
|
| 438 |
+
type: full_zh
|
| 439 |
+
metrics:
|
| 440 |
+
- type: cosine_accuracy@1
|
| 441 |
+
value: 0.6601941747572816
|
| 442 |
+
name: Cosine Accuracy@1
|
| 443 |
+
- type: cosine_accuracy@20
|
| 444 |
+
value: 0.9902912621359223
|
| 445 |
+
name: Cosine Accuracy@20
|
| 446 |
+
- type: cosine_accuracy@50
|
| 447 |
+
value: 0.9902912621359223
|
| 448 |
+
name: Cosine Accuracy@50
|
| 449 |
+
- type: cosine_accuracy@100
|
| 450 |
+
value: 0.9902912621359223
|
| 451 |
+
name: Cosine Accuracy@100
|
| 452 |
+
- type: cosine_accuracy@150
|
| 453 |
+
value: 0.9902912621359223
|
| 454 |
+
name: Cosine Accuracy@150
|
| 455 |
+
- type: cosine_accuracy@200
|
| 456 |
+
value: 0.9902912621359223
|
| 457 |
+
name: Cosine Accuracy@200
|
| 458 |
+
- type: cosine_precision@1
|
| 459 |
+
value: 0.6601941747572816
|
| 460 |
+
name: Cosine Precision@1
|
| 461 |
+
- type: cosine_precision@20
|
| 462 |
+
value: 0.46990291262135936
|
| 463 |
+
name: Cosine Precision@20
|
| 464 |
+
- type: cosine_precision@50
|
| 465 |
+
value: 0.2766990291262136
|
| 466 |
+
name: Cosine Precision@50
|
| 467 |
+
- type: cosine_precision@100
|
| 468 |
+
value: 0.17145631067961165
|
| 469 |
+
name: Cosine Precision@100
|
| 470 |
+
- type: cosine_precision@150
|
| 471 |
+
value: 0.12381877022653723
|
| 472 |
+
name: Cosine Precision@150
|
| 473 |
+
- type: cosine_precision@200
|
| 474 |
+
value: 0.09747572815533984
|
| 475 |
+
name: Cosine Precision@200
|
| 476 |
+
- type: cosine_recall@1
|
| 477 |
+
value: 0.06391645269201905
|
| 478 |
+
name: Cosine Recall@1
|
| 479 |
+
- type: cosine_recall@20
|
| 480 |
+
value: 0.5028687618433456
|
| 481 |
+
name: Cosine Recall@20
|
| 482 |
+
- type: cosine_recall@50
|
| 483 |
+
value: 0.6651242597088418
|
| 484 |
+
name: Cosine Recall@50
|
| 485 |
+
- type: cosine_recall@100
|
| 486 |
+
value: 0.7783273755437382
|
| 487 |
+
name: Cosine Recall@100
|
| 488 |
+
- type: cosine_recall@150
|
| 489 |
+
value: 0.8334866166756513
|
| 490 |
+
name: Cosine Recall@150
|
| 491 |
+
- type: cosine_recall@200
|
| 492 |
+
value: 0.8666706510858552
|
| 493 |
+
name: Cosine Recall@200
|
| 494 |
+
- type: cosine_ndcg@1
|
| 495 |
+
value: 0.6601941747572816
|
| 496 |
+
name: Cosine Ndcg@1
|
| 497 |
+
- type: cosine_ndcg@20
|
| 498 |
+
value: 0.6467729312304265
|
| 499 |
+
name: Cosine Ndcg@20
|
| 500 |
+
- type: cosine_ndcg@50
|
| 501 |
+
value: 0.6531754449097694
|
| 502 |
+
name: Cosine Ndcg@50
|
| 503 |
+
- type: cosine_ndcg@100
|
| 504 |
+
value: 0.7091690247935931
|
| 505 |
+
name: Cosine Ndcg@100
|
| 506 |
+
- type: cosine_ndcg@150
|
| 507 |
+
value: 0.7326072552384693
|
| 508 |
+
name: Cosine Ndcg@150
|
| 509 |
+
- type: cosine_ndcg@200
|
| 510 |
+
value: 0.7462718534326636
|
| 511 |
+
name: Cosine Ndcg@200
|
| 512 |
+
- type: cosine_mrr@1
|
| 513 |
+
value: 0.6601941747572816
|
| 514 |
+
name: Cosine Mrr@1
|
| 515 |
+
- type: cosine_mrr@20
|
| 516 |
+
value: 0.8101941747572816
|
| 517 |
+
name: Cosine Mrr@20
|
| 518 |
+
- type: cosine_mrr@50
|
| 519 |
+
value: 0.8101941747572816
|
| 520 |
+
name: Cosine Mrr@50
|
| 521 |
+
- type: cosine_mrr@100
|
| 522 |
+
value: 0.8101941747572816
|
| 523 |
+
name: Cosine Mrr@100
|
| 524 |
+
- type: cosine_mrr@150
|
| 525 |
+
value: 0.8101941747572816
|
| 526 |
+
name: Cosine Mrr@150
|
| 527 |
+
- type: cosine_mrr@200
|
| 528 |
+
value: 0.8101941747572816
|
| 529 |
+
name: Cosine Mrr@200
|
| 530 |
+
- type: cosine_map@1
|
| 531 |
+
value: 0.6601941747572816
|
| 532 |
+
name: Cosine Map@1
|
| 533 |
+
- type: cosine_map@20
|
| 534 |
+
value: 0.5008318658399892
|
| 535 |
+
name: Cosine Map@20
|
| 536 |
+
- type: cosine_map@50
|
| 537 |
+
value: 0.47687535367801903
|
| 538 |
+
name: Cosine Map@50
|
| 539 |
+
- type: cosine_map@100
|
| 540 |
+
value: 0.506399482523297
|
| 541 |
+
name: Cosine Map@100
|
| 542 |
+
- type: cosine_map@150
|
| 543 |
+
value: 0.515344178164581
|
| 544 |
+
name: Cosine Map@150
|
| 545 |
+
- type: cosine_map@200
|
| 546 |
+
value: 0.5196266745217748
|
| 547 |
+
name: Cosine Map@200
|
| 548 |
+
- type: cosine_map@500
|
| 549 |
+
value: 0.5245537410408139
|
| 550 |
+
name: Cosine Map@500
|
| 551 |
+
- task:
|
| 552 |
+
type: information-retrieval
|
| 553 |
+
name: Information Retrieval
|
| 554 |
+
dataset:
|
| 555 |
+
name: mix es
|
| 556 |
+
type: mix_es
|
| 557 |
+
metrics:
|
| 558 |
+
- type: cosine_accuracy@1
|
| 559 |
+
value: 0.733749349973999
|
| 560 |
+
name: Cosine Accuracy@1
|
| 561 |
+
- type: cosine_accuracy@20
|
| 562 |
+
value: 0.9604784191367655
|
| 563 |
+
name: Cosine Accuracy@20
|
| 564 |
+
- type: cosine_accuracy@50
|
| 565 |
+
value: 0.982839313572543
|
| 566 |
+
name: Cosine Accuracy@50
|
| 567 |
+
- type: cosine_accuracy@100
|
| 568 |
+
value: 0.9916796671866874
|
| 569 |
+
name: Cosine Accuracy@100
|
| 570 |
+
- type: cosine_accuracy@150
|
| 571 |
+
value: 0.9947997919916797
|
| 572 |
+
name: Cosine Accuracy@150
|
| 573 |
+
- type: cosine_accuracy@200
|
| 574 |
+
value: 0.9953198127925117
|
| 575 |
+
name: Cosine Accuracy@200
|
| 576 |
+
- type: cosine_precision@1
|
| 577 |
+
value: 0.733749349973999
|
| 578 |
+
name: Cosine Precision@1
|
| 579 |
+
- type: cosine_precision@20
|
| 580 |
+
value: 0.12433697347893914
|
| 581 |
+
name: Cosine Precision@20
|
| 582 |
+
- type: cosine_precision@50
|
| 583 |
+
value: 0.0516588663546542
|
| 584 |
+
name: Cosine Precision@50
|
| 585 |
+
- type: cosine_precision@100
|
| 586 |
+
value: 0.026229849193967765
|
| 587 |
+
name: Cosine Precision@100
|
| 588 |
+
- type: cosine_precision@150
|
| 589 |
+
value: 0.017635638758883684
|
| 590 |
+
name: Cosine Precision@150
|
| 591 |
+
- type: cosine_precision@200
|
| 592 |
+
value: 0.013273530941237652
|
| 593 |
+
name: Cosine Precision@200
|
| 594 |
+
- type: cosine_recall@1
|
| 595 |
+
value: 0.28340762201916647
|
| 596 |
+
name: Cosine Recall@1
|
| 597 |
+
- type: cosine_recall@20
|
| 598 |
+
value: 0.9186774137632172
|
| 599 |
+
name: Cosine Recall@20
|
| 600 |
+
- type: cosine_recall@50
|
| 601 |
+
value: 0.9536314785924771
|
| 602 |
+
name: Cosine Recall@50
|
| 603 |
+
- type: cosine_recall@100
|
| 604 |
+
value: 0.968538741549662
|
| 605 |
+
name: Cosine Recall@100
|
| 606 |
+
- type: cosine_recall@150
|
| 607 |
+
value: 0.9768070722828913
|
| 608 |
+
name: Cosine Recall@150
|
| 609 |
+
- type: cosine_recall@200
|
| 610 |
+
value: 0.9806205581556595
|
| 611 |
+
name: Cosine Recall@200
|
| 612 |
+
- type: cosine_ndcg@1
|
| 613 |
+
value: 0.733749349973999
|
| 614 |
+
name: Cosine Ndcg@1
|
| 615 |
+
- type: cosine_ndcg@20
|
| 616 |
+
value: 0.8074696494514497
|
| 617 |
+
name: Cosine Ndcg@20
|
| 618 |
+
- type: cosine_ndcg@50
|
| 619 |
+
value: 0.8170488841773651
|
| 620 |
+
name: Cosine Ndcg@50
|
| 621 |
+
- type: cosine_ndcg@100
|
| 622 |
+
value: 0.8203516409516334
|
| 623 |
+
name: Cosine Ndcg@100
|
| 624 |
+
- type: cosine_ndcg@150
|
| 625 |
+
value: 0.8219710202163846
|
| 626 |
+
name: Cosine Ndcg@150
|
| 627 |
+
- type: cosine_ndcg@200
|
| 628 |
+
value: 0.8226411885850343
|
| 629 |
+
name: Cosine Ndcg@200
|
| 630 |
+
- type: cosine_mrr@1
|
| 631 |
+
value: 0.733749349973999
|
| 632 |
+
name: Cosine Mrr@1
|
| 633 |
+
- type: cosine_mrr@20
|
| 634 |
+
value: 0.8015837695391573
|
| 635 |
+
name: Cosine Mrr@20
|
| 636 |
+
- type: cosine_mrr@50
|
| 637 |
+
value: 0.8023398853791036
|
| 638 |
+
name: Cosine Mrr@50
|
| 639 |
+
- type: cosine_mrr@100
|
| 640 |
+
value: 0.8024787052722444
|
| 641 |
+
name: Cosine Mrr@100
|
| 642 |
+
- type: cosine_mrr@150
|
| 643 |
+
value: 0.8025062574128484
|
| 644 |
+
name: Cosine Mrr@150
|
| 645 |
+
- type: cosine_mrr@200
|
| 646 |
+
value: 0.8025096562416121
|
| 647 |
+
name: Cosine Mrr@200
|
| 648 |
+
- type: cosine_map@1
|
| 649 |
+
value: 0.733749349973999
|
| 650 |
+
name: Cosine Map@1
|
| 651 |
+
- type: cosine_map@20
|
| 652 |
+
value: 0.7389285820519963
|
| 653 |
+
name: Cosine Map@20
|
| 654 |
+
- type: cosine_map@50
|
| 655 |
+
value: 0.7414939322506505
|
| 656 |
+
name: Cosine Map@50
|
| 657 |
+
- type: cosine_map@100
|
| 658 |
+
value: 0.7419568857454747
|
| 659 |
+
name: Cosine Map@100
|
| 660 |
+
- type: cosine_map@150
|
| 661 |
+
value: 0.7421153780150582
|
| 662 |
+
name: Cosine Map@150
|
| 663 |
+
- type: cosine_map@200
|
| 664 |
+
value: 0.742164620684282
|
| 665 |
+
name: Cosine Map@200
|
| 666 |
+
- type: cosine_map@500
|
| 667 |
+
value: 0.7422579374234903
|
| 668 |
+
name: Cosine Map@500
|
| 669 |
+
- task:
|
| 670 |
+
type: information-retrieval
|
| 671 |
+
name: Information Retrieval
|
| 672 |
+
dataset:
|
| 673 |
+
name: mix de
|
| 674 |
+
type: mix_de
|
| 675 |
+
metrics:
|
| 676 |
+
- type: cosine_accuracy@1
|
| 677 |
+
value: 0.6859074362974519
|
| 678 |
+
name: Cosine Accuracy@1
|
| 679 |
+
- type: cosine_accuracy@20
|
| 680 |
+
value: 0.9661986479459178
|
| 681 |
+
name: Cosine Accuracy@20
|
| 682 |
+
- type: cosine_accuracy@50
|
| 683 |
+
value: 0.982839313572543
|
| 684 |
+
name: Cosine Accuracy@50
|
| 685 |
+
- type: cosine_accuracy@100
|
| 686 |
+
value: 0.9927197087883516
|
| 687 |
+
name: Cosine Accuracy@100
|
| 688 |
+
- type: cosine_accuracy@150
|
| 689 |
+
value: 0.9932397295891836
|
| 690 |
+
name: Cosine Accuracy@150
|
| 691 |
+
- type: cosine_accuracy@200
|
| 692 |
+
value: 0.9937597503900156
|
| 693 |
+
name: Cosine Accuracy@200
|
| 694 |
+
- type: cosine_precision@1
|
| 695 |
+
value: 0.6859074362974519
|
| 696 |
+
name: Cosine Precision@1
|
| 697 |
+
- type: cosine_precision@20
|
| 698 |
+
value: 0.12732709308372334
|
| 699 |
+
name: Cosine Precision@20
|
| 700 |
+
- type: cosine_precision@50
|
| 701 |
+
value: 0.05308372334893397
|
| 702 |
+
name: Cosine Precision@50
|
| 703 |
+
- type: cosine_precision@100
|
| 704 |
+
value: 0.027025481019240776
|
| 705 |
+
name: Cosine Precision@100
|
| 706 |
+
- type: cosine_precision@150
|
| 707 |
+
value: 0.018103657479632513
|
| 708 |
+
name: Cosine Precision@150
|
| 709 |
+
- type: cosine_precision@200
|
| 710 |
+
value: 0.013606344253770154
|
| 711 |
+
name: Cosine Precision@200
|
| 712 |
+
- type: cosine_recall@1
|
| 713 |
+
value: 0.2577396429190501
|
| 714 |
+
name: Cosine Recall@1
|
| 715 |
+
- type: cosine_recall@20
|
| 716 |
+
value: 0.9241896342520368
|
| 717 |
+
name: Cosine Recall@20
|
| 718 |
+
- type: cosine_recall@50
|
| 719 |
+
value: 0.9614317906049575
|
| 720 |
+
name: Cosine Recall@50
|
| 721 |
+
- type: cosine_recall@100
|
| 722 |
+
value: 0.9787224822326227
|
| 723 |
+
name: Cosine Recall@100
|
| 724 |
+
- type: cosine_recall@150
|
| 725 |
+
value: 0.983359334373375
|
| 726 |
+
name: Cosine Recall@150
|
| 727 |
+
- type: cosine_recall@200
|
| 728 |
+
value: 0.9854394175767031
|
| 729 |
+
name: Cosine Recall@200
|
| 730 |
+
- type: cosine_ndcg@1
|
| 731 |
+
value: 0.6859074362974519
|
| 732 |
+
name: Cosine Ndcg@1
|
| 733 |
+
- type: cosine_ndcg@20
|
| 734 |
+
value: 0.7894367570955271
|
| 735 |
+
name: Cosine Ndcg@20
|
| 736 |
+
- type: cosine_ndcg@50
|
| 737 |
+
value: 0.7998923204035095
|
| 738 |
+
name: Cosine Ndcg@50
|
| 739 |
+
- type: cosine_ndcg@100
|
| 740 |
+
value: 0.8037683941688618
|
| 741 |
+
name: Cosine Ndcg@100
|
| 742 |
+
- type: cosine_ndcg@150
|
| 743 |
+
value: 0.8046891228048068
|
| 744 |
+
name: Cosine Ndcg@150
|
| 745 |
+
- type: cosine_ndcg@200
|
| 746 |
+
value: 0.8050715563658618
|
| 747 |
+
name: Cosine Ndcg@200
|
| 748 |
+
- type: cosine_mrr@1
|
| 749 |
+
value: 0.6859074362974519
|
| 750 |
+
name: Cosine Mrr@1
|
| 751 |
+
- type: cosine_mrr@20
|
| 752 |
+
value: 0.7703397211809108
|
| 753 |
+
name: Cosine Mrr@20
|
| 754 |
+
- type: cosine_mrr@50
|
| 755 |
+
value: 0.7708870204854694
|
| 756 |
+
name: Cosine Mrr@50
|
| 757 |
+
- type: cosine_mrr@100
|
| 758 |
+
value: 0.7710242509181896
|
| 759 |
+
name: Cosine Mrr@100
|
| 760 |
+
- type: cosine_mrr@150
|
| 761 |
+
value: 0.7710286578741289
|
| 762 |
+
name: Cosine Mrr@150
|
| 763 |
+
- type: cosine_mrr@200
|
| 764 |
+
value: 0.7710319701085292
|
| 765 |
+
name: Cosine Mrr@200
|
| 766 |
+
- type: cosine_map@1
|
| 767 |
+
value: 0.6859074362974519
|
| 768 |
+
name: Cosine Map@1
|
| 769 |
+
- type: cosine_map@20
|
| 770 |
+
value: 0.711359959198991
|
| 771 |
+
name: Cosine Map@20
|
| 772 |
+
- type: cosine_map@50
|
| 773 |
+
value: 0.7143436554485498
|
| 774 |
+
name: Cosine Map@50
|
| 775 |
+
- type: cosine_map@100
|
| 776 |
+
value: 0.7149332520404413
|
| 777 |
+
name: Cosine Map@100
|
| 778 |
+
- type: cosine_map@150
|
| 779 |
+
value: 0.7150312982701879
|
| 780 |
+
name: Cosine Map@150
|
| 781 |
+
- type: cosine_map@200
|
| 782 |
+
value: 0.7150609466134881
|
| 783 |
+
name: Cosine Map@200
|
| 784 |
+
- type: cosine_map@500
|
| 785 |
+
value: 0.715115635794944
|
| 786 |
+
name: Cosine Map@500
|
| 787 |
+
- task:
|
| 788 |
+
type: information-retrieval
|
| 789 |
+
name: Information Retrieval
|
| 790 |
+
dataset:
|
| 791 |
+
name: mix zh
|
| 792 |
+
type: mix_zh
|
| 793 |
+
metrics:
|
| 794 |
+
- type: cosine_accuracy@1
|
| 795 |
+
value: 0.1814872594903796
|
| 796 |
+
name: Cosine Accuracy@1
|
| 797 |
+
- type: cosine_accuracy@20
|
| 798 |
+
value: 1.0
|
| 799 |
+
name: Cosine Accuracy@20
|
| 800 |
+
- type: cosine_accuracy@50
|
| 801 |
+
value: 1.0
|
| 802 |
+
name: Cosine Accuracy@50
|
| 803 |
+
- type: cosine_accuracy@100
|
| 804 |
+
value: 1.0
|
| 805 |
+
name: Cosine Accuracy@100
|
| 806 |
+
- type: cosine_accuracy@150
|
| 807 |
+
value: 1.0
|
| 808 |
+
name: Cosine Accuracy@150
|
| 809 |
+
- type: cosine_accuracy@200
|
| 810 |
+
value: 1.0
|
| 811 |
+
name: Cosine Accuracy@200
|
| 812 |
+
- type: cosine_precision@1
|
| 813 |
+
value: 0.1814872594903796
|
| 814 |
+
name: Cosine Precision@1
|
| 815 |
+
- type: cosine_precision@20
|
| 816 |
+
value: 0.15439417576703063
|
| 817 |
+
name: Cosine Precision@20
|
| 818 |
+
- type: cosine_precision@50
|
| 819 |
+
value: 0.0617576703068123
|
| 820 |
+
name: Cosine Precision@50
|
| 821 |
+
- type: cosine_precision@100
|
| 822 |
+
value: 0.03087883515340615
|
| 823 |
+
name: Cosine Precision@100
|
| 824 |
+
- type: cosine_precision@150
|
| 825 |
+
value: 0.020585890102270757
|
| 826 |
+
name: Cosine Precision@150
|
| 827 |
+
- type: cosine_precision@200
|
| 828 |
+
value: 0.015439417576703075
|
| 829 |
+
name: Cosine Precision@200
|
| 830 |
+
- type: cosine_recall@1
|
| 831 |
+
value: 0.05822499566649332
|
| 832 |
+
name: Cosine Recall@1
|
| 833 |
+
- type: cosine_recall@20
|
| 834 |
+
value: 1.0
|
| 835 |
+
name: Cosine Recall@20
|
| 836 |
+
- type: cosine_recall@50
|
| 837 |
+
value: 1.0
|
| 838 |
+
name: Cosine Recall@50
|
| 839 |
+
- type: cosine_recall@100
|
| 840 |
+
value: 1.0
|
| 841 |
+
name: Cosine Recall@100
|
| 842 |
+
- type: cosine_recall@150
|
| 843 |
+
value: 1.0
|
| 844 |
+
name: Cosine Recall@150
|
| 845 |
+
- type: cosine_recall@200
|
| 846 |
+
value: 1.0
|
| 847 |
+
name: Cosine Recall@200
|
| 848 |
+
- type: cosine_ndcg@1
|
| 849 |
+
value: 0.1814872594903796
|
| 850 |
+
name: Cosine Ndcg@1
|
| 851 |
+
- type: cosine_ndcg@20
|
| 852 |
+
value: 0.5442006309834599
|
| 853 |
+
name: Cosine Ndcg@20
|
| 854 |
+
- type: cosine_ndcg@50
|
| 855 |
+
value: 0.5442006309834599
|
| 856 |
+
name: Cosine Ndcg@50
|
| 857 |
+
- type: cosine_ndcg@100
|
| 858 |
+
value: 0.5442006309834599
|
| 859 |
+
name: Cosine Ndcg@100
|
| 860 |
+
- type: cosine_ndcg@150
|
| 861 |
+
value: 0.5442006309834599
|
| 862 |
+
name: Cosine Ndcg@150
|
| 863 |
+
- type: cosine_ndcg@200
|
| 864 |
+
value: 0.5442006309834599
|
| 865 |
+
name: Cosine Ndcg@200
|
| 866 |
+
- type: cosine_mrr@1
|
| 867 |
+
value: 0.1814872594903796
|
| 868 |
+
name: Cosine Mrr@1
|
| 869 |
+
- type: cosine_mrr@20
|
| 870 |
+
value: 0.4016099489578433
|
| 871 |
+
name: Cosine Mrr@20
|
| 872 |
+
- type: cosine_mrr@50
|
| 873 |
+
value: 0.4016099489578433
|
| 874 |
+
name: Cosine Mrr@50
|
| 875 |
+
- type: cosine_mrr@100
|
| 876 |
+
value: 0.4016099489578433
|
| 877 |
+
name: Cosine Mrr@100
|
| 878 |
+
- type: cosine_mrr@150
|
| 879 |
+
value: 0.4016099489578433
|
| 880 |
+
name: Cosine Mrr@150
|
| 881 |
+
- type: cosine_mrr@200
|
| 882 |
+
value: 0.4016099489578433
|
| 883 |
+
name: Cosine Mrr@200
|
| 884 |
+
- type: cosine_map@1
|
| 885 |
+
value: 0.1814872594903796
|
| 886 |
+
name: Cosine Map@1
|
| 887 |
+
- type: cosine_map@20
|
| 888 |
+
value: 0.32662137894847204
|
| 889 |
+
name: Cosine Map@20
|
| 890 |
+
- type: cosine_map@50
|
| 891 |
+
value: 0.32662137894847204
|
| 892 |
+
name: Cosine Map@50
|
| 893 |
+
- type: cosine_map@100
|
| 894 |
+
value: 0.32662137894847204
|
| 895 |
+
name: Cosine Map@100
|
| 896 |
+
- type: cosine_map@150
|
| 897 |
+
value: 0.32662137894847204
|
| 898 |
+
name: Cosine Map@150
|
| 899 |
+
- type: cosine_map@200
|
| 900 |
+
value: 0.32662137894847204
|
| 901 |
+
name: Cosine Map@200
|
| 902 |
+
- type: cosine_map@500
|
| 903 |
+
value: 0.32662137894847204
|
| 904 |
+
name: Cosine Map@500
|
| 905 |
+
---
|
| 906 |
+
|
| 907 |
+
# SentenceTransformer based on BAAI/bge-m3
|
| 908 |
+
|
| 909 |
+
This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) on the full_en, full_de, full_es, full_zh and mix datasets. It maps sentences & paragraphs to a 1024-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.
|
| 910 |
+
|
| 911 |
+
## Model Details
|
| 912 |
+
|
| 913 |
+
### Model Description
|
| 914 |
+
- **Model Type:** Sentence Transformer
|
| 915 |
+
- **Base model:** [BAAI/bge-m3](https://huggingface.co/BAAI/bge-m3) <!-- at revision 5617a9f61b028005a4858fdac845db406aefb181 -->
|
| 916 |
+
- **Maximum Sequence Length:** 512 tokens
|
| 917 |
+
- **Output Dimensionality:** 1024 dimensions
|
| 918 |
+
- **Similarity Function:** Cosine Similarity
|
| 919 |
+
- **Training Datasets:**
|
| 920 |
+
- full_en
|
| 921 |
+
- full_de
|
| 922 |
+
- full_es
|
| 923 |
+
- full_zh
|
| 924 |
+
- mix
|
| 925 |
+
<!-- - **Language:** Unknown -->
|
| 926 |
+
<!-- - **License:** Unknown -->
|
| 927 |
+
|
| 928 |
+
### Model Sources
|
| 929 |
+
|
| 930 |
+
- **Documentation:** [Sentence Transformers Documentation](https://sbert.net)
|
| 931 |
+
- **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers)
|
| 932 |
+
- **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers)
|
| 933 |
+
|
| 934 |
+
### Full Model Architecture
|
| 935 |
+
|
| 936 |
+
```
|
| 937 |
+
SentenceTransformer(
|
| 938 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
|
| 939 |
+
(1): Pooling({'word_embedding_dimension': 1024, 'pooling_mode_cls_token': True, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
|
| 940 |
+
(2): Normalize()
|
| 941 |
+
)
|
| 942 |
+
```
|
| 943 |
+
|
| 944 |
+
## Usage
|
| 945 |
+
|
| 946 |
+
### Direct Usage (Sentence Transformers)
|
| 947 |
+
|
| 948 |
+
First install the Sentence Transformers library:
|
| 949 |
+
|
| 950 |
+
```bash
|
| 951 |
+
pip install -U sentence-transformers
|
| 952 |
+
```
|
| 953 |
+
|
| 954 |
+
Then you can load this model and run inference.
|
| 955 |
+
```python
|
| 956 |
+
from sentence_transformers import SentenceTransformer
|
| 957 |
+
|
| 958 |
+
# Download from the 🤗 Hub
|
| 959 |
+
model = SentenceTransformer("sentence_transformers_model_id")
|
| 960 |
+
# Run inference
|
| 961 |
+
sentences = [
|
| 962 |
+
'Volksvertreter',
|
| 963 |
+
'Parlamentarier',
|
| 964 |
+
'Oberbürgermeister',
|
| 965 |
+
]
|
| 966 |
+
embeddings = model.encode(sentences)
|
| 967 |
+
print(embeddings.shape)
|
| 968 |
+
# [3, 1024]
|
| 969 |
+
|
| 970 |
+
# Get the similarity scores for the embeddings
|
| 971 |
+
similarities = model.similarity(embeddings, embeddings)
|
| 972 |
+
print(similarities.shape)
|
| 973 |
+
# [3, 3]
|
| 974 |
+
```
|
| 975 |
+
|
| 976 |
+
<!--
|
| 977 |
+
### Direct Usage (Transformers)
|
| 978 |
+
|
| 979 |
+
<details><summary>Click to see the direct usage in Transformers</summary>
|
| 980 |
+
|
| 981 |
+
</details>
|
| 982 |
+
-->
|
| 983 |
+
|
| 984 |
+
<!--
|
| 985 |
+
### Downstream Usage (Sentence Transformers)
|
| 986 |
+
|
| 987 |
+
You can finetune this model on your own dataset.
|
| 988 |
+
|
| 989 |
+
<details><summary>Click to expand</summary>
|
| 990 |
+
|
| 991 |
+
</details>
|
| 992 |
+
-->
|
| 993 |
+
|
| 994 |
+
<!--
|
| 995 |
+
### Out-of-Scope Use
|
| 996 |
+
|
| 997 |
+
*List how the model may foreseeably be misused and address what users ought not to do with the model.*
|
| 998 |
+
-->
|
| 999 |
+
|
| 1000 |
+
## Evaluation
|
| 1001 |
+
|
| 1002 |
+
### Metrics
|
| 1003 |
+
|
| 1004 |
+
#### Information Retrieval
|
| 1005 |
+
|
| 1006 |
+
* Datasets: `full_en`, `full_es`, `full_de`, `full_zh`, `mix_es`, `mix_de` and `mix_zh`
|
| 1007 |
+
* Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/sentence_transformer/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator)
|
| 1008 |
+
|
| 1009 |
+
| Metric | full_en | full_es | full_de | full_zh | mix_es | mix_de | mix_zh |
|
| 1010 |
+
|:---------------------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|:-----------|
|
| 1011 |
+
| cosine_accuracy@1 | 0.6571 | 0.1135 | 0.2956 | 0.6602 | 0.7337 | 0.6859 | 0.1815 |
|
| 1012 |
+
| cosine_accuracy@20 | 0.9905 | 1.0 | 0.9803 | 0.9903 | 0.9605 | 0.9662 | 1.0 |
|
| 1013 |
+
| cosine_accuracy@50 | 0.9905 | 1.0 | 0.9852 | 0.9903 | 0.9828 | 0.9828 | 1.0 |
|
| 1014 |
+
| cosine_accuracy@100 | 0.9905 | 1.0 | 0.9852 | 0.9903 | 0.9917 | 0.9927 | 1.0 |
|
| 1015 |
+
| cosine_accuracy@150 | 0.9905 | 1.0 | 0.9901 | 0.9903 | 0.9948 | 0.9932 | 1.0 |
|
| 1016 |
+
| cosine_accuracy@200 | 0.9905 | 1.0 | 0.9901 | 0.9903 | 0.9953 | 0.9938 | 1.0 |
|
| 1017 |
+
| cosine_precision@1 | 0.6571 | 0.1135 | 0.2956 | 0.6602 | 0.7337 | 0.6859 | 0.1815 |
|
| 1018 |
+
| cosine_precision@20 | 0.5043 | 0.5678 | 0.5392 | 0.4699 | 0.1243 | 0.1273 | 0.1544 |
|
| 1019 |
+
| cosine_precision@50 | 0.3034 | 0.3862 | 0.3802 | 0.2767 | 0.0517 | 0.0531 | 0.0618 |
|
| 1020 |
+
| cosine_precision@100 | 0.1849 | 0.2496 | 0.2477 | 0.1715 | 0.0262 | 0.027 | 0.0309 |
|
| 1021 |
+
| cosine_precision@150 | 0.1316 | 0.1884 | 0.1857 | 0.1238 | 0.0176 | 0.0181 | 0.0206 |
|
| 1022 |
+
| cosine_precision@200 | 0.1021 | 0.1498 | 0.1489 | 0.0975 | 0.0133 | 0.0136 | 0.0154 |
|
| 1023 |
+
| cosine_recall@1 | 0.0675 | 0.0035 | 0.0111 | 0.0639 | 0.2834 | 0.2577 | 0.0582 |
|
| 1024 |
+
| cosine_recall@20 | 0.5373 | 0.3784 | 0.3399 | 0.5029 | 0.9187 | 0.9242 | 1.0 |
|
| 1025 |
+
| cosine_recall@50 | 0.7067 | 0.5572 | 0.5309 | 0.6651 | 0.9536 | 0.9614 | 1.0 |
|
| 1026 |
+
| cosine_recall@100 | 0.8223 | 0.6675 | 0.643 | 0.7783 | 0.9685 | 0.9787 | 1.0 |
|
| 1027 |
+
| cosine_recall@150 | 0.8681 | 0.7305 | 0.7044 | 0.8335 | 0.9768 | 0.9834 | 1.0 |
|
| 1028 |
+
| cosine_recall@200 | 0.8939 | 0.7624 | 0.7436 | 0.8667 | 0.9806 | 0.9854 | 1.0 |
|
| 1029 |
+
| cosine_ndcg@1 | 0.6571 | 0.1135 | 0.2956 | 0.6602 | 0.7337 | 0.6859 | 0.1815 |
|
| 1030 |
+
| cosine_ndcg@20 | 0.6828 | 0.6139 | 0.5621 | 0.6468 | 0.8075 | 0.7894 | 0.5442 |
|
| 1031 |
+
| cosine_ndcg@50 | 0.6935 | 0.586 | 0.5486 | 0.6532 | 0.817 | 0.7999 | 0.5442 |
|
| 1032 |
+
| cosine_ndcg@100 | 0.7508 | 0.6122 | 0.5743 | 0.7092 | 0.8204 | 0.8038 | 0.5442 |
|
| 1033 |
+
| cosine_ndcg@150 | 0.7709 | 0.6445 | 0.606 | 0.7326 | 0.822 | 0.8047 | 0.5442 |
|
| 1034 |
+
| **cosine_ndcg@200** | **0.7811** | **0.6608** | **0.6254** | **0.7463** | **0.8226** | **0.8051** | **0.5442** |
|
| 1035 |
+
| cosine_mrr@1 | 0.6571 | 0.1135 | 0.2956 | 0.6602 | 0.7337 | 0.6859 | 0.1815 |
|
| 1036 |
+
| cosine_mrr@20 | 0.8051 | 0.5536 | 0.5139 | 0.8102 | 0.8016 | 0.7703 | 0.4016 |
|
| 1037 |
+
| cosine_mrr@50 | 0.8051 | 0.5536 | 0.514 | 0.8102 | 0.8023 | 0.7709 | 0.4016 |
|
| 1038 |
+
| cosine_mrr@100 | 0.8051 | 0.5536 | 0.514 | 0.8102 | 0.8025 | 0.771 | 0.4016 |
|
| 1039 |
+
| cosine_mrr@150 | 0.8051 | 0.5536 | 0.5141 | 0.8102 | 0.8025 | 0.771 | 0.4016 |
|
| 1040 |
+
| cosine_mrr@200 | 0.8051 | 0.5536 | 0.5141 | 0.8102 | 0.8025 | 0.771 | 0.4016 |
|
| 1041 |
+
| cosine_map@1 | 0.6571 | 0.1135 | 0.2956 | 0.6602 | 0.7337 | 0.6859 | 0.1815 |
|
| 1042 |
+
| cosine_map@20 | 0.5404 | 0.4821 | 0.4201 | 0.5008 | 0.7389 | 0.7114 | 0.3266 |
|
| 1043 |
+
| cosine_map@50 | 0.5247 | 0.4261 | 0.3752 | 0.4769 | 0.7415 | 0.7143 | 0.3266 |
|
| 1044 |
+
| cosine_map@100 | 0.5575 | 0.4286 | 0.3785 | 0.5064 | 0.742 | 0.7149 | 0.3266 |
|
| 1045 |
+
| cosine_map@150 | 0.5657 | 0.4437 | 0.3929 | 0.5153 | 0.7421 | 0.715 | 0.3266 |
|
| 1046 |
+
| cosine_map@200 | 0.5689 | 0.4506 | 0.4005 | 0.5196 | 0.7422 | 0.7151 | 0.3266 |
|
| 1047 |
+
| cosine_map@500 | 0.574 | 0.4632 | 0.4142 | 0.5246 | 0.7423 | 0.7151 | 0.3266 |
|
| 1048 |
+
|
| 1049 |
+
<!--
|
| 1050 |
+
## Bias, Risks and Limitations
|
| 1051 |
+
|
| 1052 |
+
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
|
| 1053 |
+
-->
|
| 1054 |
+
|
| 1055 |
+
<!--
|
| 1056 |
+
### Recommendations
|
| 1057 |
+
|
| 1058 |
+
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
|
| 1059 |
+
-->
|
| 1060 |
+
|
| 1061 |
+
## Training Details
|
| 1062 |
+
|
| 1063 |
+
### Training Datasets
|
| 1064 |
+
<details><summary>full_en</summary>
|
| 1065 |
+
|
| 1066 |
+
#### full_en
|
| 1067 |
+
|
| 1068 |
+
* Dataset: full_en
|
| 1069 |
+
* Size: 28,880 training samples
|
| 1070 |
+
* Columns: <code>anchor</code> and <code>positive</code>
|
| 1071 |
+
* Approximate statistics based on the first 1000 samples:
|
| 1072 |
+
| | anchor | positive |
|
| 1073 |
+
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
|
| 1074 |
+
| type | string | string |
|
| 1075 |
+
| details | <ul><li>min: 3 tokens</li><li>mean: 5.68 tokens</li><li>max: 11 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 5.76 tokens</li><li>max: 12 tokens</li></ul> |
|
| 1076 |
+
* Samples:
|
| 1077 |
+
| anchor | positive |
|
| 1078 |
+
|:-----------------------------------------|:-----------------------------------------|
|
| 1079 |
+
| <code>air commodore</code> | <code>flight lieutenant</code> |
|
| 1080 |
+
| <code>command and control officer</code> | <code>flight officer</code> |
|
| 1081 |
+
| <code>air commodore</code> | <code>command and control officer</code> |
|
| 1082 |
+
* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
|
| 1083 |
+
```json
|
| 1084 |
+
{'guide': SentenceTransformer(
|
| 1085 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
| 1086 |
+
(1): Pooling({'word_embedding_dimension': 384, '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})
|
| 1087 |
+
(2): Normalize()
|
| 1088 |
+
), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
|
| 1089 |
+
```
|
| 1090 |
+
</details>
|
| 1091 |
+
<details><summary>full_de</summary>
|
| 1092 |
+
|
| 1093 |
+
#### full_de
|
| 1094 |
+
|
| 1095 |
+
* Dataset: full_de
|
| 1096 |
+
* Size: 23,023 training samples
|
| 1097 |
+
* Columns: <code>anchor</code> and <code>positive</code>
|
| 1098 |
+
* Approximate statistics based on the first 1000 samples:
|
| 1099 |
+
| | anchor | positive |
|
| 1100 |
+
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
|
| 1101 |
+
| type | string | string |
|
| 1102 |
+
| details | <ul><li>min: 3 tokens</li><li>mean: 7.99 tokens</li><li>max: 30 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.19 tokens</li><li>max: 30 tokens</li></ul> |
|
| 1103 |
+
* Samples:
|
| 1104 |
+
| anchor | positive |
|
| 1105 |
+
|:----------------------------------|:-----------------------------------------------------|
|
| 1106 |
+
| <code>Staffelkommandantin</code> | <code>Kommodore</code> |
|
| 1107 |
+
| <code>Luftwaffenoffizierin</code> | <code>Luftwaffenoffizier/Luftwaffenoffizierin</code> |
|
| 1108 |
+
| <code>Staffelkommandantin</code> | <code>Luftwaffenoffizierin</code> |
|
| 1109 |
+
* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
|
| 1110 |
+
```json
|
| 1111 |
+
{'guide': SentenceTransformer(
|
| 1112 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
| 1113 |
+
(1): Pooling({'word_embedding_dimension': 384, '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})
|
| 1114 |
+
(2): Normalize()
|
| 1115 |
+
), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
|
| 1116 |
+
```
|
| 1117 |
+
</details>
|
| 1118 |
+
<details><summary>full_es</summary>
|
| 1119 |
+
|
| 1120 |
+
#### full_es
|
| 1121 |
+
|
| 1122 |
+
* Dataset: full_es
|
| 1123 |
+
* Size: 20,724 training samples
|
| 1124 |
+
* Columns: <code>anchor</code> and <code>positive</code>
|
| 1125 |
+
* Approximate statistics based on the first 1000 samples:
|
| 1126 |
+
| | anchor | positive |
|
| 1127 |
+
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
|
| 1128 |
+
| type | string | string |
|
| 1129 |
+
| details | <ul><li>min: 3 tokens</li><li>mean: 9.13 tokens</li><li>max: 32 tokens</li></ul> | <ul><li>min: 3 tokens</li><li>mean: 8.84 tokens</li><li>max: 32 tokens</li></ul> |
|
| 1130 |
+
* Samples:
|
| 1131 |
+
| anchor | positive |
|
| 1132 |
+
|:------------------------------------|:-------------------------------------------|
|
| 1133 |
+
| <code>jefe de escuadrón</code> | <code>instructor</code> |
|
| 1134 |
+
| <code>comandante de aeronave</code> | <code>instructor de simulador</code> |
|
| 1135 |
+
| <code>instructor</code> | <code>oficial del Ejército del Aire</code> |
|
| 1136 |
+
* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
|
| 1137 |
+
```json
|
| 1138 |
+
{'guide': SentenceTransformer(
|
| 1139 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
| 1140 |
+
(1): Pooling({'word_embedding_dimension': 384, '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})
|
| 1141 |
+
(2): Normalize()
|
| 1142 |
+
), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
|
| 1143 |
+
```
|
| 1144 |
+
</details>
|
| 1145 |
+
<details><summary>full_zh</summary>
|
| 1146 |
+
|
| 1147 |
+
#### full_zh
|
| 1148 |
+
|
| 1149 |
+
* Dataset: full_zh
|
| 1150 |
+
* Size: 30,401 training samples
|
| 1151 |
+
* Columns: <code>anchor</code> and <code>positive</code>
|
| 1152 |
+
* Approximate statistics based on the first 1000 samples:
|
| 1153 |
+
| | anchor | positive |
|
| 1154 |
+
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
|
| 1155 |
+
| type | string | string |
|
| 1156 |
+
| details | <ul><li>min: 5 tokens</li><li>mean: 7.15 tokens</li><li>max: 14 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 7.46 tokens</li><li>max: 21 tokens</li></ul> |
|
| 1157 |
+
* Samples:
|
| 1158 |
+
| anchor | positive |
|
| 1159 |
+
|:------------------|:---------------------|
|
| 1160 |
+
| <code>技术总监</code> | <code>技术和运营总监</code> |
|
| 1161 |
+
| <code>技术总监</code> | <code>技术主管</code> |
|
| 1162 |
+
| <code>技术总监</code> | <code>技术艺术总监</code> |
|
| 1163 |
+
* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
|
| 1164 |
+
```json
|
| 1165 |
+
{'guide': SentenceTransformer(
|
| 1166 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
| 1167 |
+
(1): Pooling({'word_embedding_dimension': 384, '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})
|
| 1168 |
+
(2): Normalize()
|
| 1169 |
+
), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
|
| 1170 |
+
```
|
| 1171 |
+
</details>
|
| 1172 |
+
<details><summary>mix</summary>
|
| 1173 |
+
|
| 1174 |
+
#### mix
|
| 1175 |
+
|
| 1176 |
+
* Dataset: mix
|
| 1177 |
+
* Size: 21,760 training samples
|
| 1178 |
+
* Columns: <code>anchor</code> and <code>positive</code>
|
| 1179 |
+
* Approximate statistics based on the first 1000 samples:
|
| 1180 |
+
| | anchor | positive |
|
| 1181 |
+
|:--------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|
|
| 1182 |
+
| type | string | string |
|
| 1183 |
+
| details | <ul><li>min: 2 tokens</li><li>mean: 6.71 tokens</li><li>max: 19 tokens</li></ul> | <ul><li>min: 2 tokens</li><li>mean: 7.69 tokens</li><li>max: 19 tokens</li></ul> |
|
| 1184 |
+
* Samples:
|
| 1185 |
+
| anchor | positive |
|
| 1186 |
+
|:------------------------------------------|:----------------------------------------------------------------|
|
| 1187 |
+
| <code>technical manager</code> | <code>Technischer Direktor für Bühne, Film und Fernsehen</code> |
|
| 1188 |
+
| <code>head of technical</code> | <code>directora técnica</code> |
|
| 1189 |
+
| <code>head of technical department</code> | <code>技术艺术总监</code> |
|
| 1190 |
+
* Loss: [<code>GISTEmbedLoss</code>](https://sbert.net/docs/package_reference/sentence_transformer/losses.html#gistembedloss) with these parameters:
|
| 1191 |
+
```json
|
| 1192 |
+
{'guide': SentenceTransformer(
|
| 1193 |
+
(0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel
|
| 1194 |
+
(1): Pooling({'word_embedding_dimension': 384, '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})
|
| 1195 |
+
(2): Normalize()
|
| 1196 |
+
), 'temperature': 0.01, 'margin_strategy': 'absolute', 'margin': 0.0}
|
| 1197 |
+
```
|
| 1198 |
+
</details>
|
| 1199 |
+
|
| 1200 |
+
### Training Hyperparameters
|
| 1201 |
+
#### Non-Default Hyperparameters
|
| 1202 |
+
|
| 1203 |
+
- `eval_strategy`: steps
|
| 1204 |
+
- `per_device_train_batch_size`: 64
|
| 1205 |
+
- `per_device_eval_batch_size`: 128
|
| 1206 |
+
- `gradient_accumulation_steps`: 2
|
| 1207 |
+
- `num_train_epochs`: 5
|
| 1208 |
+
- `warmup_ratio`: 0.05
|
| 1209 |
+
- `log_on_each_node`: False
|
| 1210 |
+
- `fp16`: True
|
| 1211 |
+
- `dataloader_num_workers`: 4
|
| 1212 |
+
- `ddp_find_unused_parameters`: True
|
| 1213 |
+
- `batch_sampler`: no_duplicates
|
| 1214 |
+
|
| 1215 |
+
#### All Hyperparameters
|
| 1216 |
+
<details><summary>Click to expand</summary>
|
| 1217 |
+
|
| 1218 |
+
- `overwrite_output_dir`: False
|
| 1219 |
+
- `do_predict`: False
|
| 1220 |
+
- `eval_strategy`: steps
|
| 1221 |
+
- `prediction_loss_only`: True
|
| 1222 |
+
- `per_device_train_batch_size`: 64
|
| 1223 |
+
- `per_device_eval_batch_size`: 128
|
| 1224 |
+
- `per_gpu_train_batch_size`: None
|
| 1225 |
+
- `per_gpu_eval_batch_size`: None
|
| 1226 |
+
- `gradient_accumulation_steps`: 2
|
| 1227 |
+
- `eval_accumulation_steps`: None
|
| 1228 |
+
- `torch_empty_cache_steps`: None
|
| 1229 |
+
- `learning_rate`: 5e-05
|
| 1230 |
+
- `weight_decay`: 0.0
|
| 1231 |
+
- `adam_beta1`: 0.9
|
| 1232 |
+
- `adam_beta2`: 0.999
|
| 1233 |
+
- `adam_epsilon`: 1e-08
|
| 1234 |
+
- `max_grad_norm`: 1.0
|
| 1235 |
+
- `num_train_epochs`: 5
|
| 1236 |
+
- `max_steps`: -1
|
| 1237 |
+
- `lr_scheduler_type`: linear
|
| 1238 |
+
- `lr_scheduler_kwargs`: {}
|
| 1239 |
+
- `warmup_ratio`: 0.05
|
| 1240 |
+
- `warmup_steps`: 0
|
| 1241 |
+
- `log_level`: passive
|
| 1242 |
+
- `log_level_replica`: warning
|
| 1243 |
+
- `log_on_each_node`: False
|
| 1244 |
+
- `logging_nan_inf_filter`: True
|
| 1245 |
+
- `save_safetensors`: True
|
| 1246 |
+
- `save_on_each_node`: False
|
| 1247 |
+
- `save_only_model`: False
|
| 1248 |
+
- `restore_callback_states_from_checkpoint`: False
|
| 1249 |
+
- `no_cuda`: False
|
| 1250 |
+
- `use_cpu`: False
|
| 1251 |
+
- `use_mps_device`: False
|
| 1252 |
+
- `seed`: 42
|
| 1253 |
+
- `data_seed`: None
|
| 1254 |
+
- `jit_mode_eval`: False
|
| 1255 |
+
- `use_ipex`: False
|
| 1256 |
+
- `bf16`: False
|
| 1257 |
+
- `fp16`: True
|
| 1258 |
+
- `fp16_opt_level`: O1
|
| 1259 |
+
- `half_precision_backend`: auto
|
| 1260 |
+
- `bf16_full_eval`: False
|
| 1261 |
+
- `fp16_full_eval`: False
|
| 1262 |
+
- `tf32`: None
|
| 1263 |
+
- `local_rank`: 0
|
| 1264 |
+
- `ddp_backend`: None
|
| 1265 |
+
- `tpu_num_cores`: None
|
| 1266 |
+
- `tpu_metrics_debug`: False
|
| 1267 |
+
- `debug`: []
|
| 1268 |
+
- `dataloader_drop_last`: True
|
| 1269 |
+
- `dataloader_num_workers`: 4
|
| 1270 |
+
- `dataloader_prefetch_factor`: None
|
| 1271 |
+
- `past_index`: -1
|
| 1272 |
+
- `disable_tqdm`: False
|
| 1273 |
+
- `remove_unused_columns`: True
|
| 1274 |
+
- `label_names`: None
|
| 1275 |
+
- `load_best_model_at_end`: False
|
| 1276 |
+
- `ignore_data_skip`: False
|
| 1277 |
+
- `fsdp`: []
|
| 1278 |
+
- `fsdp_min_num_params`: 0
|
| 1279 |
+
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
|
| 1280 |
+
- `tp_size`: 0
|
| 1281 |
+
- `fsdp_transformer_layer_cls_to_wrap`: None
|
| 1282 |
+
- `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
|
| 1283 |
+
- `deepspeed`: None
|
| 1284 |
+
- `label_smoothing_factor`: 0.0
|
| 1285 |
+
- `optim`: adamw_torch
|
| 1286 |
+
- `optim_args`: None
|
| 1287 |
+
- `adafactor`: False
|
| 1288 |
+
- `group_by_length`: False
|
| 1289 |
+
- `length_column_name`: length
|
| 1290 |
+
- `ddp_find_unused_parameters`: True
|
| 1291 |
+
- `ddp_bucket_cap_mb`: None
|
| 1292 |
+
- `ddp_broadcast_buffers`: False
|
| 1293 |
+
- `dataloader_pin_memory`: True
|
| 1294 |
+
- `dataloader_persistent_workers`: False
|
| 1295 |
+
- `skip_memory_metrics`: True
|
| 1296 |
+
- `use_legacy_prediction_loop`: False
|
| 1297 |
+
- `push_to_hub`: False
|
| 1298 |
+
- `resume_from_checkpoint`: None
|
| 1299 |
+
- `hub_model_id`: None
|
| 1300 |
+
- `hub_strategy`: every_save
|
| 1301 |
+
- `hub_private_repo`: None
|
| 1302 |
+
- `hub_always_push`: False
|
| 1303 |
+
- `gradient_checkpointing`: False
|
| 1304 |
+
- `gradient_checkpointing_kwargs`: None
|
| 1305 |
+
- `include_inputs_for_metrics`: False
|
| 1306 |
+
- `include_for_metrics`: []
|
| 1307 |
+
- `eval_do_concat_batches`: True
|
| 1308 |
+
- `fp16_backend`: auto
|
| 1309 |
+
- `push_to_hub_model_id`: None
|
| 1310 |
+
- `push_to_hub_organization`: None
|
| 1311 |
+
- `mp_parameters`:
|
| 1312 |
+
- `auto_find_batch_size`: False
|
| 1313 |
+
- `full_determinism`: False
|
| 1314 |
+
- `torchdynamo`: None
|
| 1315 |
+
- `ray_scope`: last
|
| 1316 |
+
- `ddp_timeout`: 1800
|
| 1317 |
+
- `torch_compile`: False
|
| 1318 |
+
- `torch_compile_backend`: None
|
| 1319 |
+
- `torch_compile_mode`: None
|
| 1320 |
+
- `include_tokens_per_second`: False
|
| 1321 |
+
- `include_num_input_tokens_seen`: False
|
| 1322 |
+
- `neftune_noise_alpha`: None
|
| 1323 |
+
- `optim_target_modules`: None
|
| 1324 |
+
- `batch_eval_metrics`: False
|
| 1325 |
+
- `eval_on_start`: False
|
| 1326 |
+
- `use_liger_kernel`: False
|
| 1327 |
+
- `eval_use_gather_object`: False
|
| 1328 |
+
- `average_tokens_across_devices`: False
|
| 1329 |
+
- `prompts`: None
|
| 1330 |
+
- `batch_sampler`: no_duplicates
|
| 1331 |
+
- `multi_dataset_batch_sampler`: proportional
|
| 1332 |
+
|
| 1333 |
+
</details>
|
| 1334 |
+
|
| 1335 |
+
### Training Logs
|
| 1336 |
+
| Epoch | Step | Training Loss | full_en_cosine_ndcg@200 | full_es_cosine_ndcg@200 | full_de_cosine_ndcg@200 | full_zh_cosine_ndcg@200 | mix_es_cosine_ndcg@200 | mix_de_cosine_ndcg@200 | mix_zh_cosine_ndcg@200 |
|
| 1337 |
+
|:------:|:----:|:-------------:|:-----------------------:|:-----------------------:|:-----------------------:|:-----------------------:|:----------------------:|:----------------------:|:----------------------:|
|
| 1338 |
+
| -1 | -1 | - | 0.6856 | 0.5207 | 0.4655 | 0.6713 | 0.6224 | 0.5604 | 0.5548 |
|
| 1339 |
+
| 0.0010 | 1 | 5.3354 | - | - | - | - | - | - | - |
|
| 1340 |
+
| 0.1027 | 100 | 2.665 | - | - | - | - | - | - | - |
|
| 1341 |
+
| 0.2053 | 200 | 1.3375 | 0.7691 | 0.6530 | 0.6298 | 0.7517 | 0.7513 | 0.7393 | 0.5490 |
|
| 1342 |
+
| 0.3080 | 300 | 1.1101 | - | - | - | - | - | - | - |
|
| 1343 |
+
| 0.4107 | 400 | 0.9453 | 0.7802 | 0.6643 | 0.6246 | 0.7531 | 0.7610 | 0.7441 | 0.5493 |
|
| 1344 |
+
| 0.5133 | 500 | 0.9202 | - | - | - | - | - | - | - |
|
| 1345 |
+
| 0.6160 | 600 | 0.7887 | 0.7741 | 0.6549 | 0.6171 | 0.7542 | 0.7672 | 0.7540 | 0.5482 |
|
| 1346 |
+
| 0.7187 | 700 | 0.7604 | - | - | - | - | - | - | - |
|
| 1347 |
+
| 0.8214 | 800 | 0.7219 | 0.7846 | 0.6674 | 0.6244 | 0.7648 | 0.7741 | 0.7592 | 0.5497 |
|
| 1348 |
+
| 0.9240 | 900 | 0.6965 | - | - | - | - | - | - | - |
|
| 1349 |
+
| 1.0267 | 1000 | 0.6253 | 0.7646 | 0.6391 | 0.6122 | 0.7503 | 0.7825 | 0.7704 | 0.5463 |
|
| 1350 |
+
| 1.1294 | 1100 | 0.4737 | - | - | - | - | - | - | - |
|
| 1351 |
+
| 1.2320 | 1200 | 0.5055 | 0.7758 | 0.6582 | 0.6178 | 0.7514 | 0.7857 | 0.7764 | 0.5501 |
|
| 1352 |
+
| 1.3347 | 1300 | 0.5042 | - | - | - | - | - | - | - |
|
| 1353 |
+
| 1.4374 | 1400 | 0.5073 | 0.7613 | 0.6578 | 0.6178 | 0.7505 | 0.7829 | 0.7762 | 0.5452 |
|
| 1354 |
+
| 1.5400 | 1500 | 0.4975 | - | - | - | - | - | - | - |
|
| 1355 |
+
| 1.6427 | 1600 | 0.5242 | 0.7736 | 0.6673 | 0.6279 | 0.7555 | 0.7940 | 0.7859 | 0.5477 |
|
| 1356 |
+
| 1.7454 | 1700 | 0.4713 | - | - | - | - | - | - | - |
|
| 1357 |
+
| 1.8480 | 1800 | 0.4814 | 0.7845 | 0.6733 | 0.6285 | 0.7642 | 0.7992 | 0.7904 | 0.5449 |
|
| 1358 |
+
| 1.9507 | 1900 | 0.4526 | - | - | - | - | - | - | - |
|
| 1359 |
+
| 2.0544 | 2000 | 0.36 | 0.7790 | 0.6639 | 0.6252 | 0.7500 | 0.8032 | 0.7888 | 0.5499 |
|
| 1360 |
+
| 2.1571 | 2100 | 0.3744 | - | - | - | - | - | - | - |
|
| 1361 |
+
| 2.2598 | 2200 | 0.3031 | 0.7787 | 0.6614 | 0.6190 | 0.7537 | 0.7993 | 0.7811 | 0.5476 |
|
| 1362 |
+
| 2.3624 | 2300 | 0.3638 | - | - | - | - | - | - | - |
|
| 1363 |
+
| 2.4651 | 2400 | 0.358 | 0.7798 | 0.6615 | 0.6258 | 0.7497 | 0.8018 | 0.7828 | 0.5481 |
|
| 1364 |
+
| 2.5678 | 2500 | 0.3247 | - | - | - | - | - | - | - |
|
| 1365 |
+
| 2.6704 | 2600 | 0.3247 | 0.7854 | 0.6663 | 0.6248 | 0.7560 | 0.8081 | 0.7835 | 0.5452 |
|
| 1366 |
+
| 2.7731 | 2700 | 0.3263 | - | - | - | - | - | - | - |
|
| 1367 |
+
| 2.8758 | 2800 | 0.3212 | 0.7761 | 0.6681 | 0.6250 | 0.7517 | 0.8121 | 0.7927 | 0.5458 |
|
| 1368 |
+
| 2.9784 | 2900 | 0.3291 | - | - | - | - | - | - | - |
|
| 1369 |
+
| 3.0821 | 3000 | 0.2816 | 0.7727 | 0.6604 | 0.6163 | 0.7370 | 0.8163 | 0.7985 | 0.5473 |
|
| 1370 |
+
| 3.1848 | 3100 | 0.2698 | - | - | - | - | - | - | - |
|
| 1371 |
+
| 3.2875 | 3200 | 0.2657 | 0.7757 | 0.6615 | 0.6247 | 0.7417 | 0.8117 | 0.8004 | 0.5436 |
|
| 1372 |
+
| 3.3901 | 3300 | 0.2724 | - | - | - | - | - | - | - |
|
| 1373 |
+
| 3.4928 | 3400 | 0.2584 | 0.7850 | 0.6583 | 0.6320 | 0.7458 | 0.8120 | 0.7980 | 0.5454 |
|
| 1374 |
+
| 3.5955 | 3500 | 0.2573 | - | - | - | - | - | - | - |
|
| 1375 |
+
| 3.6982 | 3600 | 0.2744 | 0.7796 | 0.6552 | 0.6237 | 0.7409 | 0.8193 | 0.8018 | 0.5466 |
|
| 1376 |
+
| 3.8008 | 3700 | 0.3054 | - | - | - | - | - | - | - |
|
| 1377 |
+
| 3.9035 | 3800 | 0.2727 | 0.7825 | 0.6642 | 0.6293 | 0.7504 | 0.8213 | 0.8058 | 0.5463 |
|
| 1378 |
+
| 4.0062 | 3900 | 0.2353 | - | - | - | - | - | - | - |
|
| 1379 |
+
| 4.1088 | 4000 | 0.2353 | 0.7747 | 0.6628 | 0.6263 | 0.7384 | 0.8239 | 0.8065 | 0.5447 |
|
| 1380 |
+
| 4.2115 | 4100 | 0.2385 | - | - | - | - | - | - | - |
|
| 1381 |
+
| 4.3142 | 4200 | 0.231 | 0.7811 | 0.6608 | 0.6254 | 0.7463 | 0.8226 | 0.8051 | 0.5442 |
|
| 1382 |
+
|
| 1383 |
+
|
| 1384 |
+
### Framework Versions
|
| 1385 |
+
- Python: 3.11.11
|
| 1386 |
+
- Sentence Transformers: 4.1.0
|
| 1387 |
+
- Transformers: 4.51.2
|
| 1388 |
+
- PyTorch: 2.6.0+cu124
|
| 1389 |
+
- Accelerate: 1.6.0
|
| 1390 |
+
- Datasets: 3.5.0
|
| 1391 |
+
- Tokenizers: 0.21.1
|
| 1392 |
+
|
| 1393 |
+
## Citation
|
| 1394 |
+
|
| 1395 |
+
### BibTeX
|
| 1396 |
+
|
| 1397 |
+
#### Sentence Transformers
|
| 1398 |
+
```bibtex
|
| 1399 |
+
@inproceedings{reimers-2019-sentence-bert,
|
| 1400 |
+
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
|
| 1401 |
+
author = "Reimers, Nils and Gurevych, Iryna",
|
| 1402 |
+
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
|
| 1403 |
+
month = "11",
|
| 1404 |
+
year = "2019",
|
| 1405 |
+
publisher = "Association for Computational Linguistics",
|
| 1406 |
+
url = "https://arxiv.org/abs/1908.10084",
|
| 1407 |
+
}
|
| 1408 |
+
```
|
| 1409 |
+
|
| 1410 |
+
#### GISTEmbedLoss
|
| 1411 |
+
```bibtex
|
| 1412 |
+
@misc{solatorio2024gistembed,
|
| 1413 |
+
title={GISTEmbed: Guided In-sample Selection of Training Negatives for Text Embedding Fine-tuning},
|
| 1414 |
+
author={Aivin V. Solatorio},
|
| 1415 |
+
year={2024},
|
| 1416 |
+
eprint={2402.16829},
|
| 1417 |
+
archivePrefix={arXiv},
|
| 1418 |
+
primaryClass={cs.LG}
|
| 1419 |
+
}
|
| 1420 |
+
```
|
| 1421 |
+
|
| 1422 |
+
<!--
|
| 1423 |
+
## Glossary
|
| 1424 |
+
|
| 1425 |
+
*Clearly define terms in order to be accessible across audiences.*
|
| 1426 |
+
-->
|
| 1427 |
+
|
| 1428 |
+
<!--
|
| 1429 |
+
## Model Card Authors
|
| 1430 |
+
|
| 1431 |
+
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
|
| 1432 |
+
-->
|
| 1433 |
+
|
| 1434 |
+
<!--
|
| 1435 |
+
## Model Card Contact
|
| 1436 |
+
|
| 1437 |
+
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
|
| 1438 |
+
-->
|
checkpoint-4200/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b78a4739eadca247b8b2e2c00baf6260120f87a52a561be923312b94cba8232a
|
| 3 |
+
size 2271064456
|
checkpoint-4200/modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.models.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
checkpoint-4200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5999173a8d03d315a6eeef8cf9fb69d1d387f37263ccc42a43a215f5e76d8f22
|
| 3 |
+
size 4533972937
|
checkpoint-4200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58d907753d591cf08f2e02a54be246122575c6702ce42ce38fd9f774562be3d4
|
| 3 |
+
size 15958
|
checkpoint-4200/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b186621336b0abea983113004ecd9b3118c0bc11e75a3da16b0bb6e48f4f1d5
|
| 3 |
+
size 988
|
checkpoint-4200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36387b84c88d119079837fce0adc18fc34124598fb149b8eb92af5bb4134e761
|
| 3 |
+
size 1064
|
checkpoint-4200/sentence_bert_config.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"max_seq_length": 512,
|
| 3 |
+
"do_lower_case": false
|
| 4 |
+
}
|
checkpoint-4200/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
checkpoint-4200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a948c4f5667f6700da28d0d70c0c6f024b018ee933ba85d5cc9de9d626dadca
|
| 3 |
+
size 5624
|
checkpoint-4400/config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"XLMRobertaModel"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4096,
|
| 14 |
+
"layer_norm_eps": 1e-05,
|
| 15 |
+
"max_position_embeddings": 8194,
|
| 16 |
+
"model_type": "xlm-roberta",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 24,
|
| 19 |
+
"output_past": true,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.51.2",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 250002
|
| 27 |
+
}
|
checkpoint-4400/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b1f51d5c393dbe3441f3e6303002dfa4d493abbc24118e5f4d0a03ee025a9bd
|
| 3 |
+
size 2271064456
|
checkpoint-4400/modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.models.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
checkpoint-4400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a9e6288ee5586d0ffcde2044dc04da2224eade48e12128ba7e97e6946e6e525
|
| 3 |
+
size 4533972937
|
checkpoint-4400/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba81f3b1771a8b460f12027c4271da4d35cf373c809e35a113805049901d939b
|
| 3 |
+
size 988
|
checkpoint-4400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0828827d515ca1d2148a70c185e3b6c96109604210f6fb69f993d1e2b7882ffb
|
| 3 |
+
size 1064
|
checkpoint-4400/trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-4400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a948c4f5667f6700da28d0d70c0c6f024b018ee933ba85d5cc9de9d626dadca
|
| 3 |
+
size 5624
|
checkpoint-4600/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f1c9c9e2b9e3d67f10744473f5e1d1d314b24f390c90d03e669760e0af5c9c4
|
| 3 |
+
size 2271064456
|
checkpoint-4600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05e104089212061a9d12b0d2f8e82d52a0e257172d6f6a345d45abaebaf0d3bb
|
| 3 |
+
size 4533972937
|
checkpoint-4600/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
checkpoint-4600/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-4800/1_Pooling/config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"word_embedding_dimension": 1024,
|
| 3 |
+
"pooling_mode_cls_token": true,
|
| 4 |
+
"pooling_mode_mean_tokens": false,
|
| 5 |
+
"pooling_mode_max_tokens": false,
|
| 6 |
+
"pooling_mode_mean_sqrt_len_tokens": false,
|
| 7 |
+
"pooling_mode_weightedmean_tokens": false,
|
| 8 |
+
"pooling_mode_lasttoken": false,
|
| 9 |
+
"include_prompt": true
|
| 10 |
+
}
|
checkpoint-4800/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d2ac2c0c92b9ef57cc468b9281831355dd814fe1281d4477c4f70a583159129
|
| 3 |
+
size 2271064456
|
checkpoint-4800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:881841f70dc9d4f24a46057ced1d2e32ca60e5ff2f9355c3d66879ea2de63e56
|
| 3 |
+
size 4533972937
|
checkpoint-4800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0483b24401bb5c934be17d3fb87b418062454f4034967bcd424997391ddc532
|
| 3 |
+
size 15958
|
checkpoint-4800/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdf548d9246c1d9e15e20b2ddca08d24f314024d3fae6a40e3553c10631d480a
|
| 3 |
+
size 988
|
checkpoint-4800/sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
| 3 |
+
size 5069051
|
checkpoint-4800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a948c4f5667f6700da28d0d70c0c6f024b018ee933ba85d5cc9de9d626dadca
|
| 3 |
+
size 5624
|