Muennighoff commited on
Commit
1aa40e0
1 Parent(s): f9ee75d

Add SGPT-125M-weightedmean-nli-bitfit

Browse files
1_Pooling/config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 768,
3
+ "pooling_mode_cls_token": false,
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": true,
8
+ "pooling_mode_lasttoken": false
9
+ }
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ pipeline_tag: sentence-similarity
3
+ tags:
4
+ - sentence-transformers
5
+ - feature-extraction
6
+ - sentence-similarity
7
+ ---
8
+
9
+ # {MODEL_NAME}
10
+
11
+ This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
12
+
13
+ <!--- Describe your model here -->
14
+
15
+ ## Usage (Sentence-Transformers)
16
+
17
+ Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
18
+
19
+ ```
20
+ pip install -U sentence-transformers
21
+ ```
22
+
23
+ Then you can use the model like this:
24
+
25
+ ```python
26
+ from sentence_transformers import SentenceTransformer
27
+ sentences = ["This is an example sentence", "Each sentence is converted"]
28
+
29
+ model = SentenceTransformer('{MODEL_NAME}')
30
+ embeddings = model.encode(sentences)
31
+ print(embeddings)
32
+ ```
33
+
34
+
35
+
36
+ ## Evaluation Results
37
+
38
+ <!--- Describe how your model was evaluated -->
39
+
40
+ For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
41
+
42
+
43
+ ## Training
44
+ The model was trained with the parameters:
45
+
46
+ **DataLoader**:
47
+
48
+ `sentence_transformers.datasets.NoDuplicatesDataLoader.NoDuplicatesDataLoader` of length 8807 with parameters:
49
+ ```
50
+ {'batch_size': 64}
51
+ ```
52
+
53
+ **Loss**:
54
+
55
+ `sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
56
+ ```
57
+ {'scale': 20.0, 'similarity_fct': 'cos_sim'}
58
+ ```
59
+
60
+ Parameters of the fit()-Method:
61
+ ```
62
+ {
63
+ "epochs": 1,
64
+ "evaluation_steps": 880,
65
+ "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
66
+ "max_grad_norm": 1,
67
+ "optimizer_class": "<class 'transformers.optimization.AdamW'>",
68
+ "optimizer_params": {
69
+ "lr": 0.0002
70
+ },
71
+ "scheduler": "WarmupLinear",
72
+ "steps_per_epoch": null,
73
+ "warmup_steps": 881,
74
+ "weight_decay": 0.01
75
+ }
76
+ ```
77
+
78
+
79
+ ## Full Model Architecture
80
+ ```
81
+ SentenceTransformer(
82
+ (0): Transformer({'max_seq_length': 75, 'do_lower_case': False}) with Transformer model: GPTNeoModel
83
+ (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': False, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': True, 'pooling_mode_lasttoken': False})
84
+ )
85
+ ```
86
+
87
+ ## Citing & Authors
88
+
89
+ <!--- Describe where people can find more information -->
config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125M",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoModel"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local"
21
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "embed_dropout": 0,
33
+ "eos_token_id": 50256,
34
+ "gradient_checkpointing": false,
35
+ "hidden_size": 768,
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": null,
38
+ "layer_norm_epsilon": 1e-05,
39
+ "max_position_embeddings": 2048,
40
+ "model_type": "gpt_neo",
41
+ "num_heads": 12,
42
+ "num_layers": 12,
43
+ "resid_dropout": 0,
44
+ "summary_activation": null,
45
+ "summary_first_dropout": 0.1,
46
+ "summary_proj_to_labels": true,
47
+ "summary_type": "cls_index",
48
+ "summary_use_proj": true,
49
+ "torch_dtype": "float32",
50
+ "transformers_version": "4.11.3",
51
+ "use_cache": true,
52
+ "vocab_size": 50257,
53
+ "window_size": 256
54
+ }
config_sentence_transformers.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "2.1.0",
4
+ "transformers": "4.11.3",
5
+ "pytorch": "1.10.1"
6
+ }
7
+ }
eval/similarity_evaluation_sts-dev_results.csv ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ 0,880,0.7935805282586036,0.7992427775446187,0.803537861534632,0.805916670050699,0.805059340821483,0.8079543102469319,0.6671307830640825,0.6684621819534556
3
+ 0,1760,0.8046134808527559,0.8107786182458391,0.8086978734087285,0.8133365523954383,0.8090922671870324,0.8144547595728191,0.6753306754656581,0.6808083808651583
4
+ 0,2640,0.8071663314127037,0.814101216624209,0.8070289697030395,0.8121768843353525,0.8069207377987253,0.8129757176268495,0.6794178834861627,0.6878660529955196
5
+ 0,3520,0.815074415149867,0.8226330577629257,0.8100869524627125,0.8155058670597654,0.810491028785713,0.8166172379334959,0.7016014482641055,0.7055738178848763
6
+ 0,4400,0.8147366711368156,0.8244445796341602,0.8080515436814306,0.8153259149782831,0.807123798800099,0.8151436710802727,0.6977204710997762,0.7019641516927396
7
+ 0,5280,0.8137146578951234,0.8226451565257343,0.8093530231641606,0.8155311606715266,0.8092546418309003,0.8160381129786755,0.6874541592576677,0.6931991492026367
8
+ 0,6160,0.8160884516024993,0.824155111462865,0.81170105484191,0.8176421959362039,0.8116381208741832,0.8181962158914927,0.6984492699937228,0.7040686762767671
9
+ 0,7040,0.8194018402494823,0.8280521639743265,0.812544208196494,0.8189724637581505,0.8121692146892865,0.819528465921213,0.7030693863780917,0.70671445924144
10
+ 0,7920,0.8197662235433774,0.8293509565331046,0.8123052189469571,0.8187709938682243,0.8120084697933245,0.8192156265758594,0.7056315547726144,0.7099616198453297
11
+ 0,8800,0.8188362771601745,0.8278769076256222,0.8109933605125172,0.8175468576291465,0.8109463949245583,0.8181462763552495,0.7053496453872838,0.7089846796693534
12
+ 0,-1,0.8188327003033481,0.8278647579972452,0.8109904965514476,0.817513756345787,0.8109425681431794,0.8181396678097637,0.7053520156758009,0.708948745480854
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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
+ ]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a06911ddb4992164ecb57d498b75fa7bdad099b591ca0b2d0f554a43ddbba5d
3
+ size 551190545
sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 75,
3
+ "do_lower_case": false
4
+ }
similarity_evaluation_sts-test_results.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
2
+ -1,-1,0.7846537302609198,0.7857648092636241,0.7732666799261162,0.7690356065641517,0.7726690278606694,0.7693750768516694,0.5922788515539513,0.5743748488122472
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "EleutherAI/gpt-neo-125M", "tokenizer_class": "GPT2Tokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff