Training in progress, step 1000
Browse files- .amlignore +6 -0
- .amlignore.amltmp +6 -0
- .gitattributes +1 -0
- 1_Pooling/config.json +7 -0
- README.md +56 -0
- config.json +28 -0
- config_sentence_transformers.json +7 -0
- model.safetensors +3 -0
- modules.json +20 -0
- runs/Nov19_15-51-33_ordalie-a100-x2QQKCLS/events.out.tfevents.1700409156.ordalie-a100-x2QQKCLS.6282.0 +3 -0
- runs/Nov19_15-53-37_ordalie-a100-x2QQKCLS/events.out.tfevents.1700409230.ordalie-a100-x2QQKCLS.6617.0 +3 -0
- runs/Nov19_15-55-21_ordalie-a100-x2QQKCLS/events.out.tfevents.1700409334.ordalie-a100-x2QQKCLS.6909.0 +3 -0
- runs/Nov19_16-01-11_ordalie-a100-x2QQKCLS/events.out.tfevents.1700409684.ordalie-a100-x2QQKCLS.7470.0 +3 -0
- runs/Nov19_16-16-27_ordalie-a100-x2QQKCLS/events.out.tfevents.1700410600.ordalie-a100-x2QQKCLS.8410.0 +3 -0
- runs/Nov19_18-50-59_ordalie-a100-x2QQKCLS/events.out.tfevents.1700419924.ordalie-a100-x2QQKCLS.6448.0 +3 -0
- runs/Nov19_18-54-21_ordalie-a100-x2QQKCLS/events.out.tfevents.1700420074.ordalie-a100-x2QQKCLS.6796.0 +3 -0
- runs/Nov19_19-05-01_ordalie-a100-x2QQKCLS/events.out.tfevents.1700420715.ordalie-a100-x2QQKCLS.7495.0 +3 -0
- runs/Nov20_08-13-45_ordalie-a100-x2QQKCLS/events.out.tfevents.1700468087.ordalie-a100-x2QQKCLS.11663.0 +3 -0
- runs/Nov20_08-16-49_ordalie-a100-x2QQKCLS/events.out.tfevents.1700468223.ordalie-a100-x2QQKCLS.13490.0 +3 -0
- runs/Nov20_08-22-20_ordalie-a100-x2QQKCLS/events.out.tfevents.1700468552.ordalie-a100-x2QQKCLS.16802.0 +3 -0
- runs/Nov20_08-33-58_ordalie-a100-x2QQKCLS/events.out.tfevents.1700469251.ordalie-a100-x2QQKCLS.20933.0 +3 -0
- runs/Nov20_09-55-05_ordalie-a100-x2QQKCLS/events.out.tfevents.1700474169.ordalie-a100-x2QQKCLS.6023.0 +3 -0
- runs/Nov21_15-37-19_ordalie-a100-x2QQKCLS/events.out.tfevents.1700581083.ordalie-a100-x2QQKCLS.133583.0 +3 -0
- runs/Nov21_15-49-53_ordalie-a100-x2QQKCLS/events.out.tfevents.1700581807.ordalie-a100-x2QQKCLS.134417.0 +3 -0
- sentence_bert_config.json +4 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +3 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
.amlignore
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## This file was auto generated by the Azure Machine Learning Studio. Please do not remove.
|
2 |
+
## Read more about the .amlignore file here: https://docs.microsoft.com/azure/machine-learning/how-to-save-write-experiment-files#storage-limits-of-experiment-snapshots
|
3 |
+
|
4 |
+
.ipynb_aml_checkpoints/
|
5 |
+
*.amltmp
|
6 |
+
*.amltemp
|
.amlignore.amltmp
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
## This file was auto generated by the Azure Machine Learning Studio. Please do not remove.
|
2 |
+
## Read more about the .amlignore file here: https://docs.microsoft.com/azure/machine-learning/how-to-save-write-experiment-files#storage-limits-of-experiment-snapshots
|
3 |
+
|
4 |
+
.ipynb_aml_checkpoints/
|
5 |
+
*.amltmp
|
6 |
+
*.amltemp
|
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
1_Pooling/config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"word_embedding_dimension": 768,
|
3 |
+
"pooling_mode_cls_token": false,
|
4 |
+
"pooling_mode_mean_tokens": true,
|
5 |
+
"pooling_mode_max_tokens": false,
|
6 |
+
"pooling_mode_mean_sqrt_len_tokens": false
|
7 |
+
}
|
README.md
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
pipeline_tag: sentence-similarity
|
3 |
+
tags:
|
4 |
+
- sentence-transformers
|
5 |
+
- feature-extraction
|
6 |
+
- sentence-similarity
|
7 |
+
|
8 |
+
---
|
9 |
+
|
10 |
+
# {MODEL_NAME}
|
11 |
+
|
12 |
+
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.
|
13 |
+
|
14 |
+
<!--- Describe your model here -->
|
15 |
+
|
16 |
+
## Usage (Sentence-Transformers)
|
17 |
+
|
18 |
+
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
19 |
+
|
20 |
+
```
|
21 |
+
pip install -U sentence-transformers
|
22 |
+
```
|
23 |
+
|
24 |
+
Then you can use the model like this:
|
25 |
+
|
26 |
+
```python
|
27 |
+
from sentence_transformers import SentenceTransformer
|
28 |
+
sentences = ["This is an example sentence", "Each sentence is converted"]
|
29 |
+
|
30 |
+
model = SentenceTransformer('{MODEL_NAME}')
|
31 |
+
embeddings = model.encode(sentences)
|
32 |
+
print(embeddings)
|
33 |
+
```
|
34 |
+
|
35 |
+
|
36 |
+
|
37 |
+
## Evaluation Results
|
38 |
+
|
39 |
+
<!--- Describe how your model was evaluated -->
|
40 |
+
|
41 |
+
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
|
42 |
+
|
43 |
+
|
44 |
+
|
45 |
+
## Full Model Architecture
|
46 |
+
```
|
47 |
+
SentenceTransformer(
|
48 |
+
(0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: XLMRobertaModel
|
49 |
+
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
|
50 |
+
(2): Normalize()
|
51 |
+
)
|
52 |
+
```
|
53 |
+
|
54 |
+
## Citing & Authors
|
55 |
+
|
56 |
+
<!--- Describe where people can find more information -->
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "solon-base/checkpoint-1000",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.35.0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
28 |
+
}
|
config_sentence_transformers.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"__version__": {
|
3 |
+
"sentence_transformers": "2.2.2",
|
4 |
+
"transformers": "4.35.0",
|
5 |
+
"pytorch": "2.1.0+cu121"
|
6 |
+
}
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:168527d14b7be5c64ad726be2414abd1cb1ef7ce4a9a8ff52453d8559a5ac8a3
|
3 |
+
size 1112197096
|
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 |
+
]
|
runs/Nov19_15-51-33_ordalie-a100-x2QQKCLS/events.out.tfevents.1700409156.ordalie-a100-x2QQKCLS.6282.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:719dd3fa917b916c05e458ea6c0712e43eeddd31aa7ee514225b510e3115a7ed
|
3 |
+
size 3937
|
runs/Nov19_15-53-37_ordalie-a100-x2QQKCLS/events.out.tfevents.1700409230.ordalie-a100-x2QQKCLS.6617.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38b086c0162a3f5464b7c1f214585a819a2bf7181aa344e7fc8805e7f849b9d5
|
3 |
+
size 4091
|
runs/Nov19_15-55-21_ordalie-a100-x2QQKCLS/events.out.tfevents.1700409334.ordalie-a100-x2QQKCLS.6909.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e15ed90b637abb7737fcd8b252a116bfe797c5ead9d42deca9d45187ef812d38
|
3 |
+
size 7047
|
runs/Nov19_16-01-11_ordalie-a100-x2QQKCLS/events.out.tfevents.1700409684.ordalie-a100-x2QQKCLS.7470.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:39b925abf7a7476d2724f9a4f591e3a13030e593002bb817d06957549a030c49
|
3 |
+
size 13013
|
runs/Nov19_16-16-27_ordalie-a100-x2QQKCLS/events.out.tfevents.1700410600.ordalie-a100-x2QQKCLS.8410.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:207a711d446464269448b4bd4e722cf16642fce86f9f1452a5dd3f29a180b47e
|
3 |
+
size 47279
|
runs/Nov19_18-50-59_ordalie-a100-x2QQKCLS/events.out.tfevents.1700419924.ordalie-a100-x2QQKCLS.6448.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89c34979058ac045b7312a1919e31822b4559d0daf07019fa90c9055dc32cc9c
|
3 |
+
size 5645
|
runs/Nov19_18-54-21_ordalie-a100-x2QQKCLS/events.out.tfevents.1700420074.ordalie-a100-x2QQKCLS.6796.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b86375fa514fb7e734da8caa5ac3712c30bdbfd3a19a48c49eecd18ceb2c3e6
|
3 |
+
size 13495
|
runs/Nov19_19-05-01_ordalie-a100-x2QQKCLS/events.out.tfevents.1700420715.ordalie-a100-x2QQKCLS.7495.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:debb129c6ae54dbf09cbff8c9fc10255ebdcc5abc2b87145b4e118596febf883
|
3 |
+
size 73980
|
runs/Nov20_08-13-45_ordalie-a100-x2QQKCLS/events.out.tfevents.1700468087.ordalie-a100-x2QQKCLS.11663.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f65d0193bb0ddec516e6e198473ae965e74a750bd0f6c60d93c601f3c48c346a
|
3 |
+
size 5026
|
runs/Nov20_08-16-49_ordalie-a100-x2QQKCLS/events.out.tfevents.1700468223.ordalie-a100-x2QQKCLS.13490.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:737466a3aaf00a63163feb2e3aa4df58f3ae44443ce8fb2d93f2a746951f9afb
|
3 |
+
size 6901
|
runs/Nov20_08-22-20_ordalie-a100-x2QQKCLS/events.out.tfevents.1700468552.ordalie-a100-x2QQKCLS.16802.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c0993f2cfbcf16b50eb93597027261ad058a8baf7ebfec06dd680f6ce6ac54e
|
3 |
+
size 15850
|
runs/Nov20_08-33-58_ordalie-a100-x2QQKCLS/events.out.tfevents.1700469251.ordalie-a100-x2QQKCLS.20933.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b250f74be2cc675ae479f1209604e7d9e5469375902ae4d9c110d5dea2fe7b2f
|
3 |
+
size 66130
|
runs/Nov20_09-55-05_ordalie-a100-x2QQKCLS/events.out.tfevents.1700474169.ordalie-a100-x2QQKCLS.6023.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f1c13540ed818031a558944d8db8cc042c6d1139adf42411e758cdb83e8ea033
|
3 |
+
size 97961
|
runs/Nov21_15-37-19_ordalie-a100-x2QQKCLS/events.out.tfevents.1700581083.ordalie-a100-x2QQKCLS.133583.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be056fa76b265709ddb51c78fc9167e199d6d67399810046deba6fd8f8f8b4fe
|
3 |
+
size 13017
|
runs/Nov21_15-49-53_ordalie-a100-x2QQKCLS/events.out.tfevents.1700581807.ordalie-a100-x2QQKCLS.134417.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44aa63d990ad3eafe6e5e26ca1dc9db50096dc0a85b7cb3c16a6066aa9689502
|
3 |
+
size 19611
|
sentence_bert_config.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"max_seq_length": 512,
|
3 |
+
"do_lower_case": false
|
4 |
+
}
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
|
3 |
+
size 5069051
|
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 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b3f6fc9286922cf30646a1957c81e5655f977d2204c9631b7624f21d6c641b5
|
3 |
+
size 17082757
|
tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"mask_token": "<mask>",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "<pad>",
|
51 |
+
"sep_token": "</s>",
|
52 |
+
"sp_model_kwargs": {},
|
53 |
+
"tokenizer_class": "XLMRobertaTokenizer",
|
54 |
+
"unk_token": "<unk>"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1df1f26f7b0bf77a75ba72113814735a956aa99e758a5176622dc0b8a40fdcf
|
3 |
+
size 6200
|