Hugging Face's logo

xpmir
/
monobert

TensorBoard
xpmir
Model card Files Metrics Community
bpiwowar commited on
Commit
cbd5880
•
1 Parent(s): 3f02745

Add model

Browse files
Files changed (8) hide show
  1. README.md +16 -9
  2. checkpoint/info.json +1 -1
  3. checkpoint/model.pth +1 -1
  4. definition.json +1 -1
  5. runs/monobert-RR@10/1676719327.6789632/events.out.tfevents.1676719327.kavinsky.884863.1 +3 -0
  6. runs/monobert-RR@10/events.out.tfevents.1676447619.zeppelin.224877.0 +3 -0
  7. runs/monobert-RR@10/events.out.tfevents.1676473806.zz.275414.0 +3 -0
  8. runs/monobert-RR@10/events.out.tfevents.1676717394.kavinsky.884863.0 +3 -0
README.md CHANGED
@@ -2,14 +2,20 @@
2
  library_name: xpmir
3
  ---
4
  # monoBERT trained on MS-Marco
5
-
6
  Passage Re-ranking with BERT (Rodrigo Nogueira, Kyunghyun Cho). 2019.
7
  https://arxiv.org/abs/1901.04085
8
 
9
- ## Using the model)
10
- The model can be loaded with [experimaestro IR](https://experimaestro-ir.readthedocs.io/en/latest/)
 
 
11
 
12
- ```py
 
 
 
 
 
13
  from xpmir.models import AutoModel
14
 
15
  # Model that can be re-used in experiments
@@ -17,13 +23,14 @@ model = AutoModel.load_from_hf_hub("xpmir/monobert")
17
 
18
  # Use this if you want to actually use the model
19
  model = AutoModel.load_from_hf_hub("xpmir/monobert", as_instance=True)
20
- model.initialize(None)
21
- model.rsv("walgreens store sales average", "The average Walgreens salary ranges from approximately $15,000 per year for Customer Service Associate / Cashier to $179,900 per year for District Manager...")
22
  ```
23
 
24
  ## Results
 
25
  | Dataset | AP | P@20 | RR | RR@10 | nDCG | nDCG@10 | nDCG@20 |
26
  |----| ---|------|------|------|------|------|------|
27
- | msmarco_dev | 0.3574 | 0.0371 | 0.3624 | 0.3529 | 0.4640 | 0.4147 | 0.4370 |
28
- | trec2019 | 0.4908 | 0.7233 | 0.9368 | 0.9368 | 0.6871 | 0.7046 | 0.6813 |
29
- | trec2020 | 0.4803 | 0.6120 | 0.9380 | 0.9367 | 0.6865 | 0.6963 | 0.6626 |
 
2
  library_name: xpmir
3
  ---
4
  # monoBERT trained on MS-Marco
 
5
  Passage Re-ranking with BERT (Rodrigo Nogueira, Kyunghyun Cho). 2019.
6
  https://arxiv.org/abs/1901.04085
7
 
8
+ This model has been trained on MsMarco v1
9
+
10
+
11
+
12
 
13
+
14
+ ## Using the model
15
+ The model can be loaded with [experimaestro
16
+ IR](https://experimaestro-ir.readthedocs.io/en/latest/)
17
+
18
+ ```py from xpmir.models import AutoModel
19
  from xpmir.models import AutoModel
20
 
21
  # Model that can be re-used in experiments
 
23
 
24
  # Use this if you want to actually use the model
25
  model = AutoModel.load_from_hf_hub("xpmir/monobert", as_instance=True)
26
+ model.initialize()
27
+ model.rsv("walgreens store sales average", "The average Walgreens salary ranges...")
28
  ```
29
 
30
  ## Results
31
+
32
  | Dataset | AP | P@20 | RR | RR@10 | nDCG | nDCG@10 | nDCG@20 |
33
  |----| ---|------|------|------|------|------|------|
34
+ | msmarco_dev | 0.3680 | 0.0374 | 0.3729 | 0.3639 | 0.4727 | 0.4258 | 0.4469 |
35
+ | trec2019 | 0.4902 | 0.7267 | 0.9523 | 0.9523 | 0.6900 | 0.7159 | 0.6854 |
36
+ | trec2020 | 0.4790 | 0.6213 | 0.9095 | 0.9095 | 0.6844 | 0.6977 | 0.6652 |
checkpoint/info.json CHANGED
@@ -1 +1 @@
1
- {"epoch": 1504, "steps": 48128}
 
1
+ {"epoch": 1632, "steps": 52224}
checkpoint/model.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8803c9e357bceca55b6ff67cc08c2b0cf6081c1065c2a4804a1f1fd2af792d3
3
  size 438008465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b3abada471d7a83659029daeb4425ee2d4dd6bbb776d5980bfcd61fb097fb8c
3
  size 438008465
definition.json CHANGED
@@ -1 +1 @@
1
- [{"id": 139888093837680, "module": "xpmir.text.huggingface", "type": "DualTransformerEncoder", "identifier": "945cb146c597c06064946f11253b127a1152c137ca7155d220107043d7fb55ae", "typename": "xpmir.text.huggingface.DualTransformerEncoder", "ignored": [], "fields": {"model_id": "bert-base-uncased", "trainable": true, "layer": 0, "dropout": 0.1, "maxlen": 512, "version": 2}}, {"id": 139888093971504, "module": "xpmir.neural.cross", "type": "CrossScorer", "identifier": "09134f4b01bc9472d5573db7abaa489b0f6d71dd3dec2826771f88c300870bc7", "fields": {"checkpoint": {"type": "path.serialized", "value": "checkpoint", "is_folder": true}, "encoder": {"type": "python", "value": 139888093837680}}}]
 
1
+ [{"id": 140640700732448, "module": "xpmir.text.huggingface", "type": "DualTransformerEncoder", "typename": "xpmir.text.huggingface.DualTransformerEncoder", "identifier": "945cb146c597c06064946f11253b127a1152c137ca7155d220107043d7fb55ae", "fields": {"model_id": "bert-base-uncased", "trainable": true, "layer": 0, "dropout": 0.1, "maxlen": 512, "version": 2}}, {"id": 140640700853808, "module": "xpmir.neural.cross", "type": "CrossScorer", "typename": "xpmir.neural.cross.CrossScorer", "identifier": "7b7464773372bc9c8de9a7f19e53b17150c3603518bbc5bc2512ff5223f0d0f3", "fields": {"checkpoint": {"type": "path.serialized", "value": "checkpoint", "is_folder": true}, "encoder": {"type": "python", "value": 140640700732448}}}]
runs/monobert-RR@10/1676719327.6789632/events.out.tfevents.1676719327.kavinsky.884863.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81d43075210ebb2e3199c72a6581a55b951e9217a21b46a194ccc28b1c46062d
3
+ size 560
runs/monobert-RR@10/events.out.tfevents.1676447619.zeppelin.224877.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06c8440154b023601aa1aac4fe3c7851b30f07804f337fe6e1444ecabf1a1163
3
+ size 24702
runs/monobert-RR@10/events.out.tfevents.1676473806.zz.275414.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37bbe6c1f002d61bfa144cb8a80cd51108f54445a0f32baecc8d7cb6276f4e19
3
+ size 2247249
runs/monobert-RR@10/events.out.tfevents.1676717394.kavinsky.884863.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8d700a015a3dedfbc4219d4082114e8755eb9cce9230d53ac6fbd5f0ae25530
3
+ size 17224