Upload model

README.md

@@ -16,40 +16,32 @@ metrics:
 - recall
 - f1
 widget:
-- text: 'The entourage was the largest ever to accompany an ROC president abroad,
-    and included: Chuang Ming - yao -LRB- secretary - general, National Security Council
-    -RRB-, Tien Hung - mao -LRB- minister of foreign affairs -RRB-, Lin Hsin - yi
-    -LRB- minister of economic affairs -RRB-, Chen Po - chih -LRB- chairman, Council
-    of Economic Planning and Development -RRB-, Chen Hsi - huang -LRB- chairman, Council
-    of Agriculture -RRB-, Chung Chin -LRB- head of the Government Information Office
-    -RRB-, Jeffrey Koo -LRB- chairman of the National Association of Industry and
-    Commerce -RRB-, Wang Yu - tseng -LRB- chairman of the General Chamber of Commerce
-    of the ROC -RRB-, and Lin Kun - chung -LRB- chairman of the Chinese National Federation
-    of Industries -RRB-.'
-- text: During the period, IPC monopolized oil exploration inside the Red Line; excluding
-    Saudi Arabia and Bahrain, where ARAMCO (formed in 1944 by renaming of the Saudi
-    subsidiary of Standard Oil of California (Socal)) and Bahrain Petroleum Company
-    (BAPCO) respectively held controlling position.
-- text: In the early decades of the 20th century, Benoytosh Bhattacharya – an expert
-    on Tantra and the then director of the Oriental Institute of Baroda – studied
-    various texts such as the Buddhist "Sadhanamala "(1156CE), the Hindu "Chhinnamastakalpa
-    "(uncertain date), and the "Tantrasara "by Krishnananda Agamavagisha (late 16th
-    century).
-- text: A united opposition of fourteen political parties organized into the National
-    Opposition Union (Unión Nacional Oppositora, UNO) with the support of the United
-    States National Endowment for Democracy.
-- text: Lockheed said the U.S. Navy may also buy an additional 340 trainer aircraft
-    to replace its T34C trainers made by the Beech Aircraft Corp. unit of Raytheon
-    Corp.
+- text: In 2005, Shankel signed with Warner Chappell Music and while pursuing his
+    own projects created another joint venture, Shankel Songs and signed Ben Glover,
+    "Billboard "'s Christian writer of the Year, 2010, Joy Williams of The Civil Wars,
+    and, whom he also produced.
+- text: In 2002, Rodríguez moved to Mississippi and to the NASA Stennis Space Center
+    as the Director of Center Operations and as a member of the Senior Executive Service
+    where he managed facility construction, security and other programs for 4,500
+    Stennis personnel.
+- text: American Motors included Chinese officials as part of the negotiations establishing
+    Beijing Jeep (now Beijing Benz).
+- text: La Señora () is a popular Spanish television period drama series set in the
+    1920s, produced by Diagonal TV for Televisión Española that was broadcast on La
+    1 of Televisión Española from 2008 to 2010.
+- text: 'Not only did the Hungarian Ministry of Foreign Affairs approve Radio Free
+    Europe''s new location, but the Ministry of Telecommunications did something even
+    more amazing: "They found us four phone lines in central Budapest," says Geza
+    Szocs, a Radio Free Europe correspondent who helped organize the Budapest location.'
 pipeline_tag: token-classification
 co2_eq_emissions:
-  emissions: 67.50149039261815
+  emissions: 67.93561835707102
   source: codecarbon
   training_type: fine-tuning
   on_cloud: false
   cpu_model: 13th Gen Intel(R) Core(TM) i7-13700K
   ram_total_size: 31.777088165283203
-  hours_used: 0.629
+  hours_used: 0.52
   hardware_used: 1 x NVIDIA GeForce RTX 3090
 base_model: prajjwal1/bert-small
 model-index:
@@ -65,13 +57,13 @@ model-index:
       split: test
     metrics:
     - type: f1
-      value: 0.7438057260629957
+      value: 0.7547025470254703
       name: F1
     - type: precision
-      value: 0.7474561008554705
+      value: 0.7617641715116279
       name: Precision
     - type: recall
-      value: 0.7401908328874621
+      value: 0.7477706438380596
       name: Recall
 ---
 
@@ -105,8 +97,8 @@ This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model trained
 ### Metrics
 | Label   | Precision | Recall | F1     |
 |:--------|:----------|:-------|:-------|
-| **all** | 0.7475    | 0.7402 | 0.7438 |
-| ORG     | 0.7475    | 0.7402 | 0.7438 |
+| **all** | 0.7618    | 0.7478 | 0.7547 |
+| ORG     | 0.7618    | 0.7478 | 0.7547 |
 
 ## Uses
 
@@ -118,7 +110,7 @@ from span_marker import SpanMarkerModel
 # Download from the 🤗 Hub
 model = SpanMarkerModel.from_pretrained("tomaarsen/span-marker-bert-small-orgs")
 # Run inference
-entities = model.predict("Lockheed said the U.S. Navy may also buy an additional 340 trainer aircraft to replace its T34C trainers made by the Beech Aircraft Corp. unit of Raytheon Corp.")
+entities = model.predict("American Motors included Chinese officials as part of the negotiations establishing Beijing Jeep (now Beijing Benz).")
 ```
 
 ### Downstream Use
@@ -173,7 +165,7 @@ trainer.save_model("tomaarsen/span-marker-bert-small-orgs-finetuned")
 | Entities per sentence | 0   | 0.7865  | 39  |
 
 ### Training Hyperparameters
-- learning_rate: 5e-05
+- learning_rate: 0.0001
 - train_batch_size: 128
 - eval_batch_size: 128
 - seed: 42
@@ -185,16 +177,16 @@ trainer.save_model("tomaarsen/span-marker-bert-small-orgs-finetuned")
 ### Training Results
 | Epoch  | Step | Validation Loss | Validation Precision | Validation Recall | Validation F1 | Validation Accuracy |
 |:------:|:----:|:---------------:|:--------------------:|:-----------------:|:-------------:|:-------------------:|
-| 0.5720 | 600  | 0.0085          | 0.7230               | 0.6552            | 0.6874        | 0.9641              |
-| 1.1439 | 1200 | 0.0078          | 0.7324               | 0.7021            | 0.7169        | 0.9663              |
-| 1.7159 | 1800 | 0.0074          | 0.7499               | 0.7213            | 0.7353        | 0.9679              |
-| 2.2879 | 2400 | 0.0074          | 0.7611               | 0.7318            | 0.7462        | 0.9701              |
-| 2.8599 | 3000 | 0.0072          | 0.772                | 0.7268            | 0.7487        | 0.9700              |
+| 0.5720 | 600  | 0.0076          | 0.7642               | 0.6630            | 0.7100        | 0.9656              |
+| 1.1439 | 1200 | 0.0070          | 0.7705               | 0.7139            | 0.7411        | 0.9699              |
+| 1.7159 | 1800 | 0.0067          | 0.7837               | 0.7231            | 0.7522        | 0.9709              |
+| 2.2879 | 2400 | 0.0070          | 0.7768               | 0.7517            | 0.7640        | 0.9725              |
+| 2.8599 | 3000 | 0.0068          | 0.7877               | 0.7374            | 0.7617        | 0.9718              |
 
 ### Environmental Impact
 Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon).
 - **Carbon Emitted**: 0.068 kg of CO2
-- **Hours Used**: 0.629 hours
+- **Hours Used**: 0.52 hours
 
 ### Training Hardware
 - **On Cloud**: No

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b2746c1382c0ffeeeefb0de829f38c75ba3ddf9e5de8ad14277e0c443470c2e
+oid sha256:b4daa10ec601a3d8f804bad331c8c9b0b90846ea0e8bc44779c1b3405b163306
 size 115096015