Model save

README.md

@@ -1,13 +1,8 @@
 ---
 license: mit
-base_model: microsoft/deberta-v3-base
+base_model: alexeyak/deberta-v3-base-ner-B
 tags:
 - generated_from_trainer
-metrics:
-- precision
-- recall
-- f1
-- accuracy
 model-index:
 - name: deberta-v3-base-ner-B
   results: []
@@ -18,13 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # deberta-v3-base-ner-B
 
-This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.0294
-- Precision: 0.9660
-- Recall: 0.9751
-- F1: 0.9705
-- Accuracy: 0.9929
+This model is a fine-tuned version of [alexeyak/deberta-v3-base-ner-B](https://huggingface.co/alexeyak/deberta-v3-base-ner-B) on an unknown dataset.
 
 ## Model description
 
@@ -54,35 +43,6 @@ The following hyperparameters were used during training:
 - num_epochs: 3
 - mixed_precision_training: Native AMP
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| 0.0336        | 0.13  | 257  | 0.0345          | 0.9245    | 0.9386 | 0.9315 | 0.9885   |
-| 0.0309        | 0.25  | 514  | 0.0296          | 0.9161    | 0.9624 | 0.9387 | 0.9892   |
-| 0.0281        | 0.38  | 771  | 0.0251          | 0.9316    | 0.9539 | 0.9426 | 0.9908   |
-| 0.0221        | 0.5   | 1028 | 0.0259          | 0.9381    | 0.9588 | 0.9483 | 0.9910   |
-| 0.0234        | 0.63  | 1285 | 0.0260          | 0.9318    | 0.9640 | 0.9477 | 0.9904   |
-| 0.0177        | 0.75  | 1542 | 0.0248          | 0.9331    | 0.9665 | 0.9495 | 0.9909   |
-| 0.0213        | 0.88  | 1799 | 0.0228          | 0.9522    | 0.9593 | 0.9557 | 0.9918   |
-| 0.0252        | 1.0   | 2056 | 0.0233          | 0.9517    | 0.9568 | 0.9542 | 0.9917   |
-| 0.0143        | 1.13  | 2313 | 0.0256          | 0.9491    | 0.9641 | 0.9565 | 0.9918   |
-| 0.0132        | 1.25  | 2570 | 0.0247          | 0.9536    | 0.9627 | 0.9581 | 0.9921   |
-| 0.015         | 1.38  | 2827 | 0.0243          | 0.9467    | 0.9640 | 0.9553 | 0.9917   |
-| 0.0148        | 1.5   | 3084 | 0.0254          | 0.9475    | 0.9677 | 0.9575 | 0.9918   |
-| 0.0143        | 1.63  | 3341 | 0.0252          | 0.9491    | 0.9667 | 0.9578 | 0.9920   |
-| 0.0112        | 1.75  | 3598 | 0.0244          | 0.9546    | 0.9626 | 0.9586 | 0.9923   |
-| 0.0074        | 1.88  | 3855 | 0.0268          | 0.9490    | 0.9680 | 0.9584 | 0.9921   |
-| 0.0068        | 2.0   | 4112 | 0.0257          | 0.9577    | 0.9610 | 0.9594 | 0.9923   |
-| 0.0079        | 2.13  | 4369 | 0.0296          | 0.9457    | 0.9698 | 0.9576 | 0.9919   |
-| 0.0067        | 2.26  | 4626 | 0.0290          | 0.9520    | 0.9686 | 0.9602 | 0.9922   |
-| 0.0067        | 2.38  | 4883 | 0.0282          | 0.9553    | 0.9653 | 0.9603 | 0.9923   |
-| 0.0044        | 2.51  | 5140 | 0.0303          | 0.9600    | 0.9622 | 0.9611 | 0.9926   |
-| 0.005         | 2.63  | 5397 | 0.0318          | 0.9488    | 0.9703 | 0.9594 | 0.9920   |
-| 0.006         | 2.76  | 5654 | 0.0295          | 0.9564    | 0.9663 | 0.9613 | 0.9925   |
-| 0.0059        | 2.88  | 5911 | 0.0304          | 0.9586    | 0.9657 | 0.9621 | 0.9925   |
-
-
 ### Framework versions
 
 - Transformers 4.35.2

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/deberta-v3-base",
+  "_name_or_path": "alexeyak/deberta-v3-base-ner-B",
   "architectures": [
     "DebertaV2ForTokenClassification"
   ],
@@ -17,62 +17,22 @@
     "6": "I-LOC",
     "7": "B-ANIM",
     "8": "I-ANIM",
-    "9": "B-BIO",
-    "10": "I-BIO",
-    "11": "B-CEL",
-    "12": "I-CEL",
-    "13": "B-DIS",
-    "14": "I-DIS",
-    "15": "B-EVE",
-    "16": "I-EVE",
-    "17": "B-FOOD",
-    "18": "I-FOOD",
-    "19": "B-INST",
-    "20": "I-INST",
-    "21": "B-MEDIA",
-    "22": "I-MEDIA",
-    "23": "B-MYTH",
-    "24": "I-MYTH",
-    "25": "B-PLANT",
-    "26": "I-PLANT",
-    "27": "B-TIME",
-    "28": "I-TIME",
-    "29": "B-VEHI",
-    "30": "I-VEHI"
+    "9": "B-DIS",
+    "10": "I-DIS"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
     "B-ANIM": 7,
-    "B-BIO": 9,
-    "B-CEL": 11,
-    "B-DIS": 13,
-    "B-EVE": 15,
-    "B-FOOD": 17,
-    "B-INST": 19,
+    "B-DIS": 9,
     "B-LOC": 5,
-    "B-MEDIA": 21,
-    "B-MYTH": 23,
     "B-ORG": 3,
     "B-PER": 1,
-    "B-PLANT": 25,
-    "B-TIME": 27,
-    "B-VEHI": 29,
     "I-ANIM": 8,
-    "I-BIO": 10,
-    "I-CEL": 12,
-    "I-DIS": 14,
-    "I-EVE": 16,
-    "I-FOOD": 18,
-    "I-INST": 20,
+    "I-DIS": 10,
     "I-LOC": 6,
-    "I-MEDIA": 22,
-    "I-MYTH": 24,
     "I-ORG": 4,
     "I-PER": 2,
-    "I-PLANT": 26,
-    "I-TIME": 28,
-    "I-VEHI": 30,
     "O": 0
   },
   "layer_norm_eps": 1e-07,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09da02e19a05301dc6a27cd5c653331c8caee71eba6f9ff670e0e00220cd2720
-size 735445940
+oid sha256:1281df91215b2282525a6dbe0e0c0062daf4b53c002db754cafe4f2c3ef27cc2
+size 735384420

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd65f32512b20aba2a67d3614efd55ecb06e0983b6391ba4300d6571ae7d6a0f
+oid sha256:780a12095ff93f52cb510f061711438a70a90f960e2bbb6e4e6b1ddfee8285a5
 size 4600