End of training

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: dmis-lab/biobert-v1.1
+license: mit
+base_model: microsoft/BiomedNLP-KRISSBERT-PubMed-UMLS-EL
 tags:
 - generated_from_trainer
 metrics:
@@ -17,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [dmis-lab/biobert-v1.1](https://huggingface.co/dmis-lab/biobert-v1.1) on the None dataset.
+This model is a fine-tuned version of [microsoft/BiomedNLP-KRISSBERT-PubMed-UMLS-EL](https://huggingface.co/microsoft/BiomedNLP-KRISSBERT-PubMed-UMLS-EL) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4062
-- Precision: 0.9169
-- Recall: 0.9170
-- Accuracy: 0.9170
-- F1: 0.9170
+- Loss: 0.4228
+- Precision: 0.9215
+- Recall: 0.9209
+- Accuracy: 0.9211
+- F1: 0.9210
 
 ## Model description
 
@@ -54,11 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:------:|
-| No log        | 1.0   | 308  | 0.3815          | 0.8655    | 0.8595 | 0.8584   | 0.8587 |
-| 0.4485        | 2.0   | 616  | 0.3222          | 0.9076    | 0.9073 | 0.9072   | 0.9072 |
-| 0.4485        | 3.0   | 924  | 0.3684          | 0.9101    | 0.9098 | 0.9097   | 0.9099 |
-| 0.1574        | 4.0   | 1232 | 0.3878          | 0.9163    | 0.9162 | 0.9162   | 0.9162 |
-| 0.0613        | 5.0   | 1540 | 0.4062          | 0.9169    | 0.9170 | 0.9170   | 0.9170 |
+| No log        | 1.0   | 308  | 0.3266          | 0.8847    | 0.8822 | 0.8820   | 0.8824 |
+| 0.4217        | 2.0   | 616  | 0.3034          | 0.9072    | 0.9066 | 0.9064   | 0.9065 |
+| 0.4217        | 3.0   | 924  | 0.3483          | 0.9171    | 0.9170 | 0.9170   | 0.9171 |
+| 0.163         | 4.0   | 1232 | 0.3952          | 0.9227    | 0.9227 | 0.9227   | 0.9226 |
+| 0.0722        | 5.0   | 1540 | 0.4228          | 0.9215    | 0.9209 | 0.9211   | 0.9210 |
 
 
 ### Framework versions

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</ENT>": 30523,
+  "<ENT>": 30522,
+  "[DUMMY]": 30524
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "dmis-lab/biobert-v1.1",
+  "_name_or_path": "microsoft/BiomedNLP-KRISSBERT-PubMed-UMLS-EL",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -33,5 +33,5 @@
   "transformers_version": "4.35.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 30525
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a56f4cc388f1ece1288cbc2db626d27d57752ea108972addbf13f281591253f8
-size 433273844
+oid sha256:8904822494add51cb1353ddd2899772b314be500c192bb3e0083cf425c872aae
+size 437970940

runs/Feb20_12-18-47_b7bcaa3b0fd6/events.out.tfevents.1708431528.b7bcaa3b0fd6.252.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:693da275179a41f34286763d234070ecd1daf856933ef88ec5ed9ec7e34123aa
+size 7623

tokenizer_config.json

@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "100": {
+    "1": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "101": {
+    "2": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,21 +32,46 @@
       "single_word": false,
       "special": true
     },
-    "103": {
+    "4": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "30522": {
+      "content": "<ENT>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30523": {
+      "content": "</ENT>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30524": {
+      "content": "[DUMMY]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
     }
   },
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": false,
+  "do_lower_case": true,
+  "full_tokenizer_file": null,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:852a9c7ef42acb0f8f5560f49764d9c66c773586f7e3c5753cd44f76dbaba9a9
+oid sha256:322719c22edf3ee22cc1580c3b3f71214c4ea60d87a90b16be8e69d373a40d58
 size 4536