End of training

README.md

@@ -1,6 +1,5 @@
 ---
-license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: dmis-lab/biobert-v1.1
 tags:
 - generated_from_trainer
 metrics:
@@ -18,13 +17,13 @@ should probably proofread and complete it, then remove this comment. -->
 
 # sentence-classifiert
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+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.
 It achieves the following results on the evaluation set:
-- Loss: 0.6252
-- Precision: 0.7535
-- Recall: 0.7518
-- Accuracy: 0.7518
-- F1: 0.7521
+- Loss: 0.3410
+- Precision: 0.9085
+- Recall: 0.9068
+- Accuracy: 0.9072
+- F1: 0.9072
 
 ## Model description
 
@@ -55,11 +54,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:------:|
-| No log        | 1.0   | 154  | 0.9047          | 0.6004    | 0.5895 | 0.5858   | 0.5781 |
-| No log        | 2.0   | 308  | 0.7097          | 0.6792    | 0.6805 | 0.6802   | 0.6711 |
-| No log        | 3.0   | 462  | 0.6422          | 0.7320    | 0.7322 | 0.7315   | 0.7266 |
-| 0.773         | 4.0   | 616  | 0.6549          | 0.7433    | 0.7373 | 0.7364   | 0.7372 |
-| 0.773         | 5.0   | 770  | 0.6252          | 0.7535    | 0.7518 | 0.7518   | 0.7521 |
+| No log        | 1.0   | 154  | 0.4158          | 0.8549    | 0.8445 | 0.8438   | 0.8443 |
+| No log        | 2.0   | 308  | 0.3426          | 0.8875    | 0.8804 | 0.8796   | 0.8787 |
+| No log        | 3.0   | 462  | 0.3594          | 0.8945    | 0.8856 | 0.8869   | 0.8868 |
+| 0.3638        | 4.0   | 616  | 0.3302          | 0.9034    | 0.9008 | 0.9015   | 0.9014 |
+| 0.3638        | 5.0   | 770  | 0.3410          | 0.9085    | 0.9068 | 0.9072   | 0.9072 |
 
 
 ### Framework versions

config.json

@@ -1,35 +1,37 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "dmis-lab/biobert-v1.1",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "marker/mechanism",
     "1": "therapeutic",
     "2": "unrelated"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "marker/mechanism": 0,
     "therapeutic": 1,
     "unrelated": 2
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.35.2",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e8f364473a5d0cdc97b7ba27fea0e3d80139d29d9b141b5c726a951984691e7
-size 267835644
+oid sha256:16961d87c6f6df3bd24ee792cf8d03e7a44e7ee0236eac40ab03bb4d83ba5f21
+size 433273844

runs/Feb19_10-32-50_f8343483f830/events.out.tfevents.1708339279.f8343483f830.190.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a073df1104cf788097833045b39d077cce50656305d22a426abfa5e9231908
+size 560

runs/Feb19_10-44-49_f8343483f830/events.out.tfevents.1708339490.f8343483f830.190.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b7e0159ef55bd7bf371051c57eb38462ed175498ccbe6256f6c830fed91485a
+size 7319

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -46,19 +46,12 @@
   "do_basic_tokenize": true,
   "do_lower_case": false,
   "mask_token": "[MASK]",
-  "max_length": 512,
   "model_max_length": 512,
   "never_split": null,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc18a62349df19b4abd205e8db0b2f54ea5af60d684f7e5fe4b5e256cc9301eb
+oid sha256:e22546dedd67d4b9a10f3517bf8deea44f568ab3860bda6499b6969340fc66b6
 size 4600