Training in progress epoch 0

README.md

@@ -1,4 +1,5 @@
 ---
+base_model: medicalai/ClinicalBERT
 tags:
 - generated_from_keras_callback
 model-index:
@@ -11,10 +12,10 @@ probably proofread and complete it, then remove this comment. -->
 
 # FatemehYp/clinicalbert-complete_Diagnosis_in_responses_finetuned-squad
 
-This model was trained from scratch on an unknown dataset.
+This model is a fine-tuned version of [medicalai/ClinicalBERT](https://huggingface.co/medicalai/ClinicalBERT) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: 0.7541
-- Epoch: 2
+- Train Loss: 2.5659
+- Epoch: 0
 
 ## Model description
 
@@ -40,9 +41,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Epoch |
 |:----------:|:-----:|
-| 1.2579     | 0     |
-| 0.9382     | 1     |
-| 0.7541     | 2     |
+| 2.5659     | 0     |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "clinicalbert-complete_Diagnosis_in_responses_finetuned-squad",
+  "_name_or_path": "medicalai/ClinicalBERT",
   "activation": "gelu",
   "architectures": [
     "DistilBertForQuestionAnswering"

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e6d80719055ef2acc5c93d4cc4f8884fab534b3d9e7a2877bee556a5e01be6
+oid sha256:83ebaedb1c01d0cb12ba0593c0a3ec22d5abfefe25a64b0267a9661501eec880
 size 539068392

tokenizer_config.json

@@ -5,19 +5,12 @@
   "do_lower_case": true,
   "full_tokenizer_file": null,
   "mask_token": "[MASK]",
-  "max_length": 384,
   "model_max_length": 1000000000000000019884624838656,
   "never_split": null,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 128,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "only_second",
   "unk_token": "[UNK]"
 }