Model save

README.md

@@ -3,11 +3,6 @@ license: cc-by-sa-4.0
 base_model: surrey-nlp/roberta-large-finetuned-abbr-filtered-plod
 tags:
 - generated_from_trainer
-metrics:
-- precision
-- recall
-- f1
-- accuracy
 model-index:
 - name: roberta-large-finetuned-abbr-filtered-plod-finetuned-ner
   results: []
@@ -19,12 +14,6 @@ should probably proofread and complete it, then remove this comment. -->
 # roberta-large-finetuned-abbr-filtered-plod-finetuned-ner
 
 This model is a fine-tuned version of [surrey-nlp/roberta-large-finetuned-abbr-filtered-plod](https://huggingface.co/surrey-nlp/roberta-large-finetuned-abbr-filtered-plod) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.1367
-- Precision: 0.9809
-- Recall: 0.9745
-- F1: 0.9777
-- Accuracy: 0.9739
 
 ## Model description
 
@@ -44,20 +33,16 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 4
+- train_batch_size: 2
 - eval_batch_size: 4
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 6
 
-### Training results
-
-
-
 ### Framework versions
 
-- Transformers 4.39.2
-- Pytorch 1.12.1+cu102
+- Transformers 4.37.2
+- Pytorch 2.2.2+cu121
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.15.1

config.json

@@ -34,7 +34,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.39.2",
+  "transformers_version": "4.37.2",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50a81aaccc641f91bf44acb2b91b463be1a0adda5d9c59b6cfabb60b4dc97d53
+oid sha256:c618cac95e3571727d9fe07a5cd914bcf3a79a97cf6be92382846fc22fef6c6c
 size 1417309084

special_tokens_map.json

@@ -1,51 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "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

@@ -1,8 +1,7 @@
 {
-  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -10,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -18,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -26,36 +25,28 @@
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "max_length": 512,
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "stride": 0,
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a88f1629bc070d7aaea2c7652f3ebac5ba3a7647c4e9faa07e9e6890e551729c
-size 4527
+oid sha256:0b2d8c912c60187b6502d83783b89fc522bb6ed4194fd8a6151f3dae3fc58b1e
+size 4792