End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: microsoft/deberta-v3-base
+license: apache-2.0
+base_model: allenai/longformer-base-4096
 tags:
 - generated_from_trainer
 model-index:
@@ -13,17 +13,21 @@ should probably proofread and complete it, then remove this comment. -->
 
 # output
 
-This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
+This model is a fine-tuned version of [allenai/longformer-base-4096](https://huggingface.co/allenai/longformer-base-4096) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0022
-- Name Student Precision: 0.9737
+- Loss: 0.0554
+- Name Student Precision: 0.9535
 - Name Student Recall: 1.0
-- Name Student F1: 0.9867
-- Name Student Number: 37
-- Overall Precision: 0.9737
-- Overall Recall: 1.0
-- Overall F1: 0.9867
-- Overall Accuracy: 0.9975
+- Name Student F1: 0.9762
+- Name Student Number: 41
+- Url Personal Precision: 0.0
+- Url Personal Recall: 0.0
+- Url Personal F1: 0.0
+- Url Personal Number: 1
+- Overall Precision: 0.9535
+- Overall Recall: 0.9762
+- Overall F1: 0.9647
+- Overall Accuracy: 0.9925
 
 ## Model description
 
@@ -46,6 +50,8 @@ The following hyperparameters were used during training:
 - train_batch_size: 2
 - eval_batch_size: 4
 - seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
@@ -54,10 +60,10 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Name Student Precision | Name Student Recall | Name Student F1 | Name Student Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
-| 0.0002        | 1.0   | 400  | 0.0061          | 0.9737                 | 1.0                 | 0.9867          | 37                  | 0.9737            | 1.0            | 0.9867     | 0.9975           |
-| 0.0001        | 2.0   | 800  | 0.0022          | 0.9737                 | 1.0                 | 0.9867          | 37                  | 0.9737            | 1.0            | 0.9867     | 0.9975           |
+| Training Loss | Epoch | Step | Validation Loss | Name Student Precision | Name Student Recall | Name Student F1 | Name Student Number | Url Personal Precision | Url Personal Recall | Url Personal F1 | Url Personal Number | Overall Precision | Overall Recall | Overall F1 | Overall Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:----------------------:|:-------------------:|:---------------:|:-------------------:|:-----------------:|:--------------:|:----------:|:----------------:|
+| 0.0023        | 1.0   | 100  | 0.0549          | 0.9535                 | 1.0                 | 0.9762          | 41                  | 0.0                    | 0.0                 | 0.0             | 1                   | 0.9535            | 0.9762         | 0.9647     | 0.9925           |
+| 0.0009        | 2.0   | 200  | 0.0554          | 0.9535                 | 1.0                 | 0.9762          | 41                  | 0.0                    | 0.0                 | 0.0             | 1                   | 0.9535            | 0.9762         | 0.9647     | 0.9925           |
 
 
 ### Framework versions

config.json

@@ -1,9 +1,27 @@
 {
-  "_name_or_path": "microsoft/deberta-v3-base",
+  "_name_or_path": "allenai/longformer-base-4096",
   "architectures": [
-    "DebertaV2ForTokenClassification"
+    "LongformerForTokenClassification"
   ],
+  "attention_mode": "longformer",
   "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -22,6 +40,7 @@
     "11": "I-URL_PERSONAL",
     "12": "O"
   },
+  "ignore_attention_mask": false,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
@@ -39,27 +58,16 @@
     "I-URL_PERSONAL": 11,
     "O": 12
   },
-  "layer_norm_eps": 1e-07,
-  "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta-v2",
-  "norm_rel_ebd": "layer_norm",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4098,
+  "model_type": "longformer",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "pooler_dropout": 0,
-  "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 768,
-  "pos_att_type": [
-    "p2c",
-    "c2p"
-  ],
-  "position_biased_input": false,
-  "position_buckets": 256,
-  "relative_attention": true,
-  "share_att_key": true,
+  "onnx_export": false,
+  "pad_token_id": 1,
+  "sep_token_id": 2,
   "torch_dtype": "float32",
   "transformers_version": "4.38.1",
-  "type_vocab_size": 0,
-  "vocab_size": 128016
+  "type_vocab_size": 1,
+  "vocab_size": 50688
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1979329d136c00c6bd4a88376d3cceb241a7ddbb360726dacf5cb921dedc1f18
-size 735132524
+oid sha256:57f481f6cca419d995a782136b2b9c72bd262b7877ba2e639e40f8d34079ee4f
+size 593648892

special_tokens_map.json

@@ -1,15 +1,15 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": {
-    "content": "[UNK]",
-    "lstrip": false,
-    "normalized": true,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
-  }
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,58 +1,57 @@
 {
+  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "[CLS]",
+      "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "[SEP]",
+      "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "3": {
-      "content": "[UNK]",
+      "content": "<unk>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128000": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "[CLS]",
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "split_by_punct": false,
-  "tokenizer_class": "DebertaV2Tokenizer",
-  "unk_token": "[UNK]",
-  "vocab_type": "spm"
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "LongformerTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9100fcf98f4a9a8c12dcb99322ccb6ad82d49caef3c96d30dbec0ae3ed9c86db
-size 4856
+oid sha256:ac423cb02aadebb07017fcd28a0ce79ad4e5a16ce750832bf14b5b45897e48bf
+size 4920