Training in progress epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: FacebookAI/roberta-base
+base_model: microsoft/mdeberta-v3-base
 tags:
 - generated_from_keras_callback
 model-index:
@@ -13,13 +13,13 @@ probably proofread and complete it, then remove this comment. -->
 
 # khadija69/debertav3_ASE_kgl_BIES2
 
-This model is a fine-tuned version of [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Train Loss: nan
-- Train Accuracy: 0.0743
-- Validation Loss: nan
-- Validation Accuracy: 0.0726
-- Epoch: 9
+- Train Loss: 1.1865
+- Train Accuracy: 0.4781
+- Validation Loss: 0.9186
+- Validation Accuracy: 0.5364
+- Epoch: 0
 
 ## Model description
 
@@ -45,16 +45,7 @@ The following hyperparameters were used during training:
 
 | Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
 |:----------:|:--------------:|:---------------:|:-------------------:|:-----:|
-| nan        | 0.0784         | nan             | 0.0726              | 0     |
-| nan        | 0.0745         | nan             | 0.0726              | 1     |
-| nan        | 0.0742         | nan             | 0.0726              | 2     |
-| nan        | 0.0744         | nan             | 0.0726              | 3     |
-| nan        | 0.0740         | nan             | 0.0726              | 4     |
-| nan        | 0.0744         | nan             | 0.0726              | 5     |
-| nan        | 0.0745         | nan             | 0.0726              | 6     |
-| nan        | 0.0745         | nan             | 0.0726              | 7     |
-| nan        | 0.0745         | nan             | 0.0726              | 8     |
-| nan        | 0.0743         | nan             | 0.0726              | 9     |
+| 1.1865     | 0.4781         | 0.9186          | 0.5364              | 0     |
 
 
 ### Framework versions

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 250101
+}

config.json

@@ -1,12 +1,9 @@
 {
-  "_name_or_path": "FacebookAI/roberta-base",
+  "_name_or_path": "microsoft/mdeberta-v3-base",
   "architectures": [
-    "RobertaForTokenClassification"
+    "DebertaV2ForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -32,15 +29,26 @@
     "S-O": 7,
     "S-Skill": 3
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "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,
   "transformers_version": "4.41.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 50265
+  "type_vocab_size": 0,
+  "vocab_size": 251000
 }

special_tokens_map.json

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

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
+size 4305025

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c9f7d35254510e16c9d1f615fc503584ce448222575a17a78341a8cd1bc44a
-size 496532560
+oid sha256:50ed7268833acfa1f71e6f1b909ce9ee80e6f3753cd9c187b6eff1ca99d696e5
+size 1113185960

tokenizer_config.json

@@ -1,57 +1,58 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "1": {
-      "content": "<pad>",
+      "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "2": {
-      "content": "</s>",
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
     "3": {
-      "content": "<unk>",
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
+    "250101": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "trim_offsets": true,
-  "unk_token": "<unk>"
+  "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"
 }