Training in progress, epoch 1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -1,13 +1,12 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "microsoft/deberta-v3-base",
   "architectures": [
-    "DistilBertForTokenClassification"
+    "DebertaV2ForTokenClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "O",
     "1": "B-Repetition",
@@ -32,6 +31,7 @@
     "20": "I-Exaggeration,Minimisation"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "B-Appeal_to_Authority": 11,
     "B-Appeal_to_fear-prejudice": 14,
@@ -55,16 +55,27 @@
     "I-Repetition": 16,
     "O": 0
   },
+  "layer_norm_eps": 1e-07,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "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,
   "torch_dtype": "float32",
   "transformers_version": "4.30.0",
-  "vocab_size": 30522
+  "type_vocab_size": 0,
+  "vocab_size": 128100
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9f7a3bda4d5ae991bc5e7b202157a3c2504abf153a52cb1e31da7a37a7b9acb
-size 265551458
+oid sha256:83fa601239777c190ddd40eb9d6b0707b642ef60de76aee057da3de8a81fced8
+size 735464686

runs/Apr24_13-15-53_320ce5815fe3/events.out.tfevents.1713964556.320ce5815fe3.6186.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f082a72f2a6d1be773240578fde163e9f2a116eacf0772d471f244d45c3b6e71
+size 5300

runs/Apr24_14-29-45_320ce5815fe3/events.out.tfevents.1713968988.320ce5815fe3.37608.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f73f7ed95da1b15df6c25f7d97954a74f99b51198094c8537fa6104969d7a2a
+size 6022

special_tokens_map.json

@@ -1,5 +1,7 @@
 {
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -1,13 +1,16 @@
 {
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
-  "do_lower_case": true,
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
   "mask_token": "[MASK]",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60fa11aebad062de2c8fe914e3cb4bf3d875ac0663b7d4bfa8177a54e2817600
+oid sha256:3687faa3788b7cf8049a24c13b4d2d5612e90a1404319c91d37e0225f250ff5c
 size 4408