Training in progress, epoch 1

config.json

@@ -1,26 +1,21 @@
 {
-  "_name_or_path": "Tochka-AI/ruRoPEBert-classic-base-2k",
+  "_name_or_path": "cointegrated/rubert-tiny2",
   "architectures": [
-    "RoPEBertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "auto_map": {
-    "AutoConfig": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertConfig",
-    "AutoModel": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertModel",
-    "AutoModelForMaskedLM": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertForMaskedLM",
-    "AutoModelForSequenceClassification": "Tochka-AI/ruRoPEBert-classic-base-2k--modeling_rope_bert.RoPEBertForSequenceClassification"
-  },
   "classifier_dropout": null,
-  "directionality": "bidi",
+  "emb_size": 312,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 312,
   "id2label": {
     "0": "common",
     "1": "toxic"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 600,
   "label2id": {
     "common": 0,
     "toxic": 1
@@ -29,14 +24,13 @@
   "max_position_embeddings": 2048,
   "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_hidden_layers": 3,
   "pad_token_id": 0,
-  "pooler_type": "mean",
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
   "type_vocab_size": 2,
-  "vocab_size": 120138
+  "use_cache": true,
+  "vocab_size": 83828
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:766532e99133d0437568e193f326d390e516d49f3f6795f53e3746dd8a2d8d9f
-size 709323472
+oid sha256:3bd1fbd909d119bfe31a7d1fa088732357d3ecbc2a970e4f3f396839e8840db9
+size 116784136

runs/Sep12_22-59-14_legal-tech-0/events.out.tfevents.1726171155.legal-tech-0.1432.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339618d5590c611c9494e854475cb05cd21780b1a4f71a1dcfb23ec54f8caaa9
+size 5343

tokenizer_config.json

@@ -8,7 +8,7 @@
       "single_word": false,
       "special": true
     },
-    "100": {
+    "1": {
       "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
@@ -16,7 +16,7 @@
       "single_word": false,
       "special": true
     },
-    "101": {
+    "2": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,7 +32,7 @@
       "single_word": false,
       "special": true
     },
-    "103": {
+    "4": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -44,14 +44,21 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_basic_tokenize": true,
-  "do_lower_case": true,
+  "do_lower_case": false,
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
   "never_split": null,
+  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
   "sep_token": "[SEP]",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d94cb99dab90a9a1fb3d6cad477cbcc624059b0b838eed719677c70f1cf6d95
+oid sha256:ad9764698f8858c1c7bbf086145d3e65b900084b81090e9e507e1931f03cf71c
 size 5240