Training in progress, step 5

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "sberbank-ai/rugpt3small_based_on_gpt2",
-  "activation_function": "gelu_new",
+  "_name_or_path": "distilbert-base-multilingual-cased",
+  "activation": "gelu",
   "architectures": [
-    "GPT2ForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 1,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 2,
-  "gradient_checkpointing": false,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -114,27 +113,18 @@
     "LABEL_8": 8,
     "LABEL_9": 9
   },
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 2048,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 2048,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
   "problem_type": "single_label_classification",
-  "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
-  "scale_attn_by_inverse_layer_idx": false,
-  "scale_attn_weights": true,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.46.3",
-  "use_cache": true,
-  "vocab_size": 50264
+  "vocab_size": 119547
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9476d7baed8d690cc5e6a9b88dffae97e3e3740141b3306709fa5774acc15753
-size 501095120
+oid sha256:25a9f52c034d13805de9f5e92744ebb21fc17c6d179756af6626bd870ffe3f5a
+size 541465032

runs/Dec16_17-42-20_7c156b620239/events.out.tfevents.1734370941.7c156b620239.312.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000458a97707585407d39b6c11732c20cc618e682dd3c514841b3d404e5cf371
+size 7455

special_tokens_map.json

@@ -1,37 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,41 +1,39 @@
 {
-  "add_bos_token": false,
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<pad>",
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<s>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "<mask>",
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -43,16 +41,15 @@
       "special": true
     }
   },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "</s>",
-  "errors": "replace",
-  "mask_token": "<mask>",
-  "model_max_length": 2048,
-  "pad_token": "<pad>",
-  "padding_side": "left",
-  "tokenizer_class": "GPT2Tokenizer",
-  "truncation_side": "left",
-  "trust_remote_code": false,
-  "unk_token": "<unk>"
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc0126962d59e321f26c279ac7451123895591611e58819a62a22cb9caddb48
+oid sha256:7863680924f577a5d9818306e027ec8edb701b565335f7717ba78b6a48d92d98
 size 5304