Training in progress, epoch 1

config.json

@@ -1,15 +1,13 @@
 {
-  "_name_or_path": "xlm-roberta-large",
+  "_name_or_path": "distilbert-base-multilingual-cased",
+  "activation": "gelu",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "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": 1024,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "SEDIH",
     "1": "MARAH",
@@ -18,7 +16,6 @@
     "4": "SENENG"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
   "label2id": {
     "CINTA": 2,
     "MARAH": 1,
@@ -26,18 +23,18 @@
     "SENENG": 4,
     "TAKOT": 3
   },
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.30.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 119547
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e9632e8dcd5d023135ab757fa7b1e052d655a0e305d560b4258d3014dcdbd33
-size 2239722229
+oid sha256:1df529ec4ad6d3d5358645098b61b4e80edb2e9fc33bbd1e20b494de6de19d34
+size 541349549

runs/Jun23_07-45-42_ea8496c7943a/events.out.tfevents.1687506346.ea8496c7943a.6913.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa50100eaf881ec5e4b635c3069e964fdd5c73cfe8374fc5a01d86d94a32692
+size 4762

special_tokens_map.json

@@ -1,15 +1,7 @@
 {
-  "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>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
-size 17082758
+oid sha256:7d76a4d25ebe8f217654f1039bd991bfc96e7c2cd36e6d28aff941783ed1e9c8
+size 2919460

tokenizer_config.json

@@ -1,19 +1,13 @@
 {
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "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:c5c7452976d449163c0479aed9a87bf0a957b7fd4bcf7ae0d694897f32430175
+oid sha256:54ee76d53fe4ea19c9e73c11d1fffd658511feb674b906d69c41adbbdff5991e
 size 3899