Training in progress, epoch 1

config.json

@@ -1,16 +1,15 @@
 {
-  "_name_or_path": "EuroBERT/EuroBERT-610m",
   "architectures": [
     "EuroBertForSequenceClassification"
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
   "auto_map": {
-    "AutoConfig": "EuroBERT/EuroBERT-610m--configuration_eurobert.EuroBertConfig",
-    "AutoModel": "EuroBERT/EuroBERT-610m--modeling_eurobert.EuroBertModel",
-    "AutoModelForMaskedLM": "EuroBERT/EuroBERT-610m--modeling_eurobert.EuroBertForMaskedLM",
-    "AutoModelForPreTraining": "EuroBERT/EuroBERT-610m--modeling_eurobert.EuroBertPreTrainedModel",
-    "AutoModelForSequenceClassification": "EuroBERT/EuroBERT-610m--modeling_eurobert.EuroBertForSequenceClassification"
+    "AutoConfig": "EuroBERT/EuroBERT-210m--configuration_eurobert.EuroBertConfig",
+    "AutoModel": "EuroBERT/EuroBERT-210m--modeling_eurobert.EuroBertModel",
+    "AutoModelForMaskedLM": "EuroBERT/EuroBERT-210m--modeling_eurobert.EuroBertForMaskedLM",
+    "AutoModelForPreTraining": "EuroBERT/EuroBERT-210m--modeling_eurobert.EuroBertPreTrainedModel",
+    "AutoModelForSequenceClassification": "EuroBERT/EuroBERT-210m--modeling_eurobert.EuroBertForSequenceClassification"
   },
   "bos_token": "<|begin_of_text|>",
   "bos_token_id": 128000,
@@ -20,13 +19,13 @@
   "head_dim": 64,
   "hidden_act": "silu",
   "hidden_dropout": 0.0,
-  "hidden_size": 1152,
+  "hidden_size": 768,
   "id2label": {
     "0": "0",
     "1": "1"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "0": 0,
     "1": 1
@@ -36,9 +35,9 @@
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "eurobert",
-  "num_attention_heads": 18,
-  "num_hidden_layers": 26,
-  "num_key_value_heads": 6,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
   "pad_token": "<|end_of_text|>",
   "pad_token_id": 128001,
   "pretraining_tp": 1,
@@ -48,7 +47,7 @@
   "rope_theta": 250000,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.49.0",
+  "transformers_version": "4.50.0",
   "use_cache": false,
   "vocab_size": 128256
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0289bf456b13899f07fb660197e0da334142142bcb4a98041059de9722bb88b
-size 2436848328
+oid sha256:88215de169f7af3fbc30ea92fb1c74843b05370ed875686b7a1852e64231832d
+size 849445136

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b7edee952c7f1a904d544feae7c382707e1ccc4e4ba403182cfeb43e266c73
+oid sha256:336c23221c999b6703bd74f02883eb0888eebdbf42405639153ae63bc135718f
 size 5560