Training in progress, epoch 1

config.json

@@ -1,16 +1,16 @@
 {
-  "_name_or_path": "EuroBERT/EuroBERT-610m",
+  "_name_or_path": "EuroBERT/EuroBERT-210m",
   "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 +20,13 @@
   "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 +36,9 @@
   "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,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26862fb8cc9725d04d5cdec6b8254dfa8e492c73517528570538b850b8d24483
-size 2436848328
+oid sha256:d13e4146835bb9170066397a9f57729e02ac37a74b3aa88e23a812709cafd1ad
+size 849445136

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90afafb9441b9e4eeef11d619ff14569747135aaf1e83ba12aa1c734a0177edf
-size 17209997
+oid sha256:fc2befa162f4fa90daed0d884a2db4d02c2da3f6d2172dcd44b2d15259e4fb49
+size 17210081