Training in progress, step 2000

config.json

@@ -8,7 +8,7 @@
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -6009,7 +6009,7 @@
     "5996": "LABEL_5996"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -12012,8 +12012,8 @@
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "xlm-roberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7ba1872705d026eb87dc6ad9c26741ac568edf3e0fc671a7b46c94f3565f5ca
-size 2264198188
+oid sha256:8fa193de81fdda6a7ac2368929f62d24c2bf9bf1cf15e81c7af3952103bb6e9e
+size 1130645660

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7d730c79c9644b196ad157d0946aa2daa81d20af467bde412c82e55c3f5471f
+oid sha256:b8198a731182bc1262c59136ba02d447f6106eb4d2290e5e9e923fce48f4fee3
 size 5304