Training in progress, epoch 1

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "XLMRobertaForTokenClassification"
+    "RobertaForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -26,15 +26,14 @@
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "output_past": true,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fdcf7237708075e5a85d9d48607c15fa2d168208270252620e8e3b4aa5c012b
-size 1109848576
+oid sha256:69ed9e8066ec9f9ea19e52c16f58927d4ed3cc6587a51829acc9383755d9e0f3
+size 496256392

runs/Apr16_08-50-01_a8ce803913f4/events.out.tfevents.1713257406.a8ce803913f4.251.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:972a2c6acf9df7c2871f275a1bc02fd07b34e19d150091d54432557d028126d1
+size 5204

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f59925fcb90c92b894cb93e51bb9b4a6105c5c249fe54ce1c704420ac39b81af
-size 17082756
+oid sha256:fa749058bddc4469f6e7341d3d8863b77d59698b572fa9780bfd6cee5decb87d
+size 2108613

tokenizer_config.json

@@ -1,9 +1,10 @@
 {
+  "add_prefix_space": true,
   "added_tokens_decoder": {
     "0": {
       "content": "<s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -11,7 +12,7 @@
     "1": {
       "content": "<pad>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -19,7 +20,7 @@
     "2": {
       "content": "</s>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -27,12 +28,12 @@
     "3": {
       "content": "<unk>",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
+    "50264": {
       "content": "<mask>",
       "lstrip": true,
       "normalized": false,
@@ -45,10 +46,12 @@
   "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
+  "errors": "replace",
   "mask_token": "<mask>",
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
   "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ed3074d03a3a9b115eb9e0d93af72ac3c867a342442574911d0e50637b44f8
+oid sha256:f7d3505669eaa9900394790cc6368b269cfdc730c8db736902359b038b36fa74
 size 4920