Training in progress, epoch 1

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -1,7 +1,7 @@
 {
-  "_name_or_path": "openai-community/roberta-large-openai-detector",
+  "_name_or_path": "FacebookAI/xlm-roberta-large",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
@@ -22,7 +22,7 @@
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "model_type": "xlm-roberta",
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
   "output_past": true,
@@ -33,5 +33,5 @@
   "transformers_version": "4.43.2",
   "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d855d2746523a2c7026633446b5ebdf9cee3fabee761823f84cddfbc884c39bf
-size 1421495416
+oid sha256:2c2678b4f9212e27289a940b561106d3a93bba9686853ca536d78aefff55afde
+size 2239618672

runs/Jul26_16-08-17_gpu-1/events.out.tfevents.1721977699.gpu-1.291149.10

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1266a8e5ae6fafd7f5595549c7d29a5f5d7294c50e09d1d90d8305f378525a30
-size 14274
+oid sha256:bfb977544072b9358b9b812b1c8ebb6d52a3a59b64c56b15940dff7215120844
+size 14489

runs/Jul26_16-50-11_gpu-1/events.out.tfevents.1721980212.gpu-1.291149.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b139d68272594a4eaaf9c0b1a151a5c4caadf12c0659819a307cf55329dc6eb7
+size 6526

runs/Jul26_16-57-31_gpu-1/events.out.tfevents.1721980652.gpu-1.291149.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72e8ac1eefda7f93e8e9d166471cd56affffb7958002ea7c33acad3253dd64a4
+size 6425

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

tokenizer_config.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e26cb814a19e202afbfef494284645653d4b7b8be778f34870aa056dda4afcfc
+oid sha256:ed320209ba66f70704744e48d436e6770776deb8fe3b24459964229ae7724e76
 size 5176