Training in progress, epoch 21

config.json

@@ -1,11 +1,12 @@
 {
-  "_name_or_path": "google/electra-base-discriminator",
+  "_name_or_path": "xlm-roberta-base",
   "architectures": [
-    "ElectraForTokenClassification"
+    "XLMRobertaForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "embedding_size": 768,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -13,52 +14,49 @@
     "0": "O",
     "1": "B-CAMPAIGNER",
     "2": "I-CAMPAIGNER",
-    "3": "B-NEGATIVE_EFFECT",
-    "4": "I-NEGATIVE_EFFECT",
-    "5": "B-OBJECTIVE",
-    "6": "I-OBJECTIVE",
-    "7": "B-VICTIM",
-    "8": "I-VICTIM",
-    "9": "B-AGENT",
-    "10": "I-AGENT",
+    "3": "B-AGENT",
+    "4": "I-AGENT",
+    "5": "B-VICTIM",
+    "6": "I-VICTIM",
+    "7": "B-NEGATIVE_EFFECT",
+    "8": "I-NEGATIVE_EFFECT",
+    "9": "B-FACILITATOR",
+    "10": "I-FACILITATOR",
     "11": "B-X",
     "12": "I-X",
-    "13": "B-FACILITATOR",
-    "14": "I-FACILITATOR"
+    "13": "B-OBJECTIVE",
+    "14": "I-OBJECTIVE"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "B-AGENT": 9,
+    "B-AGENT": 3,
     "B-CAMPAIGNER": 1,
-    "B-FACILITATOR": 13,
-    "B-NEGATIVE_EFFECT": 3,
-    "B-OBJECTIVE": 5,
-    "B-VICTIM": 7,
+    "B-FACILITATOR": 9,
+    "B-NEGATIVE_EFFECT": 7,
+    "B-OBJECTIVE": 13,
+    "B-VICTIM": 5,
     "B-X": 11,
-    "I-AGENT": 10,
+    "I-AGENT": 4,
     "I-CAMPAIGNER": 2,
-    "I-FACILITATOR": 14,
-    "I-NEGATIVE_EFFECT": 4,
-    "I-OBJECTIVE": 6,
-    "I-VICTIM": 8,
+    "I-FACILITATOR": 10,
+    "I-NEGATIVE_EFFECT": 8,
+    "I-OBJECTIVE": 14,
+    "I-VICTIM": 6,
     "I-X": 12,
     "O": 0
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "electra",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "output_past": true,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
-  "summary_activation": "gelu",
-  "summary_last_dropout": 0.1,
-  "summary_type": "first",
-  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.41.1",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 250002
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d4f67d615a0b93761322f43bea310bccc74cc1b2644a988f30da23ebf5d6d7e
-size 435636652
+oid sha256:02b7204f7d2509facae5f868f39b5237d3d6c98527b79750a56eb3f24a8eb858
+size 1109882412

runs/May29_18-56-21_6f983583bd59/events.out.tfevents.1717008983.6f983583bd59.1236.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6d07e5e7e78fda74c00d4b9b5e56d14534ed7655000a7455311885f13466474
-size 16731
+oid sha256:134516e37c9e00b84d48044e267bbb699983384294f6c6928bfe26d9a9365fc5
+size 17203

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
 }

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435667fab0c06c165b1283ecb422497c37124f2d6a35b2ac73dc876332fc9518
-size 711494
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

tokenizer_config.json

@@ -1,55 +1,54 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "mask_token": "[MASK]",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
   "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "ElectraTokenizer",
-  "unk_token": "[UNK]"
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:672c1c7f26e8dfc64ecf520924627d7a9f342f35c14072bbd18d7c4cb3368875
+oid sha256:378cb5aa0932b8b2c957ef087bff212ad28b0ef53596cb3b02871962a0ca99ab
 size 5176