Training in progress, step 100

config.json

@@ -1,12 +1,11 @@
 {
-  "_name_or_path": "hfl/chinese-roberta-wwm-ext",
+  "_name_or_path": "xlm-roberta-base",
   "architectures": [
-    "BertForSequenceClassification"
+    "XLMRobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 0,
   "classifier_dropout": null,
-  "directionality": "bidi",
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
@@ -23,23 +22,18 @@
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "output_past": true,
-  "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "multi_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.25.1",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 21128
+  "vocab_size": 250002
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5cecef6e6c73a2c390a8a4b7d3e28280e29fb621f01fa3d87d52c7fb1a874f7
-size 409167989
+oid sha256:be780db6c58ec915bd0e5eb0777d815e2cc4c18770077c0b6e5b17239aa26323
+size 1112272565

runs/Jan17_01-13-21_eec551641185/1673918006.0414693/events.out.tfevents.1673918006.eec551641185.324.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5b793abf00fa5e692b1e5fb913fc8c9c9a0fd7cb22d930844dd9b4ecbee97bb
+size 5513

runs/Jan17_01-13-21_eec551641185/events.out.tfevents.1673918006.eec551641185.324.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a00c261386e24bdc33b2845b8b59162cbff2b87bda20f2aca382363a92333e78
+size 4592

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a8125f416a005320f0278a8e48b26ab03761f058fd7c98cdb4aa66bea40ac1
+oid sha256:a822a9ac4ae9aeb20b7fccf083752927cc06f709a1db2d4c3d4e6480ed92686c
 size 3387