Training in progress, epoch 1

config.json

@@ -1,13 +1,12 @@
 {
+  "activation": "gelu",
   "architectures": [
-    "BertForTokenClassification"
+    "DistilBertForTokenClassification"
   ],
-  "attention_probs_dropout_prob": 0.2,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.2,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.2,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "B-art",
     "1": "B-eve",
@@ -28,7 +27,6 @@
     "9": "I-eve"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "B-art": "0",
     "B-eve": "1",
@@ -48,16 +46,17 @@
     "I-tim": "15",
     "O": "16"
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.50.1",
-  "type_vocab_size": 2,
-  "use_cache": true,
   "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddf63df61afffe8c1b4ac44d754de92eda6b2f362a3d5aa05e170050aced6f5
-size 430954348
+oid sha256:6b04ab3f2a1aa3aeaba8759c23bc71d78d222ff1f3e8ced3c232d3500b66f3d2
+size 260828276

runs/Apr07_14-43-54_6c47aa6d929c/events.out.tfevents.1744037035.6c47aa6d929c.33820.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f40bd90370f52caa3e2ef1435bde22fd2422f6d96d6b09431be05cc290e196
+size 9696

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 512,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -51,6 +51,6 @@
   "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
+  "tokenizer_class": "DistilBertTokenizer",
   "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d1e3f7aeb5c8a1eb7107829cc7cabd92b4a8a7e5a1ba403f86683fd26e53452
+oid sha256:b80e66472427296bb2ee345bdddaa48ea8cff9c0b5086bd048fd5601ff327274
 size 5368