Training in progress, epoch 1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gaunernst/bert-mini-uncased",
+  "_name_or_path": "microsoft/MiniLM-L12-H384-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
@@ -7,7 +7,7 @@
   "classifier_dropout": null,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 256,
+  "hidden_size": 384,
   "id2label": {
     "0": "holdings",
     "1": "capital_gains",
@@ -24,7 +24,7 @@
     "12": "None_module"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 1024,
+  "intermediate_size": 1536,
   "label2id": {
     "Current Year": 5,
     "Daily": 7,
@@ -43,8 +43,8 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 4,
-  "num_hidden_layers": 4,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "multi_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:485ecddac54449e88fd2ef869f3dd348d24acc96c4478ddbd181f4c7718898ba
-size 44703916
+oid sha256:edba4d57f0187cf743e1b6c7ddfd0e06b2deca6238518c157f79e43415e4b4a3
+size 133483316

runs/Nov07_08-52-09_9ff412d20608/events.out.tfevents.1730969541.9ff412d20608.162.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd7ac50601dec6ee762371da317fd689ae84c68e23656da2926af04e5cd98873
+size 6354

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e0ce5d81378faa54fe5934a832f5d49ab6d1f4118d9be8c096908833cd893c
+oid sha256:e8120feaf8d0b7a4d7d63758c864c6cbde0409bbb69e11c7e01cc73a94ba1bcf
 size 5304