Training in progress, step 500

config.json

@@ -1,27 +1,50 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "albert-base-v2",
   "architectures": [
-    "BertForSequenceClassification"
+    "AlbertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
   "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
   "initializer_range": 0.02,
+  "inner_group_num": 1,
   "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
+  "model_type": "albert",
+  "net_structure_type": 0,
   "num_attention_heads": 12,
+  "num_hidden_groups": 1,
   "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
   "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 30000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f17c71dd49cec310a5b2255e6b38707197411daca82c3bfef08befb8d318668
-size 437958648
+oid sha256:52c245304e83aee3ce4b087797393147ee7781cc59432e34ce7c452e555871dd
+size 46756216

runs/Mar11_02-17-04_ebad219a5e6d/events.out.tfevents.1710123443.ebad219a5e6d.2185.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef3cc0b274be9ab556cd8ed82ee7e319893c48cff491bc5153a3f5f015155b0
+size 5527

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:112da97fdd0597e69cd1ea2408bcdf4be1810c253eaa73d63864d4320a2349bf
+oid sha256:ba4bbca5104c96f3eae07ce3d8729ffd7a2b1a0217fd343ee805bf0bda4cc182
 size 4920