Training in progress, step 500

config.json

@@ -1,43 +1,34 @@
 {
-  "_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 sha256:5c67350f715d2af72923d66487441625829de41f0a2d7d52b2574a1e9800937e
-size 437970952
+oid sha256:a5b75ef24938d9785df5fc922574db3be81f32abf95f12012d74d4cefc3a4e46
+size 46743912

runs/Mar11_03-21-56_ebad219a5e6d/events.out.tfevents.1710127317.ebad219a5e6d.2185.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b8f59230cf3b63a5c6e968ba4df731a14d4d8de92cbe0945a02b712082cb20
+size 5743

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0c93e6b798575137b867a40931f84b732fedaa5f0ead704026bb4ec5f33c7ed
+oid sha256:a89d981b6c77c4b865598567ba8078b5c04cddc89be6ec115b4c0d666b32c9c1
 size 4920