Training in progress, step 3000

config.json

@@ -1,18 +1,13 @@
 {
-  "_name_or_path": "albert-base-v2",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "AlbertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "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,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -22,8 +17,6 @@
     "5": "LABEL_5"
   },
   "initializer_range": 0.02,
-  "inner_group_num": 1,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -32,19 +25,17 @@
     "LABEL_4": 4,
     "LABEL_5": 5
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
-  "num_attention_heads": 12,
-  "num_hidden_groups": 1,
-  "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
-  "type_vocab_size": 2,
-  "vocab_size": 30000
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dce7133276c523e81b9cc0349df6ebe3e5c6d67c5b9365fe1848a7efcfd622d0
-size 46756216
+oid sha256:f9120426463e2c47a816a6cbbb7757350e3274a1199dc58f95bc75e2bba4488f
+size 267844872

runs/Mar11_03-12-38_1550443a5b04/events.out.tfevents.1710126767.1550443a5b04.3686.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84e6888ec39646d75120b215096239ddbb54b2ef6ca37cd9b08d7d98d1dfdfe4
-size 15447
+oid sha256:7cddc8b408c171db1d4ece29411591dc9e364a8b8aa690ac7eee0073a268b288
+size 15981

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b971d46c9e772e332c04ec73889b59da6d5e1b7bb456bdaeae20f555c12af4fb
-size 4856
+oid sha256:42cb9ab85c2a840f47a1a4ea0a41298b720b91f17578d6fa12fa811c7e3eefc6
+size 4920