Training in progress, step 1000

config.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9120426463e2c47a816a6cbbb7757350e3274a1199dc58f95bc75e2bba4488f
-size 267844872
+oid sha256:1a4fb4121a149f4048e1c2dd87ecc3ec0267c6e2f13e447c56830de74cacd415
+size 46756216

runs/Mar11_03-19-39_ec0f357ed92c/events.out.tfevents.1710127199.ec0f357ed92c.1142.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05056e18b53756c05368be51e75a9148e9825a91e26156de04b90f512734cc3
-size 8375
+oid sha256:5afb2e034b4d12318717e7399c07fb461e9372d230dad5eb68e67a3ef610e164
+size 8909

training_args.bin

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