Training in progress, step 1386

config.json

@@ -1,15 +1,16 @@
 {
-  "_name_or_path": "indobenchmark/indobert-large-p2",
-  "_num_labels": 5,
+  "_name_or_path": "indolem/indobertweet-base-uncased",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "directionality": "bidi",
+  "eos_token_ids": 0,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -21,7 +22,7 @@
     "7": "LABEL_7"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -35,20 +36,15 @@
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
-  "pooler_fc_size": 768,
-  "pooler_num_attention_heads": 12,
-  "pooler_num_fc_layers": 3,
-  "pooler_size_per_head": 128,
-  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 31923
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff43b81d5456ed79197955151460048ae337893715dbeca6221f0d43c3e0f02b
-size 1340647360
+oid sha256:832bf6a484f5a7413177ae637dc3d04a93df506e6e8238d2d4316cc7474819ba
+size 442280976

runs/Jun17_12-01-03_34a384f90984/events.out.tfevents.1718625668.34a384f90984.35.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c1f5d4d37c2a4440e6753b55ed61d2551d10cc281e54ef9ce9e5bca6d39b962
+size 5270

runs/Jun17_12-02-01_34a384f90984/events.out.tfevents.1718625725.34a384f90984.35.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6026c3b062d1e17ce7c66e565208c49d6a385cede1198358fd315a60eafd98
+size 5270

runs/Jun17_12-02-21_34a384f90984/events.out.tfevents.1718625744.34a384f90984.35.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:544d6f03bf279bc284e79879877c452688fcfae4aa4b25328598e1c562d42cdc
+size 153088

tokenizer_config.json

@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "[CLS]",
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,7 +25,7 @@
       "special": true
     },
     "3": {
-      "content": "[SEP]",
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -33,7 +33,7 @@
       "special": true
     },
     "4": {
-      "content": "[MASK]",
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:111c8481d172ed012edca5066dc154abef9801174d271b17d00964b9c42c4793
+oid sha256:39b9a5b3f3669d8fc64f37abee5ab1b30d10f732e707c47f1c0d8e17701872ff
 size 5112