End of training

README.md

@@ -1,6 +1,6 @@
 ---
-license: mit
-base_model: indobenchmark/indobert-large-p2
+license: apache-2.0
+base_model: indolem/indobertweet-base-uncased
 tags:
 - generated_from_trainer
 model-index:
@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 # buburayam2024_p2_14_asli
 
-This model is a fine-tuned version of [indobenchmark/indobert-large-p2](https://huggingface.co/indobenchmark/indobert-large-p2) on the None dataset.
+This model is a fine-tuned version of [indolem/indobertweet-base-uncased](https://huggingface.co/indolem/indobertweet-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.0210
-- F1 macro: 0.3791
-- Weighted: 0.5964
-- Balanced accuracy: 0.4977
+- Loss: 2.3478
+- F1 macro: 0.3466
+- Weighted: 0.5394
+- Balanced accuracy: 0.4857
 
 ## Model description
 
@@ -43,26 +43,19 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 14
+- num_epochs: 7
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | F1 macro | Weighted | Balanced accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:-----------------:|
-| 1.1074        | 1.0   | 154  | 1.2377          | 0.3519   | 0.6293   | 0.4548            |
-| 0.7157        | 2.0   | 308  | 1.2606          | 0.3927   | 0.5965   | 0.4757            |
-| 0.348         | 3.0   | 462  | 1.7488          | 0.4201   | 0.5722   | 0.5450            |
-| 0.1433        | 4.0   | 616  | 2.1221          | 0.4589   | 0.6046   | 0.5166            |
-| 0.0748        | 5.0   | 770  | 2.4451          | 0.3833   | 0.5914   | 0.5034            |
-| 0.0016        | 6.0   | 924  | 2.8787          | 0.3869   | 0.5620   | 0.5239            |
-| 0.0004        | 7.0   | 1078 | 2.0919          | 0.4192   | 0.6759   | 0.4867            |
-| 0.0003        | 8.0   | 1232 | 2.8603          | 0.3797   | 0.5930   | 0.5068            |
-| 0.0485        | 9.0   | 1386 | 2.6217          | 0.3914   | 0.6340   | 0.4941            |
-| 0.0002        | 10.0  | 1540 | 3.1652          | 0.3623   | 0.5676   | 0.4882            |
-| 0.0002        | 11.0  | 1694 | 3.0986          | 0.3719   | 0.5822   | 0.4951            |
-| 0.0002        | 12.0  | 1848 | 3.0331          | 0.3763   | 0.5917   | 0.4968            |
-| 0.0002        | 13.0  | 2002 | 3.0254          | 0.3778   | 0.5940   | 0.4973            |
-| 0.0001        | 14.0  | 2156 | 3.0210          | 0.3791   | 0.5964   | 0.4977            |
+| 1.3473        | 1.0   | 93   | 1.4538          | 0.3261   | 0.5837   | 0.4352            |
+| 0.9979        | 2.0   | 186  | 1.4648          | 0.3461   | 0.5112   | 0.4916            |
+| 0.5325        | 3.0   | 279  | 1.8786          | 0.3325   | 0.5012   | 0.4817            |
+| 0.2097        | 4.0   | 372  | 2.2614          | 0.3081   | 0.4708   | 0.4584            |
+| 0.1208        | 5.0   | 465  | 2.0293          | 0.3620   | 0.5624   | 0.4896            |
+| 0.0695        | 6.0   | 558  | 2.4287          | 0.3513   | 0.5322   | 0.4986            |
+| 0.0129        | 7.0   | 651  | 2.3478          | 0.3466   | 0.5394   | 0.4857            |
 
 
 ### Framework versions

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": "Sumber Daya Alam",
     "1": "Politik",
@@ -21,31 +22,19 @@
     "7": "Geografi"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4
-  },
+  "intermediate_size": 3072,
   "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:af84cf29983426fb96b1b4f406412895d86e8a8227c72cce5008d3383ec7e961
-size 1340647360
+oid sha256:27150179b56d170b0e3b4170d41cdf2416a4b8edbd0bb2fccd887b254fcc7175
+size 442280976

runs/Jun19_18-13-12_80516ee61c48/events.out.tfevents.1718822265.80516ee61c48.721.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3078d3fa058cc35404d1d8eb2917c279e3ed2c75afb453290c2507b8cd23493c
+size 524

runs/Jun19_18-54-03_80516ee61c48/events.out.tfevents.1718823244.80516ee61c48.721.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e404b693842b6bcc6b545d839d01803cc68b94a52bc7bbf20e06e8009393d8
+size 22242

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c48c71a90575444fdb62b1414f5699cdadbf8f76cc9895ca2a8097e3d4d103ea
+oid sha256:bd1e83d2019953804d961e797d89dcf8be3d35e7975273b0ed258b96884a5d92
 size 5176