Adzka/reward-model-distilbert-indo

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: cahya/distilbert-base-indonesian
+base_model: w11wo/indonesian-roberta-base-sentiment-classifier
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # test-reward-model
 
-This model is a fine-tuned version of [cahya/distilbert-base-indonesian](https://huggingface.co/cahya/distilbert-base-indonesian) on the None dataset.
+This model is a fine-tuned version of [w11wo/indonesian-roberta-base-sentiment-classifier](https://huggingface.co/w11wo/indonesian-roberta-base-sentiment-classifier) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8697
-- Accuracy: 0.6316
+- Loss: 0.8793
+- Accuracy: 0.6842
 
 ## Model description
 
@@ -49,14 +49,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.6672        | 1.25  | 50   | 0.5611          | 0.6316   |
-| 0.3793        | 2.5   | 100  | 0.6801          | 0.6579   |
-| 0.186         | 3.75  | 150  | 0.9431          | 0.6711   |
-| 0.0949        | 5.0   | 200  | 0.6777          | 0.6579   |
-| 0.0602        | 6.25  | 250  | 0.7489          | 0.6316   |
-| 0.0468        | 7.5   | 300  | 0.7410          | 0.6447   |
-| 0.0228        | 8.75  | 350  | 0.9266          | 0.6316   |
-| 0.019         | 10.0  | 400  | 0.8697          | 0.6316   |
+| 0.5782        | 1.25  | 50   | 0.6230          | 0.7237   |
+| 0.4206        | 2.5   | 100  | 0.5538          | 0.6842   |
+| 0.1611        | 3.75  | 150  | 0.6425          | 0.6974   |
+| 0.0803        | 5.0   | 200  | 0.7506          | 0.7105   |
+| 0.0571        | 6.25  | 250  | 0.9081          | 0.6842   |
+| 0.0222        | 7.5   | 300  | 1.0240          | 0.6842   |
+| 0.0132        | 8.75  | 350  | 0.9939          | 0.6579   |
+| 0.0275        | 10.0  | 400  | 0.8793          | 0.6842   |
 
 
 ### Framework versions

config.json

@@ -1,31 +1,39 @@
 {
-  "_name_or_path": "cahya/distilbert-base-indonesian",
-  "activation": "gelu",
+  "_name_or_path": "w11wo/indonesian-roberta-base-sentiment-classifier",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
-    "0": "LABEL_0"
+    "0": "positive",
+    "1": "neutral",
+    "2": "negative"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
-    "LABEL_0": 0
+    "negative": 2,
+    "neutral": 1,
+    "positive": 0
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_hidden_states": true,
-  "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": true,
-  "tie_weights_": true,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
-  "vocab_size": 32000
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

emissions.csv

@@ -1,3 +1,5 @@
 timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
 2024-07-02T00:11:50,codecarbon,e6298b50-8854-4fb6-a92d-43999c4601c4,338.201961517334,0.0106949476566119,3.162296164288756e-05,42.5,108.43,11.946327209472656,0.0039922668331199,0.0120461535139136,0.0011206903215284,0.0171591106685619,Indonesia,IDN,west java,,,Windows-10-10.0.19045-SP0,3.11.5,2.2.3,8,12th Gen Intel(R) Core(TM) i3-12100F,1,1 x NVIDIA GeForce RTX 3060,107.6071,-6.9217,31.85687255859375,machine,N,1.0
-2024-07-02T00:31:35,codecarbon,d29dc800-1005-4d6f-8e2e-8bab915a98a4,221.70085859298706,0.008340818735775607,3.762195053600684e-05,42.5,166.724,11.946327209472656,0.0026170430142018536,0.010030346762774322,0.0007347263725223773,0.013382116149498554,Indonesia,IDN,west java,,,Windows-10-10.0.19045-SP0,3.11.5,2.2.3,8,12th Gen Intel(R) Core(TM) i3-12100F,1,1 x NVIDIA GeForce RTX 3060,107.6071,-6.9217,31.85687255859375,machine,N,1.0
+2024-07-02T00:31:35,codecarbon,d29dc800-1005-4d6f-8e2e-8bab915a98a4,221.70085859298703,0.0083408187357756,3.762195053600684e-05,42.5,166.724,11.946327209472656,0.0026170430142018,0.0100303467627743,0.0007347263725223,0.0133821161494985,Indonesia,IDN,west java,,,Windows-10-10.0.19045-SP0,3.11.5,2.2.3,8,12th Gen Intel(R) Core(TM) i3-12100F,1,1 x NVIDIA GeForce RTX 3060,107.6071,-6.9217,31.85687255859375,machine,N,1.0
+2024-07-02T00:42:54,codecarbon,6fc0f284-35f7-4dc5-8cf7-feb218f26527,230.6575891971588,3.296991051028066e-05,1.429387631468697e-07,42.5,164.632,11.946327209472656,0.0027227585573991,0.0103819309014113,0.000764422072315,0.0138691115311254,Canada,CAN,quebec,,,Windows-10-10.0.19045-SP0,3.11.5,2.2.3,8,12th Gen Intel(R) Core(TM) i3-12100F,1,1 x NVIDIA GeForce RTX 3060,-71.2,46.8,31.85687255859375,machine,N,1.0
+2024-07-02T00:57:28,codecarbon,2fa201d4-63ba-449f-b4c0-0ed66ffe5a7e,659.3684051036835,0.021194644088943487,3.2143857553518506e-05,42.5,108.68900000000001,11.946327209472656,0.007783480898208091,0.024036789645381775,0.0021846872345928337,0.034004957778182694,Indonesia,IDN,west java,,,Windows-10-10.0.19045-SP0,3.11.5,2.2.3,8,12th Gen Intel(R) Core(TM) i3-12100F,1,1 x NVIDIA GeForce RTX 3060,107.6071,-6.9217,31.85687255859375,machine,N,1.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52c8b4a93c799a67bf0b574cd480842bd90cc6ab22bc095b5dc00ec43a5dec68
-size 272369900
+oid sha256:16ff3dffa9bd432f9c7c5a787a32ce0f46666e930134da98901df1c063f15bcd
+size 498615900

runs/Jul02_00-38-58_DESKTOP-HH0RPGN/events.out.tfevents.1719855544.DESKTOP-HH0RPGN.6200.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0373e113e5bfe8fa4c7bb95d6ed054f0978393a2b26dc26665e12953f44566c1
+size 9157

runs/Jul02_00-46-23_DESKTOP-HH0RPGN/events.out.tfevents.1719855988.DESKTOP-HH0RPGN.6200.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35432370fbd14d7c86a46c50b4408e6902ce0b4ffd94f3478bf6b13fcbd5fa74
+size 9521

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de0ed44dc3865bb9a68a129a145f8782eecf346d387339b335acb99144c27ea
+oid sha256:c3ac67df046b2d4c6b7e0d3fe78f624b663c0ff0a8b4bf0adcfb17bff0ab07be
 size 4920