djsull/binary_every_exp

README.md

@@ -1,5 +1,5 @@
 ---
-base_model: klue/roberta-small
+base_model: klue/roberta-large
 tags:
 - generated_from_trainer
 metrics:
@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # binary_every_exp
 
-This model is a fine-tuned version of [klue/roberta-small](https://huggingface.co/klue/roberta-small) on an unknown dataset.
+This model is a fine-tuned version of [klue/roberta-large](https://huggingface.co/klue/roberta-large) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0009
+- Loss: 0.0005
 - Precision: 1.0
 - Recall: 1.0
 - F1: 1.0
@@ -43,8 +43,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 64
-- eval_batch_size: 32
+- train_batch_size: 32
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -54,14 +54,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
-| No log        | 1.0   | 10   | 0.1336          | 0.8947    | 1.0    | 0.9444 | 0.96     |
-| No log        | 2.0   | 20   | 0.0048          | 1.0       | 1.0    | 1.0    | 1.0      |
-| No log        | 3.0   | 30   | 0.0608          | 1.0       | 0.9412 | 0.9697 | 0.98     |
-| No log        | 4.0   | 40   | 0.0015          | 1.0       | 1.0    | 1.0    | 1.0      |
-| No log        | 5.0   | 50   | 0.0013          | 1.0       | 1.0    | 1.0    | 1.0      |
-| No log        | 6.0   | 60   | 0.0011          | 1.0       | 1.0    | 1.0    | 1.0      |
-| No log        | 7.0   | 70   | 0.0009          | 1.0       | 1.0    | 1.0    | 1.0      |
-| No log        | 8.0   | 80   | 0.0009          | 1.0       | 1.0    | 1.0    | 1.0      |
+| No log        | 1.0   | 19   | 0.0020          | 1.0       | 1.0    | 1.0    | 1.0      |
+| No log        | 2.0   | 38   | 0.0005          | 1.0       | 1.0    | 1.0    | 1.0      |
+| No log        | 3.0   | 57   | 0.0005          | 1.0       | 1.0    | 1.0    | 1.0      |
+| No log        | 4.0   | 76   | 0.0076          | 1.0       | 1.0    | 1.0    | 1.0      |
+| No log        | 5.0   | 95   | 0.1695          | 0.9375    | 1.0    | 0.9677 | 0.98     |
+| No log        | 6.0   | 114  | 0.1624          | 0.9375    | 1.0    | 0.9677 | 0.98     |
+| No log        | 7.0   | 133  | 0.0406          | 0.9375    | 1.0    | 0.9677 | 0.98     |
+| No log        | 8.0   | 152  | 0.0033          | 1.0       | 1.0    | 1.0    | 1.0      |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "klue/roberta-small",
+  "_name_or_path": "klue/roberta-large",
   "architectures": [
     "RobertaForSequenceClassification"
   ],
@@ -10,13 +10,13 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 1024,
   "id2label": {
     "0": "None",
     "1": "Profile"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4096,
   "label2id": {
     "None": 0,
     "Profile": 1
@@ -24,8 +24,8 @@
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,
   "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b42617ccbd8b9051ff9f9859e8b49efd8311475f347c2c2842559a3d1e4c337
-size 272382200
+oid sha256:b906e47e7791b77e7bcc430e70e3b0b0fe652f94b5ea08956795f5954476fa2e
+size 1346681920

runs/Aug23_01-45-11_129-146-79-76/events.out.tfevents.1724377512.129-146-79-76.1742119.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e38d672e410bf79798f63d1aed43f2948a1403857e2a7c563512f6590834eacd
+size 88

runs/Aug23_01-45-51_129-146-79-76/events.out.tfevents.1724377552.129-146-79-76.1742507.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59383615a9f345743e4b0d5dfc319b5ef2ebe41e2f8b6a86c39f3548e711f63d
+size 9186

runs/Aug23_01-45-51_129-146-79-76/events.out.tfevents.1724377808.129-146-79-76.1742507.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82dcd93975d5ae515ba72d69f9563a7b2ae840940156338ea85316a42eba40e1
+size 560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d7d8ddb500cf5ee4f3e7b37900114ecabaa5f452a684765f867b3128495ffbe
+oid sha256:fb02f8f3178acd5e1c1a4e90647dcd6d134d003b253393f7fc6ffbed06c99f0c
 size 5176