jointriple/brand_classification_2_20240628_model_1

README.md

@@ -1,6 +1,6 @@
 ---
-license: apache-2.0
-base_model: bert-base-uncased
+license: mit
+base_model: roberta-base
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7750
-- Accuracy: 0.9257
+- Loss: 0.3028
+- Accuracy: 0.9288
 
 ## Model description
 
@@ -37,26 +37,26 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 512
-- eval_batch_size: 512
+- learning_rate: 2e-05
+- train_batch_size: 128
+- eval_batch_size: 128
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
+- lr_scheduler_warmup_steps: 1000
 - num_epochs: 7
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 6.4334        | 1.0   | 593  | 6.1799          | 0.3660   |
-| 4.3096        | 2.0   | 1186 | 3.9473          | 0.8412   |
-| 2.6773        | 3.0   | 1779 | 2.3788          | 0.9079   |
-| 1.7389        | 4.0   | 2372 | 1.5072          | 0.9197   |
-| 1.1692        | 5.0   | 2965 | 1.0537          | 0.9236   |
-| 0.9072        | 6.0   | 3558 | 0.8410          | 0.9254   |
-| 0.7699        | 7.0   | 4151 | 0.7750          | 0.9257   |
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 5.8594        | 1.0   | 2371  | 5.3310          | 0.8132   |
+| 3.1041        | 2.0   | 4742  | 2.7193          | 0.8936   |
+| 1.9352        | 3.0   | 7113  | 1.3843          | 0.9116   |
+| 0.9755        | 4.0   | 9484  | 0.7382          | 0.9176   |
+| 0.537         | 5.0   | 11855 | 0.4559          | 0.9198   |
+| 0.5705        | 6.0   | 14226 | 0.3554          | 0.9236   |
+| 0.2824        | 7.0   | 16597 | 0.3028          | 0.9288   |
 
 
 ### Framework versions

config.json

@@ -1,11 +1,12 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "BertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
+  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -4187,17 +4188,17 @@
     "\u0394\u03b9\u03bf\u03b4\u03b9\u03b1": 2084,
     "\u0395\u03bb\u03af\u03bd": 2085
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 0,
+  "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.39.3",
-  "type_vocab_size": 2,
+  "type_vocab_size": 1,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 50265
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d7a19a8227ddd87e6e3b53f02dd08fd910ce3bc82c9c5a75589343514b08cb
-size 444369032
+oid sha256:2094f4135f79892f0b142cf7b392dc7f37a00be5444a7fc941c9bdd83deae718
+size 505023216

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ead15358f313b14eaa0fa2c68ea7494eb00a2343e4786eb4d5f55e17a5c99701
+oid sha256:271d7a2b9f13f45967aac087fb6d36fb65cb899900c01193e090d0f923ecf37e
 size 4856