your_username/bert-emotion

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: bert-base-uncased
 tags:
 - generated_from_trainer
 metrics:
@@ -13,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2400
-- Accuracy: 0.8996
+- Loss: 0.3016
+- Accuracy: 0.903
 
 ## Model description
 
@@ -35,34 +37,29 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.001
+- learning_rate: 2e-05
 - train_batch_size: 16
-- eval_batch_size: 8
+- eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 500
-- num_epochs: 10
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 28   | 1.3861          | 0.2679   |
-| No log        | 2.0   | 56   | 1.3857          | 0.2723   |
-| No log        | 3.0   | 84   | 1.3847          | 0.3304   |
-| No log        | 4.0   | 112  | 1.3618          | 0.5759   |
-| No log        | 5.0   | 140  | 0.8967          | 0.6763   |
-| No log        | 6.0   | 168  | 0.5932          | 0.7969   |
-| No log        | 7.0   | 196  | 0.4044          | 0.8638   |
-| No log        | 8.0   | 224  | 0.3016          | 0.9129   |
-| No log        | 9.0   | 252  | 0.3303          | 0.8772   |
-| No log        | 10.0  | 280  | 0.2400          | 0.8996   |
+| 1.4263        | 0.16  | 100  | 1.1397          | 0.592    |
+| 0.9469        | 0.32  | 200  | 0.7879          | 0.746    |
+| 0.6107        | 0.48  | 300  | 0.4802          | 0.846    |
+| 0.4503        | 0.64  | 400  | 0.3855          | 0.874    |
+| 0.3673        | 0.8   | 500  | 0.3477          | 0.894    |
+| 0.3684        | 0.96  | 600  | 0.3263          | 0.89     |
 
 
 ### Framework versions
 
-- Transformers 4.38.2
-- Pytorch 2.1.0+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

config.json

@@ -1,23 +1,42 @@
 {
+  "_name_or_path": "bert-base-uncased",
   "architectures": [
-    "BertForMultipleChoice"
+    "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 512,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 2,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.41.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3aff7a89e5b24423fe862cc9f97467fb9580fea288665f5eaccb1b5a1a94c2
-size 98238980
+oid sha256:ce3fc13e81b1d39b0fdf519926c9f873589bbf9b211c9bca89e625060b5bd5fa
+size 437970952

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a4b6bddb543d9adde16de112b08495c03beba481f55395e1276365fbff3377
-size 4856
+oid sha256:8935652563d38ea488b568defde6f119b23f4c7b231846f9a6ec29ba1eeca4f5
+size 5048