End of training

README.md

@@ -1,13 +1,28 @@
 ---
 license: apache-2.0
-base_model: albert-base-v2
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
+datasets:
+- emotion
 metrics:
 - accuracy
 model-index:
 - name: results
-  results: []
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: emotion
+      type: emotion
+      config: split
+      split: validation
+      args: split
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.927
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7940
-- Accuracy: 0.6556
+- Loss: 0.1888
+- Accuracy: 0.927
 
 ## Model description
 
@@ -37,22 +52,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 7.45e-06
+- learning_rate: 5e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 179  | 0.6503          | 0.6492   |
-| No log        | 2.0   | 358  | 0.7322          | 0.6565   |
-| 0.4518        | 3.0   | 537  | 0.7242          | 0.6649   |
-| 0.4518        | 4.0   | 716  | 0.7997          | 0.6586   |
+| 0.2348        | 1.0   | 1000 | 0.2163          | 0.9255   |
+| 0.1337        | 2.0   | 2000 | 0.1446          | 0.94     |
+| 0.0886        | 3.0   | 3000 | 0.1541          | 0.9425   |
 
 
 ### Framework versions

config.json

@@ -1,34 +1,41 @@
 {
-  "_name_or_path": "albert-base-v2",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "AlbertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0,
-  "bos_token_id": 2,
-  "classifier_dropout_prob": 0.1,
-  "down_scale_factor": 1,
-  "embedding_size": 128,
-  "eos_token_id": 3,
-  "gap_size": 0,
-  "hidden_act": "gelu_new",
-  "hidden_dropout_prob": 0,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
   "initializer_range": 0.02,
-  "inner_group_num": 1,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
   "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
-  "num_attention_heads": 12,
-  "num_hidden_groups": 1,
-  "num_hidden_layers": 12,
-  "num_memory_blocks": 0,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.38.2",
-  "type_vocab_size": 2,
-  "vocab_size": 30000
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c21def950937d603e0c5209b8f4919e6ccd850fa82bf7502bb5b87db480922
-size 46743912
+oid sha256:7d54e4c4738766f78da46d6cd0dded2a4577f0ccaf3b33bb75a896fb44324668
+size 267844872

runs/Mar11_04-37-43_f6b7ca2de819/events.out.tfevents.1710131875.f6b7ca2de819.11996.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824c47e6c92aac32a69795f7ac30153a45ff177f942c1ac433199e3864d41486
-size 6966
+oid sha256:036ad2794043d948b8f683a723bd9c0d565d54b8d38606e460db73b2fa313633
+size 7643

runs/Mar11_04-37-43_f6b7ca2de819/events.out.tfevents.1710132833.f6b7ca2de819.11996.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04341eea254b3869f528b833a9e23df03a14efc96c89330f3a7ae95442ebff6d
+size 411

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89d981b6c77c4b865598567ba8078b5c04cddc89be6ec115b4c0d666b32c9c1
+oid sha256:75b232ae5b88203fffec359819dd835494a78f15470739cd8dade60135b72c99
 size 4920