ashuc27/DistiliBert_emotions

README.md

@@ -1,10 +1,10 @@
 ---
 license: apache-2.0
-base_model: bert-base-uncased
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
-metrics:
-- accuracy
+datasets:
+- emotion
 model-index:
 - name: results
   results: []
@@ -15,10 +15,14 @@ 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 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: 1.6234
-- Accuracy: 0.7054
+- eval_loss: 1.8177
+- eval_accuracy: 0.0345
+- eval_runtime: 10.6974
+- eval_samples_per_second: 186.961
+- eval_steps_per_second: 11.685
+- step: 0
 
 ## Model description
 
@@ -37,23 +41,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2.8e-05
-- train_batch_size: 4
-- eval_batch_size: 64
+- 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: 3
 
-### Training results
-
-| Training Loss | Epoch | Step | Validation Loss | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.7149        | 1.0   | 716  | 0.6495          | 0.6346   |
-| 0.561         | 2.0   | 1432 | 0.9508          | 0.7089   |
-| 0.2295        | 3.0   | 2148 | 1.5088          | 0.7173   |
-
-
 ### Framework versions
 
 - Transformers 4.38.2

config.json

@@ -1,14 +1,13 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
   "architectures": [
-    "BertForSequenceClassification"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -18,7 +17,6 @@
     "5": "LABEL_5"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -27,17 +25,17 @@
     "LABEL_4": 4,
     "LABEL_5": 5
   },
-  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "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,
-  "use_cache": true,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28d5fda8bdbfb4833b67583bf5d4297ff2ebfd86b2f1033660bb3bd6ba15de41
-size 437970952
+oid sha256:93b50567c9209e758921f1dfb02ae7e291a63e870feb2443af4ddca5628361f2
+size 267844872

runs/Mar15_00-56-40_63a832ae8ab7/events.out.tfevents.1710464286.63a832ae8ab7.15461.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0a260156a04cb3a0ffdef9ec62bc9605bd0b52365e1c10f5f06e310aafbf1a
+size 346

runs/Mar15_01-09-10_63a832ae8ab7/events.out.tfevents.1710465036.63a832ae8ab7.20183.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71eeed3d1248b23c40d178e71c1cfc012905c89742c83f89d9f00ee00d4ab53a
+size 346

runs/Mar15_01-11-23_63a832ae8ab7/events.out.tfevents.1710465093.63a832ae8ab7.20183.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df706ee38ad138ec59fa1a3daa6bf58d97c708f0b1789daab9b5b198576fa89f
+size 346

runs/Mar15_01-14-01_63a832ae8ab7/events.out.tfevents.1710465251.63a832ae8ab7.20183.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79a4a465dbaa76cb512319bbe78eb1f137e9002f82482ce712e6cff428b2d288
+size 346

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9eb3e141ef2273dd9a8db7310724a881b781800037a627082affdc731af360f
+oid sha256:c90f26f1b131452e9fd4771cfb540b5196e03c1ac79954eebe0401eb92b9af6b
 size 4856