ashuc27/Albert_tweetEval

README.md

@@ -1,13 +1,28 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: albert-base-v2
 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: 0.9305
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,14 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the emotion dataset.
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the emotion dataset.
 It achieves the following results on the evaluation set:
-- 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
+- Loss: 0.2314
+- Accuracy: 0.9305
 
 ## Model description
 
@@ -41,14 +52,23 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
+- learning_rate: 2.8e-05
+- train_batch_size: 4
+- eval_batch_size: 64
 - 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 |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.4298        | 1.0   | 4000  | 0.4243          | 0.9085   |
+| 0.2389        | 2.0   | 8000  | 0.3465          | 0.922    |
+| 0.1856        | 3.0   | 12000 | 0.2700          | 0.929    |
+
+
 ### Framework versions
 
 - Transformers 4.38.2

config.json

@@ -1,13 +1,18 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "albert-base-v2",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "AlbertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "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,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -17,6 +22,8 @@
     "5": "LABEL_5"
   },
   "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -25,17 +32,19 @@
     "LABEL_4": 4,
     "LABEL_5": 5
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
   "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",
-  "vocab_size": 30522
+  "type_vocab_size": 2,
+  "vocab_size": 30000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b50567c9209e758921f1dfb02ae7e291a63e870feb2443af4ddca5628361f2
-size 267844872
+oid sha256:28406c318314a09a392b68f9b5cf2bb3c584c75e616706e62b7d47f8cd706d14
+size 46756216

runs/Mar15_01-18-58_7e523dcb7947/events.out.tfevents.1710465561.7e523dcb7947.21996.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684a72d48660e76972937b21197799f9c64768d09a7870f7845c04e1b72aeb7a
+size 346

runs/Mar15_01-20-48_7e523dcb7947/events.out.tfevents.1710465673.7e523dcb7947.21996.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9601805a6bce2b53b248fb3f60cd91af1a3f2ba866bf94d198d93659b02f3a81
+size 346

runs/Mar15_01-22-22_7e523dcb7947/events.out.tfevents.1710465926.7e523dcb7947.21996.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb2989970de40543fe93693cc7da7a703f82c30deaea50309767b059ab1684b0
+size 11660

runs/Mar15_01-22-22_7e523dcb7947/events.out.tfevents.1710468056.7e523dcb7947.21996.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a34253b883cccc77b886f83fc81d753e13c6ea45f05f2b85123124592397a182
+size 1057

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c90f26f1b131452e9fd4771cfb540b5196e03c1ac79954eebe0401eb92b9af6b
+oid sha256:d235e97416679ab43ed03b93bfcb66dd82ad38ba15d06958a37f3bd034217efa
 size 4856