End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: distilbert-base-uncased
+base_model: albert-base-v2
 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 [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8835
-- Accuracy: 0.6862
+- Loss: 0.7940
+- Accuracy: 0.6556
 
 ## Model description
 
@@ -37,21 +37,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
+- learning_rate: 7.45e-06
 - 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
+- num_epochs: 4
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 179  | 0.6302          | 0.6440   |
-| No log        | 2.0   | 358  | 0.6395          | 0.6712   |
-| 0.4692        | 3.0   | 537  | 0.8529          | 0.6764   |
+| 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   |
 
 
 ### Framework versions

config.json

@@ -1,25 +1,34 @@
 {
-  "_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,
   "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "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:f69324d10cdc73964c32464f405ad0069c508e9f932626911a28d379bbc8d2e0
-size 267832560
+oid sha256:55c21def950937d603e0c5209b8f4919e6ccd850fa82bf7502bb5b87db480922
+size 46743912

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:370f97111278dc5bae72fbbf275aed53cb61ea6388e34a2a26d1d6ae9fb34780
+oid sha256:a89d981b6c77c4b865598567ba8078b5c04cddc89be6ec115b4c0d666b32c9c1
 size 4920