Training completed!

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:
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # distilbert-base-uncased-finetuned-stationary-update
 
-This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.7653
-- Accuracy: 0.78
-- F1: 0.7754
+- Loss: 1.0900
+- Accuracy: 0.6433
+- F1: 0.6299
 
 ## Model description
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 0.6107        | 1.0   | 38   | 0.5478          | 0.6733   | 0.5542 |
-| 0.4795        | 2.0   | 76   | 0.4683          | 0.7867   | 0.7822 |
-| 0.375         | 3.0   | 114  | 0.4781          | 0.7867   | 0.7822 |
-| 0.2975        | 4.0   | 152  | 0.5327          | 0.7767   | 0.7739 |
-| 0.2132        | 5.0   | 190  | 0.6008          | 0.7767   | 0.7663 |
-| 0.166         | 6.0   | 228  | 0.6748          | 0.7633   | 0.7534 |
-| 0.1366        | 7.0   | 266  | 0.7065          | 0.77     | 0.7593 |
-| 0.0883        | 8.0   | 304  | 0.7413          | 0.7733   | 0.7652 |
-| 0.0831        | 9.0   | 342  | 0.7618          | 0.77     | 0.7613 |
-| 0.0684        | 10.0  | 380  | 0.7653          | 0.78     | 0.7754 |
+| 0.6574        | 1.0   | 38   | 0.6395          | 0.6667   | 0.5333 |
+| 0.6401        | 2.0   | 76   | 0.6525          | 0.6667   | 0.5333 |
+| 0.6219        | 3.0   | 114  | 0.6405          | 0.6667   | 0.5333 |
+| 0.5799        | 4.0   | 152  | 0.6763          | 0.5367   | 0.5474 |
+| 0.4911        | 5.0   | 190  | 0.6744          | 0.6      | 0.6091 |
+| 0.4344        | 6.0   | 228  | 0.7307          | 0.61     | 0.6160 |
+| 0.3324        | 7.0   | 266  | 0.8688          | 0.6167   | 0.6081 |
+| 0.2567        | 8.0   | 304  | 0.9367          | 0.6333   | 0.6304 |
+| 0.1934        | 9.0   | 342  | 1.0836          | 0.6233   | 0.6075 |
+| 0.1904        | 10.0  | 380  | 1.0900          | 0.6433   | 0.6299 |
 
 
 ### 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": "4.35.2",
-  "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 sha256:2ed32f5d7c771f9e0c71da5f0a8f5219b57b6b884d853d26b86bfddbab928c74
-size 267832560
+oid sha256:f00555a8e254e8fe7a020b332bbdb6dfe8948317dbec0d7ee7e25b46ad9bd6c5
+size 46743912

runs/Dec14_10-54-28_5ee824405939/events.out.tfevents.1702551281.5ee824405939.1473.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d7ed79dbe86843b542dacefb8e8ee0bbfba6c1480833eb1212db4e7324c369f
+size 10053

special_tokens_map.json

@@ -1,7 +1,15 @@
 {
+  "bos_token": "[CLS]",
   "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
   "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "unk_token": "<unk>"
 }

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

tokenizer_config.json

@@ -1,22 +1,22 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
+    "1": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
+    "2": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "102": {
+    "3": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,24 +32,27 @@
       "single_word": false,
       "special": true
     },
-    "103": {
+    "4": {
       "content": "[MASK]",
-      "lstrip": false,
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "[CLS]",
   "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "[PAD]",
+  "pad_token": "<pad>",
+  "remove_space": true,
   "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eeb1b7d6ba2803f3167b2096e4f0681de0e860f00cf928fd88cb7e71244977b
+oid sha256:aa2993e551c7579543ed699d4e3a39208ffcc0bce2bf03bf43961c91973e30a9
 size 4664