Training completed!

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: albert-base-v2
+base_model: distilbert-base-uncased
 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 [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
+This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0900
-- Accuracy: 0.6433
-- F1: 0.6299
+- Loss: 0.7730
+- Accuracy: 0.7833
+- F1: 0.7806
 
 ## Model description
 
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 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 |
+| 0.6079        | 1.0   | 38   | 0.5325          | 0.7      | 0.6134 |
+| 0.4686        | 2.0   | 76   | 0.4729          | 0.7867   | 0.7849 |
+| 0.3713        | 3.0   | 114  | 0.4896          | 0.8033   | 0.8009 |
+| 0.2955        | 4.0   | 152  | 0.5363          | 0.78     | 0.7782 |
+| 0.2141        | 5.0   | 190  | 0.6037          | 0.7867   | 0.7782 |
+| 0.1664        | 6.0   | 228  | 0.6722          | 0.7633   | 0.7554 |
+| 0.1343        | 7.0   | 266  | 0.6951          | 0.79     | 0.7829 |
+| 0.0854        | 8.0   | 304  | 0.7358          | 0.77     | 0.7678 |
+| 0.0888        | 9.0   | 342  | 0.7616          | 0.7767   | 0.7724 |
+| 0.0669        | 10.0  | 380  | 0.7730          | 0.7833   | 0.7806 |
 
 
 ### Framework versions

config.json

@@ -1,34 +1,25 @@
 {
-  "_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,
   "initializer_range": 0.02,
-  "inner_group_num": 1,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
   "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": "4.35.2",
-  "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:f00555a8e254e8fe7a020b332bbdb6dfe8948317dbec0d7ee7e25b46ad9bd6c5
-size 46743912
+oid sha256:f406fb213669022deeedef9a56cba802591de18fb1d5815e4bb16c2d687a084c
+size 267832560

runs/Dec14_11-11-16_3db6737419e9/events.out.tfevents.1702552282.3db6737419e9.1045.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97057110177bbd52f38f4f13c0e9c90f98b3c96c3f1baebaa069f3b0d23386a
+size 9779

special_tokens_map.json

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

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
     },
-    "1": {
-      "content": "<unk>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
+    "101": {
       "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
@@ -24,7 +24,7 @@
       "single_word": false,
       "special": true
     },
-    "3": {
+    "102": {
       "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
@@ -32,27 +32,24 @@
       "single_word": false,
       "special": true
     },
-    "4": {
+    "103": {
       "content": "[MASK]",
-      "lstrip": true,
+      "lstrip": false,
       "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>",
-  "remove_space": true,
+  "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "sp_model_kwargs": {},
-  "tokenizer_class": "AlbertTokenizer",
-  "unk_token": "<unk>"
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2993e551c7579543ed699d4e3a39208ffcc0bce2bf03bf43961c91973e30a9
+oid sha256:45a7f80eb75c2fb52e6f739532cf8c84bd72b539d06137bc5b7e36e4cc71f0c7
 size 4664