eng_subcate

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: tangminhanh/eng_cate
+base_model: microsoft/deberta-v3-small
 tags:
 - generated_from_trainer
 metrics:
@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # eng_subcate
 
-This model is a fine-tuned version of [tangminhanh/eng_cate](https://huggingface.co/tangminhanh/eng_cate) on the None dataset.
+This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0618
+- Loss: 0.0837
 - Accuracy: 0.0
 - F1: 0.0
 - Precision: 0.0
@@ -44,8 +44,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- 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
@@ -55,11 +55,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1  | Precision | Recall |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|:---------:|:------:|
-| No log        | 1.0   | 106  | 0.1322          | 0.0      | 0.0 | 0.0       | 0.0    |
-| No log        | 2.0   | 212  | 0.0709          | 0.0      | 0.0 | 0.0       | 0.0    |
-| No log        | 3.0   | 318  | 0.0638          | 0.0      | 0.0 | 0.0       | 0.0    |
-| No log        | 4.0   | 424  | 0.0622          | 0.0      | 0.0 | 0.0       | 0.0    |
-| 0.1331        | 5.0   | 530  | 0.0618          | 0.0      | 0.0 | 0.0       | 0.0    |
+| No log        | 1.0   | 53   | 0.3166          | 0.0      | 0.0 | 0.0       | 0.0    |
+| No log        | 2.0   | 106  | 0.1509          | 0.0      | 0.0 | 0.0       | 0.0    |
+| No log        | 3.0   | 159  | 0.1024          | 0.0      | 0.0 | 0.0       | 0.0    |
+| No log        | 4.0   | 212  | 0.0874          | 0.0      | 0.0 | 0.0       | 0.0    |
+| No log        | 5.0   | 265  | 0.0837          | 0.0      | 0.0 | 0.0       | 0.0    |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "tangminhanh/eng_cate",
+  "_name_or_path": "microsoft/deberta-v3-small",
   "architectures": [
     "DebertaV2ForSequenceClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e4dd4d00e77e0866d2e670ccb91ed6284ceecfeb166446dc265fbf6ddd2f1b8
+oid sha256:4312f37a25e0576e90f562f8f21456baffbb3aa12b79eb2c0be8fb2d1519446c
 size 567826192

runs/Jul30_05-59-44_c03b3356afb4/events.out.tfevents.1722319188.c03b3356afb4.2693.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be54e7e874928e65e2ebfce986ef5af2f37696e74e40bf9b6672a8bc303ef09
+size 13739

runs/Jul30_05-59-44_c03b3356afb4/events.out.tfevents.1722319501.c03b3356afb4.2693.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:439d4495448a0cabbf70c1b77cde73ebac3c62778bce7b1a78ba3f530cfb487c
+size 560

special_tokens_map.json

@@ -1,46 +1,10 @@
 {
-  "bos_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "[CLS]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "mask_token": {
-    "content": "[MASK]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "[PAD]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "[SEP]",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,

tokenizer_config.json

@@ -47,19 +47,12 @@
   "do_lower_case": false,
   "eos_token": "[SEP]",
   "mask_token": "[MASK]",
-  "max_length": 512,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
   "sp_model_kwargs": {},
   "split_by_punct": false,
-  "stride": 0,
   "tokenizer_class": "DebertaV2Tokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": "[UNK]",
   "vocab_type": "spm"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b94e93ff9656c6eb8ddd2a1601739adff98b6a7977b11a0de7ccd45cd5c0e17e
+oid sha256:8ba617718869a282dea248cf017e1705f747fdfc5bd996e552a9fd558b9e35b9
 size 5112