End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: microsoft/deberta-base
+base_model: microsoft/deberta-v3-base
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # deberta_textclassification
 
-This model is a fine-tuned version of [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) on the None dataset.
+This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3919
-- Accuracy: 0.9156
+- Loss: 0.3350
+- Accuracy: 0.9062
 
 ## Model description
 
@@ -37,7 +37,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
@@ -49,11 +49,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 180  | 0.2849          | 0.8906   |
-| No log        | 2.0   | 360  | 0.4328          | 0.8375   |
-| 0.3096        | 3.0   | 540  | 0.2765          | 0.9156   |
-| 0.3096        | 4.0   | 720  | 0.3247          | 0.9125   |
-| 0.3096        | 5.0   | 900  | 0.3919          | 0.9156   |
+| No log        | 1.0   | 180  | 0.2740          | 0.8875   |
+| No log        | 2.0   | 360  | 0.2828          | 0.8875   |
+| 0.3594        | 3.0   | 540  | 0.3322          | 0.8812   |
+| 0.3594        | 4.0   | 720  | 0.3220          | 0.9031   |
+| 0.3594        | 5.0   | 900  | 0.3350          | 0.9062   |
 
 
 ### Framework versions

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

runs/Sep04_16-42-01_0ecfd9ff1619/events.out.tfevents.1725468135.0ecfd9ff1619.2927.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30bf85c66824aec3e0d6e422bb2d59c21a1f5c8bcdc5d823eb1529f242c13884
-size 6573
+oid sha256:3983a9db16217bd94c6ed1501560c3d6a72b27cfe61af4cdd659ade1a2b24c22
+size 7250

special_tokens_map.json

@@ -1,50 +1,14 @@
 {
-  "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": true,
-    "normalized": true,
-    "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,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   }

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -1,6 +1,4 @@
 {
-  "add_bos_token": false,
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
       "content": "[PAD]",
@@ -29,15 +27,15 @@
     "3": {
       "content": "[UNK]",
       "lstrip": false,
-      "normalized": false,
+      "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
+    "128000": {
       "content": "[MASK]",
-      "lstrip": true,
-      "normalized": true,
+      "lstrip": false,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
@@ -48,19 +46,13 @@
   "cls_token": "[CLS]",
   "do_lower_case": false,
   "eos_token": "[SEP]",
-  "errors": "replace",
   "mask_token": "[MASK]",
-  "max_length": 195,
   "model_max_length": 1000000000000000019884624838656,
-  "pad_to_multiple_of": null,
   "pad_token": "[PAD]",
-  "pad_token_type_id": 0,
-  "padding_side": "right",
   "sep_token": "[SEP]",
-  "stride": 0,
-  "tokenizer_class": "DebertaTokenizer",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
   "unk_token": "[UNK]",
-  "vocab_type": "gpt2"
+  "vocab_type": "spm"
 }