End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,6 +1,6 @@
 ---
 license: mit
-base_model: microsoft/deberta-v3-small
+base_model: MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7
 tags:
 - generated_from_trainer
 metrics:
@@ -15,10 +15,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # my-dear-watson-nli-model
 
-This model is a fine-tuned version of [microsoft/deberta-v3-small](https://huggingface.co/microsoft/deberta-v3-small) on the None dataset.
+This model is a fine-tuned version of [MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7](https://huggingface.co/MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.1118
-- Accuracy: 0.6972
+- Loss: 0.9620
+- Accuracy: 0.8540
 
 ## Model description
 
@@ -51,10 +51,10 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.9568        | 1.0   | 682  | 0.7779          | 0.6551   |
-| 0.719         | 2.0   | 1364 | 0.7380          | 0.6881   |
-| 0.4004        | 3.0   | 2046 | 0.9168          | 0.6832   |
-| 0.2709        | 4.0   | 2728 | 1.1118          | 0.6972   |
+| 0.4765        | 1.0   | 682  | 0.4576          | 0.8267   |
+| 0.3844        | 2.0   | 1364 | 0.5010          | 0.8325   |
+| 0.1273        | 3.0   | 2046 | 0.7488          | 0.8540   |
+| 0.052         | 4.0   | 2728 | 0.9620          | 0.8540   |
 
 
 ### Framework versions

added_tokens.json

@@ -1,3 +1,3 @@
 {
-  "[MASK]": 128000
+  "[MASK]": 250101
 }

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "microsoft/deberta-v3-small",
+  "_name_or_path": "MoritzLaurer/mDeBERTa-v3-base-xnli-multilingual-nli-2mil7",
   "architectures": [
     "DebertaV2ForSequenceClassification"
   ],
@@ -25,7 +25,7 @@
   "model_type": "deberta-v2",
   "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "pooler_dropout": 0,
   "pooler_hidden_act": "gelu",
@@ -41,5 +41,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.40.0",
   "type_vocab_size": 0,
-  "vocab_size": 128100
+  "vocab_size": 251000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e6a9c0a301aad3ba74dbe1b752d54e854edc5cb69fd3c6526edf399af9f5e1
-size 567601628
+oid sha256:9f73b717e97fba0bd7a07ba80d8826c75bb582f758609fb0e56483eb258e450b
+size 1115271284

special_tokens_map.json

@@ -1,14 +1,50 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
+  "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
+  },
   "unk_token": {
     "content": "[UNK]",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

spm.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
-size 2464616
+oid sha256:13c8d666d62a7bc4ac8f040aab68e942c861f93303156cc28f5c7e885d86d6e3
+size 4305025

tokenizer_config.json

@@ -27,12 +27,12 @@
     "3": {
       "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "128000": {
+    "250101": {
       "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
@@ -47,12 +47,16 @@
   "do_lower_case": false,
   "eos_token": "[SEP]",
   "mask_token": "[MASK]",
+  "max_length": 512,
   "model_max_length": 512,
   "pad_token": "[PAD]",
   "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:dcc0d60b2e0df1e6194a7e5c5f56d3b1c6c4cfa00bf23f23cfdfe4775780a544
+oid sha256:3a6852d51a5a877a45c81587cd414548fe12bc6dc53cdb6110895d28fd3231d7
 size 4984