Uploaded model.

README.md

@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the msra_ner dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0474
-- F1: 0.9211
+- Loss: 0.0661
+- F1: 0.8221
 
 ## Model description
 
@@ -40,8 +40,8 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 12
-- eval_batch_size: 12
+- train_batch_size: 48
+- eval_batch_size: 48
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -49,13 +49,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step  | Validation Loss | F1     |
-|:-------------:|:-----:|:-----:|:---------------:|:------:|
-| 0.0751        | 1.0   | 3751  | 0.0426          | 0.8744 |
-| 0.0319        | 2.0   | 7502  | 0.0408          | 0.8897 |
-| 0.018         | 3.0   | 11253 | 0.0404          | 0.9102 |
-| 0.0095        | 4.0   | 15004 | 0.0421          | 0.9150 |
-| 0.0045        | 5.0   | 18755 | 0.0474          | 0.9211 |
+| Training Loss | Epoch | Step | Validation Loss | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.1946        | 1.0   | 938  | 0.0948          | 0.6865 |
+| 0.0744        | 2.0   | 1876 | 0.0813          | 0.7592 |
+| 0.0466        | 3.0   | 2814 | 0.0697          | 0.7956 |
+| 0.0307        | 4.0   | 3752 | 0.0655          | 0.8104 |
+| 0.0219        | 5.0   | 4690 | 0.0661          | 0.8221 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efda69d0db1693c6938e674d27826dada7689d7f940b00da2f5e45651f3d8d98
+oid sha256:fd153ee9c2aea0ea881733091a5079bb6f14aa470c080503d59a38779f8930b3
 size 1109857804

runs/Nov09_19-30-07_223feb2fe375/events.out.tfevents.1699558216.223feb2fe375.6517.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66900a3c693661bcf1347f33d0deabda4c4e8a0f6a03aac2d7c815a0f0dc5d96
+size 7402

special_tokens_map.json

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

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19232daba569c004c5fbe45f373ccaf2ee505055da00969f78a99e5754db8f25
-size 17082688
+oid sha256:48cea5d44424912a6fd1ea647bf4fe50b55ab8b1e5879c3275f80e339e8fae26
+size 439125

tokenizer_config.json

@@ -1,54 +1,55 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "250001": {
-      "content": "<mask>",
-      "lstrip": true,
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "XLMRobertaTokenizer",
-  "unk_token": "<unk>"
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c08714eee494993e872738b2f7cae62d9e6226ef55b84ed06f9249cafdc1776
+oid sha256:58a44cbfb8de0ef1e39d722afda0d2e03e7042e1fb0b66b90e673fe2f6c4f76f
 size 4664