vazish/paraphrase-multilingual-MiniLM-L12-v2

Browse files

Files changed (9) hide show

.gitattributes +2 -0
README.md +112 -52
config.json +22 -17
model.safetensors +2 -2
special_tokens_map.json +49 -5
tokenizer.json +0 -0
tokenizer_config.json +26 -17
training_args.bin +1 -1
unigram.json +3 -0

.gitattributes CHANGED Viewed

@@ -33,3 +33,5 @@ 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

 *.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
+unigram.json filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 library_name: transformers
 license: apache-2.0
-base_model: distilbert/distilbert-base-multilingual-cased
 tags:
 - generated_from_trainer
 metrics:
@@ -11,8 +11,6 @@ metrics:
 model-index:
 - name: fine-tuned-distilbert-autofill
   results: []
-datasets:
-- vazish/autofill_15_labels
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -20,42 +18,29 @@ should probably proofread and complete it, then remove this comment. -->
 # fine-tuned-distilbert-autofill
-This model is a fine-tuned version of [distilbert/distilbert-base-multilingual-cased](https://huggingface.co/distilbert/distilbert-base-multilingual-cased) on the [autofill_15_labels](https://huggingface.co/datasets/vazish/autofill_15_labels) dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2261
-- Precision: 0.9637
-- Recall: 0.9582
-- F1: 0.9601
-- Confusion Matrix: [[  93    7    0    0    0    0    0    0    0    0    0    0    0    0
-     0]
- [   9   49    0    0    0    0    0    0    0    0    0    0    0    0
-     0]
- [   0    0   51    0    0    0    0    0    0    0    0    0    0    0
-     9]
- [   0    0    0   33    0    0    0    0    1    1    0    0    0    0
-     0]
- [   0    0    1    0   66    0    0    0    0    0    0    0    0    0
-     9]
- [   0    0    0    0    0   53    0    0    1    1    0    0    0    0
-     0]
- [   0    0    0    0    0    0   37    1    0    0    0    0    0    0
-     3]
- [   0    0    0    0    0    0    4   35    0    0    0    0    0    0
-     2]
- [   0    0    0    0    0    1    0    0   46    0    0    0    0    0
-     0]
- [   0    0    0    0    0    0    0    0    0   32    0    0    0    0
-     0]
- [   0    0    0    0    0    0    0    2    0    0   12    0    0    0
-     0]
- [   0    0    0    0    0    0    0    1    0    0    1   16    0    0
-     0]
- [   0    0    0    0    0    0    0    0    0    1    0    0    5    0
-     0]
- [   0    0    0    0    0    0    0    0    0    1    0    0    0    5
-     0]
- [   2    0   39    3   12    0    4    0    6    1    2    0    3    1
-  2427]]
 ## Model description
@@ -80,22 +65,97 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
-| 0.902         | 1.0   | 598  | 0.2462          | 0.9202    | 0.9304 | 0.9208 |
-| 0.4122        | 2.0   | 1196 | 0.2071          | 0.9561    | 0.9456 | 0.9457 |
-| 0.2816        | 3.0   | 1794 | 0.2004          | 0.9566    | 0.9508 | 0.9518 |
-| 0.2272        | 4.0   | 2392 | 0.1930          | 0.9651    | 0.9595 | 0.9606 |
-| 0.1854        | 5.0   | 2990 | 0.2301          | 0.9593    | 0.9501 | 0.9529 |
-| 0.1064        | 6.0   | 3588 | 0.2330          | 0.9593    | 0.9518 | 0.9539 |
-| 0.0756        | 7.0   | 4186 | 0.2207          | 0.9641    | 0.9592 | 0.9606 |
-| 0.0815        | 8.0   | 4784 | 0.2203          | 0.9651    | 0.9615 | 0.9621 |
-| 0.0677        | 9.0   | 5382 | 0.2214          | 0.9636    | 0.9586 | 0.9602 |
-| 0.0579        | 10.0  | 5980 | 0.2261          | 0.9637    | 0.9582 | 0.9601 |
 ### Framework versions
@@ -103,4 +163,4 @@ The following hyperparameters were used during training:
 - Transformers 4.44.2
 - Pytorch 2.1.2
 - Datasets 2.19.2
-- Tokenizers 0.19.1

 ---
 library_name: transformers
 license: apache-2.0
+base_model: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
 tags:
 - generated_from_trainer
 metrics:
 model-index:
 - name: fine-tuned-distilbert-autofill
   results: []
 ---
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 # fine-tuned-distilbert-autofill
+This model is a fine-tuned version of [sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2](https://huggingface.co/sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2) on the None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.2367
+- Precision: 0.9484
+- Recall: 0.9473
+- F1: 0.9473
+- Confusion Matrix: [[ 94   5   0   0   0   0   0   0   0   0   0   0   0   0   1   0   0]
+ [ 14  44   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]
+ [  0   0 130   0   0   0   0   0   0   0   0   0   0   0   0   0   9]
+ [  0   0   0  33   0   0   0   0   0   0   0   0   0   0   2   0   0]
+ [  0   0   2   0  64   0   0   0   0   0   3   0   0   0   0   0   7]
+ [  0   0   0   0   0  53   0   0   0   0   0   0   0   0   2   0   0]
+ [  0   0   0   0   0   0  37   1   0   0   0   0   0   0   0   0   3]
+ [  0   0   0   0   0   0   4  35   0   0   0   0   0   0   0   0   2]
+ [  1   0   0   0   0   1   0   0  43   0   0   0   0   0   2   0   0]
+ [  0   0   0   0   0   0   0   0   0  31   0   0   0   0   1   0   0]
+ [  0   0   0   0   2   0   0   2   0   0  10   0   0   0   0   0   0]
+ [  0   0   0   0   0   0   0   1   0   0   1  16   0   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   1   0   0   5   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   0   0   0   0   6   0   0   0]
+ [  0   0   0   1   0   0   1   0   0   0   0   0   0   0  73   0   0]
+ [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   3   0]
+ [  1   0   9   1   4   0   0   0   2   0   2   0   1   2   1   0 977]]
 ## Model description
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 5
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Confusion Matrix                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|
+| 0.7726        | 1.0   | 987  | 0.3096          | 0.8920    | 0.9141 | 0.8988 | [[100   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]
+ [ 58   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]
+ [  0   0 129   0   0   0   0   0   0   0   0   0   0   0   0   0  10]
+ [  0   0   0  32   0   0   0   0   1   1   0   0   0   0   0   0   1]
+ [  0   0   4   0  63   0   0   0   0   0   0   0   0   0   0   0   9]
+ [  0   0   0   0   0  52   0   0   0   2   0   0   0   0   0   0   1]
+ [  0   0   0   0   0   0  36   0   0   0   2   0   0   0   0   0   3]
+ [  0   0   0   0   0   0   2  33   0   0   4   0   0   0   0   0   2]
+ [  1   0   0   0   0   1   0   0  43   2   0   0   0   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0  32   0   0   0   0   0   0   0]
+ [  0   0   0   0   2   0   0   0   0   0  12   0   0   0   0   0   0]
+ [  0   0   0   0   0   0   4   0   0   0   1  13   0   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   6   0   0   0   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   6   0   0   0   0   0   0   0]
+ [  0   0   0   0   0   0   1   0   1   2   0   0   0   0  71   0   0]
+ [  0   0   0   0   2   0   0   0   0   1   0   0   0   0   0   0   0]
+ [  1   0   7   1   5   0   0   0   1   3   1   0   0   0   1   0 980]] |
+| 0.2616        | 2.0   | 1974 | 0.2645          | 0.9356    | 0.9273 | 0.9179 | [[ 99   0   0   0   0   0   0   0   0   0   0   0   0   0   1   0   0]
+ [ 43   7   5   0   0   0   0   0   0   0   0   0   0   0   0   0   3]
+ [  0   0 128   0   0   0   0   0   0   0   0   0   0   0   0   0  11]
+ [  0   0   0  33   0   0   0   0   1   0   0   0   0   0   0   0   1]
+ [  0   0   0   0  64   0   0   0   0   0   0   0   0   0   0   0  12]
+ [  0   0   0   1   0  53   0   0   0   0   0   0   0   0   0   0   1]
+ [  0   0   0   0   0   0  36   2   0   0   0   0   0   0   0   0   3]
+ [  0   0   0   0   0   0   3  36   0   0   0   0   0   0   0   0   2]
+ [  1   0   0   0   0   2   0   0  43   0   0   0   0   0   0   0   1]
+ [  0   0   0   1   0   0   0   0   0  31   0   0   0   0   0   0   0]
+ [  0   0   0   0   2   0   0   3   0   0   9   0   0   0   0   0   0]
+ [  0   0   0   0   0   0   1   3   0   0   1  13   0   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   1   0   0   5   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   0   0   0   0   6   0   0   0]
+ [  0   0   0   1   0   0   1   0   1   1   0   0   0   0  71   0   0]
+ [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   3   0]
+ [  1   0   6   1   3   0   0   0   1   0   2   0   1   2   1   0 982]] |
+| 0.1814        | 3.0   | 2961 | 0.2332          | 0.9437    | 0.9422 | 0.9420 | [[ 94   5   0   0   0   0   0   0   0   0   0   0   0   0   1   0   0]
+ [ 15  43   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]
+ [  0   0 127   0   1   0   0   0   0   0   0   0   0   0   0   0  11]
+ [  0   0   0  34   0   0   0   0   0   0   0   0   0   0   0   0   1]
+ [  0   0   1   0  63   0   0   0   0   0   2   0   0   0   0   0  10]
+ [  0   0   0   1   0  52   0   0   0   1   1   0   0   0   0   0   0]
+ [  0   0   0   0   0   0  37   1   0   0   0   0   0   0   0   0   3]
+ [  0   0   0   0   0   0   4  35   0   0   0   0   0   0   0   0   2]
+ [  1   0   0   0   0   1   0   0  43   2   0   0   0   0   0   0   0]
+ [  0   0   0   1   0   0   0   0   0  31   0   0   0   0   0   0   0]
+ [  0   0   0   0   2   0   0   2   0   0  10   0   0   0   0   0   0]
+ [  0   0   0   0   0   0   2   2   0   0   1  13   0   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   1   0   0   5   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   0   0   0   0   6   0   0   0]
+ [  0   0   0   1   0   0   1   0   0   1   0   0   1   0  71   0   0]
+ [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   3   0]
+ [  1   0   8   1   4   0   0   1   1   0   2   0   1   2   1   0 978]] |
+| 0.1248        | 4.0   | 3948 | 0.2255          | 0.9501    | 0.9479 | 0.9482 | [[ 95   4   0   0   0   0   0   0   0   0   0   0   0   0   1   0   0]
+ [ 13  45   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]
+ [  0   0 130   0   0   0   0   0   0   0   0   0   0   0   0   0   9]
+ [  0   0   0  33   0   0   0   0   0   0   0   0   0   0   2   0   0]
+ [  0   0   2   0  65   0   0   0   0   0   4   0   0   0   0   0   5]
+ [  0   0   0   0   0  52   0   0   0   0   1   0   0   0   2   0   0]
+ [  0   0   0   0   0   0  38   0   0   0   0   0   0   0   0   0   3]
+ [  0   0   0   0   0   0   5  34   0   0   0   0   0   0   0   0   2]
+ [  1   0   0   0   0   1   0   0  43   0   0   0   0   0   2   0   0]
+ [  0   0   0   0   0   0   0   0   1  30   0   0   0   0   1   0   0]
+ [  0   0   0   0   2   0   2   0   0   0  10   0   0   0   0   0   0]
+ [  0   0   0   0   0   0   0   1   0   0   1  16   0   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   1   0   0   5   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   0   0   0   0   6   0   0   0]
+ [  0   0   0   1   0   0   1   0   0   0   0   0   0   0  73   0   0]
+ [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   3   0]
+ [  1   0   9   1   4   0   0   0   2   0   2   0   1   2   1   0 977]] |
+| 0.1032        | 5.0   | 4935 | 0.2367          | 0.9484    | 0.9473 | 0.9473 | [[ 94   5   0   0   0   0   0   0   0   0   0   0   0   0   1   0   0]
+ [ 14  44   0   0   0   0   0   0   0   0   0   0   0   0   0   0   0]
+ [  0   0 130   0   0   0   0   0   0   0   0   0   0   0   0   0   9]
+ [  0   0   0  33   0   0   0   0   0   0   0   0   0   0   2   0   0]
+ [  0   0   2   0  64   0   0   0   0   0   3   0   0   0   0   0   7]
+ [  0   0   0   0   0  53   0   0   0   0   0   0   0   0   2   0   0]
+ [  0   0   0   0   0   0  37   1   0   0   0   0   0   0   0   0   3]
+ [  0   0   0   0   0   0   4  35   0   0   0   0   0   0   0   0   2]
+ [  1   0   0   0   0   1   0   0  43   0   0   0   0   0   2   0   0]
+ [  0   0   0   0   0   0   0   0   0  31   0   0   0   0   1   0   0]
+ [  0   0   0   0   2   0   0   2   0   0  10   0   0   0   0   0   0]
+ [  0   0   0   0   0   0   0   1   0   0   1  16   0   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   1   0   0   5   0   0   0   0]
+ [  0   0   0   0   0   0   0   0   0   0   0   0   0   6   0   0   0]
+ [  0   0   0   1   0   0   1   0   0   0   0   0   0   0  73   0   0]
+ [  0   0   0   0   0   0   0   0   0   0   0   0   0   0   0   3   0]
+ [  1   0   9   1   4   0   0   0   2   0   2   0   1   2   1   0 977]] |
 ### Framework versions
 - Transformers 4.44.2
 - Pytorch 2.1.2
 - Datasets 2.19.2
+- Tokenizers 0.19.1

config.json CHANGED Viewed

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "distilbert/distilbert-base-multilingual-cased",
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -23,9 +24,12 @@
     "11": "LABEL_11",
     "12": "LABEL_12",
     "13": "LABEL_13",
-    "14": "LABEL_14"
   },
   "initializer_range": 0.02,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -34,6 +38,8 @@
     "LABEL_12": 12,
     "LABEL_13": 13,
     "LABEL_14": 14,
     "LABEL_2": 2,
     "LABEL_3": 3,
     "LABEL_4": 4,
@@ -43,18 +49,17 @@
     "LABEL_8": 8,
     "LABEL_9": 9
   },
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
   "pad_token_id": 0,
   "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": "4.44.2",
-  "vocab_size": 119547
 }

 {
+  "_name_or_path": "sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2",
   "architectures": [
+    "BertForSequenceClassification"
   ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
     "11": "LABEL_11",
     "12": "LABEL_12",
     "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 1536,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_12": 12,
     "LABEL_13": 13,
     "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
     "LABEL_2": 2,
     "LABEL_3": 3,
     "LABEL_4": 4,
     "LABEL_8": 8,
     "LABEL_9": 9
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ec8fa4b168d85eab3d8a71c9fe2f7a6991f3b3a9ba48307d85fb67d9c4e3b68
-size 541357364

 version https://git-lfs.github.com/spec/v1
+oid sha256:5d42a3ba75adf65462c2a5132b58cd0419eba6423439d38ef0895d9ce20b34dd
+size 470664764

special_tokens_map.json CHANGED Viewed

@@ -1,7 +1,51 @@
 {
-  "cls_token": "[CLS]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
 }

 {
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -1,55 +1,64 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "100": {
-      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "101": {
-      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "102": {
-      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "103": {
-      "content": "[MASK]",
-      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_lower_case": false,
-  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
   "strip_accents": null,
   "tokenize_chinese_chars": true,
-  "tokenizer_class": "DistilBertTokenizer",
-  "unk_token": "[UNK]"
 }

 {
   "added_tokens_decoder": {
     "0": {
+      "content": "<s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
+    "1": {
+      "content": "<pad>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
+    "2": {
+      "content": "</s>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
+    "3": {
+      "content": "<unk>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "max_length": 128,
   "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "stride": 0,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
 }

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291aa03153329af908c92a49b63a89dcf928a4a32e0ae2e64c63015ee3d6b40a
 size 5176

 version https://git-lfs.github.com/spec/v1
+oid sha256:76b894dfd5dfa4dd424ce8a12f04180f4166fafa716af6c53cc59dfe08c60790
 size 5176

unigram.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:da145b5e7700ae40f16691ec32a0b1fdc1ee3298db22a31ea55f57a966c4a65d
+size 14763260