Training complete

README.md

@@ -1,5 +1,6 @@
 ---
 license: apache-2.0
+base_model: distilbert-base-uncased
 tags:
 - generated_from_trainer
 datasets:
@@ -21,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9458064516129032
+      value: 0.9341935483870968
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -31,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the clinc_oos dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3003
-- Accuracy: 0.9458
+- Loss: 0.0586
+- Accuracy: 0.9342
 
 ## Model description
 
@@ -57,26 +58,27 @@ 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: 9
+- num_epochs: 10
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 4.1086        | 1.0   | 318  | 3.0771          | 0.7519   |
-| 2.3554        | 2.0   | 636  | 1.5490          | 0.8539   |
-| 1.1715        | 3.0   | 954  | 0.7930          | 0.9145   |
-| 0.5985        | 4.0   | 1272 | 0.4936          | 0.9319   |
-| 0.3437        | 5.0   | 1590 | 0.3741          | 0.9439   |
-| 0.2306        | 6.0   | 1908 | 0.3294          | 0.9439   |
-| 0.1752        | 7.0   | 2226 | 0.3079          | 0.9468   |
-| 0.1489        | 8.0   | 2544 | 0.3035          | 0.9458   |
-| 0.1375        | 9.0   | 2862 | 0.3003          | 0.9458   |
+| 0.5748        | 1.0   | 318  | 0.3326          | 0.6881   |
+| 0.2709        | 2.0   | 636  | 0.1687          | 0.8652   |
+| 0.1649        | 3.0   | 954  | 0.1127          | 0.9152   |
+| 0.1218        | 4.0   | 1272 | 0.0873          | 0.9219   |
+| 0.1           | 5.0   | 1590 | 0.0744          | 0.9290   |
+| 0.0879        | 6.0   | 1908 | 0.0673          | 0.9306   |
+| 0.0805        | 7.0   | 2226 | 0.0631          | 0.9365   |
+| 0.0757        | 8.0   | 2544 | 0.0607          | 0.9345   |
+| 0.073         | 9.0   | 2862 | 0.0592          | 0.9342   |
+| 0.0714        | 10.0  | 3180 | 0.0586          | 0.9342   |
 
 
 ### Framework versions
 
-- Transformers 4.26.1
-- Pytorch 1.13.1+cu116
-- Datasets 2.10.1
-- Tokenizers 0.13.2
+- Transformers 4.34.0
+- Pytorch 2.0.1+cu118
+- Datasets 2.14.5
+- Tokenizers 0.14.1

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "[CLS]": 101,
+  "[MASK]": 103,
+  "[PAD]": 0,
+  "[SEP]": 102,
+  "[UNK]": 100
+}

config.json

@@ -326,6 +326,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
+  "transformers_version": "4.34.0",
   "vocab_size": 30522
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30c63b6778e50518d5d98c7a5864f092ee5f0440f9dbca16c14f6368deb9162
+oid sha256:3b980810b4a416dc40ed808c24604bf7e91f662fec49f5608b01dbd60d963f2f
 size 268313837

tokenizer_config.json

@@ -1,12 +1,54 @@
 {
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
   "model_max_length": 512,
-  "name_or_path": "distilbert-base-uncased",
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
   "strip_accents": null,
   "tokenize_chinese_chars": true,
   "tokenizer_class": "DistilBertTokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdc7415f49cdd3d139a8e4edd293a3ec479e7695973422c41668abd2ba214b3b
-size 3643
+oid sha256:098e1ff64934b1fec3f5767aca9a4fa705657d2d7fce9cd74acf4df388985f9e
+size 4219