End of training

README.md

@@ -4,6 +4,11 @@ language:
 base_model: bayartsogt/mongolian-roberta-base
 tags:
 - generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
 model-index:
 - name: roberta-base-ner-demo
   results: []
@@ -15,6 +20,12 @@ should probably proofread and complete it, then remove this comment. -->
 # roberta-base-ner-demo
 
 This model is a fine-tuned version of [bayartsogt/mongolian-roberta-base](https://huggingface.co/bayartsogt/mongolian-roberta-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1755
+- Precision: 0.6435
+- Recall: 0.7245
+- F1: 0.6816
+- Accuracy: 0.9422
 
 ## Model description
 
@@ -41,9 +52,25 @@ The following hyperparameters were used during training:
 - lr_scheduler_type: linear
 - num_epochs: 10
 
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.8641        | 1.0   | 20   | 0.5621          | 0.1015    | 0.0475 | 0.0647 | 0.8218   |
+| 0.4142        | 2.0   | 40   | 0.3176          | 0.4453    | 0.4347 | 0.4399 | 0.8967   |
+| 0.2366        | 3.0   | 60   | 0.2381          | 0.5624    | 0.6105 | 0.5854 | 0.9218   |
+| 0.1456        | 4.0   | 80   | 0.2017          | 0.5864    | 0.6770 | 0.6284 | 0.9299   |
+| 0.0993        | 5.0   | 100  | 0.1808          | 0.6170    | 0.6888 | 0.6510 | 0.9336   |
+| 0.0679        | 6.0   | 120  | 0.1820          | 0.6410    | 0.7126 | 0.6749 | 0.9403   |
+| 0.0484        | 7.0   | 140  | 0.1752          | 0.6439    | 0.7173 | 0.6787 | 0.9408   |
+| 0.0409        | 8.0   | 160  | 0.1747          | 0.6358    | 0.7173 | 0.6741 | 0.9403   |
+| 0.0374        | 9.0   | 180  | 0.1744          | 0.6369    | 0.7292 | 0.6800 | 0.9412   |
+| 0.0383        | 10.0  | 200  | 0.1755          | 0.6435    | 0.7245 | 0.6816 | 0.9422   |
+
+
 ### Framework versions
 
-- Transformers 4.38.2
+- Transformers 4.40.1
 - Pytorch 2.2.1+cu121
-- Datasets 2.18.0
-- Tokenizers 0.15.2
+- Datasets 2.19.0
+- Tokenizers 0.19.1

config.json

@@ -36,7 +36,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.1",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 50265

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9360f9e9680c0a5bad4a17c1707960515899e1bae9833a043a23b277d41ad153
+oid sha256:3914d34666b8c6d4edcf154a9d385da76a301fcca5d3c2df362727a7e7ee0cb9
 size 496259468

runs/May02_15-24-27_cc9d4b6d7634/events.out.tfevents.1714663468.cc9d4b6d7634.314.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f295a225f6fec4dc5b3eb7d0e7713b05d749aa1cf7d90591457d70686d50b5
+size 12094

tokenizer.json

@@ -76,6 +76,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": false,
     "byte_fallback": false,
+    "ignore_merges": false,
     "vocab": {
       "<s>": 0,
       "<pad>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbae43d8cdd2a0b0dacbf0d54f1fdbd32f5ac3f0763a1136312587bcf108b7b6
-size 4856
+oid sha256:f54becf043b1a3b7e77247fceca27030f60d7f900bfbeea59f1ed767e9931e23
+size 4984