End of training

README.md

@@ -1,6 +1,11 @@
 ---
 tags:
 - generated_from_trainer
+metrics:
+- precision
+- recall
+- f1
+- accuracy
 model-index:
 - name: RoBERTa-ext-large-crf-chinese-finetuned-ner
   results: []
@@ -13,15 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 93.6921
-- eval_precision: 0.6788
-- eval_recall: 0.7538
-- eval_f1: 0.7143
-- eval_accuracy: 0.9634
-- eval_runtime: 23.7231
-- eval_samples_per_second: 21.203
-- eval_steps_per_second: 2.656
-- step: 0
+- Loss: 0.7186
+- Precision: 0.6813
+- Recall: 0.7573
+- F1: 0.7173
+- Accuracy: 0.9639
 
 ## Model description
 
@@ -46,7 +47,23 @@ 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: 1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
+| 0.0197        | 1.0   | 503  | 0.6375          | 0.6663    | 0.7314 | 0.6973 | 0.9621   |
+| 0.0251        | 2.0   | 1006 | 0.6048          | 0.6494    | 0.7435 | 0.6933 | 0.9611   |
+| 0.0176        | 3.0   | 1509 | 0.6196          | 0.6669    | 0.7389 | 0.7011 | 0.9618   |
+| 0.0116        | 4.0   | 2012 | 0.6361          | 0.6511    | 0.7560 | 0.6997 | 0.9624   |
+| 0.0082        | 5.0   | 2515 | 0.6682          | 0.6746    | 0.7387 | 0.7052 | 0.9622   |
+| 0.0067        | 6.0   | 3018 | 0.6587          | 0.6715    | 0.7409 | 0.7045 | 0.9635   |
+| 0.0046        | 7.0   | 3521 | 0.6846          | 0.6770    | 0.7613 | 0.7167 | 0.9636   |
+| 0.0019        | 8.0   | 4024 | 0.7081          | 0.6766    | 0.7510 | 0.7118 | 0.9630   |
+| 0.0014        | 9.0   | 4527 | 0.7064          | 0.6812    | 0.7553 | 0.7163 | 0.9641   |
+| 0.001         | 10.0  | 5030 | 0.7186          | 0.6813    | 0.7573 | 0.7173 | 0.9639   |
+
 
 ### Framework versions
 

config.json

@@ -1,12 +1,9 @@
 {
-  "_name_or_path": "gyr66/RoBERTa-ext-large-crf-chinese-finetuned-ner",
+  "_name_or_path": "./RoBERTa-ext-large-chinese-finetuned-ner",
   "architectures": [
     "BertCrfForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "auto_map": {
-    "AutoModelForTokenClassification": "model.BertCrfForTokenClassification"
-  },
   "bos_token_id": 0,
   "classifier_dropout": null,
   "directionality": "bidi",
@@ -92,7 +89,7 @@
   "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
+  "transformers_version": "4.35.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 21128

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74054eb7525f1811fa4d9eb645e99008be1db9a50cf9a058f271ef4bbf641458
+oid sha256:4e59832720d5c9f592f83c8d61fb253d5ae9b360190d7833f8d214c8017e0050
 size 1298060872

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dca0bbb1c7d575f8c093b1d4826a8230a7cb1937f36a0f5b4f0536003486723
+oid sha256:4d8ac636c9476822572910e287b4304549222e1270ea149729a3156f35fb5841
 size 4600