End of training

README.md

@@ -2,6 +2,8 @@
 base_model: microsoft/mpnet-base
 tags:
 - generated_from_trainer
+metrics:
+- f1
 model-index:
 - name: mpnet-base-airlines-news-multi-label
   results: []
@@ -14,15 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [microsoft/mpnet-base](https://huggingface.co/microsoft/mpnet-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.2754
-- eval_f1: 0.6334
-- eval_roc_auc: 0.7772
-- eval_accuracy: 0.5938
-- eval_runtime: 122.2791
-- eval_samples_per_second: 1.832
-- eval_steps_per_second: 0.229
-- epoch: 16.56
-- step: 3726
+- Loss: 0.2478
+- F1: 0.8938
+- Roc Auc: 0.6465
 
 ## Model description
 
@@ -41,17 +37,63 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 9e-06
-- train_batch_size: 8
-- eval_batch_size: 8
+- learning_rate: 7e-05
+- train_batch_size: 32
+- eval_batch_size: 32
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 30
+- num_epochs: 40
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Roc Auc |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|
+| No log        | 1.0   | 57   | 0.3726          | 0.8319 | 0.5     |
+| No log        | 2.0   | 114  | 0.3361          | 0.8319 | 0.5     |
+| No log        | 3.0   | 171  | 0.3303          | 0.8319 | 0.5     |
+| No log        | 4.0   | 228  | 0.3249          | 0.8319 | 0.5     |
+| No log        | 5.0   | 285  | 0.3188          | 0.8319 | 0.5     |
+| No log        | 6.0   | 342  | 0.3141          | 0.8319 | 0.5     |
+| No log        | 7.0   | 399  | 0.3089          | 0.8319 | 0.5     |
+| No log        | 8.0   | 456  | 0.3042          | 0.8319 | 0.5     |
+| 0.3595        | 9.0   | 513  | 0.2997          | 0.8319 | 0.5     |
+| 0.3595        | 10.0  | 570  | 0.2940          | 0.8319 | 0.5     |
+| 0.3595        | 11.0  | 627  | 0.2898          | 0.8319 | 0.5     |
+| 0.3595        | 12.0  | 684  | 0.2856          | 0.8463 | 0.5032  |
+| 0.3595        | 13.0  | 741  | 0.2819          | 0.8593 | 0.5096  |
+| 0.3595        | 14.0  | 798  | 0.2789          | 0.8600 | 0.5128  |
+| 0.3595        | 15.0  | 855  | 0.2757          | 0.8701 | 0.5220  |
+| 0.3595        | 16.0  | 912  | 0.2723          | 0.8733 | 0.5312  |
+| 0.3595        | 17.0  | 969  | 0.2698          | 0.8733 | 0.5312  |
+| 0.2983        | 18.0  | 1026 | 0.2670          | 0.8808 | 0.5629  |
+| 0.2983        | 19.0  | 1083 | 0.2652          | 0.8814 | 0.5661  |
+| 0.2983        | 20.0  | 1140 | 0.2630          | 0.8786 | 0.5744  |
+| 0.2983        | 21.0  | 1197 | 0.2612          | 0.8807 | 0.5840  |
+| 0.2983        | 22.0  | 1254 | 0.2596          | 0.8818 | 0.5900  |
+| 0.2983        | 23.0  | 1311 | 0.2580          | 0.8841 | 0.6024  |
+| 0.2983        | 24.0  | 1368 | 0.2562          | 0.8878 | 0.6153  |
+| 0.2983        | 25.0  | 1425 | 0.2555          | 0.8851 | 0.6056  |
+| 0.2983        | 26.0  | 1482 | 0.2544          | 0.8860 | 0.6088  |
+| 0.2747        | 27.0  | 1539 | 0.2535          | 0.8868 | 0.6148  |
+| 0.2747        | 28.0  | 1596 | 0.2527          | 0.8878 | 0.6153  |
+| 0.2747        | 29.0  | 1653 | 0.2519          | 0.8869 | 0.6121  |
+| 0.2747        | 30.0  | 1710 | 0.2512          | 0.8875 | 0.6180  |
+| 0.2747        | 31.0  | 1767 | 0.2501          | 0.8900 | 0.6277  |
+| 0.2747        | 32.0  | 1824 | 0.2495          | 0.8923 | 0.6401  |
+| 0.2747        | 33.0  | 1881 | 0.2492          | 0.8907 | 0.6337  |
+| 0.2747        | 34.0  | 1938 | 0.2488          | 0.8922 | 0.6401  |
+| 0.2747        | 35.0  | 1995 | 0.2485          | 0.8915 | 0.6369  |
+| 0.2633        | 36.0  | 2052 | 0.2480          | 0.8922 | 0.6401  |
+| 0.2633        | 37.0  | 2109 | 0.2478          | 0.8938 | 0.6465  |
+| 0.2633        | 38.0  | 2166 | 0.2477          | 0.8930 | 0.6433  |
+| 0.2633        | 39.0  | 2223 | 0.2476          | 0.8938 | 0.6465  |
+| 0.2633        | 40.0  | 2280 | 0.2476          | 0.8938 | 0.6465  |
+
 
 ### Framework versions
 
-- Transformers 4.41.0
+- Transformers 4.41.1
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

config.json

@@ -11,8 +11,8 @@
   "hidden_size": 768,
   "id2label": {
     "0": "capacity expansion",
-    "1": "market expansion",
-    "2": "marketing",
+    "1": "legal action",
+    "2": "market expansion",
     "3": "merger & acquisition and finance investments",
     "4": "outsourcing and alliance",
     "5": "product introductions and improvements"
@@ -21,8 +21,8 @@
   "intermediate_size": 3072,
   "label2id": {
     "capacity expansion": 0,
-    "market expansion": 1,
-    "marketing": 2,
+    "legal action": 1,
+    "market expansion": 2,
     "merger & acquisition and finance investments": 3,
     "outsourcing and alliance": 4,
     "product introductions and improvements": 5
@@ -36,6 +36,6 @@
   "problem_type": "multi_label_classification",
   "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
-  "transformers_version": "4.41.0",
+  "transformers_version": "4.41.1",
   "vocab_size": 30527
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:774810f17c701ef3af7f707cf02ebf71043b03f8c3ce0b5b31140acd9f2706b1
-size 437987504
+oid sha256:e48e5c04022531c9afce686f13e6957e74f8c64b316e8be49e0448aab3e9719b
+size 438775128

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a805017e4e16bd85791ee947680469996153b0a4343c97fd25d968db4344f44
+oid sha256:6722ff36b427261af23977edbfc6bab9cc1ace7c105f229a78d5b79025104570
 size 5176