End of training

README.md

@@ -17,9 +17,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [ProsusAI/finbert](https://huggingface.co/ProsusAI/finbert) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.3737
-- Accuracy: 0.8455
-- F1: 0.8449
+- Loss: 0.3175
+- Accuracy: 0.8890
+- F1: 0.8878
 
 ## Model description
 
@@ -38,21 +38,43 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3.249997519166043e-05
-- train_batch_size: 1
+- learning_rate: 6.709451461670167e-05
+- train_batch_size: 16
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 10
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
+| 0.5653        | 0.15  | 100  | 0.4640          | 0.8293   | 0.8162 |
+| 0.5231        | 0.3   | 200  | 0.3839          | 0.8509   | 0.8542 |
+| 0.4908        | 0.46  | 300  | 0.3755          | 0.8545   | 0.8580 |
+| 0.4285        | 0.61  | 400  | 0.4072          | 0.8509   | 0.8562 |
+| 0.4002        | 0.76  | 500  | 0.3370          | 0.8646   | 0.8672 |
+| 0.3754        | 0.91  | 600  | 0.3175          | 0.8890   | 0.8878 |
+| 0.3276        | 1.06  | 700  | 0.3481          | 0.8948   | 0.8931 |
+| 0.2462        | 1.21  | 800  | 0.3259          | 0.8905   | 0.8909 |
+| 0.2321        | 1.37  | 900  | 0.3405          | 0.8775   | 0.8801 |
+| 0.2177        | 1.52  | 1000 | 0.3446          | 0.8941   | 0.8932 |
+| 0.2467        | 1.67  | 1100 | 0.3743          | 0.8833   | 0.8854 |
+| 0.189         | 1.82  | 1200 | 0.4024          | 0.8955   | 0.8955 |
+| 0.2254        | 1.97  | 1300 | 0.3965          | 0.8869   | 0.8862 |
+| 0.1129        | 2.12  | 1400 | 0.4883          | 0.8912   | 0.8928 |
+| 0.0747        | 2.28  | 1500 | 0.4643          | 0.8984   | 0.8993 |
+| 0.0984        | 2.43  | 1600 | 0.4820          | 0.9020   | 0.9025 |
+| 0.0937        | 2.58  | 1700 | 0.4642          | 0.8991   | 0.8993 |
+| 0.1109        | 2.73  | 1800 | 0.4563          | 0.8984   | 0.8994 |
+| 0.084         | 2.88  | 1900 | 0.4441          | 0.9042   | 0.9046 |
 
 
 ### Framework versions
 
-- Transformers 4.35.2
+- Transformers 4.37.2
 - Pytorch 2.1.0+cu121
-- Datasets 2.16.1
-- Tokenizers 0.15.1
+- Datasets 2.17.1
+- Tokenizers 0.15.2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9574fbe5c9a5285030f56d9181bd882a3fd785aa98b5eb3bcf454c0d5558005
+oid sha256:ffe887031bbad7303c589e521962f71e8ea234623fe12c64dd5c3649b02c961a
 size 437961724

runs/Feb26_02-17-25_c4e415ddba5b/events.out.tfevents.1708913846.c4e415ddba5b.1123.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4647fe6e7b89b012d5dffea40580d16bb53816f76f5c2f8dc786562922a40ce
-size 14014
+oid sha256:bbcbb3a72e60cba0ec12e374b622d224cd74ae0bd6f28284d635ebad78b3362b
+size 14894

runs/Feb26_02-17-25_c4e415ddba5b/events.out.tfevents.1708914115.c4e415ddba5b.1123.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1e2457eb73dce2b2551ef69eaa2667b3bc83bd4ca22fffecc4652e945e70ad0
+size 457