healthcare-ner-colab

README.md

@@ -20,10 +20,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.5513
-- Precision: 0.55
-- Recall: 0.6286
-- F1: 0.4633
+- Loss: 1.7401
+- Precision: 0.3034
+- Recall: 0.3889
+- F1: 0.2611
 
 ## Model description
 
@@ -54,9 +54,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|
-| No log        | 1.0   | 1    | 1.7093          | 0.2917    | 0.5    | 0.3400 |
-| No log        | 2.0   | 2    | 1.5986          | 0.3444    | 0.6    | 0.4061 |
-| No log        | 3.0   | 3    | 1.5513          | 0.55      | 0.6286 | 0.4633 |
+| No log        | 1.0   | 1    | 1.8269          | 0.3056    | 0.3889 | 0.2643 |
+| No log        | 2.0   | 2    | 1.7679          | 0.3034    | 0.3889 | 0.2611 |
+| No log        | 3.0   | 3    | 1.7401          | 0.3034    | 0.3889 | 0.2611 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b24f8250ba3fc2fc8274e07a16e662b70ee68050f6222adf74e489f2a069326
+oid sha256:ddb4b556ba0a97cb0b96d20dfe94393872002573609996dd34cecd9fbf16cda5
 size 430920512

runs/Aug01_05-52-52_08abe0a12f6f/events.out.tfevents.1754027576.08abe0a12f6f.191.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:668f43a045afe81973ea74e82cfb11238dc06b9f758f7c13019deb3982503a69
+size 6804

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88d6ab5767df18e129611d4dc56ce334dbc2677604166c4f48d55b13833f5e83
+oid sha256:7125e14da78ecc5580f267a2d95b703fda2d058982284b3986b587cc8c1861fa
 size 5368