ilsilfverskiold/tech-keywords-extractor

README.md

@@ -14,6 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
 # bart_developer_keywords
 
 This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8795
 
 ## Model description
 
@@ -33,11 +35,11 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 8
-- eval_batch_size: 8
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - gradient_accumulation_steps: 16
-- total_train_batch_size: 128
+- total_train_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_steps: 500
@@ -45,6 +47,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.5095        | 0.44  | 50   | 1.1766          |
+| 1.1875        | 0.89  | 100  | 0.9652          |
+| 1.0428        | 1.33  | 150  | 1.0587          |
+| 0.9392        | 1.78  | 200  | 0.8968          |
+| 0.786         | 2.22  | 250  | 1.0131          |
+| 0.8503        | 2.67  | 300  | 0.8795          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c680b52a63695bc92fa17b72ed8c3f70fbde60fe56c45591d27a25eb5dd7599
+oid sha256:44d7c1c233f550be3125e27e7b9e3058b04504082cfde533bb0a4528c02deb56
 size 1625426996

runs/Nov29_13-15-48_e99ba39f9fcd/events.out.tfevents.1701263754.e99ba39f9fcd.300.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3bc0e1d56db0ef961aabc1742c09d1cf673855b7080e2bccb16a5305a9c3bff
+size 12372

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b1c910df602fe433574e4851ea7937e1269835ba2e0ad50e9d201eb427b24f
+oid sha256:411c5a13eb762f1d51310d74e7eede27f3ef4efc6aaa1c835c02f16d874486ec
 size 4600