fine_tune_v3

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [SG1123/boolq_model_v2](https://huggingface.co/SG1123/boolq_model_v2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.3909
+- Loss: 0.1470
 
 ## Model description
 
@@ -46,11 +46,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 33   | 0.3592          |
-| No log        | 2.0   | 66   | 0.3178          |
-| No log        | 3.0   | 99   | 0.3683          |
-| No log        | 4.0   | 132  | 0.3783          |
-| No log        | 5.0   | 165  | 0.3909          |
+| No log        | 1.0   | 18   | 0.1415          |
+| No log        | 2.0   | 36   | 0.1653          |
+| No log        | 3.0   | 54   | 0.1687          |
+| No log        | 4.0   | 72   | 0.1677          |
+| No log        | 5.0   | 90   | 0.1470          |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b4385db50e783d0a917c3b28daaa47dde06a06e60e959560153e1b66207b29
+oid sha256:e9f9ee6e166d464bb27c7f6bb0c5bc5cd7bc01443e7bc1dea94d95456530ad9b
 size 498612824

runs/Dec05_04-43-54_1a30b4fe72e4/events.out.tfevents.1701751445.1a30b4fe72e4.2123.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c9f8ef9fea58bd73a041d546b55baea39543b5e82a483771d6e16d52b7f080d
+size 5987

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9bfa6392fa85e6a804328537fb8b9a82b84ca122f4a8e87ac67fea94b88a724
+oid sha256:9df2413140543853c58f11e999b4ac18e4bb1bc24c49c60af157ca07b39c2158
 size 4600