davidadamczyk/all-mpnet-base-v2-ag_news

README.md

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [sentence-transformers/all-mpnet-base-v2](https://huggingface.co/sentence-transformers/all-mpnet-base-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0120
+- Loss: 0.1708
 
 ## Model description
 
@@ -45,18 +45,18 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.0978        | 1.0   | 267  | 1.0558          |
-| 0.9553        | 2.0   | 534  | 1.0120          |
-| 0.818         | 3.0   | 801  | 1.0295          |
-| 0.7829        | 4.0   | 1068 | 1.0446          |
-| 0.5788        | 5.0   | 1335 | 1.1085          |
-| 0.4684        | 6.0   | 1602 | 1.2071          |
-| 0.3698        | 7.0   | 1869 | 1.2835          |
-| 0.3758        | 8.0   | 2136 | 1.3379          |
-| 0.3312        | 9.0   | 2403 | 1.4056          |
-| 0.283         | 10.0  | 2670 | 1.4214          |
+| Training Loss | Epoch | Step  | Validation Loss |
+|:-------------:|:-----:|:-----:|:---------------:|
+| 0.1466        | 1.0   | 3750  | 0.1715          |
+| 0.1508        | 2.0   | 7500  | 0.1708          |
+| 0.1141        | 3.0   | 11250 | 0.1771          |
+| 0.038         | 4.0   | 15000 | 0.2023          |
+| 0.0475        | 5.0   | 18750 | 0.2415          |
+| 0.0443        | 6.0   | 22500 | 0.2599          |
+| 0.0341        | 7.0   | 26250 | 0.3055          |
+| 0.0207        | 8.0   | 30000 | 0.3224          |
+| 0.0174        | 9.0   | 33750 | 0.3432          |
+| 0.0093        | 10.0  | 37500 | 0.3711          |
 
 
 ### Framework versions

config.json

@@ -13,8 +13,7 @@
     "0": "LABEL_0",
     "1": "LABEL_1",
     "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4"
+    "3": "LABEL_3"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
@@ -22,8 +21,7 @@
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4
+    "LABEL_3": 3
   },
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 514,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3316e88f430817c07621fc913b134984888c824c6f34527155b32ba97aed01b5
-size 437984428
+oid sha256:fd529ca53f13f53e71e89389269510204641e3b0d20c5aa25f2167cf2713e67c
+size 437981352