skylord/distillbert-talk2loop

README.md

@@ -18,9 +18,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4817
-- Accuracy: 0.9808
-- F1: 0.9808
+- Loss: 0.1715
+- Accuracy: 0.9615
+- F1: 0.9615
 
 ## Model description
 
@@ -51,8 +51,8 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
-| 1.2397        | 1.0   | 28   | 0.7445          | 0.9615   | 0.9617 |
-| 0.6008        | 2.0   | 56   | 0.4817          | 0.9808   | 0.9808 |
+| 0.548         | 1.0   | 28   | 0.2977          | 0.9808   | 0.9808 |
+| 0.2369        | 2.0   | 56   | 0.1715          | 0.9615   | 0.9615 |
 
 
 ### Framework versions

config.json

@@ -8,23 +8,7 @@
   "dim": 768,
   "dropout": 0.1,
   "hidden_dim": 3072,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2",
-    "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5"
-  },
   "initializer_range": 0.02,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2,
-    "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5
-  },
   "max_position_embeddings": 512,
   "model_type": "distilbert",
   "n_heads": 12,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbbeb90b4b33cd662d24343256c005193db834bafc85ae6e3a31a854fdecbc3c
-size 267844872
+oid sha256:7793263e4dd184bc447cd67ed779b89d77566d5ac0bf72a491ce0af698242387
+size 267832560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18b48a17aab69c473cce09933e049e4e711aa4e056871db999e16568de52a9d
+oid sha256:8570ab07aafcd55086b81dd3a1169a6c62473d443d12e6d94d32f90e30b922e0
 size 4728