starmodel

README.md

@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: nan
-- Accuracy: 0.2969
-- Precision: 0.0881
-- Recall: 0.2969
-- F1: 0.1359
+- Loss: 0.3786
+- Accuracy: 0.9219
+- Precision: 0.9256
+- Recall: 0.9219
+- F1: 0.9214
 
 ## Model description
 
@@ -56,9 +56,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.7944        | 1.0   | 16   | nan             | 0.2969   | 0.0881    | 0.2969 | 0.1359 |
-| 0.0           | 2.0   | 32   | nan             | 0.2969   | 0.0881    | 0.2969 | 0.1359 |
-| 0.0           | 3.0   | 48   | nan             | 0.2969   | 0.0881    | 0.2969 | 0.1359 |
+| 1.2882        | 1.0   | 16   | 0.5571          | 0.8438   | 0.8726    | 0.8438 | 0.8450 |
+| 0.2007        | 2.0   | 32   | 0.4352          | 0.8906   | 0.9051    | 0.8906 | 0.8929 |
+| 0.0485        | 3.0   | 48   | 0.3786          | 0.9219   | 0.9256    | 0.9219 | 0.9214 |
 
 
 ### Framework versions

config.json

@@ -53,7 +53,7 @@
   "sep_token_id": 50282,
   "sparse_pred_ignore_index": -100,
   "sparse_prediction": false,
-  "torch_dtype": "float16",
+  "torch_dtype": "float32",
   "transformers_version": "4.48.0.dev0",
   "vocab_size": 50368
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9205a749d3b0d5735de5731a71837f39abec83609e4246c1c0ed1a5f0bbfce3a
-size 299230024
+oid sha256:0fc80a9617c0900faafbc6dd0f62c51353752cc763775685cae82bad76ad2d19
+size 598445936