loha_fine_tuned_copa

README.md

@@ -6,6 +6,7 @@ tags:
 base_model: google-bert/bert-base-uncased
 metrics:
 - accuracy
+- f1
 model-index:
 - name: loha_fine_tuned_copa
   results: []
@@ -18,8 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.1041
-- Accuracy: 0.3182
+- Loss: 0.6922
+- Accuracy: 0.5
+- F1: 0.5
 
 ## Model description
 
@@ -38,9 +40,9 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-05
-- train_batch_size: 1
-- eval_batch_size: 1
+- learning_rate: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
@@ -48,6 +50,16 @@ The following hyperparameters were used during training:
 
 ### Training results
 
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1  |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:---:|
+| 0.7089        | 1.0   | 50   | 0.6923          | 0.5      | 0.5 |
+| 0.7026        | 2.0   | 100  | 0.6923          | 0.5      | 0.5 |
+| 0.6995        | 3.0   | 150  | 0.6923          | 0.5      | 0.5 |
+| 0.7009        | 4.0   | 200  | 0.6923          | 0.5      | 0.5 |
+| 0.6997        | 5.0   | 250  | 0.6923          | 0.5      | 0.5 |
+| 0.7028        | 6.0   | 300  | 0.6922          | 0.5      | 0.5 |
+| 0.6951        | 7.0   | 350  | 0.6922          | 0.5      | 0.5 |
+| 0.6949        | 8.0   | 400  | 0.6922          | 0.5      | 0.5 |
 
 
 ### Framework versions

adapter_config.json

@@ -18,8 +18,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "value",
-    "query"
+    "query",
+    "value"
   ],
   "task_type": "SEQ_CLS",
   "use_effective_conv2d": false

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d510cdec228ce1880a1b222b4ebc447d22389f4c4fec35dbc526ddfce7f3012b
-size 4741180
+oid sha256:cb35f9f5b8fb1708c6e3d5944d6bf05515a225f6349d63da9fdb8c270f5c4789
+size 4735028

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab9f57b4957c62e58a41ac3adf35f97b3d9a087cfbaa271d6fe3ea090ee85ffd
+oid sha256:e5f5de39816101e3e159129e85cb7194db20265925733a0354a16ba877346be5
 size 4984