jslai//content/sample_data/best_models//MBERT_uncased_CrossEntropyLoss_lora

README.md

@@ -21,12 +21,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [google-bert/bert-base-multilingual-uncased](https://huggingface.co/google-bert/bert-base-multilingual-uncased) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6661
-- Accuracy: 0.724
-- F1: 0.8399
-- Precision: 0.724
-- Recall: 1.0
-- Roc Auc: 0.5
+- Loss: 0.6924
+- Accuracy: 0.518
+- F1: 0.6730
+- Precision: 0.6613
+- Recall: 0.6851
+- Roc Auc: 0.3824
 
 ## Model description
 
@@ -61,9 +61,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy | F1     | Precision | Recall | Roc Auc |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:|:-------:|
-| No log        | 0.992 | 31   | 0.6806          | 0.673    | 0.7940 | 0.7300    | 0.8702 | 0.5130  |
-| No log        | 1.984 | 62   | 0.6696          | 0.724    | 0.8399 | 0.724     | 1.0    | 0.5     |
-| No log        | 2.976 | 93   | 0.6661          | 0.724    | 0.8399 | 0.724     | 1.0    | 0.5     |
+| No log        | 0.992 | 31   | 0.7081          | 0.347    | 0.4287 | 0.5847    | 0.3384 | 0.3540  |
+| No log        | 1.984 | 62   | 0.6961          | 0.479    | 0.6354 | 0.6440    | 0.6271 | 0.3588  |
+| No log        | 2.976 | 93   | 0.6924          | 0.518    | 0.6730 | 0.6613    | 0.6851 | 0.3824  |
 
 
 ### Framework versions

adapter_config.json

@@ -3,6 +3,7 @@
   "auto_mapping": null,
   "base_model_name_or_path": "google-bert/bert-base-multilingual-uncased",
   "bias": "none",
+  "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -25,10 +26,22 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "attention.output.dense",
+    "2.output.dense",
+    "10.output.dense",
+    "7.output.dense",
+    "0.output.dense",
+    "11.output.dense",
+    "6.output.dense",
     "query",
+    "intermediate.dense",
+    "1.output.dense",
+    "3.output.dense",
+    "8.output.dense",
     "key",
-    "value"
+    "4.output.dense",
+    "value",
+    "9.output.dense",
+    "5.output.dense"
   ],
   "task_type": "SEQ_CLS",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60574d14a542f2baac667447c36c40f22f0c071753f78d4bd8b3dce2afd37236
-size 4738488
+oid sha256:bbf2f8bd5fd0b9ee7d80ff96a52e17294e9a5993f0c4ff96bc133dee7c672233
+size 9460216

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a012e14337c6de9ce53cd647f95a4d1a5be53eb769d49ae62fc6681f71ebd6c
+oid sha256:82b2fd2247497f5b190738596ccaf24d58f63e59709eca93de454d50b8b80ef9
 size 5304