eskayML/interview_electra

README.md

@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mrm8488/electra-small-finetuned-squadv2](https://huggingface.co/mrm8488/electra-small-finetuned-squadv2) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.4751
-- Accuracy: 0.2305
+- Loss: 0.8333
+- Accuracy: 0.6316
 
 ## Model description
 
@@ -42,29 +42,24 @@ The following hyperparameters were used during training:
 - train_batch_size: 2
 - eval_batch_size: 2
 - seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 10
+- num_epochs: 5
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| No log        | 1.0   | 152  | 2.8162          | 0.2272   |
-| No log        | 2.0   | 304  | 2.6814          | 0.2263   |
-| No log        | 3.0   | 456  | 2.5987          | 0.2263   |
-| 2.759         | 4.0   | 608  | 2.5461          | 0.2263   |
-| 2.759         | 5.0   | 760  | 2.5203          | 0.2272   |
-| 2.759         | 6.0   | 912  | 2.4958          | 0.2272   |
-| 2.5023        | 7.0   | 1064 | 2.4920          | 0.2305   |
-| 2.5023        | 8.0   | 1216 | 2.4850          | 0.2305   |
-| 2.5023        | 9.0   | 1368 | 2.4786          | 0.2296   |
-| 2.372         | 10.0  | 1520 | 2.4751          | 0.2305   |
+| No log        | 1.0   | 95   | 1.0014          | 0.5526   |
+| No log        | 2.0   | 190  | 0.9542          | 0.5526   |
+| No log        | 3.0   | 285  | 0.9142          | 0.5526   |
+| No log        | 4.0   | 380  | 0.8572          | 0.6316   |
+| No log        | 5.0   | 475  | 0.8333          | 0.6316   |
 
 
 ### Framework versions
 
-- Transformers 4.44.2
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.1
-- Tokenizers 0.19.1
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -10,50 +10,16 @@
   "hidden_dropout_prob": 0.1,
   "hidden_size": 256,
   "id2label": {
-    "0": "ALGORITHM",
-    "1": "COMANAGEMENT",
-    "2": "COMPETING PRIORITIES",
-    "3": "COST",
-    "4": "COVID",
-    "5": "EHR",
-    "6": "GUIDELINES",
-    "7": "HFREF COMFORT MANAGING",
-    "8": "INFO NEEDS",
-    "9": "INTERNAL & EXTERNAL SUPPORT BAR",
-    "10": "JUICY QUOTE",
-    "11": "MAGIC WAND",
-    "12": "MED MANAGEMENT",
-    "13": "OTHER",
-    "14": "PATIENT DIGITAL TOOLS",
-    "15": "PATIENTS",
-    "16": "PROVIDER EDUCATION",
-    "17": "ROLE OF OTHER STAFF",
-    "18": "TIME CONSTRAINTS",
-    "19": "WORKFLOW"
+    "0": "multi_level_org_char",
+    "1": "multi_level_org_perspect",
+    "2": "impl_sust_infra"
   },
   "initializer_range": 0.02,
   "intermediate_size": 1024,
   "label2id": {
-    "ALGORITHM": 0,
-    "COMANAGEMENT": 1,
-    "COMPETING PRIORITIES": 2,
-    "COST": 3,
-    "COVID": 4,
-    "EHR": 5,
-    "GUIDELINES": 6,
-    "HFREF COMFORT MANAGING": 7,
-    "INFO NEEDS": 8,
-    "INTERNAL & EXTERNAL SUPPORT BAR": 9,
-    "JUICY QUOTE": 10,
-    "MAGIC WAND": 11,
-    "MED MANAGEMENT": 12,
-    "OTHER": 13,
-    "PATIENT DIGITAL TOOLS": 14,
-    "PATIENTS": 15,
-    "PROVIDER EDUCATION": 16,
-    "ROLE OF OTHER STAFF": 17,
-    "TIME CONSTRAINTS": 18,
-    "WORKFLOW": 19
+    "impl_sust_infra": 2,
+    "multi_level_org_char": 0,
+    "multi_level_org_perspect": 1
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
@@ -68,7 +34,7 @@
   "summary_type": "first",
   "summary_use_proj": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
+  "transformers_version": "4.46.2",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:309612d49ad131b9df62294bef9d1d48285a346e9121559ed563704470432338
-size 54239712
+oid sha256:bd26f6c33f8d77ba64f4be863e580323fb8e5d14d6ad07950c3e89acb0f0b6b6
+size 54222228

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59c7749d1812864cdb82fd1553bf513392820fa93c6e6061a9a65e2909020c8e
-size 5176
+oid sha256:fd78eec26b21fb161eccebcfe70951605ce8b107fdcc84f5c0b455589be01483
+size 5240