Fine-tuned on product search domain (brand, product name, origin)

README.md

@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1729
+- Loss: 0.1663
 
 ## Model description
 
@@ -33,21 +33,22 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 5e-06
+- learning_rate: 3e-05
 - train_batch_size: 16
 - eval_batch_size: 16
 - seed: 42
 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 2
+- num_epochs: 3
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 0.2435        | 1.0   | 1137 | 0.1872          |
-| 0.1952        | 2.0   | 2274 | 0.1729          |
+| 0.1896        | 1.0   | 1138 | 0.1478          |
+| 0.1433        | 2.0   | 2276 | 0.1183          |
+| 0.0732        | 3.0   | 3414 | 0.1663          |
 
 
 ### Framework versions

best/config.json

@@ -11,79 +11,83 @@
   "hidden_size": 768,
   "id2label": {
     "0": "B-UoM",
-    "1": "B-color",
-    "2": "B-condition",
-    "3": "B-content",
-    "4": "B-core_product_type",
-    "5": "B-creator",
-    "6": "B-department",
-    "7": "B-material",
-    "8": "B-modifier",
-    "9": "B-occasion",
-    "10": "B-origin",
-    "11": "B-price",
-    "12": "B-product_name",
-    "13": "B-product_number",
-    "14": "B-quantity",
-    "15": "B-shape",
-    "16": "B-time",
-    "17": "I-UoM",
-    "18": "I-color",
-    "19": "I-condition",
-    "20": "I-content",
-    "21": "I-core_product_type",
-    "22": "I-creator",
-    "23": "I-department",
-    "24": "I-material",
-    "25": "I-modifier",
-    "26": "I-occasion",
-    "27": "I-origin",
-    "28": "I-price",
-    "29": "I-product_name",
-    "30": "I-product_number",
-    "31": "I-quantity",
-    "32": "I-shape",
-    "33": "I-time",
-    "34": "O"
+    "1": "B-certification",
+    "2": "B-color",
+    "3": "B-condition",
+    "4": "B-content",
+    "5": "B-core_product_type",
+    "6": "B-creator",
+    "7": "B-department",
+    "8": "B-material",
+    "9": "B-modifier",
+    "10": "B-occasion",
+    "11": "B-origin",
+    "12": "B-price",
+    "13": "B-product_name",
+    "14": "B-product_number",
+    "15": "B-quantity",
+    "16": "B-shape",
+    "17": "B-time",
+    "18": "I-UoM",
+    "19": "I-certification",
+    "20": "I-color",
+    "21": "I-condition",
+    "22": "I-content",
+    "23": "I-core_product_type",
+    "24": "I-creator",
+    "25": "I-department",
+    "26": "I-material",
+    "27": "I-modifier",
+    "28": "I-occasion",
+    "29": "I-origin",
+    "30": "I-price",
+    "31": "I-product_name",
+    "32": "I-product_number",
+    "33": "I-quantity",
+    "34": "I-shape",
+    "35": "I-time",
+    "36": "O"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
     "B-UoM": 0,
-    "B-color": 1,
-    "B-condition": 2,
-    "B-content": 3,
-    "B-core_product_type": 4,
-    "B-creator": 5,
-    "B-department": 6,
-    "B-material": 7,
-    "B-modifier": 8,
-    "B-occasion": 9,
-    "B-origin": 10,
-    "B-price": 11,
-    "B-product_name": 12,
-    "B-product_number": 13,
-    "B-quantity": 14,
-    "B-shape": 15,
-    "B-time": 16,
-    "I-UoM": 17,
-    "I-color": 18,
-    "I-condition": 19,
-    "I-content": 20,
-    "I-core_product_type": 21,
-    "I-creator": 22,
-    "I-department": 23,
-    "I-material": 24,
-    "I-modifier": 25,
-    "I-occasion": 26,
-    "I-origin": 27,
-    "I-price": 28,
-    "I-product_name": 29,
-    "I-product_number": 30,
-    "I-quantity": 31,
-    "I-shape": 32,
-    "I-time": 33,
-    "O": 34
+    "B-certification": 1,
+    "B-color": 2,
+    "B-condition": 3,
+    "B-content": 4,
+    "B-core_product_type": 5,
+    "B-creator": 6,
+    "B-department": 7,
+    "B-material": 8,
+    "B-modifier": 9,
+    "B-occasion": 10,
+    "B-origin": 11,
+    "B-price": 12,
+    "B-product_name": 13,
+    "B-product_number": 14,
+    "B-quantity": 15,
+    "B-shape": 16,
+    "B-time": 17,
+    "I-UoM": 18,
+    "I-certification": 19,
+    "I-color": 20,
+    "I-condition": 21,
+    "I-content": 22,
+    "I-core_product_type": 23,
+    "I-creator": 24,
+    "I-department": 25,
+    "I-material": 26,
+    "I-modifier": 27,
+    "I-occasion": 28,
+    "I-origin": 29,
+    "I-price": 30,
+    "I-product_name": 31,
+    "I-product_number": 32,
+    "I-quantity": 33,
+    "I-shape": 34,
+    "I-time": 35,
+    "O": 36
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

best/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa26b9b77b9afc55cfc1e1bba1b6a4a7be78388652075c574feefa2825fdaa9
-size 435697596
+oid sha256:2a7466a95edb1b6ff3025e44cd7b8604a11ffef0240eb96d26e63c60e967cc28
+size 435703748

best/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:703df3b8da86bf6f64a2c6832ca1056b83cc0e20fe93d96065e4d6497a6b33eb
+oid sha256:700ee203f7008d2129a1925ab437a16003c54e26d270517448f9f9477115364f
 size 5969

config.json

@@ -11,79 +11,83 @@
   "hidden_size": 768,
   "id2label": {
     "0": "B-UoM",
-    "1": "B-color",
-    "2": "B-condition",
-    "3": "B-content",
-    "4": "B-core_product_type",
-    "5": "B-creator",
-    "6": "B-department",
-    "7": "B-material",
-    "8": "B-modifier",
-    "9": "B-occasion",
-    "10": "B-origin",
-    "11": "B-price",
-    "12": "B-product_name",
-    "13": "B-product_number",
-    "14": "B-quantity",
-    "15": "B-shape",
-    "16": "B-time",
-    "17": "I-UoM",
-    "18": "I-color",
-    "19": "I-condition",
-    "20": "I-content",
-    "21": "I-core_product_type",
-    "22": "I-creator",
-    "23": "I-department",
-    "24": "I-material",
-    "25": "I-modifier",
-    "26": "I-occasion",
-    "27": "I-origin",
-    "28": "I-price",
-    "29": "I-product_name",
-    "30": "I-product_number",
-    "31": "I-quantity",
-    "32": "I-shape",
-    "33": "I-time",
-    "34": "O"
+    "1": "B-certification",
+    "2": "B-color",
+    "3": "B-condition",
+    "4": "B-content",
+    "5": "B-core_product_type",
+    "6": "B-creator",
+    "7": "B-department",
+    "8": "B-material",
+    "9": "B-modifier",
+    "10": "B-occasion",
+    "11": "B-origin",
+    "12": "B-price",
+    "13": "B-product_name",
+    "14": "B-product_number",
+    "15": "B-quantity",
+    "16": "B-shape",
+    "17": "B-time",
+    "18": "I-UoM",
+    "19": "I-certification",
+    "20": "I-color",
+    "21": "I-condition",
+    "22": "I-content",
+    "23": "I-core_product_type",
+    "24": "I-creator",
+    "25": "I-department",
+    "26": "I-material",
+    "27": "I-modifier",
+    "28": "I-occasion",
+    "29": "I-origin",
+    "30": "I-price",
+    "31": "I-product_name",
+    "32": "I-product_number",
+    "33": "I-quantity",
+    "34": "I-shape",
+    "35": "I-time",
+    "36": "O"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
     "B-UoM": 0,
-    "B-color": 1,
-    "B-condition": 2,
-    "B-content": 3,
-    "B-core_product_type": 4,
-    "B-creator": 5,
-    "B-department": 6,
-    "B-material": 7,
-    "B-modifier": 8,
-    "B-occasion": 9,
-    "B-origin": 10,
-    "B-price": 11,
-    "B-product_name": 12,
-    "B-product_number": 13,
-    "B-quantity": 14,
-    "B-shape": 15,
-    "B-time": 16,
-    "I-UoM": 17,
-    "I-color": 18,
-    "I-condition": 19,
-    "I-content": 20,
-    "I-core_product_type": 21,
-    "I-creator": 22,
-    "I-department": 23,
-    "I-material": 24,
-    "I-modifier": 25,
-    "I-occasion": 26,
-    "I-origin": 27,
-    "I-price": 28,
-    "I-product_name": 29,
-    "I-product_number": 30,
-    "I-quantity": 31,
-    "I-shape": 32,
-    "I-time": 33,
-    "O": 34
+    "B-certification": 1,
+    "B-color": 2,
+    "B-condition": 3,
+    "B-content": 4,
+    "B-core_product_type": 5,
+    "B-creator": 6,
+    "B-department": 7,
+    "B-material": 8,
+    "B-modifier": 9,
+    "B-occasion": 10,
+    "B-origin": 11,
+    "B-price": 12,
+    "B-product_name": 13,
+    "B-product_number": 14,
+    "B-quantity": 15,
+    "B-shape": 16,
+    "B-time": 17,
+    "I-UoM": 18,
+    "I-certification": 19,
+    "I-color": 20,
+    "I-condition": 21,
+    "I-content": 22,
+    "I-core_product_type": 23,
+    "I-creator": 24,
+    "I-department": 25,
+    "I-material": 26,
+    "I-modifier": 27,
+    "I-occasion": 28,
+    "I-origin": 29,
+    "I-price": 30,
+    "I-product_name": 31,
+    "I-product_number": 32,
+    "I-quantity": 33,
+    "I-shape": 34,
+    "I-time": 35,
+    "O": 36
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa26b9b77b9afc55cfc1e1bba1b6a4a7be78388652075c574feefa2825fdaa9
-size 435697596
+oid sha256:2a7466a95edb1b6ff3025e44cd7b8604a11ffef0240eb96d26e63c60e967cc28
+size 435703748

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:703df3b8da86bf6f64a2c6832ca1056b83cc0e20fe93d96065e4d6497a6b33eb
+oid sha256:700ee203f7008d2129a1925ab437a16003c54e26d270517448f9f9477115364f
 size 5969