Model save

README.md

@@ -4,6 +4,10 @@ license: apache-2.0
 base_model: Snowflake/snowflake-arctic-embed-m-v1.5
 tags:
 - generated_from_trainer
+metrics:
+- precision
+- recall
+- accuracy
 model-index:
 - name: alignment-score-model
   results: []
@@ -15,6 +19,12 @@ should probably proofread and complete it, then remove this comment. -->
 # alignment-score-model
 
 This model is a fine-tuned version of [Snowflake/snowflake-arctic-embed-m-v1.5](https://huggingface.co/Snowflake/snowflake-arctic-embed-m-v1.5) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0741
+- Precision: 0.9478
+- Recall: 0.9446
+- F1 Macro: 0.9451
+- Accuracy: 0.9453
 
 ## Model description
 
@@ -33,19 +43,21 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 0.0003
-- train_batch_size: 512
-- eval_batch_size: 256
+- learning_rate: 3e-05
+- train_batch_size: 256
+- eval_batch_size: 128
 - seed: 0
 - optimizer: Use OptimizerNames.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: 20
+- num_epochs: 5
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy |
-|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
-| No log        | 0     | 0    | 0.4675          | 0.2450    | 0.5    | 0.3289   | 0.4900   |
+| Training Loss | Epoch  | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|:--------:|:--------:|
+| No log        | 0      | 0    | 0.5153          | 0.2449    | 0.5    | 0.3288   | 0.4898   |
+| No log        | 1.7241 | 50   | 0.1180          | 0.9049    | 0.8869 | 0.8874   | 0.8889   |
+| 0.1417        | 3.4483 | 100  | 0.0741          | 0.9478    | 0.9446 | 0.9451   | 0.9453   |
 
 
 ### Framework versions

final/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4524ed729c0229b0b09751a72bab295fd6fd29a7fb266ccb3a7567373148249
+oid sha256:b11cd85a276262120b18e44ecb5583db91930f9836d49a62d850a569437cee56
 size 437955572

final/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dde81f1fa1366f22ec0d32eee0b536ae0786b88916168aa83366cd4700a2038
-size 5841
+oid sha256:9899cd08f7db8ba4b255283881b609c809e26278c816f0a75b9cd62159c47b47
+size 5777

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4b76142f512da290e0346d35a6ccb923f73ad19e78ec2be7ed3e352d978900
+oid sha256:b11cd85a276262120b18e44ecb5583db91930f9836d49a62d850a569437cee56
 size 437955572