keylazy
/

Llama-2-7b-chat-hf-ark-ft

Text Classification

Generated from Trainer

text-generation-inference

Model card Files Files and versions

Metrics Training metrics Community

keylazy commited on Nov 10, 2023

Commit

753d50a

·

1 Parent(s): f91d51d

End of training

Files changed (2) hide show

README.md +12 -14
model.safetensors +1 -1

README.md CHANGED Viewed

@@ -19,11 +19,11 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [keylazy/Llama-2-7b-chat-hf-ark](https://huggingface.co/keylazy/Llama-2-7b-chat-hf-ark) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5437
-- Accuracy: 0.721
-- Precision: 0.7219
-- Recall: 0.721
-- F1: 0.7212
 ## Model description
@@ -50,19 +50,17 @@ The following hyperparameters were used during training:
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
 - mixed_precision_training: Native AMP
 ### Training results
-| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1     |
-|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|
-| 0.5702        | 0.5   | 39   | 0.5251          | 0.679    | 0.6827    | 0.679  | 0.6743 |
-| 0.5012        | 1.0   | 78   | 0.4611          | 0.707    | 0.7080    | 0.707  | 0.7052 |
-| 0.3074        | 1.5   | 117  | 0.4884          | 0.714    | 0.7138    | 0.714  | 0.7138 |
-| 0.3293        | 2.0   | 156  | 0.4819          | 0.723    | 0.7230    | 0.723  | 0.7230 |
-| 0.1268        | 2.5   | 195  | 0.5323          | 0.724    | 0.7243    | 0.724  | 0.7241 |
-| 0.0968        | 3.0   | 234  | 0.5437          | 0.721    | 0.7219    | 0.721  | 0.7212 |
 ### Framework versions

 This model is a fine-tuned version of [keylazy/Llama-2-7b-chat-hf-ark](https://huggingface.co/keylazy/Llama-2-7b-chat-hf-ark) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.1851
+- Accuracy: 0.9428
+- Precision: 0.9429
+- Recall: 0.9428
+- F1: 0.9428
 ## Model description
 - total_train_batch_size: 128
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
+- num_epochs: 2
 - mixed_precision_training: Native AMP
 ### Training results
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy | Precision | Recall | F1     |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
+| 0.1635        | 0.5   | 3828  | 0.1612          | 0.9267   | 0.9270    | 0.9267 | 0.9267 |
+| 0.1302        | 1.0   | 7656  | 0.1330          | 0.9424   | 0.9429    | 0.9424 | 0.9423 |
+| 0.0352        | 1.5   | 11484 | 0.1845          | 0.9435   | 0.9435    | 0.9435 | 0.9434 |
+| 0.0316        | 2.0   | 15312 | 0.1851          | 0.9428   | 0.9429    | 0.9428 | 0.9428 |
 ### Framework versions

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b150d40cb081f69f68dccbb2ec7341ffa6a87591a6ae42e82b37e85e3107dc6f
 size 398865392

 version https://git-lfs.github.com/spec/v1
+oid sha256:45bc87a2ef02e887cd9931fe4d670240ca8fdcb7e989f49c050a5d7b6bb4e4bf
 size 398865392