Sorour
/

cls_headline_llama3_v1

Generated from Trainer

Model card Files Files and versions Metrics Training metrics Community

Sorour commited on May 23, 2024

Commit

fd3f449

·

verified ·

1 Parent(s): 1ae5287

Model save

Files changed (1) hide show

README.md +10 -19

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4093
 ## Model description
@@ -55,29 +55,20 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.7006        | 0.1116 | 20   | 0.6798          |
-| 0.6142        | 0.2232 | 40   | 0.6206          |
-| 0.5765        | 0.3347 | 60   | 0.5811          |
-| 0.5665        | 0.4463 | 80   | 0.5487          |
-| 0.5511        | 0.5579 | 100  | 0.5362          |
-| 0.5297        | 0.6695 | 120  | 0.5161          |
-| 0.5028        | 0.7810 | 140  | 0.4949          |
-| 0.4922        | 0.8926 | 160  | 0.4742          |
-| 0.4844        | 1.0042 | 180  | 0.4652          |
-| 0.367         | 1.1158 | 200  | 0.4576          |
-| 0.3784        | 1.2273 | 220  | 0.4493          |
-| 0.3198        | 1.3389 | 240  | 0.4465          |
-| 0.336         | 1.4505 | 260  | 0.4360          |
-| 0.3084        | 1.5621 | 280  | 0.4293          |
-| 0.3707        | 1.6736 | 300  | 0.4211          |
-| 0.3358        | 1.7852 | 320  | 0.4141          |
-| 0.3307        | 1.8968 | 340  | 0.4093          |
 ### Framework versions
 - PEFT 0.11.1
-- Transformers 4.41.0
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1

 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.2617
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
+| 0.3038        | 0.2353 | 20   | 0.2961          |
+| 0.2899        | 0.4706 | 40   | 0.2809          |
+| 0.2707        | 0.7059 | 60   | 0.2714          |
+| 0.2615        | 0.9412 | 80   | 0.2697          |
+| 0.2357        | 1.1765 | 100  | 0.2707          |
+| 0.2377        | 1.4118 | 120  | 0.2667          |
+| 0.2346        | 1.6471 | 140  | 0.2662          |
+| 0.2357        | 1.8824 | 160  | 0.2617          |
 ### Framework versions
 - PEFT 0.11.1
+- Transformers 4.41.1
 - Pytorch 2.3.0+cu121
 - Datasets 2.19.1
 - Tokenizers 0.19.1