chchen
/

Llama-3.1-8B-Instruct-PsyCourse-doc-fold3

Generated from Trainer

Model card Files Files and versions Community

chchen commited on Feb 5

Commit

7dad9ee

·

verified ·

1 Parent(s): 4dedb49

Model save

Files changed (2) hide show

README.md +14 -14
adapter_model.safetensors +1 -1

README.md CHANGED Viewed

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # Llama-3.1-8B-Instruct-PsyCourse-doc-fold3
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the course-doc-train-fold3 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.0548
 ## Model description
@@ -52,18 +52,18 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 0.1252        | 0.3951 | 10   | 0.1334          |
-| 0.0806        | 0.7901 | 20   | 0.0817          |
-| 0.0967        | 1.1852 | 30   | 0.0673          |
-| 0.103         | 1.5802 | 40   | 0.0613          |
-| 0.0784        | 1.9753 | 50   | 0.0586          |
-| 0.0422        | 2.3704 | 60   | 0.0573          |
-| 0.0666        | 2.7654 | 70   | 0.0555          |
-| 0.1382        | 3.1605 | 80   | 0.0552          |
-| 0.0778        | 3.5556 | 90   | 0.0559          |
-| 0.0234        | 3.9506 | 100  | 0.0548          |
-| 0.0568        | 4.3457 | 110  | 0.0550          |
-| 0.0773        | 4.7407 | 120  | 0.0549          |
 ### Framework versions

 # Llama-3.1-8B-Instruct-PsyCourse-doc-fold3
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 0.0164
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
+| 0.0899        | 0.3951 | 10   | 0.0847          |
+| 0.0334        | 0.7901 | 20   | 0.0355          |
+| 0.0204        | 1.1852 | 30   | 0.0244          |
+| 0.0215        | 1.5802 | 40   | 0.0207          |
+| 0.0173        | 1.9753 | 50   | 0.0186          |
+| 0.014         | 2.3704 | 60   | 0.0179          |
+| 0.0131        | 2.7654 | 70   | 0.0171          |
+| 0.0152        | 3.1605 | 80   | 0.0165          |
+| 0.014         | 3.5556 | 90   | 0.0170          |
+| 0.0106        | 3.9506 | 100  | 0.0164          |
+| 0.0133        | 4.3457 | 110  | 0.0165          |
+| 0.013         | 4.7407 | 120  | 0.0164          |
 ### Framework versions

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c050203f8cda7c6925ceec6ccf5d1cb9a0cba9ad6bc5c6b46d96f89285700d88
 size 83945296

 version https://git-lfs.github.com/spec/v1
+oid sha256:3e14695426576fe4c3b93393c977eba4dbfb2463e9d5303746a35aefe86572ae
 size 83945296