hlillemark
/

llama3_8b_sft_mc

Text Generation

Generated from Trainer

text-generation-inference

Model card Files Files and versions

hlillemark commited on Mar 8

Commit

e0be075

·

verified ·

1 Parent(s): 506bac8

Model save

Files changed (1) hide show

README.md +15 -15

README.md CHANGED Viewed

@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # sft_mc
-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 identity and the data_mc datasets.
 It achieves the following results on the evaluation set:
-- Loss: 2.3274
 ## Model description
@@ -55,19 +55,19 @@ The following hyperparameters were used during training:
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.053         | 0.7463 | 50   | 1.2667          |
-| 0.8178        | 1.4925 | 100  | 1.3230          |
-| 0.3803        | 2.2388 | 150  | 1.5491          |
-| 0.436         | 2.9851 | 200  | 1.5159          |
-| 0.2529        | 3.7313 | 250  | 1.6716          |
-| 0.1555        | 4.4776 | 300  | 1.8479          |
-| 0.078         | 5.2239 | 350  | 2.0375          |
-| 0.0726        | 5.9701 | 400  | 1.8966          |
-| 0.0411        | 6.7164 | 450  | 2.1223          |
-| 0.0127        | 7.4627 | 500  | 2.1808          |
-| 0.0083        | 8.2090 | 550  | 2.2392          |
-| 0.0049        | 8.9552 | 600  | 2.3008          |
-| 0.0035        | 9.7015 | 650  | 2.3232          |
 ### Framework versions

 # sft_mc
+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 None dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.3016
 ## Model description
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
+| 1.0534        | 0.7463 | 50   | 1.2635          |
+| 0.8118        | 1.4925 | 100  | 1.3805          |
+| 0.3889        | 2.2388 | 150  | 1.6007          |
+| 0.4361        | 2.9851 | 200  | 1.5327          |
+| 0.265         | 3.7313 | 250  | 1.6067          |
+| 0.1347        | 4.4776 | 300  | 1.8177          |
+| 0.0857        | 5.2239 | 350  | 1.9771          |
+| 0.0709        | 5.9701 | 400  | 1.9008          |
+| 0.0474        | 6.7164 | 450  | 2.1317          |
+| 0.0286        | 7.4627 | 500  | 2.2199          |
+| 0.0091        | 8.2090 | 550  | 2.2086          |
+| 0.0054        | 8.9552 | 600  | 2.2865          |
+| 0.0038        | 9.7015 | 650  | 2.3016          |
 ### Framework versions