Model save

README.md

@@ -1,16 +1,10 @@
 ---
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 datasets:
-- africa-intelligence/yahma-alpaca-cleaned-tn
-- africa-intelligence/yahma-alpaca-cleaned-xh
-- africa-intelligence/yahma-alpaca-cleaned-zu
-- africa-intelligence/yahma-alpaca-cleaned-af
-- africa-intelligence/yahma-alpaca-cleaned-en
-- africa-intelligence/yahma-alpaca-cleaned-nso
+- generator
 library_name: peft
 license: llama3.1
 tags:
-- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -24,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama-8b-south-africa
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the africa-intelligence/yahma-alpaca-cleaned-tn, the africa-intelligence/yahma-alpaca-cleaned-xh, the africa-intelligence/yahma-alpaca-cleaned-zu, the africa-intelligence/yahma-alpaca-cleaned-af, the africa-intelligence/yahma-alpaca-cleaned-en and the africa-intelligence/yahma-alpaca-cleaned-nso datasets.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the generator dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.0571
 
@@ -61,7 +55,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.0962        | 0.9999 | 5596 | 1.0571          |
+| 1.0959        | 0.9999 | 5596 | 1.0571          |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,9 @@
 {
     "epoch": 0.9999106584472438,
-    "eval_loss": 1.0571058988571167,
-    "eval_runtime": 871.0794,
-    "eval_samples": 31055,
-    "eval_samples_per_second": 5.121,
-    "eval_steps_per_second": 0.641,
     "total_flos": 4.151601388859687e+18,
-    "train_loss": 1.2674157931559251,
-    "train_runtime": 31909.1388,
+    "train_loss": 1.267410275018411,
+    "train_runtime": 31869.1034,
     "train_samples": 310544,
-    "train_samples_per_second": 1.403,
-    "train_steps_per_second": 0.175
+    "train_samples_per_second": 1.405,
+    "train_steps_per_second": 0.176
 }

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 0.9999106584472438,
     "total_flos": 4.151601388859687e+18,
-    "train_loss": 1.2674157931559251,
-    "train_runtime": 31909.1388,
+    "train_loss": 1.267410275018411,
+    "train_runtime": 31869.1034,
     "train_samples": 310544,
-    "train_samples_per_second": 1.403,
-    "train_steps_per_second": 0.175
+    "train_samples_per_second": 1.405,
+    "train_steps_per_second": 0.176
 }