End of training

README.md

@@ -3,11 +3,20 @@ library_name: transformers
 license: llama3.1
 base_model: meta-llama/Llama-3.1-8B
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- oxford-llms/ultrachat_filtered
+- oxford-llms/Magpie-Qwen2.5-Pro-1M-v0.1-filtered
+- oxford-llms/european_social_survey_2020_sft
+- oxford-llms/european_social_survey_2023_sft
+- oxford-llms/world_values_survey_2017_2022_sft
+- oxford-llms/european_social_survey_2023_germany_sft
 model-index:
 - name: llama3-1-ox-llms-8b-sft-full-germany-data
   results: []
@@ -18,7 +27,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-1-ox-llms-8b-sft-full-germany-data
 
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the generator dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B](https://huggingface.co/meta-llama/Llama-3.1-8B) on the oxford-llms/ultrachat_filtered, the oxford-llms/Magpie-Qwen2.5-Pro-1M-v0.1-filtered, the oxford-llms/european_social_survey_2020_sft, the oxford-llms/european_social_survey_2023_sft, the oxford-llms/world_values_survey_2017_2022_sft and the oxford-llms/european_social_survey_2023_germany_sft datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.7417
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.0,
+    "eval_loss": 0.741725742816925,
+    "eval_runtime": 110.9341,
+    "eval_samples": 46460,
+    "eval_samples_per_second": 77.172,
+    "eval_steps_per_second": 1.208,
     "total_flos": 879394553856000.0,
     "train_loss": 0.6596568237599872,
     "train_runtime": 12326.0183,

config.json

@@ -31,6 +31,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 0.741725742816925,
+    "eval_runtime": 110.9341,
+    "eval_samples": 46460,
+    "eval_samples_per_second": 77.172,
+    "eval_steps_per_second": 1.208
+}