End of training

README.md

@@ -4,6 +4,7 @@ license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.3
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: mistral-v0.3-7b-instruct-full-pretrain-mix-low-tweet-1m-en-gpt
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mistral-v0.3-7b-instruct-full-pretrain-mix-low-tweet-1m-en-gpt
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on an unknown dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the mix_low_tweet_1m_en_gpt dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 6997841510400.0,
+    "train_loss": 2.2597316542646895,
+    "train_runtime": 32349.5291,
+    "train_samples_per_second": 3.646,
+    "train_steps_per_second": 0.228
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 6997841510400.0,
+    "train_loss": 2.2597316542646895,
+    "train_runtime": 32349.5291,
+    "train_samples_per_second": 3.646,
+    "train_steps_per_second": 0.228
+}