Tim-05369/orpo_train_using_space_demo

README.md

@@ -1,4 +1,6 @@
 ---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
 - trl
 - orpo
@@ -13,20 +15,20 @@ should probably proofread and complete it, then remove this comment. -->
 
 # results
 
-This model was trained from scratch on the None dataset.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.7473
-- Rewards/chosen: -0.1208
-- Rewards/rejected: -0.0591
-- Rewards/accuracies: 0.0
-- Rewards/margins: -0.0617
-- Logps/rejected: -1.1825
-- Logps/chosen: -2.4166
-- Logits/rejected: -2.2554
-- Logits/chosen: -2.5517
-- Nll Loss: 2.6563
-- Log Odds Ratio: -1.8199
-- Log Odds Chosen: -1.6127
+- Loss: 1.8073
+- Rewards/chosen: -0.0719
+- Rewards/rejected: -0.1594
+- Rewards/accuracies: 0.6667
+- Rewards/margins: 0.0874
+- Logps/rejected: -3.1874
+- Logps/chosen: -1.4385
+- Logits/rejected: -2.2859
+- Logits/chosen: -2.4167
+- Nll Loss: 1.7887
+- Log Odds Ratio: -0.3720
+- Log Odds Chosen: 2.6873
 
 ## Model description
 

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33b44e9ee80b7b4d6082302c08b749ded15097de50d89e365d4e1ac0ec9c0ccc
+oid sha256:74ddbbdceecb03ec6e89c6ae9a82ff27449b7190a035a4c92a99d41dc6a682c0
 size 4400216536

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2971db7610c3103eb27b87f68da49638853ed4e2be3209e0dadd8d0d86162e
+oid sha256:ccba72281dc9a290f89ffb1ade8e85412a27e156a73f32f98f07081e5a0b7c57
 size 5496