End of training

README.md

@@ -1,7 +1,12 @@
 ---
 base_model: slm-research-vn/Qwen2-7B-Instruct-SPPO-Function-call-v2.1
+datasets:
+- slm-research-vn/dpo-format-function-calling-v4
+- slm-research-vn/dpo-format-glaive-code-assistant-v3-with-mistral-large-slm-iter4
+- argilla/dpo-mix-7k
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
@@ -15,17 +20,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Qwen2-7B-Instruct-SPPO-Function-call-v2.4
 
-This model is a fine-tuned version of [slm-research-vn/Qwen2-7B-Instruct-SPPO-Function-call-v2.1](https://huggingface.co/slm-research-vn/Qwen2-7B-Instruct-SPPO-Function-call-v2.1) on the None dataset.
+This model is a fine-tuned version of [slm-research-vn/Qwen2-7B-Instruct-SPPO-Function-call-v2.1](https://huggingface.co/slm-research-vn/Qwen2-7B-Instruct-SPPO-Function-call-v2.1) on the slm-research-vn/dpo-format-function-calling-v4, the slm-research-vn/dpo-format-glaive-code-assistant-v3-with-mistral-large-slm-iter4 and the argilla/dpo-mix-7k datasets.
 It achieves the following results on the evaluation set:
-- Loss: 0.3144
-- Rewards/chosen: 1.9968
-- Rewards/rejected: 0.2178
-- Rewards/accuracies: 0.8844
-- Rewards/margins: 1.7789
-- Logps/rejected: -267.1377
-- Logps/chosen: -202.5171
-- Logits/rejected: -0.6136
-- Logits/chosen: -0.6052
+- Loss: 0.3152
+- Rewards/chosen: 1.9961
+- Rewards/rejected: 0.2161
+- Rewards/accuracies: 0.8815
+- Rewards/margins: 1.7800
+- Logps/rejected: -267.1725
+- Logps/chosen: -202.5304
+- Logits/rejected: -0.6205
+- Logits/chosen: -0.6185
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -0.6185179352760315,
+    "eval_logits/rejected": -0.6204895973205566,
+    "eval_logps/chosen": -202.53036499023438,
+    "eval_logps/rejected": -267.17254638671875,
+    "eval_loss": 0.3152291178703308,
+    "eval_rewards/accuracies": 0.8815028667449951,
+    "eval_rewards/chosen": 1.9960932731628418,
+    "eval_rewards/margins": 1.7800120115280151,
+    "eval_rewards/rejected": 0.2160811871290207,
+    "eval_runtime": 252.3512,
+    "eval_samples": 2763,
+    "eval_samples_per_second": 10.949,
+    "eval_steps_per_second": 1.371,
     "total_flos": 0.0,
     "train_loss": 0.39260031933687173,
     "train_runtime": 7916.79,

eval_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 0.9996824388694824,
-    "eval_logits/chosen": -0.7089246511459351,
-    "eval_logits/rejected": -0.7224333882331848,
-    "eval_logps/chosen": -261.0423889160156,
-    "eval_logps/rejected": -333.52276611328125,
-    "eval_loss": 0.4344652593135834,
-    "eval_rewards/accuracies": 0.8185185194015503,
-    "eval_rewards/chosen": 1.3033398389816284,
-    "eval_rewards/margins": 1.0257779359817505,
-    "eval_rewards/rejected": 0.27756187319755554,
-    "eval_runtime": 185.0205,
-    "eval_samples": 2155,
-    "eval_samples_per_second": 11.647,
-    "eval_steps_per_second": 1.459
+    "epoch": 1.0,
+    "eval_logits/chosen": -0.6185179352760315,
+    "eval_logits/rejected": -0.6204895973205566,
+    "eval_logps/chosen": -202.53036499023438,
+    "eval_logps/rejected": -267.17254638671875,
+    "eval_loss": 0.3152291178703308,
+    "eval_rewards/accuracies": 0.8815028667449951,
+    "eval_rewards/chosen": 1.9960932731628418,
+    "eval_rewards/margins": 1.7800120115280151,
+    "eval_rewards/rejected": 0.2160811871290207,
+    "eval_runtime": 252.3512,
+    "eval_samples": 2763,
+    "eval_samples_per_second": 10.949,
+    "eval_steps_per_second": 1.371
 }