Model save

README.md

@@ -3,16 +3,10 @@ library_name: transformers
 license: apache-2.0
 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 tags:
-- alignment-handbook
-- trl
-- dpo
-- generated_from_trainer
 - trl
 - dpo
+- alignment-handbook
 - generated_from_trainer
-datasets:
-- data/ui_math_ref
-- data/ui_coding_ref
 model-index:
 - name: tinyllama-1.1b-chat-v1.0-ui-math-coding-group-dpo
   results: []
@@ -23,17 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-chat-v1.0-ui-math-coding-group-dpo
 
-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 data/ui_math_ref and the data/ui_coding_ref datasets.
-It achieves the following results on the evaluation set:
-- Loss: 0.6931
-- Rewards/chosen: 0.0
-- Rewards/rejected: 0.0
-- Rewards/accuracies: 0.0
-- Rewards/margins: 0.0
-- Logps/rejected: -291.9316
-- Logps/chosen: -308.5898
-- Logits/rejected: -2.1579
-- Logits/chosen: -2.1562
+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.
 
 ## Model description
 

all_results.json

@@ -1,5 +1,5 @@
 {
-    "epoch": 1.0,
+    "epoch": 0.9963369963369964,
     "eval_logits/chosen": -2.156226873397827,
     "eval_logits/rejected": -2.1579225063323975,
     "eval_logps/chosen": -308.5898132324219,
@@ -14,9 +14,9 @@
     "eval_samples_per_second": 66.156,
     "eval_steps_per_second": 0.662,
     "total_flos": 0.0,
-    "train_loss": 0.016206350177526474,
-    "train_runtime": 33.2224,
-    "train_samples": 99,
-    "train_samples_per_second": 2.98,
-    "train_steps_per_second": 0.03
+    "train_loss": 0.09771968247186319,
+    "train_runtime": 5407.8058,
+    "train_samples": 209650,
+    "train_samples_per_second": 38.768,
+    "train_steps_per_second": 0.038
 }

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 1.0,
+    "epoch": 0.9963369963369964,
     "total_flos": 0.0,
-    "train_loss": 0.016206350177526474,
-    "train_runtime": 33.2224,
-    "train_samples": 99,
-    "train_samples_per_second": 2.98,
-    "train_steps_per_second": 0.03
+    "train_loss": 0.09771968247186319,
+    "train_runtime": 5407.8058,
+    "train_samples": 209650,
+    "train_samples_per_second": 38.768,
+    "train_steps_per_second": 0.038
 }