End of training

README.md

@@ -3,6 +3,8 @@ library_name: transformers
 license: llama3.1
 base_model: mlfoundations-dev/stackoverflow_25000tasks_1p
 tags:
+- llama-factory
+- full
 - trl
 - dpo
 - llama-factory
@@ -17,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # simpo-stackoverflow_25000tasks_1p
 
-This model is a fine-tuned version of [mlfoundations-dev/stackoverflow_25000tasks_1p](https://huggingface.co/mlfoundations-dev/stackoverflow_25000tasks_1p) on an unknown dataset.
+This model is a fine-tuned version of [mlfoundations-dev/stackoverflow_25000tasks_1p](https://huggingface.co/mlfoundations-dev/stackoverflow_25000tasks_1p) on the mlfoundations-dev/gemma2-ultrafeedback-armorm dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.5764
 - Rewards/chosen: -41.7245

all_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 0.9997172745264349,
+    "eval_logits/chosen": -1.0220762491226196,
+    "eval_logits/rejected": -1.0401626825332642,
+    "eval_logps/chosen": -4.1724467277526855,
+    "eval_logps/rejected": -4.85194206237793,
+    "eval_loss": 2.5764122009277344,
+    "eval_rewards/accuracies": 0.7931150197982788,
+    "eval_rewards/chosen": -41.724464416503906,
+    "eval_rewards/margins": 6.794952392578125,
+    "eval_rewards/rejected": -48.51942443847656,
+    "eval_runtime": 50.6713,
+    "eval_samples_per_second": 58.791,
+    "eval_steps_per_second": 3.69,
+    "total_flos": 134366991482880.0,
+    "train_loss": 3.350108276664941,
+    "train_runtime": 3771.9425,
+    "train_samples_per_second": 15.003,
+    "train_steps_per_second": 0.117
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.9997172745264349,
+    "eval_logits/chosen": -1.0220762491226196,
+    "eval_logits/rejected": -1.0401626825332642,
+    "eval_logps/chosen": -4.1724467277526855,
+    "eval_logps/rejected": -4.85194206237793,
+    "eval_loss": 2.5764122009277344,
+    "eval_rewards/accuracies": 0.7931150197982788,
+    "eval_rewards/chosen": -41.724464416503906,
+    "eval_rewards/margins": 6.794952392578125,
+    "eval_rewards/rejected": -48.51942443847656,
+    "eval_runtime": 50.6713,
+    "eval_samples_per_second": 58.791,
+    "eval_steps_per_second": 3.69
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9997172745264349,
+    "total_flos": 134366991482880.0,
+    "train_loss": 3.350108276664941,
+    "train_runtime": 3771.9425,
+    "train_samples_per_second": 15.003,
+    "train_steps_per_second": 0.117
+}