End of training

README.md

@@ -18,20 +18,20 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/xzcjqvtn)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/loubnabnl/huggingface/runs/ellmeibr)
 # cosmo2-1.7B-webinst-sc2-dpo-helpsteer-ep1
 
 This model is a fine-tuned version of [HuggingFaceTB/cosmo2-1.7B-webinst-sc2](https://huggingface.co/HuggingFaceTB/cosmo2-1.7B-webinst-sc2) on the HuggingFaceTB/Helpsteer dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6675
-- Rewards/chosen: -0.0462
-- Rewards/rejected: -0.0926
-- Rewards/accuracies: 0.5667
-- Rewards/margins: 0.0464
-- Logps/rejected: -149.4179
-- Logps/chosen: -121.9775
-- Logits/rejected: 0.8652
-- Logits/chosen: 0.9563
+- Loss: 0.6672
+- Rewards/chosen: -0.0466
+- Rewards/rejected: -0.0933
+- Rewards/accuracies: 0.5500
+- Rewards/margins: 0.0467
+- Logps/rejected: -149.4311
+- Logps/chosen: -121.9851
+- Logits/rejected: 0.8632
+- Logits/chosen: 0.9551
 
 ## Model description
 

all_results.json

@@ -1,18 +1,18 @@
 {
     "epoch": 0.9872958257713249,
-    "eval_logits/chosen": 0.9563044309616089,
-    "eval_logits/rejected": 0.865182638168335,
-    "eval_logps/chosen": -121.97750854492188,
-    "eval_logps/rejected": -149.4178924560547,
-    "eval_loss": 0.6674867272377014,
-    "eval_rewards/accuracies": 0.5666666626930237,
-    "eval_rewards/chosen": -0.04618287831544876,
-    "eval_rewards/margins": 0.046417996287345886,
-    "eval_rewards/rejected": -0.09260086715221405,
-    "eval_runtime": 4.5645,
+    "eval_logits/chosen": 0.9550817608833313,
+    "eval_logits/rejected": 0.8631864190101624,
+    "eval_logps/chosen": -121.98506164550781,
+    "eval_logps/rejected": -149.43112182617188,
+    "eval_loss": 0.6671856641769409,
+    "eval_rewards/accuracies": 0.550000011920929,
+    "eval_rewards/chosen": -0.0465608611702919,
+    "eval_rewards/margins": 0.04670196771621704,
+    "eval_rewards/rejected": -0.09326283633708954,
+    "eval_runtime": 4.6203,
     "eval_samples": 464,
-    "eval_samples_per_second": 101.654,
-    "eval_steps_per_second": 3.286,
+    "eval_samples_per_second": 100.425,
+    "eval_steps_per_second": 3.247,
     "total_flos": 0.0,
     "train_loss": 0.6753217893488267,
     "train_runtime": 321.7901,

eval_results.json

@@ -1,16 +1,16 @@
 {
     "epoch": 0.9872958257713249,
-    "eval_logits/chosen": 0.9563044309616089,
-    "eval_logits/rejected": 0.865182638168335,
-    "eval_logps/chosen": -121.97750854492188,
-    "eval_logps/rejected": -149.4178924560547,
-    "eval_loss": 0.6674867272377014,
-    "eval_rewards/accuracies": 0.5666666626930237,
-    "eval_rewards/chosen": -0.04618287831544876,
-    "eval_rewards/margins": 0.046417996287345886,
-    "eval_rewards/rejected": -0.09260086715221405,
-    "eval_runtime": 4.5645,
+    "eval_logits/chosen": 0.9550817608833313,
+    "eval_logits/rejected": 0.8631864190101624,
+    "eval_logps/chosen": -121.98506164550781,
+    "eval_logps/rejected": -149.43112182617188,
+    "eval_loss": 0.6671856641769409,
+    "eval_rewards/accuracies": 0.550000011920929,
+    "eval_rewards/chosen": -0.0465608611702919,
+    "eval_rewards/margins": 0.04670196771621704,
+    "eval_rewards/rejected": -0.09326283633708954,
+    "eval_runtime": 4.6203,
     "eval_samples": 464,
-    "eval_samples_per_second": 101.654,
-    "eval_steps_per_second": 3.286
+    "eval_samples_per_second": 100.425,
+    "eval_steps_per_second": 3.247
 }

runs/Jul15_23-01-52_ip-26-0-171-168/events.out.tfevents.1721085183.ip-26-0-171-168.1537695.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27a6a863f4bf58d6242e050e5e56402f3611cf866ad775259a318e644ad89c3d
+size 815