End of training

README.md

@@ -2,11 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - dpo
-- alignment-handbook
 - generated_from_trainer
 base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+datasets:
+- openai/summarize_from_feedback
 model-index:
 - name: tinyllama-1.1b-sum-dpo-qlora
   results: []
@@ -17,17 +19,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-sum-dpo-qlora
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on an unknown dataset.
+This model is a fine-tuned version of [martimfasantos/tinyllama-1.1b-sum-sft-qlora](https://huggingface.co/martimfasantos/tinyllama-1.1b-sum-sft-qlora) on the openai/summarize_from_feedback dataset.
 It achieves the following results on the evaluation set:
-- Logits/chosen: -3.0239
-- Logits/rejected: -3.0176
-- Logps/chosen: -166.7881
-- Logps/rejected: -187.0472
 - Loss: 0.6482
-- Rewards/accuracies: 0.6171
 - Rewards/chosen: -0.9538
-- Rewards/margins: 0.1656
 - Rewards/rejected: -1.1194
+- Rewards/accuracies: 0.6171
+- Rewards/margins: 0.1656
+- Logps/rejected: -187.0472
+- Logps/chosen: -166.7881
+- Logits/rejected: -3.0176
+- Logits/chosen: -3.0239
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -3.023923397064209,
+    "eval_logits/rejected": -3.017603874206543,
+    "eval_logps/chosen": -166.78807067871094,
+    "eval_logps/rejected": -187.0471954345703,
+    "eval_loss": 0.6481729745864868,
+    "eval_rewards/accuracies": 0.6171003580093384,
+    "eval_rewards/chosen": -0.9537805914878845,
+    "eval_rewards/margins": 0.1656205952167511,
+    "eval_rewards/rejected": -1.1194013357162476,
+    "eval_runtime": 483.9291,
+    "eval_samples": 4304,
+    "eval_samples_per_second": 8.894,
+    "eval_steps_per_second": 1.112,
     "train_loss": 0.0003277428618961422,
     "train_runtime": 17.7068,
     "train_samples": 92858,

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -3.023923397064209,
+    "eval_logits/rejected": -3.017603874206543,
+    "eval_logps/chosen": -166.78807067871094,
+    "eval_logps/rejected": -187.0471954345703,
+    "eval_loss": 0.6481729745864868,
+    "eval_rewards/accuracies": 0.6171003580093384,
+    "eval_rewards/chosen": -0.9537805914878845,
+    "eval_rewards/margins": 0.1656205952167511,
+    "eval_rewards/rejected": -1.1194013357162476,
+    "eval_runtime": 483.9291,
+    "eval_samples": 4304,
+    "eval_samples_per_second": 8.894,
+    "eval_steps_per_second": 1.112
+}

runs/May10_17-24-35_poseidon/events.out.tfevents.1715362408.poseidon.2825808.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17351d92b525e2982b03f12e406dede84638b2c14162f66f4796dfa5070a83b8
+size 828