End of training

README.md

@@ -3,9 +3,15 @@ library_name: transformers
 license: llama3.1
 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- tanliboy/orca_dpo_pairs
 model-index:
 - name: lambda-llama-3-8b-dpo-test-orca
   results: []
@@ -16,7 +22,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # lambda-llama-3-8b-dpo-test-orca
 
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the tanliboy/orca_dpo_pairs dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1235
+- Rewards/chosen: -2.8028
+- Rewards/rejected: -6.6852
+- Rewards/accuracies: 0.9643
+- Rewards/margins: 3.8824
+- Logps/rejected: -970.0546
+- Logps/chosen: -562.0943
+- Logits/rejected: -1.9611
+- Logits/chosen: -2.4346
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 0.9947643979057592,
+    "eval_logits/chosen": -2.4346187114715576,
+    "eval_logits/rejected": -1.9611175060272217,
+    "eval_logps/chosen": -562.0942993164062,
+    "eval_logps/rejected": -970.0545654296875,
+    "eval_loss": 0.12353485077619553,
+    "eval_rewards/accuracies": 0.9642857313156128,
+    "eval_rewards/chosen": -2.802823305130005,
+    "eval_rewards/margins": 3.8823659420013428,
+    "eval_rewards/rejected": -6.685189247131348,
+    "eval_runtime": 28.3026,
+    "eval_samples": 643,
+    "eval_samples_per_second": 22.719,
+    "eval_steps_per_second": 0.742,
     "total_flos": 0.0,
     "train_loss": 0.38092811358602424,
     "train_runtime": 1269.7396,

config.json

@@ -34,6 +34,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 128256
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.9947643979057592,
+    "eval_logits/chosen": -2.4346187114715576,
+    "eval_logits/rejected": -1.9611175060272217,
+    "eval_logps/chosen": -562.0942993164062,
+    "eval_logps/rejected": -970.0545654296875,
+    "eval_loss": 0.12353485077619553,
+    "eval_rewards/accuracies": 0.9642857313156128,
+    "eval_rewards/chosen": -2.802823305130005,
+    "eval_rewards/margins": 3.8823659420013428,
+    "eval_rewards/rejected": -6.685189247131348,
+    "eval_runtime": 28.3026,
+    "eval_samples": 643,
+    "eval_samples_per_second": 22.719,
+    "eval_steps_per_second": 0.742
+}

runs/Sep21_03-02-26_action-graph-trainer/events.out.tfevents.1726889465.action-graph-trainer.3128259.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52abb1016aed31a4d9dc6d838fcf0c76a39ecdb80e60977b426952993bfb4e96
+size 815