End of training

README.md

@@ -3,9 +3,16 @@ library_name: transformers
 license: apache-2.0
 base_model: pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-revision-only
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- pbevan11/multilingual-constitutional-preference-pairs-revision-only
+- pbevan11/ultrafeedback_binarized_multilingual
 model-index:
 - name: Mistral-Nemo-Instruct-MCAI-SFT-DPO-revision-only
   results: []
@@ -16,7 +23,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Mistral-Nemo-Instruct-MCAI-SFT-DPO-revision-only
 
-This model is a fine-tuned version of [pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-revision-only](https://huggingface.co/pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-revision-only) on the None dataset.
+This model is a fine-tuned version of [pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-revision-only](https://huggingface.co/pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-revision-only) on the pbevan11/multilingual-constitutional-preference-pairs-revision-only and the pbevan11/ultrafeedback_binarized_multilingual datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.5140
+- Rewards/chosen: -0.6440
+- Rewards/rejected: -1.3117
+- Rewards/accuracies: 0.6824
+- Rewards/margins: 0.6678
+- Logps/rejected: -215.4680
+- Logps/chosen: -196.1248
+- Logits/rejected: -0.0511
+- Logits/chosen: -0.0322
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": -0.03224845603108406,
+    "eval_logits/rejected": -0.051055099815130234,
+    "eval_logps/chosen": -196.12477111816406,
+    "eval_logps/rejected": -215.46804809570312,
+    "eval_loss": 0.5139751434326172,
+    "eval_rewards/accuracies": 0.6824324131011963,
+    "eval_rewards/chosen": -0.6439886093139648,
+    "eval_rewards/margins": 0.6677516102790833,
+    "eval_rewards/rejected": -1.3117402791976929,
+    "eval_runtime": 216.2859,
+    "eval_samples": 2341,
+    "eval_samples_per_second": 10.824,
+    "eval_steps_per_second": 0.171,
     "total_flos": 0.0,
     "train_loss": 0.5670995542988975,
     "train_runtime": 1780.4141,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 131072
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -0.03224845603108406,
+    "eval_logits/rejected": -0.051055099815130234,
+    "eval_logps/chosen": -196.12477111816406,
+    "eval_logps/rejected": -215.46804809570312,
+    "eval_loss": 0.5139751434326172,
+    "eval_rewards/accuracies": 0.6824324131011963,
+    "eval_rewards/chosen": -0.6439886093139648,
+    "eval_rewards/margins": 0.6677516102790833,
+    "eval_rewards/rejected": -1.3117402791976929,
+    "eval_runtime": 216.2859,
+    "eval_samples": 2341,
+    "eval_samples_per_second": 10.824,
+    "eval_steps_per_second": 0.171
+}

runs/Oct05_11-54-20_68660d2c5c1b/events.out.tfevents.1728131559.68660d2c5c1b.2665.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b93ed606d70a40984dcd9bf4cab55b5b65610e9e21aceabb10e50d2e468389ca
+size 828