End of training

README.md

@@ -3,9 +3,16 @@ library_name: transformers
 license: apache-2.0
 base_model: pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-3Epochs
 tags:
+- alignment-handbook
 - trl
 - dpo
 - generated_from_trainer
+- trl
+- dpo
+- generated_from_trainer
+datasets:
+- pbevan11/multilingual-constitutional-preference-pairs
+- pbevan11/ultrafeedback_binarized_multilingual
 model-index:
 - name: Mistral-Nemo-Instruct-MCAI-SFT-DPO-3Epochs
   results: []
@@ -16,7 +23,17 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Mistral-Nemo-Instruct-MCAI-SFT-DPO-3Epochs
 
-This model is a fine-tuned version of [pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-3Epochs](https://huggingface.co/pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-3Epochs) on the None dataset.
+This model is a fine-tuned version of [pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-3Epochs](https://huggingface.co/pbevan11/Mistral-Nemo-Instruct-MCAI-SFT-3Epochs) on the pbevan11/multilingual-constitutional-preference-pairs and the pbevan11/ultrafeedback_binarized_multilingual datasets.
+It achieves the following results on the evaluation set:
+- Loss: 0.5579
+- Rewards/chosen: -0.4264
+- Rewards/rejected: -0.9042
+- Rewards/accuracies: 0.7466
+- Rewards/margins: 0.4777
+- Logps/rejected: -213.7833
+- Logps/chosen: -192.1762
+- Logits/rejected: 0.5653
+- Logits/chosen: 0.5394
 
 ## Model description
 

all_results.json

@@ -1,5 +1,18 @@
 {
     "epoch": 1.0,
+    "eval_logits/chosen": 0.539411723613739,
+    "eval_logits/rejected": 0.5653398036956787,
+    "eval_logps/chosen": -192.1762237548828,
+    "eval_logps/rejected": -213.7832794189453,
+    "eval_loss": 0.5578895807266235,
+    "eval_rewards/accuracies": 0.7466216087341309,
+    "eval_rewards/chosen": -0.42640554904937744,
+    "eval_rewards/margins": 0.47774478793144226,
+    "eval_rewards/rejected": -0.9041503667831421,
+    "eval_runtime": 231.2679,
+    "eval_samples": 2305,
+    "eval_samples_per_second": 9.967,
+    "eval_steps_per_second": 0.16,
     "total_flos": 0.0,
     "train_loss": 0.5964088123964976,
     "train_runtime": 1125.1043,

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": 0.539411723613739,
+    "eval_logits/rejected": 0.5653398036956787,
+    "eval_logps/chosen": -192.1762237548828,
+    "eval_logps/rejected": -213.7832794189453,
+    "eval_loss": 0.5578895807266235,
+    "eval_rewards/accuracies": 0.7466216087341309,
+    "eval_rewards/chosen": -0.42640554904937744,
+    "eval_rewards/margins": 0.47774478793144226,
+    "eval_rewards/rejected": -0.9041503667831421,
+    "eval_runtime": 231.2679,
+    "eval_samples": 2305,
+    "eval_samples_per_second": 9.967,
+    "eval_steps_per_second": 0.16
+}

runs/Sep30_15-39-35_280ca1cd997c/events.out.tfevents.1727712969.280ca1cd997c.3414.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c0ca00453dc877585f9bf652a37eabfd529e7f29374420009e81e4c9a8ffcf9
+size 815