End of training

README.md

@@ -3,11 +3,16 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-Nemo-Base-2407
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- pbevan11/multilingual-constitutional-preference-pairs-revision-only
+- pbevan11/ultrafeedback_binarized_multilingual
 model-index:
 - name: Mistral-Nemo-Instruct-MCAI-SFT-revision-only
   results: []
@@ -18,7 +23,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # Mistral-Nemo-Instruct-MCAI-SFT-revision-only
 
-This model is a fine-tuned version of [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) 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: 1.1494
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.8363636363636364,
+    "eval_loss": 1.1494024991989136,
+    "eval_runtime": 16.7764,
+    "eval_samples": 2341,
+    "eval_samples_per_second": 23.903,
+    "eval_steps_per_second": 0.417,
     "total_flos": 50553107251200.0,
     "train_loss": 1.2458087847783015,
     "train_runtime": 1582.9273,

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 +1,8 @@
+{
+    "epoch": 2.8363636363636364,
+    "eval_loss": 1.1494024991989136,
+    "eval_runtime": 16.7764,
+    "eval_samples": 2341,
+    "eval_samples_per_second": 23.903,
+    "eval_steps_per_second": 0.417
+}

runs/Oct05_07-19-13_400ec9955dd3/events.out.tfevents.1728114718.400ec9955dd3.1668.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f1a5df3e9a8445908d5e2b32baceb07984b8b07a56828dce8421547123a98e
+size 354