Model save

README.md

@@ -1,20 +1,17 @@
 ---
 base_model: mistralai/Mistral-7B-v0.1
-datasets: HuggingFaceH4/ultrafeedback_binarized
 library_name: transformers
-model_name: mistralai/Mistral-7B-v0.1
+model_name: math_ultrachatmistral32_4_3
 tags:
 - generated_from_trainer
-- alignment-handbook
-- HuggingFaceH4/ultrafeedback_binarized
 - trl
 - dpo
 licence: license
 ---
 
-# Model Card for mistralai/Mistral-7B-v0.1
+# Model Card for math_ultrachatmistral32_4_3
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the [HuggingFaceH4/ultrafeedback_binarized](https://huggingface.co/datasets/HuggingFaceH4/ultrafeedback_binarized) dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start

all_results.json

@@ -14,9 +14,9 @@
     "eval_samples_per_second": 17.291,
     "eval_steps_per_second": 0.139,
     "total_flos": 0.0,
-    "train_loss": 0.676513671875,
-    "train_runtime": 3055.0984,
+    "train_loss": 0.0,
+    "train_runtime": 0.0144,
     "train_samples": 5776,
-    "train_samples_per_second": 5.874,
-    "train_steps_per_second": 0.008
+    "train_samples_per_second": 1249870.973,
+    "train_steps_per_second": 1671.509
 }

runs/Jun04_13-49-16_cn-d004.server.mila.quebec/events.out.tfevents.1749059573.cn-d004.server.mila.quebec.3254818.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbedf723673ea5b0c9cf2b54b0ed8e90169a0a88308d9eff97076c66c64d3955
+size 6427

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 0.0,
-    "train_loss": 0.676513671875,
-    "train_runtime": 3055.0984,
+    "train_loss": 0.0,
+    "train_runtime": 0.0144,
     "train_samples": 5776,
-    "train_samples_per_second": 5.874,
-    "train_steps_per_second": 0.008
+    "train_samples_per_second": 1249870.973,
+    "train_steps_per_second": 1671.509
 }

trainer_state.json

@@ -43,10 +43,10 @@
       "epoch": 1.0,
       "step": 24,
       "total_flos": 0.0,
-      "train_loss": 0.676513671875,
-      "train_runtime": 3055.0984,
-      "train_samples_per_second": 5.874,
-      "train_steps_per_second": 0.008
+      "train_loss": 0.0,
+      "train_runtime": 0.0144,
+      "train_samples_per_second": 1249870.973,
+      "train_steps_per_second": 1671.509
     }
   ],
   "logging_steps": 20,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6303bdf060efe7d91327d9dd58b2614aa6f548519c1a96381816ba3e68d68547
+oid sha256:4ce2a6f13889d9d9ddb9f2427b82c40679930850515e595db3187099f489153a
 size 8209