Model save

README.md

@@ -3,15 +3,10 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-Instruct-v0.2
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
-datasets:
-- preference-data
 model-index:
 - name: preference_p0.1_seed42_level3_stylemix
   results: []
@@ -22,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.1_seed42_level3_stylemix
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the preference-data dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset.
 
 ## Model description
 

all_results.json

@@ -5,9 +5,9 @@
     "eval_samples_per_second": 3.092,
     "eval_steps_per_second": 0.928,
     "total_flos": 6.266791881867264e+16,
-    "train_loss": 0.5434653141299719,
-    "train_runtime": 21156.3929,
+    "train_loss": 0.0,
+    "train_runtime": 0.0114,
     "train_samples": 98881,
-    "train_samples_per_second": 1.832,
-    "train_steps_per_second": 0.057
+    "train_samples_per_second": 3391435.371,
+    "train_steps_per_second": 105946.814
 }

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.44.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

runs/Sep17_12-32-05_COE-CS-sv004/events.out.tfevents.1726577157.COE-CS-sv004.2505167.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f29cd6bcfcb720fa8f1b1df2b8f53be79b8d13655ab6a29c2b95d3bd0ba887
+size 5596

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 0.9995872884853487,
     "total_flos": 6.266791881867264e+16,
-    "train_loss": 0.5434653141299719,
-    "train_runtime": 21156.3929,
+    "train_loss": 0.0,
+    "train_runtime": 0.0114,
     "train_samples": 98881,
-    "train_samples_per_second": 1.832,
-    "train_steps_per_second": 0.057
+    "train_samples_per_second": 3391435.371,
+    "train_steps_per_second": 105946.814
 }

trainer_state.json

@@ -1720,10 +1720,10 @@
       "epoch": 0.9995872884853487,
       "step": 1211,
       "total_flos": 6.266791881867264e+16,
-      "train_loss": 0.5434653141299719,
-      "train_runtime": 21156.3929,
-      "train_samples_per_second": 1.832,
-      "train_steps_per_second": 0.057
+      "train_loss": 0.0,
+      "train_runtime": 0.0114,
+      "train_samples_per_second": 3391435.371,
+      "train_steps_per_second": 105946.814
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82583aa9ade6c02a7d4b99f543b0d3d04f9f99e20b1efc7e83c95036fbf6c1f2
+oid sha256:7db03e9b760dd6162ba3fa85f02008527ac2d3eae2d43db7067d498194042ead
 size 7032