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_level2_styledirtybatch16
   results: []
@@ -22,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.1_seed42_level2_styledirtybatch16
 
-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": 4.034,
     "eval_steps_per_second": 1.21,
     "total_flos": 228328514519040.0,
-    "train_loss": 0.5532772317904499,
-    "train_runtime": 23497.974,
+    "train_loss": 0.0,
+    "train_runtime": 0.0089,
     "train_samples": 88990,
-    "train_samples_per_second": 1.484,
-    "train_steps_per_second": 0.093
+    "train_samples_per_second": 3927873.864,
+    "train_steps_per_second": 245597.686
 }

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/Sep24_11-35-23_COE-CS-sv003/events.out.tfevents.1727177787.COE-CS-sv003.781312.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d82828d79244bfd19840e2a2def798e7f8da85ebf943baed0109d539336eb4e8
+size 5632

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 228328514519040.0,
-    "train_loss": 0.5532772317904499,
-    "train_runtime": 23497.974,
+    "train_loss": 0.0,
+    "train_runtime": 0.0089,
     "train_samples": 88990,
-    "train_samples_per_second": 1.484,
-    "train_steps_per_second": 0.093
+    "train_samples_per_second": 3927873.864,
+    "train_steps_per_second": 245597.686
 }

trainer_state.json

@@ -3078,10 +3078,10 @@
       "epoch": 1.0,
       "step": 2181,
       "total_flos": 228328514519040.0,
-      "train_loss": 0.5532772317904499,
-      "train_runtime": 23497.974,
-      "train_samples_per_second": 1.484,
-      "train_steps_per_second": 0.093
+      "train_loss": 0.0,
+      "train_runtime": 0.0089,
+      "train_samples_per_second": 3927873.864,
+      "train_steps_per_second": 245597.686
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd00014f3441848b183e295ee69da00b47678cb5098e119097a4cee8c8282db2
+oid sha256:b36b32d9b83d115b27cf8088220fd98cdad11b8eaf483607ab43048c73377417
 size 7032