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_syntaxdirtybatch16
   results: []
@@ -22,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.1_seed42_level2_syntaxdirtybatch16
 
-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": 3.083,
     "eval_steps_per_second": 0.925,
     "total_flos": 252302485094400.0,
-    "train_loss": 0.5277333631555075,
-    "train_runtime": 21339.31,
+    "train_loss": 0.0,
+    "train_runtime": 0.0084,
     "train_samples": 98873,
-    "train_samples_per_second": 1.807,
-    "train_steps_per_second": 0.113
+    "train_samples_per_second": 4572412.844,
+    "train_steps_per_second": 285835.105
 }

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_11-52-09_COE-CS-sv003/events.out.tfevents.1727178790.COE-CS-sv003.783277.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3398618257e2cab1993636dd1e2481b0e2461edddfe452ee4c29f0c6ad177d7
+size 5636

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 252302485094400.0,
-    "train_loss": 0.5277333631555075,
-    "train_runtime": 21339.31,
+    "train_loss": 0.0,
+    "train_runtime": 0.0084,
     "train_samples": 98873,
-    "train_samples_per_second": 1.807,
-    "train_steps_per_second": 0.113
+    "train_samples_per_second": 4572412.844,
+    "train_steps_per_second": 285835.105
 }

trainer_state.json

@@ -3400,10 +3400,10 @@
       "epoch": 1.0,
       "step": 2410,
       "total_flos": 252302485094400.0,
-      "train_loss": 0.5277333631555075,
-      "train_runtime": 21339.31,
-      "train_samples_per_second": 1.807,
-      "train_steps_per_second": 0.113
+      "train_loss": 0.0,
+      "train_runtime": 0.0084,
+      "train_samples_per_second": 4572412.844,
+      "train_steps_per_second": 285835.105
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c7b45b26d2a61d4e5ec4bf1f0e09c6962529fb06f47382a22b6a6c86a1420ff
+oid sha256:b9f4c694cdbc73873eb9d340ffa2b447cac889323de54b9f716fa8ba9668848f
 size 7032