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_raredirtybatch16
   results: []
@@ -22,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.1_seed42_level2_raredirtybatch16
 
-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": 4.017,
     "eval_steps_per_second": 1.205,
     "total_flos": 252721244405760.0,
-    "train_loss": 0.5154845056794553,
-    "train_runtime": 25692.1832,
+    "train_loss": 0.0,
+    "train_runtime": 0.0084,
     "train_samples": 98881,
-    "train_samples_per_second": 1.503,
-    "train_steps_per_second": 0.094
+    "train_samples_per_second": 4618577.431,
+    "train_steps_per_second": 288668.563
 }

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_11-24-38_COE-CS-sv003/events.out.tfevents.1727177144.COE-CS-sv003.780245.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a854c37190146b8b7d541f827d52acc11b9d8d49dee77a86d9c855c943d759ad
+size 5628

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 252721244405760.0,
-    "train_loss": 0.5154845056794553,
-    "train_runtime": 25692.1832,
+    "train_loss": 0.0,
+    "train_runtime": 0.0084,
     "train_samples": 98881,
-    "train_samples_per_second": 1.503,
-    "train_steps_per_second": 0.094
+    "train_samples_per_second": 4618577.431,
+    "train_steps_per_second": 288668.563
 }

trainer_state.json

@@ -3400,10 +3400,10 @@
       "epoch": 1.0,
       "step": 2414,
       "total_flos": 252721244405760.0,
-      "train_loss": 0.5154845056794553,
-      "train_runtime": 25692.1832,
-      "train_samples_per_second": 1.503,
-      "train_steps_per_second": 0.094
+      "train_loss": 0.0,
+      "train_runtime": 0.0084,
+      "train_samples_per_second": 4618577.431,
+      "train_steps_per_second": 288668.563
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f33b878ca97e7dd652ce2dc84216d23f932e49346283212187995d9aaf880cfd
+oid sha256:7d2dd54a4b21fd36845a9bb8599650144d3e8dd6c71b388b45e22df8c4d933ef
 size 7032