Model save

README.md

@@ -3,16 +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_syntaxcleanbatch16
   results: []
@@ -23,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.1_seed42_level2_syntaxcleanbatch16
 
-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

@@ -6,8 +6,8 @@
     "eval_steps_per_second": 0.7,
     "total_flos": 252093105438720.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0086,
+    "train_runtime": 0.0085,
     "train_samples": 98873,
-    "train_samples_per_second": 4498777.325,
-    "train_steps_per_second": 281231.978
+    "train_samples_per_second": 4527521.09,
+    "train_steps_per_second": 283028.837
 }

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/Sep21_05-04-47_COE-CS-sv003/events.out.tfevents.1726895142.COE-CS-sv003.508021.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db03b09656c58e2387999cc74dc63bad748d2d18feb6a808440c440af04de01
+size 5636

runs/Sep24_11-48-41_COE-CS-sv003/events.out.tfevents.1727178584.COE-CS-sv003.782924.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c5e859515973403ab484f29bbc7aec6de6650e3057a8c65ea68629c2e81405a
+size 5636

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 252093105438720.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0086,
+    "train_runtime": 0.0085,
     "train_samples": 98873,
-    "train_samples_per_second": 4498777.325,
-    "train_steps_per_second": 281231.978
+    "train_samples_per_second": 4527521.09,
+    "train_steps_per_second": 283028.837
 }

trainer_state.json

@@ -3394,9 +3394,9 @@
       "step": 2408,
       "total_flos": 252093105438720.0,
       "train_loss": 0.0,
-      "train_runtime": 0.0086,
-      "train_samples_per_second": 4498777.325,
-      "train_steps_per_second": 281231.978
+      "train_runtime": 0.0085,
+      "train_samples_per_second": 4527521.09,
+      "train_steps_per_second": 283028.837
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7b57c060a73ea290b5790196b9ae03f4116327ae602b84c4b5a55a6287b07ec
+oid sha256:5ac2c91cbabb95e107013286bf041f01055a74b0056df40e1b39a65e788b98ec
 size 7032