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_syntaxmixbatch16
   results: []
@@ -22,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.1_seed42_level2_syntaxmixbatch16
 
-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": 3.076,
     "eval_steps_per_second": 0.923,
     "total_flos": 252302485094400.0,
-    "train_loss": 0.532793834051156,
-    "train_runtime": 21449.5235,
+    "train_loss": 0.0,
+    "train_runtime": 0.0091,
     "train_samples": 98873,
-    "train_samples_per_second": 1.797,
-    "train_steps_per_second": 0.112
+    "train_samples_per_second": 4252334.509,
+    "train_steps_per_second": 265770.907
 }

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_11-39-07_COE-CS-sv003/events.out.tfevents.1727178370.COE-CS-sv003.781675.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06fa62e995a7265cfdbd6bbd2cdd67b87657fab057e1d6aaff04c992e993668a
+size 5628

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 252302485094400.0,
-    "train_loss": 0.532793834051156,
-    "train_runtime": 21449.5235,
+    "train_loss": 0.0,
+    "train_runtime": 0.0091,
     "train_samples": 98873,
-    "train_samples_per_second": 1.797,
-    "train_steps_per_second": 0.112
+    "train_samples_per_second": 4252334.509,
+    "train_steps_per_second": 265770.907
 }

trainer_state.json

@@ -3400,14 +3400,14 @@
       "epoch": 1.0,
       "step": 2410,
       "total_flos": 252302485094400.0,
-      "train_loss": 0.532793834051156,
-      "train_runtime": 21449.5235,
-      "train_samples_per_second": 1.797,
-      "train_steps_per_second": 0.112
+      "train_loss": 0.0,
+      "train_runtime": 0.0091,
+      "train_samples_per_second": 4252334.509,
+      "train_steps_per_second": 265770.907
     }
   ],
   "logging_steps": 5,
-  "max_steps": 2410,
+  "max_steps": 2409,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2684308020b21b2b93aa923fa39aeb36b7abf59fbf74d6bdaafc9d89803e9f2
+oid sha256:7f05a918c8bd6a079a3110d5e0e6c1e9f3027d7250df1f53442242c8a9435327
 size 7032