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_stylemixbatch16
   results: []
@@ -22,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.1_seed42_level2_stylemixbatch16
 
-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": 3.078,
     "eval_steps_per_second": 0.924,
     "total_flos": 253663452856320.0,
-    "train_loss": 0.5332261629454912,
-    "train_runtime": 21421.0705,
+    "train_loss": 0.0,
+    "train_runtime": 0.0092,
     "train_samples": 98881,
-    "train_samples_per_second": 1.81,
-    "train_steps_per_second": 0.113
+    "train_samples_per_second": 4222296.524,
+    "train_steps_per_second": 263913.955
 }

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_11-28-16_COE-CS-sv003/events.out.tfevents.1727177359.COE-CS-sv003.780607.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4de32e4ef700866779915429360ab0f40f07e325e269e6b096dade2bc35ae32a
+size 5624

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 253663452856320.0,
-    "train_loss": 0.5332261629454912,
-    "train_runtime": 21421.0705,
+    "train_loss": 0.0,
+    "train_runtime": 0.0092,
     "train_samples": 98881,
-    "train_samples_per_second": 1.81,
-    "train_steps_per_second": 0.113
+    "train_samples_per_second": 4222296.524,
+    "train_steps_per_second": 263913.955
 }

trainer_state.json

@@ -3414,10 +3414,10 @@
       "epoch": 1.0,
       "step": 2423,
       "total_flos": 253663452856320.0,
-      "train_loss": 0.5332261629454912,
-      "train_runtime": 21421.0705,
-      "train_samples_per_second": 1.81,
-      "train_steps_per_second": 0.113
+      "train_loss": 0.0,
+      "train_runtime": 0.0092,
+      "train_samples_per_second": 4222296.524,
+      "train_steps_per_second": 263913.955
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c940ca7bee6a9692f918e0f0e6e537af3cc6e108a875f8821b7f3d521a5e5aea
+oid sha256:79cbbe05e7c7b7829ed6e1bbb580fb2965f046fc6fd452c201b5c6aebf3e6910
 size 7032