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: feedback_p0.05_seed42_level2_raredirtybatch16
   results: []
@@ -22,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # feedback_p0.05_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": 3.147,
     "eval_steps_per_second": 0.944,
     "total_flos": 195037149265920.0,
-    "train_loss": 0.5025508344909291,
-    "train_runtime": 16743.285,
+    "train_loss": 0.0,
+    "train_runtime": 0.0084,
     "train_samples": 98952,
-    "train_samples_per_second": 1.78,
-    "train_steps_per_second": 0.111
+    "train_samples_per_second": 3568486.833,
+    "train_steps_per_second": 223052.876
 }

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/Sep22_05-05-45_COE-CS-sv003/events.out.tfevents.1726981611.COE-CS-sv003.654422.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb8cba0f3e68f5c8d82f578f9e4b396ce245c9a910d6407b49d6537c02fdad6
+size 5624

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 195037149265920.0,
-    "train_loss": 0.5025508344909291,
-    "train_runtime": 16743.285,
+    "train_loss": 0.0,
+    "train_runtime": 0.0084,
     "train_samples": 98952,
-    "train_samples_per_second": 1.78,
-    "train_steps_per_second": 0.111
+    "train_samples_per_second": 3568486.833,
+    "train_steps_per_second": 223052.876
 }

trainer_state.json

@@ -2630,10 +2630,10 @@
       "epoch": 1.0,
       "step": 1863,
       "total_flos": 195037149265920.0,
-      "train_loss": 0.5025508344909291,
-      "train_runtime": 16743.285,
-      "train_samples_per_second": 1.78,
-      "train_steps_per_second": 0.111
+      "train_loss": 0.0,
+      "train_runtime": 0.0084,
+      "train_samples_per_second": 3568486.833,
+      "train_steps_per_second": 223052.876
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba20262b91d1c5bd36ec84daa40444b32b0b2ded70bfd2d7bbb532d9644364c6
+oid sha256:9ec15cf7f3d7674b8632ba4265172cc34db912cf47629cdd878878ad6a4fb739
 size 7032