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_p0.2_seed42_level2_raremixbatch16
   results: []
@@ -23,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # preference_p0.2_seed42_level2_raremixbatch16
 
-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.
 It achieves the following results on the evaluation set:
 - Loss: 0.2978
 

all_results.json

@@ -7,8 +7,8 @@
     "eval_steps_per_second": 0.726,
     "total_flos": 252616554577920.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0114,
+    "train_runtime": 0.0168,
     "train_samples": 98881,
-    "train_samples_per_second": 3374709.271,
-    "train_steps_per_second": 210930.256
+    "train_samples_per_second": 2300336.689,
+    "train_steps_per_second": 143778.491
 }

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/Sep15_22-45-09_COE-CS-sv004/events.out.tfevents.1726440649.COE-CS-sv004.2195195.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b475d59f8da642a78a2be0226419fe461518d2cea5c774143f977e82cae6833
+size 5620

train_results.json

@@ -2,8 +2,8 @@
     "epoch": 1.0,
     "total_flos": 252616554577920.0,
     "train_loss": 0.0,
-    "train_runtime": 0.0114,
+    "train_runtime": 0.0168,
     "train_samples": 98881,
-    "train_samples_per_second": 3374709.271,
-    "train_steps_per_second": 210930.256
+    "train_samples_per_second": 2300336.689,
+    "train_steps_per_second": 143778.491
 }

trainer_state.json

@@ -3402,9 +3402,9 @@
       "step": 2413,
       "total_flos": 252616554577920.0,
       "train_loss": 0.0,
-      "train_runtime": 0.0114,
-      "train_samples_per_second": 3374709.271,
-      "train_steps_per_second": 210930.256
+      "train_runtime": 0.0168,
+      "train_samples_per_second": 2300336.689,
+      "train_steps_per_second": 143778.491
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f601c7b20f78cffbc8d6ff050826de00392857a78353c245cf7f34118053e52
+oid sha256:e8c4cd34a8b532f002cb3131760a58b4cdf67a4d98d1a58674d5f7c6566d3f2e
 size 7032