Model save

README.md

@@ -2,13 +2,9 @@
 license: mit
 base_model: HuggingFaceH4/mistral-7b-sft-beta
 tags:
-- alignment-handbook
-- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
-datasets:
-- HuggingFaceH4/ultrafeedback_binarized
 model-index:
 - name: 0.001_ablation_5iters_bs256_useresponse_iter_1
   results: []
@@ -19,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 0.001_ablation_5iters_bs256_useresponse_iter_1
 
-This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the HuggingFaceH4/ultrafeedback_binarized dataset.
+This model is a fine-tuned version of [HuggingFaceH4/mistral-7b-sft-beta](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta) on the None dataset.
 
 ## Model description
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.6586156586805979,
-    "train_runtime": 1568.1432,
+    "train_runtime": 1568.8191,
     "train_samples": 12227,
-    "train_samples_per_second": 7.797,
+    "train_samples_per_second": 7.794,
     "train_steps_per_second": 0.031
 }

config.json

@@ -21,6 +21,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.36.2",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.6586156586805979,
-    "train_runtime": 1568.1432,
+    "train_runtime": 1568.8191,
     "train_samples": 12227,
-    "train_samples_per_second": 7.797,
+    "train_samples_per_second": 7.794,
     "train_steps_per_second": 0.031
 }

trainer_state.json

@@ -83,8 +83,8 @@
       "step": 48,
       "total_flos": 0.0,
       "train_loss": 0.6586156586805979,
-      "train_runtime": 1568.1432,
-      "train_samples_per_second": 7.797,
+      "train_runtime": 1568.8191,
+      "train_samples_per_second": 7.794,
       "train_steps_per_second": 0.031
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f90809a5038805d2a38eb324d516f4f17de5e1916473427b7d0ba6ad8f4289a
+oid sha256:f502b7122662c0249e61734395c5160b2de5a88e885168b906dabfa4ded72faf
 size 6072