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_idpo_noreplacerej_iter_1
   results: []
@@ -19,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 0.001_idpo_noreplacerej_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": 0.6063382550605438,
-    "train_runtime": 2626.1756,
+    "train_runtime": 2647.1387,
     "train_samples": 20378,
-    "train_samples_per_second": 7.76,
-    "train_steps_per_second": 0.061
+    "train_samples_per_second": 7.698,
+    "train_steps_per_second": 0.06
 }

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": 0.6063382550605438,
-    "train_runtime": 2626.1756,
+    "train_runtime": 2647.1387,
     "train_samples": 20378,
-    "train_samples_per_second": 7.76,
-    "train_steps_per_second": 0.061
+    "train_samples_per_second": 7.698,
+    "train_steps_per_second": 0.06
 }

trainer_state.json

@@ -237,9 +237,9 @@
       "step": 159,
       "total_flos": 0.0,
       "train_loss": 0.6063382550605438,
-      "train_runtime": 2626.1756,
-      "train_samples_per_second": 7.76,
-      "train_steps_per_second": 0.061
+      "train_runtime": 2647.1387,
+      "train_samples_per_second": 7.698,
+      "train_steps_per_second": 0.06
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a3466ed1604ae2fa960e81346581a9e90a87caac0e156aa8518c901c425532
+oid sha256:794467fa1f38a47d2e48c6c02f093849019c2db508d808d7ee06a84183b3c312
 size 6008