Model save

README.md

@@ -2,14 +2,9 @@
 license: mit
 base_model: HuggingFaceH4/mistral-7b-sft-beta
 tags:
-- alignment-handbook
-- generated_from_trainer
 - trl
 - dpo
 - generated_from_trainer
-datasets:
-- updated
-- original
 model-index:
 - name: 0.01_ablation_4iters_bs128_nodpo_iter_1
   results: []
@@ -20,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # 0.01_ablation_4iters_bs128_nodpo_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 updated and the original datasets.
+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": 0.5490188137823794,
-    "train_runtime": 3587.2769,
+    "train_runtime": 3582.4753,
     "train_samples": 15283,
-    "train_samples_per_second": 4.26,
+    "train_samples_per_second": 4.266,
     "train_steps_per_second": 0.033
 }

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": 0.5490188137823794,
-    "train_runtime": 3587.2769,
+    "train_runtime": 3582.4753,
     "train_samples": 15283,
-    "train_samples_per_second": 4.26,
+    "train_samples_per_second": 4.266,
     "train_steps_per_second": 0.033
 }

trainer_state.json

@@ -205,8 +205,8 @@
       "step": 119,
       "total_flos": 0.0,
       "train_loss": 0.5490188137823794,
-      "train_runtime": 3587.2769,
-      "train_samples_per_second": 4.26,
+      "train_runtime": 3582.4753,
+      "train_samples_per_second": 4.266,
       "train_steps_per_second": 0.033
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529d821c97437a9b989a1f96a34505d00f728f96f8280d807ae30f6671b4166f
+oid sha256:8a9cf604498e169f855af637bc7c725dab3540a7f233f2c61e8075edb57c0488
 size 6008