Model save

README.md

@@ -2,14 +2,10 @@
 license: apache-2.0
 library_name: peft
 tags:
-- alignment-handbook
-- generated_from_trainer
 - trl
 - dpo
+- generated_from_trainer
 base_model: mistralai/Mistral-7B-v0.1
-datasets:
-- updated
-- original
 model-index:
 - name: zephyr-7b-dpo-qlora-min-pi-part-0
   results: []
@@ -20,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-dpo-qlora-min-pi-part-0
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-qlora](https://huggingface.co/alignment-handbook/zephyr-7b-sft-qlora) on the updated and the original datasets.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
 
 ## Model description
 
@@ -61,6 +57,6 @@ The following hyperparameters were used during training:
 
 - PEFT 0.7.1
 - Transformers 4.36.2
-- Pytorch 2.2.2+cu121
+- Pytorch 2.1.2+cu121
 - Datasets 2.14.6
 - Tokenizers 0.15.2

adapter_config.json

@@ -19,13 +19,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "v_proj",
+    "k_proj",
     "gate_proj",
-    "up_proj",
+    "v_proj",
+    "down_proj",
     "o_proj",
-    "q_proj",
-    "k_proj"
+    "up_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

all_results.json

@@ -1,8 +1,21 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.6650766546909626,
-    "train_runtime": 4758.2952,
+    "eval_logits/chosen": -2.498661994934082,
+    "eval_logits/rejected": -2.4008209705352783,
+    "eval_logps/chosen": -269.65570068359375,
+    "eval_logps/rejected": -257.6377868652344,
+    "eval_loss": 0.6512373089790344,
+    "eval_rewards/accuracies": 0.6639999747276306,
+    "eval_rewards/chosen": -0.06204665079712868,
+    "eval_rewards/margins": 0.10243026912212372,
+    "eval_rewards/rejected": -0.1644769161939621,
+    "eval_runtime": 542.9483,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 3.684,
+    "eval_steps_per_second": 0.46,
+    "train_loss": 0.0,
+    "train_runtime": 0.0278,
     "train_samples": 10000,
-    "train_samples_per_second": 2.102,
-    "train_steps_per_second": 0.008
+    "train_samples_per_second": 359461.447,
+    "train_steps_per_second": 1401.9
 }

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.498661994934082,
+    "eval_logits/rejected": -2.4008209705352783,
+    "eval_logps/chosen": -269.65570068359375,
+    "eval_logps/rejected": -257.6377868652344,
+    "eval_loss": 0.6512373089790344,
+    "eval_rewards/accuracies": 0.6639999747276306,
+    "eval_rewards/chosen": -0.06204665079712868,
+    "eval_rewards/margins": 0.10243026912212372,
+    "eval_rewards/rejected": -0.1644769161939621,
+    "eval_runtime": 542.9483,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 3.684,
+    "eval_steps_per_second": 0.46
+}

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "train_loss": 0.6650766546909626,
-    "train_runtime": 4758.2952,
+    "train_loss": 0.0,
+    "train_runtime": 0.0278,
     "train_samples": 10000,
-    "train_samples_per_second": 2.102,
-    "train_steps_per_second": 0.008
+    "train_samples_per_second": 359461.447,
+    "train_steps_per_second": 1401.9
 }

trainer_state.json

@@ -68,10 +68,10 @@
       "epoch": 1.0,
       "step": 39,
       "total_flos": 0.0,
-      "train_loss": 0.6650766546909626,
-      "train_runtime": 4758.2952,
-      "train_samples_per_second": 2.102,
-      "train_steps_per_second": 0.008
+      "train_loss": 0.0,
+      "train_runtime": 0.0278,
+      "train_samples_per_second": 359461.447,
+      "train_steps_per_second": 1401.9
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac3e2a31f3ecad27f8827f733beacca25723928c8705f348e8c262c8cffefd3e
+oid sha256:a135e6d79034267e47a5f6bac112759419a4e5e36f186ec21020a7bd9b34bf14
 size 4920