End of training

DPO/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "up_proj",
-    "o_proj",
     "v_proj",
-    "q_proj",
+    "o_proj",
     "k_proj",
     "gate_proj",
-    "down_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

DPO/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6e040a505a298435ee58552b938292bf111ae714f41cc7d826e18909606676
+oid sha256:2a7eb1c70ec3f189be41d13b604d9f501f3d2ca8443b33aabb787b6477ba051a
 size 167832240

README.md

@@ -1,11 +1,11 @@
 ---
-license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.1
 library_name: peft
+license: apache-2.0
 tags:
 - trl
 - dpo
 - generated_from_trainer
-base_model: mistralai/Mistral-7B-v0.1
 model-index:
 - name: mistral_dpo
   results: []
@@ -18,15 +18,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 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.
 It achieves the following results on the evaluation set:
-- Loss: 0.6867
-- Rewards/chosen: 0.0388
-- Rewards/rejected: 0.0248
-- Rewards/accuracies: 0.5990
-- Rewards/margins: 0.0141
-- Logps/rejected: -54.3813
-- Logps/chosen: -67.8578
-- Logits/rejected: -0.5593
-- Logits/chosen: -0.6842
+- Loss: 0.6901
+- Rewards/chosen: 0.0478
+- Rewards/rejected: 0.0414
+- Rewards/accuracies: 0.5986
+- Rewards/margins: 0.0065
+- Logps/rejected: -55.2578
+- Logps/chosen: -58.2493
+- Logits/rejected: -0.0691
+- Logits/chosen: -0.1144
 
 ## Model description
 
@@ -60,11 +60,11 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
 |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
-| 0.6925        | 0.0214 | 20   | 0.6915          | 0.0109         | 0.0076           | 0.5925             | 0.0034          | -54.5535       | -68.1368     | -0.5594         | -0.6846       |
-| 0.6903        | 0.0427 | 40   | 0.6893          | 0.0276         | 0.0195           | 0.5909             | 0.0081          | -54.4341       | -67.9702     | -0.5593         | -0.6844       |
-| 0.6886        | 0.0641 | 60   | 0.6877          | 0.0353         | 0.0236           | 0.5974             | 0.0117          | -54.3930       | -67.8934     | -0.5592         | -0.6842       |
-| 0.6862        | 0.0855 | 80   | 0.6869          | 0.0385         | 0.0250           | 0.6055             | 0.0136          | -54.3795       | -67.8606     | -0.5593         | -0.6842       |
-| 0.6865        | 0.1068 | 100  | 0.6867          | 0.0388         | 0.0248           | 0.5990             | 0.0141          | -54.3813       | -67.8578     | -0.5593         | -0.6842       |
+| 0.693         | 0.0882 | 20   | 0.6928          | 0.0070         | 0.0063           | 0.5487             | 0.0007          | -55.6083       | -58.6576     | -0.0693         | -0.1147       |
+| 0.6919        | 0.1763 | 40   | 0.6915          | 0.0249         | 0.0215           | 0.6064             | 0.0034          | -55.4560       | -58.4780     | -0.0692         | -0.1146       |
+| 0.6908        | 0.2645 | 60   | 0.6907          | 0.0344         | 0.0292           | 0.6038             | 0.0051          | -55.3790       | -58.3838     | -0.0694         | -0.1148       |
+| 0.691         | 0.3526 | 80   | 0.6901          | 0.0421         | 0.0358           | 0.6012             | 0.0063          | -55.3130       | -58.3061     | -0.0691         | -0.1144       |
+| 0.6895        | 0.4408 | 100  | 0.6901          | 0.0478         | 0.0414           | 0.5986             | 0.0065          | -55.2578       | -58.2493     | -0.0691         | -0.1144       |
 
 
 ### Framework versions
@@ -72,5 +72,5 @@ The following hyperparameters were used during training:
 - PEFT 0.11.1
 - Transformers 4.41.2
 - Pytorch 2.3.1+cu121
-- Datasets 2.19.2
+- Datasets 2.20.0
 - Tokenizers 0.19.1

reference/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "up_proj",
-    "o_proj",
     "v_proj",
-    "q_proj",
+    "o_proj",
     "k_proj",
     "gate_proj",
-    "down_proj"
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

reference/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91a0be67a4aa48180959c987df10e500f2e014e3bb46ae88fe9a3187a43bd2ca
+oid sha256:0993053d1cb8f5126339726b78be278d424a5ab65a62968aae521c6578153dfa
 size 167832240

runs/Jun24_03-31-02_167-234-221-159/events.out.tfevents.1719199875.167-234-221-159.30322.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc4ac054377c06ec3670233347aa22ed4562c75a3e5e16d6b16e182abbbd203
+size 5985

runs/Jun24_04-52-10_167-234-221-159/events.out.tfevents.1719204730.167-234-221-159.46214.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e478c345f100c14e4fa758ae240e9e7a786f4338f4bdbe6937b3349a913b5d5
+size 4184

runs/Jun24_04-53-49_167-234-221-159/events.out.tfevents.1719204830.167-234-221-159.46861.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd66b1168fa79be76d516883a255f0f523f31ff5768d19811a960204e8953575
+size 13348

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a501fa5a4ae26c6409a60d5b0c60df4bcc4cbaea877a0cec2e000b74cd6d6627
+oid sha256:0a5da2270c2f48ae24e54031e2da497def000d592b75f0b67f1870f62144598e
 size 5688