dpo_79pt692h

README.md

@@ -17,15 +17,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on the None dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.6736
-- Rewards/chosen: 0.5769
-- Rewards/rejected: 0.5039
-- Rewards/accuracies: 0.6000
-- Rewards/margins: 0.0730
-- Logps/rejected: -171.1358
-- Logps/chosen: -181.4562
-- Logits/rejected: -0.0987
-- Logits/chosen: -0.0683
+- Loss: 0.6931
+- Rewards/chosen: 0.0
+- Rewards/rejected: 0.0
+- Rewards/accuracies: 0.0
+- Rewards/margins: 0.0
+- Logps/rejected: -32.6347
+- Logps/chosen: -35.1065
+- Logits/rejected: -1.1843
+- Logits/chosen: -1.2320
 
 ## Model description
 
@@ -48,12 +48,10 @@ The following hyperparameters were used during training:
 - train_batch_size: 1
 - eval_batch_size: 1
 - seed: 0
-- gradient_accumulation_steps: 2
-- total_train_batch_size: 2
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_steps: 100
-- training_steps: 250
+- training_steps: 2
 
 ### Training results
 

adapter_config.json

@@ -16,17 +16,17 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 256,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "out_proj",
     "q_proj",
-    "k_proj",
-    "v_proj",
     "wte",
-    "out_proj",
-    "fc_in",
-    "fc_out"
+    "fc_out",
+    "v_proj",
+    "k_proj",
+    "fc_in"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85dfe4c31ce75352ba7da7625b5006dc78d1a2f79e0b277aecc078d20f5b0d6b
-size 302016416
+oid sha256:5ab0fda06fcdd9a8e16d9a236718f37697611b438e210d287c0a0fcbfea98ee7
+size 18900240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c66e9158b2f49b9b0b295f6b1b5de6c5745a63fb6f87dc5e502958055b3947
-size 5496
+oid sha256:6177b9cb5727cbe1c1928de9d1c03adfeb642b365c0c8718daea0f8e4049eb85
+size 5560