OumaymaeELBIACH/Results_deepseek

README.md

@@ -37,8 +37,8 @@ This model was trained with SFT.
 
 - TRL: 0.15.2
 - Transformers: 4.48.3
-- Pytorch: 2.6.0
-- Datasets: 3.3.2
+- Pytorch: 2.6.0+cu124
+- Datasets: 3.4.0
 - Tokenizers: 0.21.0
 
 ## Citations

adapter_config.json

@@ -14,22 +14,22 @@
   "loftq_config": {},
   "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0,
+  "lora_dropout": 0.5,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "gate_proj",
     "up_proj",
-    "o_proj",
-    "v_proj",
     "q_proj",
+    "down_proj",
+    "v_proj",
     "k_proj",
-    "down_proj"
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c39d1541016b2520f5e927237787630be4da5e2d25efb43ce116eed973f512
-size 167832240
+oid sha256:c60767656cc5e970d113dde1e4a5f531ee68e9b22751da91182a3eac375573b0
+size 335604696

runs/Mar15_11-28-08_ca51643881dd/events.out.tfevents.1742038163.ca51643881dd.5562.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7964a2b4e75478f5000e4fbcc920b78572a2e113521383e61a066341e162c372
+size 11951

runs/Mar15_11-28-08_ca51643881dd/events.out.tfevents.1742038727.ca51643881dd.5562.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e71293f3bf5f1ed6dc659845a5b8ddf4cc9875821526c3b288cfb2dbcabe86f
+size 422

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be4d8ea6c277c6d21f16057b4d29bac1a8418e6e87f417c2b88a6fe3e07b6bc4
+oid sha256:f67e7bfaffe5eacadd01da108aaa6d737a0347ca83024b5f74924b95d9c19def
 size 5624