EdBerg/outputs

README.md

@@ -53,8 +53,8 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- PEFT 0.13.2
-- Transformers 4.44.2
+- PEFT 0.13.3.dev0
+- Transformers 4.45.2
 - Pytorch 2.4.1+cu121
 - Datasets 3.0.1
-- Tokenizers 0.19.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -3,6 +3,7 @@
   "auto_mapping": null,
   "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
   "bias": "none",
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -20,13 +21,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
-    "k_proj",
     "gate_proj",
+    "v_proj",
+    "o_proj",
     "up_proj",
+    "q_proj",
     "down_proj",
-    "v_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ae10cc9d58125a9e96c7ddcc4b075fd50ca0cfd9c5394c3731aec6d37f133e
+oid sha256:5443a6a21c4eedc437bdc8e5102721d67044aeba2b82b28915837c2b3e9aa7f8
 size 83945296

runs/Oct22_01-24-56_a4ffd5fd6443/events.out.tfevents.1729560303.a4ffd5fd6443.373.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3302ae4cdd7dbe659c8544db0a7b560a641f888ac0c7bc05fc222145a50ca726
+size 216659

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e134af98b985517b4f068e3755ae90d4e9cd2d45d328325dc503f1c6b2d06cc7
-size 9085698
+oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
+size 17209961

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e43b475bf0b50bb9499545d5578bf9bcbe197ad091c87fd1619e8a0193e3f72d
+oid sha256:3050d70ad27c9524f5c98150d5f0a5538fc3a5ed848dcf4b1aea2b8f14542a25
 size 5432