Training in progress, step 100

adapter_config.json

@@ -24,11 +24,11 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "k_proj",
-    "q_proj",
     "o_proj",
     "gate_proj",
+    "q_proj",
     "up_proj",
+    "k_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69449872642ddc4c13d822950e9704ac8f55b29327cdc25083c8b78d3599e563
+oid sha256:c6492873010a429dd177e3ee2819ac93ee7e93a36bd64ea161b708b1bb5716b2
 size 319876032

angle_config.json

@@ -1,6 +1,6 @@
 {
   "model_name_or_path": "NousResearch/Llama-2-7b-hf",
-  "max_length": 512,
+  "max_length": 256,
   "model_kwargs": {},
   "pooling_strategy": "last",
   "lora_config_kwargs": {

runs/Oct02_09-06-52_0b353871aabe/events.out.tfevents.1727860015.0b353871aabe.11493.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa26a5fa34a52a8d1a7a9e5270e1def462340a7fa8a5ff2c1994e5605a18b741
+size 5303

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a6568e15c6b60b109e325f517b7782aad251ceaf93aeffac6a7d054553f4d2
+oid sha256:24c4a20a9d7810e865eb2761367fcfcc51c1609eca5659a7d6d5ff52bd211f05
 size 5176