Training in progress, epoch 1

adapter_config.json

@@ -12,20 +12,22 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 2,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
-  "modules_to_save": null,
+  "modules_to_save": [
+    "embed_tokens"
+  ],
   "peft_type": "LORA",
-  "r": 2,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "down_proj",
-    "up_proj"
+    "up_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48eae71d085c351daa4ab6e985c6cb57d623bb58889dd08d4b13736dd370296f
-size 5051864
+oid sha256:bd4e714c34edc55f8637b26ca48421f9d53825a683a283f4619193ea4fd42faf
+size 1248236248

runs/Mar22_17-11-40_HAL/events.out.tfevents.1742681507.HAL.13785.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be82e1370856343d29b049aa621f0799361c58afb9955fabfafa8f6c7718107
+size 7549

runs/Mar22_17-12-35_HAL/events.out.tfevents.1742681572.HAL.14165.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db97f648f2347f112e7c08cd599286b327b015058e6d84eaffd1ad5d8cbc4631
+size 9932

runs/Mar22_17-40-49_HAL/events.out.tfevents.1742683257.HAL.15975.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df0af90a85f4db71f846f07794b937c22cfda9381ffe1124c7506ea081d1272
+size 6412

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b07cf20199f26b11f77c242d2ad8d7dad1e64b668ecdd60f8ff639f248988fb
+oid sha256:00630686d04903543d71f5785d379e194009fce1c8be394f0a5e1339c69ad2b3
 size 5624