Training in progress, epoch 0

adapter_config.json

@@ -9,13 +9,13 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 256,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa710d2ba40988f0db89fd1fbff354081d38820005d5a34cbc9ba31f344d7523
-size 27280152
+oid sha256:938ef691422383a2496bf29e77854f9449f023d8698d812fb65f9f1c41837ef8
+size 218121344

runs/Jan27_19-53-13_41d5647e4f65/events.out.tfevents.1706385200.41d5647e4f65.3074.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7328e9c3a7e852a1868635093a010d10498acdab0cbd582477cf4e4328aef7f6
+size 7991

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 128,
+    "max_length": 256,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df4892f8d93e184470cb8bd8d39f9db225e57a9d8d0e3fb83838cf4548640f3
+oid sha256:c31374184bd387f1a1db84b8c50eac4a9c6e5abc476c333220020d4b07be5adc
 size 4728