Training in progress, step 33

adapter_config.json

@@ -2,32 +2,41 @@
   "alpha_pattern": {},
   "auto_mapping": null,
   "base_model_name_or_path": "tiiuae/falcon-11B",
+  "beta1": 0.85,
+  "beta2": 0.85,
   "bias": "none",
+  "deltaT": 1,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
+  "init_r": 12,
   "layer_replication": null,
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 2,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.01,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": [
     "classifier",
     "score"
   ],
-  "peft_type": "LORA",
-  "r": 8,
-  "rank_pattern": {},
+  "orth_reg_weight": 0.5,
+  "peft_type": "ADALORA",
+  "r": 2,
+  "rank_pattern": null,
   "revision": null,
   "target_modules": [
-    "dense_4h_to_h",
     "query_key_value",
+    "dense_4h_to_h",
     "dense_h_to_4h"
   ],
+  "target_r": 8,
   "task_type": "SEQ_CLS",
+  "tfinal": 0,
+  "tinit": 0,
+  "total_step": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdcb2229f86a200df1a5b7b24ac6f1bf46f59a5d0dd00d1e7057bce1cb0ea42d
-size 98387400
+oid sha256:15ac6b82791562199642e0730017c4857315128aec43aa4540e84e6e2c9ff714
+size 147569848

runs/Sep29_12-59-11_e3d96b08e858/events.out.tfevents.1727614752.e3d96b08e858.1297.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df2452b3857f7786d47dba6b2e318e5d1ce42bb9f7084fe12b90f0869b31ee7
+size 13368

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f58392b55571c43a95e5831930510cf8aca4553d7bea5991a6c8325b026b59d
+oid sha256:d6d37eb0148f1a37a83c9bef028ee9f98438987c56bdf8023e635dbf864e7910
 size 5176