Training in progress, step 40

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "data/Tukan-1.1B-Chat-reasoning-sft-COLA_merged_1",
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -16,13 +16,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "v_proj",
-    "up_proj",
     "gate_proj",
-    "lm_head",
-    "q_proj",
     "k_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "o_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM"

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faec55aa5e087bfcfcc1a48ca7befe73c653e838144f524d8570f3d354d9d2f8
+oid sha256:456824575cd57e54816548c499b1e3da4fb99469a631d70c7bab4f601205e09f
 size 26361536

runs/Jan22_06-23-00_98f107f1aa39/events.out.tfevents.1705904680.98f107f1aa39.11425.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b90b0bf1827414beb28dec3c97b743f6535c43f610e16c1b71d600af083b2a29
+size 6990

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54992a2c8472fa25aaf5bd77b4f99dc364639b438e0687926d0334ae0c178a23
+oid sha256:477443261437113b380ef9fb369f48b0f2b95f8302c409abbdf3d552f348b0c2
 size 4792