Upload my model weights

adapter_config.json

@@ -27,20 +27,20 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "model.layers.1.mlp.up_proj",
-    "model.layers.1.self_attn.o_proj",
+    "model.layers.0.mlp.down_proj",
+    "model.layers.0.self_attn.o_proj",
     "model.layers.1.self_attn.q_proj",
-    "model.layers.0.mlp.gate_proj",
+    "model.layers.1.mlp.down_proj",
     "model.layers.0.mlp.up_proj",
-    "model.layers.0.self_attn.k_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.0.self_attn.v_proj",
     "model.layers.0.self_attn.q_proj",
-    "model.layers.1.self_attn.k_proj",
+    "model.layers.1.self_attn.o_proj",
     "model.layers.1.mlp.gate_proj",
-    "model.layers.0.self_attn.o_proj",
-    "model.layers.1.self_attn.v_proj",
-    "model.layers.0.mlp.down_proj",
-    "model.layers.1.mlp.down_proj",
-    "model.layers.0.self_attn.v_proj"
+    "model.layers.0.mlp.gate_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.1.self_attn.k_proj",
+    "model.layers.1.mlp.up_proj"
   ],
   "task_type": "SEQ_CLS",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0403ba39e7a9507711e75286f824af82aab1ff85cb396440454381fea81ad2
+oid sha256:bb0f6a1776dd30469c050b715cb9f5adf1a0598ad6ecb7d0b5e41a6cbe82caa3
 size 97952

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6782033cd5d1a2f2df5d19a468041cc5d5af9dd4b94c5fa889e0f13cb3767bed
+oid sha256:31c949146c4fab7d766d3a9f424ee797acf412495494df9db34986452f912d11
 size 212551

trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_global_step": 315,
-  "best_metric": 0.38667929292929293,
-  "best_model_checkpoint": "/home/kat/git-repos/icse/results/rsa/20-05-2025:14-27-00/checkpoint-315",
+  "best_metric": 0.3161184210526316,
+  "best_model_checkpoint": "/home/kat/git-repos/icse/results/rsa/20-05-2025:14-29-59/checkpoint-315",
   "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 315,
@@ -11,57 +11,57 @@
   "log_history": [
     {
       "epoch": 0.15873015873015872,
-      "grad_norm": 3.0029046535491943,
+      "grad_norm": 2.9088521003723145,
       "learning_rate": 1.688888888888889e-05,
-      "loss": 0.7009,
+      "loss": 0.6904,
       "step": 50
     },
     {
       "epoch": 0.31746031746031744,
-      "grad_norm": 2.6273458003997803,
+      "grad_norm": 2.7309181690216064,
       "learning_rate": 1.3714285714285716e-05,
-      "loss": 0.6876,
+      "loss": 0.6939,
       "step": 100
     },
     {
       "epoch": 0.47619047619047616,
-      "grad_norm": 3.0084035396575928,
+      "grad_norm": 2.9125733375549316,
       "learning_rate": 1.053968253968254e-05,
-      "loss": 0.6956,
+      "loss": 0.6951,
       "step": 150
     },
     {
       "epoch": 0.6349206349206349,
-      "grad_norm": 3.0137736797332764,
+      "grad_norm": 2.9027392864227295,
       "learning_rate": 7.3650793650793666e-06,
-      "loss": 0.6956,
+      "loss": 0.7009,
       "step": 200
     },
     {
       "epoch": 0.7936507936507936,
-      "grad_norm": 3.0123727321624756,
+      "grad_norm": 2.7402257919311523,
       "learning_rate": 4.190476190476191e-06,
-      "loss": 0.7088,
+      "loss": 0.6971,
       "step": 250
     },
     {
       "epoch": 0.9523809523809523,
-      "grad_norm": 2.635606288909912,
+      "grad_norm": 2.8944599628448486,
       "learning_rate": 1.015873015873016e-06,
-      "loss": 0.7082,
+      "loss": 0.6969,
       "step": 300
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.546875,
+      "eval_accuracy": 0.484375,
       "eval_balanced_accuracy": 0.0,
-      "eval_f1_score": 0.38667929292929293,
-      "eval_loss": 0.6890829801559448,
-      "eval_precision": 0.299072265625,
-      "eval_recall": 0.546875,
-      "eval_runtime": 2.6619,
-      "eval_samples_per_second": 24.043,
-      "eval_steps_per_second": 24.043,
+      "eval_f1_score": 0.3161184210526316,
+      "eval_loss": 0.6945174932479858,
+      "eval_precision": 0.234619140625,
+      "eval_recall": 0.484375,
+      "eval_runtime": 2.5614,
+      "eval_samples_per_second": 24.986,
+      "eval_steps_per_second": 24.986,
       "step": 315
     }
   ],

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b55b2ba730a7205c610421782097802192afdc20a1152752fe308cdb42ad647
+oid sha256:ab7e0fcff977b76babdfaac9882c8d1060739bc69fa4585e839049d2bac151c7
 size 5432