Upload my model weights

adapter_config.json

@@ -27,8 +27,20 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "model.layers.1.mlp.up_proj",
+    "model.layers.1.self_attn.o_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.0.mlp.gate_proj",
+    "model.layers.0.mlp.up_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.1.self_attn.k_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"
   ],
   "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:f3f2dc857ece2ff26d331ff634f8de10cfcfa950f3dcb2e34546a1cba03a0618
-size 17640
+oid sha256:4e0403ba39e7a9507711e75286f824af82aab1ff85cb396440454381fea81ad2
+size 97952

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:423fac003844c02895c0874e0f5b2ef407026dff7a4d214b1ae5bbaa3e0cc68f
-size 41027
+oid sha256:6782033cd5d1a2f2df5d19a468041cc5d5af9dd4b94c5fa889e0f13cb3767bed
+size 212551

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef19ffcd56004336b9f135564a902e1a7a7d8c546c184bdeed5ab4417799b240
+oid sha256:15642206c30a6720476d2069a8d548683b40db8eb817bd605e168475fcd2d5e4
 size 13990

trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_global_step": 315,
-  "best_metric": 0.36862244897959184,
-  "best_model_checkpoint": "/home/kat/git-repos/icse/results/rsa/19-05-2025:16-53-56/checkpoint-315",
+  "best_metric": 0.38667929292929293,
+  "best_model_checkpoint": "/home/kat/git-repos/icse/results/rsa/20-05-2025:14-27-00/checkpoint-315",
   "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 315,
@@ -11,57 +11,57 @@
   "log_history": [
     {
       "epoch": 0.15873015873015872,
-      "grad_norm": 2.652902364730835,
+      "grad_norm": 3.0029046535491943,
       "learning_rate": 1.688888888888889e-05,
-      "loss": 0.7018,
+      "loss": 0.7009,
       "step": 50
     },
     {
       "epoch": 0.31746031746031744,
-      "grad_norm": 2.970874786376953,
+      "grad_norm": 2.6273458003997803,
       "learning_rate": 1.3714285714285716e-05,
-      "loss": 0.6905,
+      "loss": 0.6876,
       "step": 100
     },
     {
       "epoch": 0.47619047619047616,
-      "grad_norm": 2.647416114807129,
+      "grad_norm": 3.0084035396575928,
       "learning_rate": 1.053968253968254e-05,
-      "loss": 0.6973,
+      "loss": 0.6956,
       "step": 150
     },
     {
       "epoch": 0.6349206349206349,
-      "grad_norm": 2.643963575363159,
+      "grad_norm": 3.0137736797332764,
       "learning_rate": 7.3650793650793666e-06,
-      "loss": 0.6904,
+      "loss": 0.6956,
       "step": 200
     },
     {
       "epoch": 0.7936507936507936,
-      "grad_norm": 2.978494882583618,
+      "grad_norm": 3.0123727321624756,
       "learning_rate": 4.190476190476191e-06,
-      "loss": 0.6785,
+      "loss": 0.7088,
       "step": 250
     },
     {
       "epoch": 0.9523809523809523,
-      "grad_norm": 2.981330633163452,
+      "grad_norm": 2.635606288909912,
       "learning_rate": 1.015873015873016e-06,
-      "loss": 0.6877,
+      "loss": 0.7082,
       "step": 300
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.53125,
+      "eval_accuracy": 0.546875,
       "eval_balanced_accuracy": 0.0,
-      "eval_f1_score": 0.36862244897959184,
-      "eval_loss": 0.691247820854187,
-      "eval_precision": 0.2822265625,
-      "eval_recall": 0.53125,
-      "eval_runtime": 2.2767,
-      "eval_samples_per_second": 28.111,
-      "eval_steps_per_second": 28.111,
+      "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,
       "step": 315
     }
   ],
@@ -82,7 +82,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 47016456480.0,
+  "total_flos": 120596908320.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5199e916690144873725b290cf2696ac54eb2bebad6f29ab35e3e59d203073b4
+oid sha256:2b55b2ba730a7205c610421782097802192afdc20a1152752fe308cdb42ad647
 size 5432