Model save

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "k_proj",
     "o_proj",
+    "q_proj",
     "down_proj",
     "gate_proj",
-    "q_proj",
-    "k_proj",
-    "v_proj",
-    "up_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee301ae8658ad54a8214ec130a4adf65df37c06bfee5f5d0cc110bf91d4ff62
+oid sha256:60b52762cf7801185937e75435d400062f4235e285022b9fe2401a88b49afe3d
 size 1684597880

trainer_state.json

@@ -10,236 +10,236 @@
   "log_history": [
     {
       "epoch": 0.12135922330097088,
-      "grad_norm": 1.0340704917907715,
+      "grad_norm": 0.9599943161010742,
       "learning_rate": 9.698956057295461e-05,
-      "loss": 1.2072,
+      "loss": 1.2196,
       "step": 250
     },
     {
       "epoch": 0.24271844660194175,
-      "grad_norm": 1.0259687900543213,
+      "grad_norm": 1.0285232067108154,
       "learning_rate": 9.395484340859432e-05,
-      "loss": 0.6533,
+      "loss": 0.6688,
       "step": 500
     },
     {
       "epoch": 0.3640776699029126,
-      "grad_norm": 0.8549349308013916,
+      "grad_norm": 0.8658091425895691,
       "learning_rate": 9.092012624423404e-05,
-      "loss": 0.5518,
+      "loss": 0.5603,
       "step": 750
     },
     {
       "epoch": 0.4854368932038835,
-      "grad_norm": 0.7689054608345032,
+      "grad_norm": 0.8770154714584351,
       "learning_rate": 8.788540907987377e-05,
-      "loss": 0.5109,
+      "loss": 0.5165,
       "step": 1000
     },
     {
       "epoch": 0.6067961165048543,
-      "grad_norm": 0.6630316972732544,
+      "grad_norm": 0.6812583208084106,
       "learning_rate": 8.485069191551348e-05,
-      "loss": 0.4973,
+      "loss": 0.5015,
       "step": 1250
     },
     {
       "epoch": 0.7281553398058253,
-      "grad_norm": 0.6936432719230652,
+      "grad_norm": 0.6911689043045044,
       "learning_rate": 8.181597475115321e-05,
-      "loss": 0.4815,
+      "loss": 0.4846,
       "step": 1500
     },
     {
       "epoch": 0.8495145631067961,
-      "grad_norm": 0.6800591945648193,
+      "grad_norm": 0.6556753516197205,
       "learning_rate": 7.878125758679291e-05,
-      "loss": 0.4741,
+      "loss": 0.4769,
       "step": 1750
     },
     {
       "epoch": 0.970873786407767,
-      "grad_norm": 0.6063706278800964,
+      "grad_norm": 0.5876182317733765,
       "learning_rate": 7.574654042243264e-05,
-      "loss": 0.4672,
+      "loss": 0.4701,
       "step": 2000
     },
     {
       "epoch": 1.0922330097087378,
-      "grad_norm": 0.6320546865463257,
+      "grad_norm": 0.6175569891929626,
       "learning_rate": 7.271182325807235e-05,
-      "loss": 0.4585,
+      "loss": 0.4616,
       "step": 2250
     },
     {
       "epoch": 1.2135922330097086,
-      "grad_norm": 0.6298216581344604,
+      "grad_norm": 0.6353004574775696,
       "learning_rate": 6.967710609371208e-05,
-      "loss": 0.4474,
+      "loss": 0.4518,
       "step": 2500
     },
     {
       "epoch": 1.3349514563106797,
-      "grad_norm": 0.6066320538520813,
+      "grad_norm": 0.5879459977149963,
       "learning_rate": 6.664238892935178e-05,
-      "loss": 0.4425,
+      "loss": 0.4483,
       "step": 2750
     },
     {
       "epoch": 1.4563106796116505,
-      "grad_norm": 0.7594243884086609,
+      "grad_norm": 0.6575189232826233,
       "learning_rate": 6.360767176499151e-05,
-      "loss": 0.4289,
+      "loss": 0.4367,
       "step": 3000
     },
     {
       "epoch": 1.5776699029126213,
-      "grad_norm": 0.8379995822906494,
+      "grad_norm": 0.724533200263977,
       "learning_rate": 6.0572954600631224e-05,
-      "loss": 0.4119,
+      "loss": 0.4226,
       "step": 3250
     },
     {
       "epoch": 1.6990291262135924,
-      "grad_norm": 0.8765040040016174,
+      "grad_norm": 0.7686433792114258,
       "learning_rate": 5.7538237436270945e-05,
-      "loss": 0.3954,
+      "loss": 0.4104,
       "step": 3500
     },
     {
       "epoch": 1.820388349514563,
-      "grad_norm": 0.8040120005607605,
+      "grad_norm": 0.7101556658744812,
       "learning_rate": 5.450352027191066e-05,
-      "loss": 0.3772,
+      "loss": 0.3954,
       "step": 3750
     },
     {
       "epoch": 1.941747572815534,
-      "grad_norm": 0.8949540257453918,
+      "grad_norm": 0.7856088280677795,
       "learning_rate": 5.146880310755038e-05,
-      "loss": 0.3596,
+      "loss": 0.3827,
       "step": 4000
     },
     {
       "epoch": 2.063106796116505,
-      "grad_norm": 0.986718475818634,
+      "grad_norm": 0.8785816431045532,
       "learning_rate": 4.84340859431901e-05,
-      "loss": 0.332,
+      "loss": 0.3585,
       "step": 4250
     },
     {
       "epoch": 2.1844660194174756,
-      "grad_norm": 0.9565535187721252,
+      "grad_norm": 0.858726441860199,
       "learning_rate": 4.539936877882982e-05,
-      "loss": 0.313,
+      "loss": 0.341,
       "step": 4500
     },
     {
       "epoch": 2.3058252427184467,
-      "grad_norm": 0.9416393041610718,
+      "grad_norm": 0.8789017200469971,
       "learning_rate": 4.236465161446954e-05,
-      "loss": 0.3034,
+      "loss": 0.3313,
       "step": 4750
     },
     {
       "epoch": 2.4271844660194173,
-      "grad_norm": 1.002323865890503,
+      "grad_norm": 0.9984813928604126,
       "learning_rate": 3.932993445010925e-05,
-      "loss": 0.2928,
+      "loss": 0.321,
       "step": 5000
     },
     {
       "epoch": 2.5485436893203883,
-      "grad_norm": 0.9281540513038635,
+      "grad_norm": 0.8649771213531494,
       "learning_rate": 3.6295217285748975e-05,
-      "loss": 0.2829,
+      "loss": 0.3104,
       "step": 5250
     },
     {
       "epoch": 2.6699029126213594,
-      "grad_norm": 1.0740528106689453,
+      "grad_norm": 0.9905620217323303,
       "learning_rate": 3.326050012138869e-05,
-      "loss": 0.2732,
+      "loss": 0.3008,
       "step": 5500
     },
     {
       "epoch": 2.79126213592233,
-      "grad_norm": 0.952369749546051,
+      "grad_norm": 0.9460727572441101,
       "learning_rate": 3.022578295702841e-05,
-      "loss": 0.2692,
+      "loss": 0.2965,
       "step": 5750
     },
     {
       "epoch": 2.912621359223301,
-      "grad_norm": 0.9148930907249451,
+      "grad_norm": 0.8885589241981506,
       "learning_rate": 2.7191065792668125e-05,
-      "loss": 0.261,
+      "loss": 0.2876,
       "step": 6000
     },
     {
       "epoch": 3.033980582524272,
-      "grad_norm": 0.9394662380218506,
+      "grad_norm": 0.9261214733123779,
       "learning_rate": 2.4156348628307843e-05,
-      "loss": 0.2489,
+      "loss": 0.2759,
       "step": 6250
     },
     {
       "epoch": 3.1553398058252426,
-      "grad_norm": 0.9207432866096497,
+      "grad_norm": 0.9241772294044495,
       "learning_rate": 2.112163146394756e-05,
-      "loss": 0.2351,
+      "loss": 0.2618,
       "step": 6500
     },
     {
       "epoch": 3.2766990291262137,
-      "grad_norm": 0.9576259255409241,
+      "grad_norm": 0.929602861404419,
       "learning_rate": 1.808691429958728e-05,
-      "loss": 0.2315,
+      "loss": 0.2578,
       "step": 6750
     },
     {
       "epoch": 3.3980582524271843,
-      "grad_norm": 1.0424150228500366,
+      "grad_norm": 0.9885833263397217,
       "learning_rate": 1.5052197135226997e-05,
-      "loss": 0.2287,
+      "loss": 0.2547,
       "step": 7000
     },
     {
       "epoch": 3.5194174757281553,
-      "grad_norm": 0.9650384783744812,
+      "grad_norm": 0.9474493861198425,
       "learning_rate": 1.2017479970866715e-05,
-      "loss": 0.2267,
+      "loss": 0.2528,
       "step": 7250
     },
     {
       "epoch": 3.6407766990291264,
-      "grad_norm": 0.939440131187439,
+      "grad_norm": 0.9105657935142517,
       "learning_rate": 8.982762806506435e-06,
-      "loss": 0.2245,
+      "loss": 0.25,
       "step": 7500
     },
     {
       "epoch": 3.762135922330097,
-      "grad_norm": 0.9506264328956604,
+      "grad_norm": 0.9185407161712646,
       "learning_rate": 5.948045642146152e-06,
-      "loss": 0.221,
+      "loss": 0.2463,
       "step": 7750
     },
     {
       "epoch": 3.883495145631068,
-      "grad_norm": 0.9145563244819641,
+      "grad_norm": 0.8763870000839233,
       "learning_rate": 2.9133284777858704e-06,
-      "loss": 0.2214,
+      "loss": 0.2462,
       "step": 8000
     },
     {
       "epoch": 4.0,
       "step": 8240,
       "total_flos": 1.1079720316327956e+18,
-      "train_loss": 0.38045854198122486,
-      "train_runtime": 14779.6974,
-      "train_samples_per_second": 35.681,
-      "train_steps_per_second": 0.558
+      "train_loss": 0.39851856185394585,
+      "train_runtime": 97554.2615,
+      "train_samples_per_second": 5.406,
+      "train_steps_per_second": 0.084
     }
   ],
   "logging_steps": 250,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2e5010aee0656a196ff6fb1e40552ae9c562641a4e0fd86668ac7f370da2f9
+oid sha256:b207d7b4b95c725e5af7402457b9eb0332219dc968567f69b710daa980d1135f
 size 5240