Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,11 +20,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "fc2",
     "q_proj",
+    "dense",
     "v_proj",
     "k_proj",
+    "fc2",
     "fc1"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6571a906d4df91914eca8e71ce716c2354aec7d69e35cd9a9f76715ddaaaa778
+oid sha256:2c0bff069eccbcc3f252ace5c4116139501f4e6e8ef3fe15020dfea281dc4a02
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a569c558957c9346f42541bd503a09a796e89487bfb872188ecbf9d98280aa33
+oid sha256:d9ef67a92001a8ebc3a739b8d545e5a52e4205d57c8d0a84e1e5c15fba5ebe1b
 size 222294

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 6.90932035446167,
+  "best_metric": 6.907079696655273,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 1.1764705882352942,
   "eval_steps": 25,
@@ -10,193 +10,193 @@
   "log_history": [
     {
       "epoch": 0.047058823529411764,
-      "grad_norm": 0.21819724142551422,
+      "grad_norm": 0.2197900116443634,
       "learning_rate": 5e-05,
       "loss": 6.9356,
       "step": 1
     },
     {
       "epoch": 0.047058823529411764,
-      "eval_loss": 6.933749675750732,
-      "eval_runtime": 0.1253,
-      "eval_samples_per_second": 1149.197,
-      "eval_steps_per_second": 143.65,
+      "eval_loss": 6.93379020690918,
+      "eval_runtime": 0.1173,
+      "eval_samples_per_second": 1227.778,
+      "eval_steps_per_second": 153.472,
       "step": 1
     },
     {
       "epoch": 0.09411764705882353,
-      "grad_norm": 0.23392507433891296,
+      "grad_norm": 0.23598474264144897,
       "learning_rate": 0.0001,
       "loss": 6.9345,
       "step": 2
     },
     {
       "epoch": 0.1411764705882353,
-      "grad_norm": 0.21760986745357513,
+      "grad_norm": 0.22106465697288513,
       "learning_rate": 9.989294616193017e-05,
       "loss": 6.9338,
       "step": 3
     },
     {
       "epoch": 0.18823529411764706,
-      "grad_norm": 0.2519800364971161,
+      "grad_norm": 0.2562369108200073,
       "learning_rate": 9.957224306869053e-05,
       "loss": 6.9328,
       "step": 4
     },
     {
       "epoch": 0.23529411764705882,
-      "grad_norm": 0.2736882269382477,
+      "grad_norm": 0.27944687008857727,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 6.9286,
+      "loss": 6.9285,
       "step": 5
     },
     {
       "epoch": 0.2823529411764706,
-      "grad_norm": 0.21310661733150482,
+      "grad_norm": 0.2180635929107666,
       "learning_rate": 9.829629131445342e-05,
       "loss": 6.9316,
       "step": 6
     },
     {
       "epoch": 0.32941176470588235,
-      "grad_norm": 0.20439282059669495,
+      "grad_norm": 0.21152342855930328,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 6.9272,
+      "loss": 6.9271,
       "step": 7
     },
     {
       "epoch": 0.3764705882352941,
-      "grad_norm": 0.23206020891666412,
+      "grad_norm": 0.23825813829898834,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 6.9267,
+      "loss": 6.9263,
       "step": 8
     },
     {
       "epoch": 0.4235294117647059,
-      "grad_norm": 0.23456871509552002,
+      "grad_norm": 0.24669218063354492,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 6.9244,
+      "loss": 6.9238,
       "step": 9
     },
     {
       "epoch": 0.47058823529411764,
-      "grad_norm": 0.24816955626010895,
+      "grad_norm": 0.259551465511322,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 6.9231,
+      "loss": 6.9223,
       "step": 10
     },
     {
       "epoch": 0.5176470588235295,
-      "grad_norm": 0.22822989523410797,
+      "grad_norm": 0.23696023225784302,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 6.9228,
+      "loss": 6.9223,
       "step": 11
     },
     {
       "epoch": 0.5647058823529412,
-      "grad_norm": 0.1995086669921875,
+      "grad_norm": 0.2057735174894333,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 6.9243,
+      "loss": 6.9238,
       "step": 12
     },
     {
       "epoch": 0.611764705882353,
-      "grad_norm": 0.22449171543121338,
+      "grad_norm": 0.23521941900253296,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 6.9212,
+      "loss": 6.9205,
       "step": 13
     },
     {
       "epoch": 0.6588235294117647,
-      "grad_norm": 0.2463487982749939,
+      "grad_norm": 0.26085859537124634,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 6.917,
+      "loss": 6.9158,
       "step": 14
     },
     {
       "epoch": 0.7058823529411765,
-      "grad_norm": 0.23512305319309235,
+      "grad_norm": 0.2542021572589874,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 6.9182,
+      "loss": 6.9166,
       "step": 15
     },
     {
       "epoch": 0.7529411764705882,
-      "grad_norm": 0.24918068945407867,
+      "grad_norm": 0.26281988620758057,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 6.9125,
+      "loss": 6.9112,
       "step": 16
     },
     {
       "epoch": 0.8,
-      "grad_norm": 0.19672776758670807,
+      "grad_norm": 0.20492899417877197,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 6.922,
+      "loss": 6.9214,
       "step": 17
     },
     {
       "epoch": 0.8470588235294118,
-      "grad_norm": 0.22348777949810028,
+      "grad_norm": 0.2326112985610962,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 6.917,
+      "loss": 6.9162,
       "step": 18
     },
     {
       "epoch": 0.8941176470588236,
-      "grad_norm": 0.24797621369361877,
+      "grad_norm": 0.25904643535614014,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 6.9131,
+      "loss": 6.9117,
       "step": 19
     },
     {
       "epoch": 0.9411764705882353,
-      "grad_norm": 0.2576676607131958,
+      "grad_norm": 0.28032180666923523,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 6.9083,
+      "loss": 6.9061,
       "step": 20
     },
     {
       "epoch": 0.9882352941176471,
-      "grad_norm": 0.2767176330089569,
+      "grad_norm": 0.2956153154373169,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 6.9037,
+      "loss": 6.9017,
       "step": 21
     },
     {
       "epoch": 1.035294117647059,
-      "grad_norm": 0.41804033517837524,
+      "grad_norm": 0.43831008672714233,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 12.1933,
+      "loss": 12.1913,
       "step": 22
     },
     {
       "epoch": 1.0823529411764705,
-      "grad_norm": 0.23595315217971802,
+      "grad_norm": 0.24661988019943237,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 6.7918,
+      "loss": 6.7906,
       "step": 23
     },
     {
       "epoch": 1.1294117647058823,
-      "grad_norm": 0.2416248470544815,
+      "grad_norm": 0.26080018281936646,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 6.9668,
+      "loss": 6.9653,
       "step": 24
     },
     {
       "epoch": 1.1764705882352942,
-      "grad_norm": 0.27485209703445435,
+      "grad_norm": 0.29405051469802856,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 6.7366,
+      "loss": 6.7342,
       "step": 25
     },
     {
       "epoch": 1.1764705882352942,
-      "eval_loss": 6.90932035446167,
-      "eval_runtime": 0.1329,
-      "eval_samples_per_second": 1083.523,
-      "eval_steps_per_second": 135.44,
+      "eval_loss": 6.907079696655273,
+      "eval_runtime": 0.1147,
+      "eval_samples_per_second": 1255.072,
+      "eval_steps_per_second": 156.884,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac40a2a8dba01c5dfec735379b0d6aaafc1124d9f51e774c8273efc8e6fc7714
+oid sha256:2f84aa723924298c428cfc079f9bc73e01baed2fb1275230b50fa001c00d4943
 size 6776