Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "o_proj",
     "v_proj",
-    "down_proj",
     "k_proj",
-    "gate_proj",
-    "q_proj"
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2450dd66ca61f4b9d9e8c71e6e5c53f6c2fab331f2090a0aa360f0e4f8a547
+oid sha256:7f3f2cf3c31cadf85597fca70a05acd3d16e8b12436a4e29c1e3526c2b74a510
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da122591e61c417b03747b18f9405f5e807c17fbfd01269ff58e33b3f7f20812
+oid sha256:9f4ae0bcffe0e5e3abfb00eff5efdaa8a4def12905ce06b546f7e18e85d97aea
 size 671466706

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.249739170074463,
+  "best_metric": 1.246433138847351,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 0.5012531328320802,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.020050125313283207,
-      "grad_norm": 57.873714447021484,
+      "grad_norm": 57.262550354003906,
       "learning_rate": 5e-05,
       "loss": 29.8366,
       "step": 1
@@ -18,185 +18,185 @@
     {
       "epoch": 0.020050125313283207,
       "eval_loss": 1.9029018878936768,
-      "eval_runtime": 9.9982,
-      "eval_samples_per_second": 33.706,
-      "eval_steps_per_second": 4.301,
+      "eval_runtime": 9.9628,
+      "eval_samples_per_second": 33.826,
+      "eval_steps_per_second": 4.316,
       "step": 1
     },
     {
       "epoch": 0.040100250626566414,
-      "grad_norm": 62.899574279785156,
+      "grad_norm": 61.9777946472168,
       "learning_rate": 0.0001,
       "loss": 30.5166,
       "step": 2
     },
     {
       "epoch": 0.06015037593984962,
-      "grad_norm": 42.16913986206055,
+      "grad_norm": 41.373321533203125,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 28.234,
+      "loss": 28.2141,
       "step": 3
     },
     {
       "epoch": 0.08020050125313283,
-      "grad_norm": 36.5384635925293,
+      "grad_norm": 35.427249908447266,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 26.0241,
+      "loss": 25.9472,
       "step": 4
     },
     {
       "epoch": 0.10025062656641603,
-      "grad_norm": 32.83475875854492,
+      "grad_norm": 32.058868408203125,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 25.1274,
+      "loss": 25.0425,
       "step": 5
     },
     {
       "epoch": 0.12030075187969924,
-      "grad_norm": 38.119998931884766,
+      "grad_norm": 31.39280891418457,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 22.9009,
+      "loss": 22.7109,
       "step": 6
     },
     {
       "epoch": 0.14035087719298245,
-      "grad_norm": 29.334177017211914,
+      "grad_norm": 27.022315979003906,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 22.2066,
+      "loss": 22.0858,
       "step": 7
     },
     {
       "epoch": 0.16040100250626566,
-      "grad_norm": 23.21502113342285,
+      "grad_norm": 22.689998626708984,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 21.994,
+      "loss": 21.8407,
       "step": 8
     },
     {
       "epoch": 0.18045112781954886,
-      "grad_norm": 21.088743209838867,
+      "grad_norm": 23.095903396606445,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 21.5407,
+      "loss": 21.4493,
       "step": 9
     },
     {
       "epoch": 0.20050125313283207,
-      "grad_norm": 15.787688255310059,
+      "grad_norm": 15.283258438110352,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 20.9165,
+      "loss": 20.7956,
       "step": 10
     },
     {
       "epoch": 0.22055137844611528,
-      "grad_norm": 18.21103286743164,
+      "grad_norm": 19.957977294921875,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 20.4984,
+      "loss": 20.4935,
       "step": 11
     },
     {
       "epoch": 0.24060150375939848,
-      "grad_norm": 14.928971290588379,
+      "grad_norm": 14.825860023498535,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 21.3668,
+      "loss": 21.3076,
       "step": 12
     },
     {
       "epoch": 0.2606516290726817,
-      "grad_norm": 30.611663818359375,
+      "grad_norm": 32.27811813354492,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 23.0383,
+      "loss": 22.9758,
       "step": 13
     },
     {
       "epoch": 0.2807017543859649,
-      "grad_norm": 15.54765796661377,
+      "grad_norm": 14.461236000061035,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 21.7901,
+      "loss": 21.7338,
       "step": 14
     },
     {
       "epoch": 0.3007518796992481,
-      "grad_norm": 13.202474594116211,
+      "grad_norm": 13.161033630371094,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 21.5219,
+      "loss": 21.4966,
       "step": 15
     },
     {
       "epoch": 0.3208020050125313,
-      "grad_norm": 14.390384674072266,
+      "grad_norm": 13.530344009399414,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 20.4065,
+      "loss": 20.3507,
       "step": 16
     },
     {
       "epoch": 0.3408521303258145,
-      "grad_norm": 13.841839790344238,
+      "grad_norm": 15.065783500671387,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 19.9871,
+      "loss": 19.967,
       "step": 17
     },
     {
       "epoch": 0.3609022556390977,
-      "grad_norm": 10.296717643737793,
+      "grad_norm": 10.283108711242676,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 20.2823,
+      "loss": 20.2849,
       "step": 18
     },
     {
       "epoch": 0.38095238095238093,
-      "grad_norm": 13.013739585876465,
+      "grad_norm": 11.738165855407715,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 19.5543,
+      "loss": 19.5285,
       "step": 19
     },
     {
       "epoch": 0.40100250626566414,
-      "grad_norm": 12.78657341003418,
+      "grad_norm": 12.6289701461792,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 19.7823,
+      "loss": 19.7657,
       "step": 20
     },
     {
       "epoch": 0.42105263157894735,
-      "grad_norm": 12.13170051574707,
+      "grad_norm": 11.915717124938965,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 19.1667,
+      "loss": 19.1391,
       "step": 21
     },
     {
       "epoch": 0.44110275689223055,
-      "grad_norm": 12.084077835083008,
+      "grad_norm": 12.708892822265625,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 18.9524,
+      "loss": 18.9334,
       "step": 22
     },
     {
       "epoch": 0.46115288220551376,
-      "grad_norm": 11.325791358947754,
+      "grad_norm": 11.339106559753418,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 19.398,
+      "loss": 19.3876,
       "step": 23
     },
     {
       "epoch": 0.48120300751879697,
-      "grad_norm": 14.2548189163208,
+      "grad_norm": 13.785265922546387,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 19.2122,
+      "loss": 19.19,
       "step": 24
     },
     {
       "epoch": 0.5012531328320802,
-      "grad_norm": 13.156657218933105,
+      "grad_norm": 13.614476203918457,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 20.1689,
+      "loss": 20.1636,
       "step": 25
     },
     {
       "epoch": 0.5012531328320802,
-      "eval_loss": 1.249739170074463,
-      "eval_runtime": 9.9797,
-      "eval_samples_per_second": 33.769,
-      "eval_steps_per_second": 4.309,
+      "eval_loss": 1.246433138847351,
+      "eval_runtime": 9.9398,
+      "eval_samples_per_second": 33.904,
+      "eval_steps_per_second": 4.326,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49aff211ae8ea18a4c81022d1a6bf1adb7442e3700fb490be0575b42e1f1010b
+oid sha256:7110c76ab6599cc95833cc63d481839aa6a5296b3d3896723abb98e54f6d9f6f
 size 6776