Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
+    "o_proj",
     "v_proj",
-    "k_proj",
-    "q_proj",
     "down_proj",
-    "o_proj",
-    "gate_proj"
+    "k_proj",
+    "gate_proj",
+    "q_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:dc541a5e2f6ab287dd5d927da237acf49a2f6908fcdea5a3b379204e1ed0bee1
+oid sha256:c5804f7ce3e4f165e38c00a62ab27ff1015149bd69f49f81ccf5098224bb7fc3
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:629035f3e0bd246235b65cad3b10985653da1336b672feeca886ffc9bccf8f6a
+oid sha256:ef63d657326c021d1a85b15883579674641de7324b4c4a05954f6b9210941ebf
 size 671466706

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.202621579170227,
+  "best_metric": 1.2036230564117432,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
   "epoch": 1.0025062656641603,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.020050125313283207,
-      "grad_norm": 57.262550354003906,
+      "grad_norm": 57.873714447021484,
       "learning_rate": 5e-05,
       "loss": 29.8366,
       "step": 1
@@ -18,368 +18,368 @@
     {
       "epoch": 0.020050125313283207,
       "eval_loss": 1.9029018878936768,
-      "eval_runtime": 9.9628,
-      "eval_samples_per_second": 33.826,
-      "eval_steps_per_second": 4.316,
+      "eval_runtime": 9.9982,
+      "eval_samples_per_second": 33.706,
+      "eval_steps_per_second": 4.301,
       "step": 1
     },
     {
       "epoch": 0.040100250626566414,
-      "grad_norm": 61.9777946472168,
+      "grad_norm": 62.899574279785156,
       "learning_rate": 0.0001,
       "loss": 30.5166,
       "step": 2
     },
     {
       "epoch": 0.06015037593984962,
-      "grad_norm": 41.373321533203125,
+      "grad_norm": 42.16913986206055,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 28.2141,
+      "loss": 28.234,
       "step": 3
     },
     {
       "epoch": 0.08020050125313283,
-      "grad_norm": 35.427249908447266,
+      "grad_norm": 36.5384635925293,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 25.9472,
+      "loss": 26.0241,
       "step": 4
     },
     {
       "epoch": 0.10025062656641603,
-      "grad_norm": 32.058868408203125,
+      "grad_norm": 32.83475875854492,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 25.0425,
+      "loss": 25.1274,
       "step": 5
     },
     {
       "epoch": 0.12030075187969924,
-      "grad_norm": 31.39280891418457,
+      "grad_norm": 38.119998931884766,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 22.7109,
+      "loss": 22.9009,
       "step": 6
     },
     {
       "epoch": 0.14035087719298245,
-      "grad_norm": 27.022315979003906,
+      "grad_norm": 29.334177017211914,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 22.0858,
+      "loss": 22.2066,
       "step": 7
     },
     {
       "epoch": 0.16040100250626566,
-      "grad_norm": 22.689998626708984,
+      "grad_norm": 23.21502113342285,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 21.8407,
+      "loss": 21.994,
       "step": 8
     },
     {
       "epoch": 0.18045112781954886,
-      "grad_norm": 23.095903396606445,
+      "grad_norm": 21.088743209838867,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 21.4493,
+      "loss": 21.5407,
       "step": 9
     },
     {
       "epoch": 0.20050125313283207,
-      "grad_norm": 15.283258438110352,
+      "grad_norm": 15.787688255310059,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 20.7956,
+      "loss": 20.9165,
       "step": 10
     },
     {
       "epoch": 0.22055137844611528,
-      "grad_norm": 19.957977294921875,
+      "grad_norm": 18.21103286743164,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 20.4935,
+      "loss": 20.4984,
       "step": 11
     },
     {
       "epoch": 0.24060150375939848,
-      "grad_norm": 14.825860023498535,
+      "grad_norm": 14.928971290588379,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 21.3076,
+      "loss": 21.3668,
       "step": 12
     },
     {
       "epoch": 0.2606516290726817,
-      "grad_norm": 32.27811813354492,
+      "grad_norm": 30.611663818359375,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 22.9758,
+      "loss": 23.0383,
       "step": 13
     },
     {
       "epoch": 0.2807017543859649,
-      "grad_norm": 14.461236000061035,
+      "grad_norm": 15.54765796661377,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 21.7338,
+      "loss": 21.7901,
       "step": 14
     },
     {
       "epoch": 0.3007518796992481,
-      "grad_norm": 13.161033630371094,
+      "grad_norm": 13.202474594116211,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 21.4966,
+      "loss": 21.5219,
       "step": 15
     },
     {
       "epoch": 0.3208020050125313,
-      "grad_norm": 13.530344009399414,
+      "grad_norm": 14.390384674072266,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 20.3507,
+      "loss": 20.4065,
       "step": 16
     },
     {
       "epoch": 0.3408521303258145,
-      "grad_norm": 15.065783500671387,
+      "grad_norm": 13.841839790344238,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 19.967,
+      "loss": 19.9871,
       "step": 17
     },
     {
       "epoch": 0.3609022556390977,
-      "grad_norm": 10.283108711242676,
+      "grad_norm": 10.296717643737793,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 20.2849,
+      "loss": 20.2823,
       "step": 18
     },
     {
       "epoch": 0.38095238095238093,
-      "grad_norm": 11.738165855407715,
+      "grad_norm": 13.013739585876465,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 19.5285,
+      "loss": 19.5543,
       "step": 19
     },
     {
       "epoch": 0.40100250626566414,
-      "grad_norm": 12.6289701461792,
+      "grad_norm": 12.78657341003418,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 19.7657,
+      "loss": 19.7823,
       "step": 20
     },
     {
       "epoch": 0.42105263157894735,
-      "grad_norm": 11.915717124938965,
+      "grad_norm": 12.13170051574707,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 19.1391,
+      "loss": 19.1667,
       "step": 21
     },
     {
       "epoch": 0.44110275689223055,
-      "grad_norm": 12.708892822265625,
+      "grad_norm": 12.084077835083008,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 18.9334,
+      "loss": 18.9524,
       "step": 22
     },
     {
       "epoch": 0.46115288220551376,
-      "grad_norm": 11.339106559753418,
+      "grad_norm": 11.325791358947754,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 19.3876,
+      "loss": 19.398,
       "step": 23
     },
     {
       "epoch": 0.48120300751879697,
-      "grad_norm": 13.785265922546387,
+      "grad_norm": 14.2548189163208,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 19.19,
+      "loss": 19.2122,
       "step": 24
     },
     {
       "epoch": 0.5012531328320802,
-      "grad_norm": 13.614476203918457,
+      "grad_norm": 13.156657218933105,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 20.1636,
+      "loss": 20.1689,
       "step": 25
     },
     {
       "epoch": 0.5012531328320802,
-      "eval_loss": 1.246433138847351,
-      "eval_runtime": 9.9398,
-      "eval_samples_per_second": 33.904,
-      "eval_steps_per_second": 4.326,
+      "eval_loss": 1.249739170074463,
+      "eval_runtime": 9.9797,
+      "eval_samples_per_second": 33.769,
+      "eval_steps_per_second": 4.309,
       "step": 25
     },
     {
       "epoch": 0.5213032581453634,
-      "grad_norm": 22.65152931213379,
+      "grad_norm": 23.704652786254883,
       "learning_rate": 5e-05,
-      "loss": 20.6473,
+      "loss": 20.6883,
       "step": 26
     },
     {
       "epoch": 0.5413533834586466,
-      "grad_norm": 15.269755363464355,
+      "grad_norm": 14.832305908203125,
       "learning_rate": 4.6729843538492847e-05,
-      "loss": 20.1124,
+      "loss": 20.1373,
       "step": 27
     },
     {
       "epoch": 0.5614035087719298,
-      "grad_norm": 11.2027006149292,
+      "grad_norm": 11.976579666137695,
       "learning_rate": 4.347369038899744e-05,
-      "loss": 19.4812,
+      "loss": 19.5452,
       "step": 28
     },
     {
       "epoch": 0.581453634085213,
-      "grad_norm": 10.389817237854004,
+      "grad_norm": 10.882586479187012,
       "learning_rate": 4.0245483899193595e-05,
-      "loss": 19.5182,
+      "loss": 19.5761,
       "step": 29
     },
     {
       "epoch": 0.6015037593984962,
-      "grad_norm": 11.606437683105469,
+      "grad_norm": 11.646707534790039,
       "learning_rate": 3.705904774487396e-05,
-      "loss": 19.2824,
+      "loss": 19.3076,
       "step": 30
     },
     {
       "epoch": 0.6215538847117794,
-      "grad_norm": 10.24315357208252,
+      "grad_norm": 9.98674201965332,
       "learning_rate": 3.392802673484193e-05,
-      "loss": 18.6898,
+      "loss": 18.681,
       "step": 31
     },
     {
       "epoch": 0.6416040100250626,
-      "grad_norm": 11.810291290283203,
+      "grad_norm": 11.689668655395508,
       "learning_rate": 3.086582838174551e-05,
-      "loss": 19.2295,
+      "loss": 19.2537,
       "step": 32
     },
     {
       "epoch": 0.6616541353383458,
-      "grad_norm": 12.391736030578613,
+      "grad_norm": 13.143380165100098,
       "learning_rate": 2.7885565489049946e-05,
-      "loss": 18.7425,
+      "loss": 18.7668,
       "step": 33
     },
     {
       "epoch": 0.681704260651629,
-      "grad_norm": 11.576544761657715,
+      "grad_norm": 12.091079711914062,
       "learning_rate": 2.500000000000001e-05,
-      "loss": 18.2593,
+      "loss": 18.3006,
       "step": 34
     },
     {
       "epoch": 0.7017543859649122,
-      "grad_norm": 10.067651748657227,
+      "grad_norm": 10.118612289428711,
       "learning_rate": 2.2221488349019903e-05,
-      "loss": 18.5798,
+      "loss": 18.5983,
       "step": 35
     },
     {
       "epoch": 0.7218045112781954,
-      "grad_norm": 10.310379981994629,
+      "grad_norm": 10.50097370147705,
       "learning_rate": 1.9561928549563968e-05,
-      "loss": 18.5488,
+      "loss": 18.5867,
       "step": 36
     },
     {
       "epoch": 0.7418546365914787,
-      "grad_norm": 11.977128982543945,
+      "grad_norm": 12.277196884155273,
       "learning_rate": 1.703270924499656e-05,
-      "loss": 19.958,
+      "loss": 19.9844,
       "step": 37
     },
     {
       "epoch": 0.7619047619047619,
-      "grad_norm": 11.227585792541504,
+      "grad_norm": 10.94597339630127,
       "learning_rate": 1.4644660940672627e-05,
-      "loss": 20.1358,
+      "loss": 20.1554,
       "step": 38
     },
     {
       "epoch": 0.7819548872180451,
-      "grad_norm": 12.250752449035645,
+      "grad_norm": 11.656758308410645,
       "learning_rate": 1.2408009626051137e-05,
-      "loss": 19.6867,
+      "loss": 19.7091,
       "step": 39
     },
     {
       "epoch": 0.8020050125313283,
-      "grad_norm": 10.369344711303711,
+      "grad_norm": 10.188664436340332,
       "learning_rate": 1.0332332985438248e-05,
-      "loss": 19.6549,
+      "loss": 19.6656,
       "step": 40
     },
     {
       "epoch": 0.8220551378446115,
-      "grad_norm": 10.211109161376953,
+      "grad_norm": 10.168734550476074,
       "learning_rate": 8.426519384872733e-06,
-      "loss": 19.1544,
+      "loss": 19.1933,
       "step": 41
     },
     {
       "epoch": 0.8421052631578947,
-      "grad_norm": 10.223684310913086,
+      "grad_norm": 10.26856517791748,
       "learning_rate": 6.698729810778065e-06,
-      "loss": 19.547,
+      "loss": 19.5783,
       "step": 42
     },
     {
       "epoch": 0.8621553884711779,
-      "grad_norm": 9.276268005371094,
+      "grad_norm": 9.320960998535156,
       "learning_rate": 5.156362923365588e-06,
-      "loss": 18.4639,
+      "loss": 18.4852,
       "step": 43
     },
     {
       "epoch": 0.8822055137844611,
-      "grad_norm": 9.275793075561523,
+      "grad_norm": 9.326827049255371,
       "learning_rate": 3.8060233744356633e-06,
-      "loss": 18.9127,
+      "loss": 18.9433,
       "step": 44
     },
     {
       "epoch": 0.9022556390977443,
-      "grad_norm": 8.820109367370605,
+      "grad_norm": 8.721112251281738,
       "learning_rate": 2.653493525244721e-06,
-      "loss": 18.035,
+      "loss": 18.0672,
       "step": 45
     },
     {
       "epoch": 0.9223057644110275,
-      "grad_norm": 9.497257232666016,
+      "grad_norm": 9.535524368286133,
       "learning_rate": 1.70370868554659e-06,
-      "loss": 18.3713,
+      "loss": 18.3811,
       "step": 46
     },
     {
       "epoch": 0.9423558897243107,
-      "grad_norm": 9.700572967529297,
+      "grad_norm": 9.78469467163086,
       "learning_rate": 9.607359798384785e-07,
-      "loss": 19.0926,
+      "loss": 19.1243,
       "step": 47
     },
     {
       "epoch": 0.9624060150375939,
-      "grad_norm": 10.158452987670898,
+      "grad_norm": 10.034987449645996,
       "learning_rate": 4.277569313094809e-07,
-      "loss": 18.515,
+      "loss": 18.5354,
       "step": 48
     },
     {
       "epoch": 0.9824561403508771,
-      "grad_norm": 14.737983703613281,
+      "grad_norm": 14.561535835266113,
       "learning_rate": 1.0705383806982606e-07,
-      "loss": 18.3978,
+      "loss": 18.4239,
       "step": 49
     },
     {
       "epoch": 1.0025062656641603,
-      "grad_norm": 9.30565071105957,
+      "grad_norm": 9.270000457763672,
       "learning_rate": 0.0,
-      "loss": 19.3901,
+      "loss": 19.4229,
       "step": 50
     },
     {
       "epoch": 1.0025062656641603,
-      "eval_loss": 1.202621579170227,
-      "eval_runtime": 9.9541,
-      "eval_samples_per_second": 33.855,
-      "eval_steps_per_second": 4.32,
+      "eval_loss": 1.2036230564117432,
+      "eval_runtime": 9.9779,
+      "eval_samples_per_second": 33.775,
+      "eval_steps_per_second": 4.31,
       "step": 50
     }
   ],

last-checkpoint/training_args.bin

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