Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "down_proj",
-    "k_proj",
     "o_proj",
-    "up_proj",
+    "k_proj",
     "gate_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "up_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:d117bbf168d69f60a424a760bef6fccfca0091958260bd87f76e3d6a8ae886d1
+oid sha256:d8c4390df21e68610fbe4614aa868b686c741edd9e413d9af9231973d4a6652c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d59ab68e69fe90c404a9065268d3667645439eef9d21fb33266e28e74b23d9c8
+oid sha256:6fb20557a384a3a096bfa6d4ff1fdcff81e585814f1f2c927a1c12318e3a5b27
 size 671466706

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8842406272888184,
+  "best_metric": 0.8842917680740356,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
   "epoch": 0.042030051486813075,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.0008406010297362615,
-      "grad_norm": 29.893037796020508,
+      "grad_norm": 29.086793899536133,
       "learning_rate": 5e-05,
       "loss": 1.1322,
       "step": 1
@@ -18,368 +18,368 @@
     {
       "epoch": 0.0008406010297362615,
       "eval_loss": 1.5847445726394653,
-      "eval_runtime": 328.1623,
-      "eval_samples_per_second": 24.424,
-      "eval_steps_per_second": 3.053,
+      "eval_runtime": 329.2359,
+      "eval_samples_per_second": 24.344,
+      "eval_steps_per_second": 3.043,
       "step": 1
     },
     {
       "epoch": 0.001681202059472523,
-      "grad_norm": 38.240726470947266,
+      "grad_norm": 37.103294372558594,
       "learning_rate": 0.0001,
       "loss": 1.1903,
       "step": 2
     },
     {
       "epoch": 0.0025218030892087844,
-      "grad_norm": 22.42188835144043,
+      "grad_norm": 22.057762145996094,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.099,
+      "loss": 1.0993,
       "step": 3
     },
     {
       "epoch": 0.003362404118945046,
-      "grad_norm": 27.676525115966797,
+      "grad_norm": 27.0430850982666,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 1.0275,
+      "loss": 1.0276,
       "step": 4
     },
     {
       "epoch": 0.004203005148681307,
-      "grad_norm": 21.674997329711914,
+      "grad_norm": 21.204166412353516,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 0.9484,
+      "loss": 0.9479,
       "step": 5
     },
     {
       "epoch": 0.005043606178417569,
-      "grad_norm": 16.474008560180664,
+      "grad_norm": 16.131593704223633,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 0.9437,
+      "loss": 0.9434,
       "step": 6
     },
     {
       "epoch": 0.00588420720815383,
-      "grad_norm": 14.874077796936035,
+      "grad_norm": 14.928062438964844,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 0.9291,
+      "loss": 0.9296,
       "step": 7
     },
     {
       "epoch": 0.006724808237890092,
-      "grad_norm": 16.181907653808594,
+      "grad_norm": 15.689757347106934,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 0.8951,
+      "loss": 0.8946,
       "step": 8
     },
     {
       "epoch": 0.007565409267626353,
-      "grad_norm": 16.14239501953125,
+      "grad_norm": 15.841815948486328,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.9345,
+      "loss": 0.9336,
       "step": 9
     },
     {
       "epoch": 0.008406010297362614,
-      "grad_norm": 20.997081756591797,
+      "grad_norm": 21.234691619873047,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 0.9352,
+      "loss": 0.9359,
       "step": 10
     },
     {
       "epoch": 0.009246611327098876,
-      "grad_norm": 46.29018020629883,
+      "grad_norm": 46.254371643066406,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 0.943,
+      "loss": 0.9442,
       "step": 11
     },
     {
       "epoch": 0.010087212356835138,
-      "grad_norm": 39.82704162597656,
+      "grad_norm": 39.27686309814453,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 0.9758,
+      "loss": 0.9759,
       "step": 12
     },
     {
       "epoch": 0.010927813386571398,
-      "grad_norm": 43.356971740722656,
+      "grad_norm": 42.7838020324707,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 1.1871,
+      "loss": 1.1893,
       "step": 13
     },
     {
       "epoch": 0.01176841441630766,
-      "grad_norm": 43.99378967285156,
+      "grad_norm": 43.22084045410156,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 1.0819,
+      "loss": 1.087,
       "step": 14
     },
     {
       "epoch": 0.012609015446043922,
-      "grad_norm": 31.90110969543457,
+      "grad_norm": 31.586978912353516,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 1.017,
+      "loss": 1.022,
       "step": 15
     },
     {
       "epoch": 0.013449616475780184,
-      "grad_norm": 19.444290161132812,
+      "grad_norm": 19.490676879882812,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.9459,
+      "loss": 0.9471,
       "step": 16
     },
     {
       "epoch": 0.014290217505516444,
-      "grad_norm": 16.75783920288086,
+      "grad_norm": 15.468281745910645,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.9341,
+      "loss": 0.9333,
       "step": 17
     },
     {
       "epoch": 0.015130818535252706,
-      "grad_norm": 13.813448905944824,
+      "grad_norm": 13.710147857666016,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.8744,
+      "loss": 0.8749,
       "step": 18
     },
     {
       "epoch": 0.015971419564988966,
-      "grad_norm": 14.708357810974121,
+      "grad_norm": 14.42135238647461,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.9037,
+      "loss": 0.9027,
       "step": 19
     },
     {
       "epoch": 0.016812020594725228,
-      "grad_norm": 15.051857948303223,
+      "grad_norm": 15.01803970336914,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.889,
+      "loss": 0.891,
       "step": 20
     },
     {
       "epoch": 0.01765262162446149,
-      "grad_norm": 14.950255393981934,
+      "grad_norm": 14.898659706115723,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.8916,
+      "loss": 0.8931,
       "step": 21
     },
     {
       "epoch": 0.01849322265419775,
-      "grad_norm": 16.55318832397461,
+      "grad_norm": 16.494243621826172,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.9164,
+      "loss": 0.9187,
       "step": 22
     },
     {
       "epoch": 0.019333823683934014,
-      "grad_norm": 24.609590530395508,
+      "grad_norm": 24.648656845092773,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.9521,
+      "loss": 0.9515,
       "step": 23
     },
     {
       "epoch": 0.020174424713670275,
-      "grad_norm": 57.03383255004883,
+      "grad_norm": 59.49314880371094,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 1.0749,
+      "loss": 1.0793,
       "step": 24
     },
     {
       "epoch": 0.021015025743406537,
-      "grad_norm": 113.75789642333984,
+      "grad_norm": 118.05199432373047,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 1.2929,
+      "loss": 1.2911,
       "step": 25
     },
     {
       "epoch": 0.021015025743406537,
-      "eval_loss": 0.9329141974449158,
-      "eval_runtime": 328.0979,
-      "eval_samples_per_second": 24.429,
-      "eval_steps_per_second": 3.054,
+      "eval_loss": 0.9318052530288696,
+      "eval_runtime": 329.4878,
+      "eval_samples_per_second": 24.326,
+      "eval_steps_per_second": 3.041,
       "step": 25
     },
     {
       "epoch": 0.021855626773142796,
-      "grad_norm": 21.47029685974121,
+      "grad_norm": 21.1945743560791,
       "learning_rate": 5e-05,
-      "loss": 0.9629,
+      "loss": 0.9618,
       "step": 26
     },
     {
       "epoch": 0.022696227802879058,
-      "grad_norm": 18.87315559387207,
+      "grad_norm": 18.67919921875,
       "learning_rate": 4.6729843538492847e-05,
-      "loss": 0.9489,
+      "loss": 0.9474,
       "step": 27
     },
     {
       "epoch": 0.02353682883261532,
-      "grad_norm": 15.906596183776855,
+      "grad_norm": 15.636688232421875,
       "learning_rate": 4.347369038899744e-05,
-      "loss": 0.9097,
+      "loss": 0.9087,
       "step": 28
     },
     {
       "epoch": 0.02437742986235158,
-      "grad_norm": 14.059663772583008,
+      "grad_norm": 13.814027786254883,
       "learning_rate": 4.0245483899193595e-05,
       "loss": 0.895,
       "step": 29
     },
     {
       "epoch": 0.025218030892087843,
-      "grad_norm": 12.472660064697266,
+      "grad_norm": 12.284393310546875,
       "learning_rate": 3.705904774487396e-05,
-      "loss": 0.8505,
+      "loss": 0.8517,
       "step": 30
     },
     {
       "epoch": 0.026058631921824105,
-      "grad_norm": 11.869236946105957,
+      "grad_norm": 12.033905029296875,
       "learning_rate": 3.392802673484193e-05,
-      "loss": 0.8515,
+      "loss": 0.8517,
       "step": 31
     },
     {
       "epoch": 0.026899232951560367,
-      "grad_norm": 12.28493881225586,
+      "grad_norm": 12.209423065185547,
       "learning_rate": 3.086582838174551e-05,
-      "loss": 0.8315,
+      "loss": 0.8325,
       "step": 32
     },
     {
       "epoch": 0.027739833981296626,
-      "grad_norm": 14.952657699584961,
+      "grad_norm": 14.647412300109863,
       "learning_rate": 2.7885565489049946e-05,
-      "loss": 0.8651,
+      "loss": 0.8644,
       "step": 33
     },
     {
       "epoch": 0.028580435011032888,
-      "grad_norm": 15.232952117919922,
+      "grad_norm": 14.768932342529297,
       "learning_rate": 2.500000000000001e-05,
-      "loss": 0.841,
+      "loss": 0.8397,
       "step": 34
     },
     {
       "epoch": 0.02942103604076915,
-      "grad_norm": 17.50577735900879,
+      "grad_norm": 17.525489807128906,
       "learning_rate": 2.2221488349019903e-05,
-      "loss": 0.8881,
+      "loss": 0.8872,
       "step": 35
     },
     {
       "epoch": 0.03026163707050541,
-      "grad_norm": 24.29168128967285,
+      "grad_norm": 24.56749725341797,
       "learning_rate": 1.9561928549563968e-05,
-      "loss": 0.9428,
+      "loss": 0.9443,
       "step": 36
     },
     {
       "epoch": 0.031102238100241673,
-      "grad_norm": 36.69811248779297,
+      "grad_norm": 37.059207916259766,
       "learning_rate": 1.703270924499656e-05,
-      "loss": 1.0153,
+      "loss": 1.0107,
       "step": 37
     },
     {
       "epoch": 0.03194283912997793,
-      "grad_norm": 40.169559478759766,
+      "grad_norm": 40.10791778564453,
       "learning_rate": 1.4644660940672627e-05,
-      "loss": 1.0802,
+      "loss": 1.0808,
       "step": 38
     },
     {
       "epoch": 0.0327834401597142,
-      "grad_norm": 13.106291770935059,
+      "grad_norm": 12.88058090209961,
       "learning_rate": 1.2408009626051137e-05,
-      "loss": 0.8705,
+      "loss": 0.871,
       "step": 39
     },
     {
       "epoch": 0.033624041189450456,
-      "grad_norm": 12.658334732055664,
+      "grad_norm": 12.215153694152832,
       "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.8757,
+      "loss": 0.8761,
       "step": 40
     },
     {
       "epoch": 0.03446464221918672,
-      "grad_norm": 11.946065902709961,
+      "grad_norm": 12.088946342468262,
       "learning_rate": 8.426519384872733e-06,
-      "loss": 0.8489,
+      "loss": 0.85,
       "step": 41
     },
     {
       "epoch": 0.03530524324892298,
-      "grad_norm": 11.120903015136719,
+      "grad_norm": 11.080222129821777,
       "learning_rate": 6.698729810778065e-06,
-      "loss": 0.7939,
+      "loss": 0.7963,
       "step": 42
     },
     {
       "epoch": 0.03614584427865924,
-      "grad_norm": 10.89737606048584,
+      "grad_norm": 11.147324562072754,
       "learning_rate": 5.156362923365588e-06,
       "loss": 0.8308,
       "step": 43
     },
     {
       "epoch": 0.0369864453083955,
-      "grad_norm": 11.188016891479492,
+      "grad_norm": 11.311895370483398,
       "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.8416,
+      "loss": 0.844,
       "step": 44
     },
     {
       "epoch": 0.03782704633813176,
-      "grad_norm": 11.53243637084961,
+      "grad_norm": 11.452832221984863,
       "learning_rate": 2.653493525244721e-06,
-      "loss": 0.8469,
+      "loss": 0.8485,
       "step": 45
     },
     {
       "epoch": 0.03866764736786803,
-      "grad_norm": 12.847345352172852,
+      "grad_norm": 12.819865226745605,
       "learning_rate": 1.70370868554659e-06,
-      "loss": 0.8525,
+      "loss": 0.8536,
       "step": 46
     },
     {
       "epoch": 0.039508248397604286,
-      "grad_norm": 14.478405952453613,
+      "grad_norm": 14.396231651306152,
       "learning_rate": 9.607359798384785e-07,
-      "loss": 0.8955,
+      "loss": 0.8954,
       "step": 47
     },
     {
       "epoch": 0.04034884942734055,
-      "grad_norm": 19.109928131103516,
+      "grad_norm": 19.015718460083008,
       "learning_rate": 4.277569313094809e-07,
-      "loss": 0.9401,
+      "loss": 0.9406,
       "step": 48
     },
     {
       "epoch": 0.04118945045707681,
-      "grad_norm": 28.560216903686523,
+      "grad_norm": 28.2912540435791,
       "learning_rate": 1.0705383806982606e-07,
-      "loss": 0.8167,
+      "loss": 0.8178,
       "step": 49
     },
     {
       "epoch": 0.042030051486813075,
-      "grad_norm": 50.27409744262695,
+      "grad_norm": 50.38022994995117,
       "learning_rate": 0.0,
-      "loss": 1.1451,
+      "loss": 1.1406,
       "step": 50
     },
     {
       "epoch": 0.042030051486813075,
-      "eval_loss": 0.8842406272888184,
-      "eval_runtime": 331.3451,
-      "eval_samples_per_second": 24.189,
-      "eval_steps_per_second": 3.024,
+      "eval_loss": 0.8842917680740356,
+      "eval_runtime": 329.7013,
+      "eval_samples_per_second": 24.31,
+      "eval_steps_per_second": 3.039,
       "step": 50
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1cacc4070899ec6140ce624ad9111e3cd3116b234a9d45e345cdf260945df5f
+oid sha256:06ea9b0e7461d608bdc78005e0ce4a13003303f92c48ee59de6dd64648eec034
 size 6776