Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
     "q_proj",
+    "k_proj",
     "gate_proj",
     "down_proj",
     "v_proj",
-    "k_proj"
+    "o_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 sha256:8aa329c5af8be49237ec6cbf7cd7b41a9d168f1bd675bb8dd6c40d1f9e518fa0
+oid sha256:20dba402be068580d83c349df7bfa19ffa24da5405bb81aac9b521966ba1281b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e523954bfced769866218d35dee78603de618ab1436e409282cb882182c7c4
+oid sha256:f0d0373a5bb2e653c160150cd9460848f2f9dd55c2249f0621f848263f819ddf
 size 671466706

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.0359615087509155,
+  "best_metric": 1.035404920578003,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
   "epoch": 0.6182380216383307,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.012364760432766615,
-      "grad_norm": 65.4753189086914,
+      "grad_norm": 64.29004669189453,
       "learning_rate": 5e-05,
       "loss": 1.7005,
       "step": 1
@@ -18,368 +18,368 @@
     {
       "epoch": 0.012364760432766615,
       "eval_loss": 1.5441035032272339,
-      "eval_runtime": 26.9469,
-      "eval_samples_per_second": 20.225,
-      "eval_steps_per_second": 2.561,
+      "eval_runtime": 27.0566,
+      "eval_samples_per_second": 20.143,
+      "eval_steps_per_second": 2.55,
       "step": 1
     },
     {
       "epoch": 0.02472952086553323,
-      "grad_norm": 63.677093505859375,
+      "grad_norm": 62.47732162475586,
       "learning_rate": 0.0001,
       "loss": 1.5408,
       "step": 2
     },
     {
       "epoch": 0.03709428129829984,
-      "grad_norm": 38.44874954223633,
+      "grad_norm": 37.50821304321289,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.4339,
+      "loss": 1.4364,
       "step": 3
     },
     {
       "epoch": 0.04945904173106646,
-      "grad_norm": 36.82088088989258,
+      "grad_norm": 35.94296646118164,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 1.2845,
+      "loss": 1.285,
       "step": 4
     },
     {
       "epoch": 0.061823802163833076,
-      "grad_norm": 18.930330276489258,
+      "grad_norm": 18.204742431640625,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 1.2066,
+      "loss": 1.2052,
       "step": 5
     },
     {
       "epoch": 0.07418856259659969,
-      "grad_norm": 19.951047897338867,
+      "grad_norm": 19.261959075927734,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 1.1864,
+      "loss": 1.1855,
       "step": 6
     },
     {
       "epoch": 0.0865533230293663,
-      "grad_norm": 15.55380630493164,
+      "grad_norm": 14.603866577148438,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 1.115,
+      "loss": 1.1152,
       "step": 7
     },
     {
       "epoch": 0.09891808346213292,
-      "grad_norm": 51.38351821899414,
+      "grad_norm": 16.302173614501953,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 1.1459,
+      "loss": 1.1424,
       "step": 8
     },
     {
       "epoch": 0.11128284389489954,
-      "grad_norm": 20.464824676513672,
+      "grad_norm": 15.016532897949219,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 1.1179,
+      "loss": 1.1089,
       "step": 9
     },
     {
       "epoch": 0.12364760432766615,
-      "grad_norm": 14.560519218444824,
+      "grad_norm": 15.044660568237305,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 1.0324,
+      "loss": 1.0282,
       "step": 10
     },
     {
       "epoch": 0.13601236476043277,
-      "grad_norm": 16.44891357421875,
+      "grad_norm": 14.534330368041992,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 1.0985,
+      "loss": 1.0921,
       "step": 11
     },
     {
       "epoch": 0.14837712519319937,
-      "grad_norm": 13.887516021728516,
+      "grad_norm": 14.35930347442627,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 1.0447,
+      "loss": 1.0389,
       "step": 12
     },
     {
       "epoch": 0.160741885625966,
-      "grad_norm": 17.173248291015625,
+      "grad_norm": 16.542173385620117,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 1.1134,
+      "loss": 1.1104,
       "step": 13
     },
     {
       "epoch": 0.1731066460587326,
-      "grad_norm": 18.054431915283203,
+      "grad_norm": 15.786033630371094,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 1.1994,
+      "loss": 1.1943,
       "step": 14
     },
     {
       "epoch": 0.18547140649149924,
-      "grad_norm": 13.658798217773438,
+      "grad_norm": 13.105801582336426,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 1.138,
+      "loss": 1.1353,
       "step": 15
     },
     {
       "epoch": 0.19783616692426584,
-      "grad_norm": 15.112719535827637,
+      "grad_norm": 14.734046936035156,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 1.1268,
+      "loss": 1.1239,
       "step": 16
     },
     {
       "epoch": 0.21020092735703247,
-      "grad_norm": 14.573080062866211,
+      "grad_norm": 13.833138465881348,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 1.0827,
+      "loss": 1.0785,
       "step": 17
     },
     {
       "epoch": 0.22256568778979907,
-      "grad_norm": 12.513110160827637,
+      "grad_norm": 12.960760116577148,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 1.0823,
+      "loss": 1.0789,
       "step": 18
     },
     {
       "epoch": 0.23493044822256567,
-      "grad_norm": 14.179524421691895,
+      "grad_norm": 14.09332275390625,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 1.0901,
+      "loss": 1.0874,
       "step": 19
     },
     {
       "epoch": 0.2472952086553323,
-      "grad_norm": 12.364250183105469,
+      "grad_norm": 11.763240814208984,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 1.0374,
+      "loss": 1.0358,
       "step": 20
     },
     {
       "epoch": 0.2596599690880989,
-      "grad_norm": 12.568696022033691,
+      "grad_norm": 12.183867454528809,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 1.0597,
+      "loss": 1.0567,
       "step": 21
     },
     {
       "epoch": 0.27202472952086554,
-      "grad_norm": 12.904902458190918,
+      "grad_norm": 12.834959983825684,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.9841,
+      "loss": 0.9824,
       "step": 22
     },
     {
       "epoch": 0.28438948995363217,
-      "grad_norm": 13.623453140258789,
+      "grad_norm": 12.709415435791016,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 1.0478,
+      "loss": 1.0453,
       "step": 23
     },
     {
       "epoch": 0.29675425038639874,
-      "grad_norm": 15.266836166381836,
+      "grad_norm": 12.786401748657227,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.9646,
+      "loss": 0.9603,
       "step": 24
     },
     {
       "epoch": 0.3091190108191654,
-      "grad_norm": 13.770989418029785,
+      "grad_norm": 14.301573753356934,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.9647,
+      "loss": 0.9649,
       "step": 25
     },
     {
       "epoch": 0.3091190108191654,
-      "eval_loss": 1.0564574003219604,
-      "eval_runtime": 26.9441,
-      "eval_samples_per_second": 20.227,
-      "eval_steps_per_second": 2.561,
+      "eval_loss": 1.0556217432022095,
+      "eval_runtime": 27.0621,
+      "eval_samples_per_second": 20.139,
+      "eval_steps_per_second": 2.55,
       "step": 25
     },
     {
       "epoch": 0.321483771251932,
-      "grad_norm": 15.856243133544922,
+      "grad_norm": 16.074369430541992,
       "learning_rate": 5e-05,
-      "loss": 1.2542,
+      "loss": 1.2545,
       "step": 26
     },
     {
       "epoch": 0.33384853168469864,
-      "grad_norm": 16.397891998291016,
+      "grad_norm": 15.460994720458984,
       "learning_rate": 4.6729843538492847e-05,
-      "loss": 1.1305,
+      "loss": 1.1281,
       "step": 27
     },
     {
       "epoch": 0.3462132921174652,
-      "grad_norm": 13.795293807983398,
+      "grad_norm": 13.048852920532227,
       "learning_rate": 4.347369038899744e-05,
-      "loss": 1.0607,
+      "loss": 1.0592,
       "step": 28
     },
     {
       "epoch": 0.35857805255023184,
-      "grad_norm": 12.077628135681152,
+      "grad_norm": 11.718851089477539,
       "learning_rate": 4.0245483899193595e-05,
-      "loss": 1.1596,
+      "loss": 1.1608,
       "step": 29
     },
     {
       "epoch": 0.37094281298299847,
-      "grad_norm": 11.004748344421387,
+      "grad_norm": 11.466394424438477,
       "learning_rate": 3.705904774487396e-05,
-      "loss": 1.0742,
+      "loss": 1.0716,
       "step": 30
     },
     {
       "epoch": 0.38330757341576505,
-      "grad_norm": 11.478070259094238,
+      "grad_norm": 11.176027297973633,
       "learning_rate": 3.392802673484193e-05,
-      "loss": 1.0366,
+      "loss": 1.0359,
       "step": 31
     },
     {
       "epoch": 0.3956723338485317,
-      "grad_norm": 13.015902519226074,
+      "grad_norm": 10.946759223937988,
       "learning_rate": 3.086582838174551e-05,
-      "loss": 1.0506,
+      "loss": 1.0483,
       "step": 32
     },
     {
       "epoch": 0.4080370942812983,
-      "grad_norm": 11.043506622314453,
+      "grad_norm": 10.408958435058594,
       "learning_rate": 2.7885565489049946e-05,
-      "loss": 0.9651,
+      "loss": 0.9645,
       "step": 33
     },
     {
       "epoch": 0.42040185471406494,
-      "grad_norm": 11.857297897338867,
+      "grad_norm": 10.959866523742676,
       "learning_rate": 2.500000000000001e-05,
-      "loss": 1.0363,
+      "loss": 1.0344,
       "step": 34
     },
     {
       "epoch": 0.4327666151468315,
-      "grad_norm": 10.669569969177246,
+      "grad_norm": 10.49497127532959,
       "learning_rate": 2.2221488349019903e-05,
-      "loss": 0.9911,
+      "loss": 0.9897,
       "step": 35
     },
     {
       "epoch": 0.44513137557959814,
-      "grad_norm": 12.18918514251709,
+      "grad_norm": 11.895526885986328,
       "learning_rate": 1.9561928549563968e-05,
-      "loss": 1.0056,
+      "loss": 1.0052,
       "step": 36
     },
     {
       "epoch": 0.4574961360123648,
-      "grad_norm": 11.107763290405273,
+      "grad_norm": 10.539115905761719,
       "learning_rate": 1.703270924499656e-05,
-      "loss": 0.9801,
+      "loss": 0.9767,
       "step": 37
     },
     {
       "epoch": 0.46986089644513135,
-      "grad_norm": 12.230752944946289,
+      "grad_norm": 11.975604057312012,
       "learning_rate": 1.4644660940672627e-05,
-      "loss": 1.1017,
+      "loss": 1.102,
       "step": 38
     },
     {
       "epoch": 0.482225656877898,
-      "grad_norm": 11.509124755859375,
+      "grad_norm": 11.794081687927246,
       "learning_rate": 1.2408009626051137e-05,
-      "loss": 1.1986,
+      "loss": 1.197,
       "step": 39
     },
     {
       "epoch": 0.4945904173106646,
-      "grad_norm": 11.408638000488281,
+      "grad_norm": 11.514941215515137,
       "learning_rate": 1.0332332985438248e-05,
-      "loss": 1.0935,
+      "loss": 1.0931,
       "step": 40
     },
     {
       "epoch": 0.5069551777434312,
-      "grad_norm": 11.174295425415039,
+      "grad_norm": 11.728755950927734,
       "learning_rate": 8.426519384872733e-06,
-      "loss": 1.1101,
+      "loss": 1.1109,
       "step": 41
     },
     {
       "epoch": 0.5193199381761978,
-      "grad_norm": 12.814458847045898,
+      "grad_norm": 12.327763557434082,
       "learning_rate": 6.698729810778065e-06,
-      "loss": 1.0953,
+      "loss": 1.0959,
       "step": 42
     },
     {
       "epoch": 0.5316846986089645,
-      "grad_norm": 11.73488712310791,
+      "grad_norm": 11.505321502685547,
       "learning_rate": 5.156362923365588e-06,
-      "loss": 1.1307,
+      "loss": 1.1281,
       "step": 43
     },
     {
       "epoch": 0.5440494590417311,
-      "grad_norm": 10.956543922424316,
+      "grad_norm": 10.898706436157227,
       "learning_rate": 3.8060233744356633e-06,
-      "loss": 1.0286,
+      "loss": 1.0272,
       "step": 44
     },
     {
       "epoch": 0.5564142194744977,
-      "grad_norm": 10.427705764770508,
+      "grad_norm": 10.793313980102539,
       "learning_rate": 2.653493525244721e-06,
-      "loss": 0.991,
+      "loss": 0.9923,
       "step": 45
     },
     {
       "epoch": 0.5687789799072643,
-      "grad_norm": 11.056525230407715,
+      "grad_norm": 10.757425308227539,
       "learning_rate": 1.70370868554659e-06,
-      "loss": 1.0113,
+      "loss": 1.0094,
       "step": 46
     },
     {
       "epoch": 0.5811437403400309,
-      "grad_norm": 10.139036178588867,
+      "grad_norm": 10.546533584594727,
       "learning_rate": 9.607359798384785e-07,
-      "loss": 0.9341,
+      "loss": 0.934,
       "step": 47
     },
     {
       "epoch": 0.5935085007727975,
-      "grad_norm": 10.551136016845703,
+      "grad_norm": 11.380433082580566,
       "learning_rate": 4.277569313094809e-07,
-      "loss": 1.0015,
+      "loss": 1.0027,
       "step": 48
     },
     {
       "epoch": 0.6058732612055642,
-      "grad_norm": 10.819656372070312,
+      "grad_norm": 11.34750747680664,
       "learning_rate": 1.0705383806982606e-07,
-      "loss": 0.9729,
+      "loss": 0.9724,
       "step": 49
     },
     {
       "epoch": 0.6182380216383307,
-      "grad_norm": 11.754311561584473,
+      "grad_norm": 13.081766128540039,
       "learning_rate": 0.0,
-      "loss": 0.9203,
+      "loss": 0.9192,
       "step": 50
     },
     {
       "epoch": 0.6182380216383307,
-      "eval_loss": 1.0359615087509155,
-      "eval_runtime": 26.9396,
-      "eval_samples_per_second": 20.23,
-      "eval_steps_per_second": 2.561,
+      "eval_loss": 1.035404920578003,
+      "eval_runtime": 27.0703,
+      "eval_samples_per_second": 20.133,
+      "eval_steps_per_second": 2.549,
       "step": 50
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ec7a24b66787d2564811f1dc1209b71bc9e9e6e058875b5a7e97f8a60519fc7
+oid sha256:d5088dc23c6397af8783b01b33eec8575b490cbf9f4f4e1a8c92e7c4b1b56b82
 size 6776