Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "v_proj",
-    "q_proj",
     "o_proj",
     "k_proj",
+    "q_proj",
     "up_proj",
+    "gate_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970983beb227cbdf03920b3359889e93ef6318894b71759a6605baf75761df4a
+oid sha256:071b0ddb639201caefbd7366a2d3a873cc422c43b26de593250499dc3d8621f7
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86dfe560d119b76eaebae45282b354a8be799ef37b3707e27a3f88aab9c0fe01
+oid sha256:e0580b7467f75cdd81f4e20efc98c0f23ff78b2b8e7a50e16b1c66f122e09498
 size 671466706

last-checkpoint/trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.005856515373352855,
-      "grad_norm": 15.496756553649902,
+      "grad_norm": 14.918622016906738,
       "learning_rate": 5e-05,
       "loss": 12.0475,
       "step": 1
@@ -18,367 +18,367 @@
     {
       "epoch": 0.005856515373352855,
       "eval_loss": NaN,
-      "eval_runtime": 61.9886,
-      "eval_samples_per_second": 9.292,
-      "eval_steps_per_second": 2.323,
+      "eval_runtime": 61.8615,
+      "eval_samples_per_second": 9.311,
+      "eval_steps_per_second": 2.328,
       "step": 1
     },
     {
       "epoch": 0.01171303074670571,
-      "grad_norm": 15.924586296081543,
+      "grad_norm": 15.316301345825195,
       "learning_rate": 0.0001,
       "loss": 12.0052,
       "step": 2
     },
     {
       "epoch": 0.017569546120058566,
-      "grad_norm": 15.222366333007812,
+      "grad_norm": 14.685007095336914,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 11.3312,
+      "loss": 11.3609,
       "step": 3
     },
     {
       "epoch": 0.02342606149341142,
-      "grad_norm": 19.860849380493164,
+      "grad_norm": 19.817583084106445,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 7.8323,
+      "loss": 7.8627,
       "step": 4
     },
     {
       "epoch": 0.029282576866764276,
-      "grad_norm": 23.579730987548828,
+      "grad_norm": 23.481311798095703,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 4.6097,
+      "loss": 4.6256,
       "step": 5
     },
     {
       "epoch": 0.03513909224011713,
-      "grad_norm": 10.636271476745605,
+      "grad_norm": 10.337242126464844,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 1.295,
+      "loss": 1.2877,
       "step": 6
     },
     {
       "epoch": 0.040995607613469986,
-      "grad_norm": 5.987366199493408,
+      "grad_norm": 5.961005210876465,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 1.0086,
+      "loss": 1.0103,
       "step": 7
     },
     {
       "epoch": 0.04685212298682284,
-      "grad_norm": 1.646188735961914,
+      "grad_norm": 1.6553868055343628,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 0.8241,
+      "loss": 0.8216,
       "step": 8
     },
     {
       "epoch": 0.0527086383601757,
-      "grad_norm": 2.6454412937164307,
+      "grad_norm": 2.7141830921173096,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.8716,
+      "loss": 0.8739,
       "step": 9
     },
     {
       "epoch": 0.05856515373352855,
-      "grad_norm": 7.2094197273254395,
+      "grad_norm": 7.1666765213012695,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 0.8594,
+      "loss": 0.867,
       "step": 10
     },
     {
       "epoch": 0.06442166910688141,
-      "grad_norm": 3.0146830081939697,
+      "grad_norm": 2.97510027885437,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 0.8516,
+      "loss": 0.8511,
       "step": 11
     },
     {
       "epoch": 0.07027818448023426,
-      "grad_norm": 1.9659565687179565,
+      "grad_norm": 1.8449912071228027,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 0.8137,
+      "loss": 0.8066,
       "step": 12
     },
     {
       "epoch": 0.07613469985358712,
-      "grad_norm": 2.2249815464019775,
+      "grad_norm": 2.3348140716552734,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 0.8381,
+      "loss": 0.8408,
       "step": 13
     },
     {
       "epoch": 0.08199121522693997,
-      "grad_norm": 1.781930923461914,
+      "grad_norm": 1.684567928314209,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 0.8279,
+      "loss": 0.8245,
       "step": 14
     },
     {
       "epoch": 0.08784773060029283,
-      "grad_norm": 2.185213804244995,
+      "grad_norm": 2.3096187114715576,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.8448,
+      "loss": 0.8502,
       "step": 15
     },
     {
       "epoch": 0.09370424597364568,
-      "grad_norm": 1.5236265659332275,
+      "grad_norm": 1.6289703845977783,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.8256,
+      "loss": 0.8207,
       "step": 16
     },
     {
       "epoch": 0.09956076134699854,
-      "grad_norm": 1.9822412729263306,
+      "grad_norm": 1.9827245473861694,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.8664,
+      "loss": 0.8615,
       "step": 17
     },
     {
       "epoch": 0.1054172767203514,
-      "grad_norm": 1.8333975076675415,
+      "grad_norm": 1.87930428981781,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.8443,
+      "loss": 0.8393,
       "step": 18
     },
     {
       "epoch": 0.11127379209370425,
-      "grad_norm": 0.9962472319602966,
+      "grad_norm": 1.0317063331604004,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.799,
+      "loss": 0.7976,
       "step": 19
     },
     {
       "epoch": 0.1171303074670571,
-      "grad_norm": 2.1424520015716553,
+      "grad_norm": 2.2506728172302246,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.8484,
+      "loss": 0.8483,
       "step": 20
     },
     {
       "epoch": 0.12298682284040996,
-      "grad_norm": 0.4117889106273651,
+      "grad_norm": 0.4539792239665985,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.7974,
+      "loss": 0.8,
       "step": 21
     },
     {
       "epoch": 0.12884333821376281,
-      "grad_norm": 0.46038737893104553,
+      "grad_norm": 0.520776093006134,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.8049,
+      "loss": 0.8107,
       "step": 22
     },
     {
       "epoch": 0.13469985358711567,
-      "grad_norm": 1.3282312154769897,
+      "grad_norm": 1.4138851165771484,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.8265,
+      "loss": 0.8293,
       "step": 23
     },
     {
       "epoch": 0.14055636896046853,
-      "grad_norm": 1.1813817024230957,
+      "grad_norm": 1.2263822555541992,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.8277,
+      "loss": 0.8302,
       "step": 24
     },
     {
       "epoch": 0.14641288433382138,
-      "grad_norm": 1.2727360725402832,
+      "grad_norm": 1.314178228378296,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.8242,
+      "loss": 0.8236,
       "step": 25
     },
     {
       "epoch": 0.14641288433382138,
       "eval_loss": NaN,
-      "eval_runtime": 61.9153,
-      "eval_samples_per_second": 9.303,
+      "eval_runtime": 61.9009,
+      "eval_samples_per_second": 9.305,
       "eval_steps_per_second": 2.326,
       "step": 25
     },
     {
       "epoch": 0.15226939970717424,
-      "grad_norm": 0.991141676902771,
+      "grad_norm": 1.018844723701477,
       "learning_rate": 5e-05,
-      "loss": 0.8228,
+      "loss": 0.8276,
       "step": 26
     },
     {
       "epoch": 0.1581259150805271,
-      "grad_norm": 1.5344549417495728,
+      "grad_norm": 1.5573893785476685,
       "learning_rate": 4.6729843538492847e-05,
-      "loss": 0.834,
+      "loss": 0.8342,
       "step": 27
     },
     {
       "epoch": 0.16398243045387995,
-      "grad_norm": 1.1114848852157593,
+      "grad_norm": 1.1054158210754395,
       "learning_rate": 4.347369038899744e-05,
-      "loss": 0.7982,
+      "loss": 0.7928,
       "step": 28
     },
     {
       "epoch": 0.1698389458272328,
-      "grad_norm": 0.5201159715652466,
+      "grad_norm": 0.49394914507865906,
       "learning_rate": 4.0245483899193595e-05,
-      "loss": 0.7959,
+      "loss": 0.8016,
       "step": 29
     },
     {
       "epoch": 0.17569546120058566,
-      "grad_norm": 0.6724088191986084,
+      "grad_norm": 0.6805071830749512,
       "learning_rate": 3.705904774487396e-05,
-      "loss": 0.8066,
+      "loss": 0.8038,
       "step": 30
     },
     {
       "epoch": 0.1815519765739385,
-      "grad_norm": 0.7300559878349304,
+      "grad_norm": 0.742039680480957,
       "learning_rate": 3.392802673484193e-05,
-      "loss": 0.8315,
+      "loss": 0.8326,
       "step": 31
     },
     {
       "epoch": 0.18740849194729137,
-      "grad_norm": 0.8889698386192322,
+      "grad_norm": 0.8860661387443542,
       "learning_rate": 3.086582838174551e-05,
-      "loss": 0.8408,
+      "loss": 0.8392,
       "step": 32
     },
     {
       "epoch": 0.19326500732064422,
-      "grad_norm": 0.4890342354774475,
+      "grad_norm": 0.37492647767066956,
       "learning_rate": 2.7885565489049946e-05,
-      "loss": 0.8032,
+      "loss": 0.809,
       "step": 33
     },
     {
       "epoch": 0.19912152269399708,
-      "grad_norm": 0.67667555809021,
+      "grad_norm": 0.6945987939834595,
       "learning_rate": 2.500000000000001e-05,
-      "loss": 0.8094,
+      "loss": 0.8074,
       "step": 34
     },
     {
       "epoch": 0.20497803806734993,
-      "grad_norm": 1.1676506996154785,
+      "grad_norm": 1.208330750465393,
       "learning_rate": 2.2221488349019903e-05,
-      "loss": 0.858,
+      "loss": 0.8544,
       "step": 35
     },
     {
       "epoch": 0.2108345534407028,
-      "grad_norm": 0.6951544880867004,
+      "grad_norm": 0.6995104551315308,
       "learning_rate": 1.9561928549563968e-05,
-      "loss": 0.8227,
+      "loss": 0.8252,
       "step": 36
     },
     {
       "epoch": 0.21669106881405564,
-      "grad_norm": 0.6004828214645386,
+      "grad_norm": 0.555928647518158,
       "learning_rate": 1.703270924499656e-05,
-      "loss": 0.8094,
+      "loss": 0.8103,
       "step": 37
     },
     {
       "epoch": 0.2225475841874085,
-      "grad_norm": 0.38111612200737,
+      "grad_norm": 0.3408339321613312,
       "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.807,
+      "loss": 0.8013,
       "step": 38
     },
     {
       "epoch": 0.22840409956076135,
-      "grad_norm": 0.465547651052475,
+      "grad_norm": 0.4947563111782074,
       "learning_rate": 1.2408009626051137e-05,
-      "loss": 0.7956,
+      "loss": 0.7977,
       "step": 39
     },
     {
       "epoch": 0.2342606149341142,
-      "grad_norm": 0.6924857497215271,
+      "grad_norm": 0.6463351249694824,
       "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.7911,
+      "loss": 0.788,
       "step": 40
     },
     {
       "epoch": 0.24011713030746706,
-      "grad_norm": 0.9701064825057983,
+      "grad_norm": 0.936543881893158,
       "learning_rate": 8.426519384872733e-06,
-      "loss": 0.8248,
+      "loss": 0.8299,
       "step": 41
     },
     {
       "epoch": 0.24597364568081992,
-      "grad_norm": 0.47871139645576477,
+      "grad_norm": 0.4004238247871399,
       "learning_rate": 6.698729810778065e-06,
-      "loss": 0.7925,
+      "loss": 0.7961,
       "step": 42
     },
     {
       "epoch": 0.2518301610541728,
-      "grad_norm": 0.7060790657997131,
+      "grad_norm": 0.6793810725212097,
       "learning_rate": 5.156362923365588e-06,
-      "loss": 0.8076,
+      "loss": 0.8074,
       "step": 43
     },
     {
       "epoch": 0.25768667642752563,
-      "grad_norm": 0.4863818287849426,
+      "grad_norm": 0.47148361802101135,
       "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.8132,
+      "loss": 0.8173,
       "step": 44
     },
     {
       "epoch": 0.2635431918008785,
-      "grad_norm": 1.0663129091262817,
+      "grad_norm": 1.0098521709442139,
       "learning_rate": 2.653493525244721e-06,
-      "loss": 0.8377,
+      "loss": 0.8319,
       "step": 45
     },
     {
       "epoch": 0.26939970717423134,
-      "grad_norm": 0.40442147850990295,
+      "grad_norm": 0.4209153652191162,
       "learning_rate": 1.70370868554659e-06,
-      "loss": 0.8052,
+      "loss": 0.8057,
       "step": 46
     },
     {
       "epoch": 0.2752562225475842,
-      "grad_norm": 0.27849093079566956,
+      "grad_norm": 0.28130272030830383,
       "learning_rate": 9.607359798384785e-07,
-      "loss": 0.7993,
+      "loss": 0.7952,
       "step": 47
     },
     {
       "epoch": 0.28111273792093705,
-      "grad_norm": 0.9323040246963501,
+      "grad_norm": 0.8941959142684937,
       "learning_rate": 4.277569313094809e-07,
-      "loss": 0.8299,
+      "loss": 0.8271,
       "step": 48
     },
     {
       "epoch": 0.2869692532942899,
-      "grad_norm": 0.7039565443992615,
+      "grad_norm": 0.7027775645256042,
       "learning_rate": 1.0705383806982606e-07,
-      "loss": 0.8115,
+      "loss": 0.8116,
       "step": 49
     },
     {
       "epoch": 0.29282576866764276,
-      "grad_norm": 0.7268103957176208,
+      "grad_norm": 0.7722964286804199,
       "learning_rate": 0.0,
-      "loss": 0.8126,
+      "loss": 0.8128,
       "step": 50
     },
     {
       "epoch": 0.29282576866764276,
       "eval_loss": NaN,
-      "eval_runtime": 61.9133,
-      "eval_samples_per_second": 9.303,
+      "eval_runtime": 61.9207,
+      "eval_samples_per_second": 9.302,
       "eval_steps_per_second": 2.326,
       "step": 50
     }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc3fbd90ca4e100745ea377972802db0002547fc42dbc426493ea4a34df3d614
+oid sha256:b36009de0fa883d25e567fdaa3dc7a0afe18c8311b45c35c78d0205eca007468
 size 6776