Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -23,10 +23,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "qkv_proj",
-    "gate_up_proj",
     "o_proj",
-    "down_proj"
+    "gate_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 sha256:4346de8e123621fa784152d44afc1c586bee15be27c19a00af68719decdd75bb
+oid sha256:bac66d72e1753bfad0345f31dad861431d3c52bc8978bb430532a788b90454c5
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea1217972468798b5af30fa6b2e904549f091e63f7421e306c1cb9f09af51e7
+oid sha256:2e0effb1ca3a85a1e023fa1064f8545a6a6b9cb6d4ef8777698b7fd278b0c5b2
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:498350e05afca0a044e5519efa697c68264ab9a442010421bb8f434d9fa19fb7
+oid sha256:a2705bae7590ac3e77fc1acca8c8f5a597bae1627599f5801c6cea4c9e470e54
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3448596b868950df977d44a3ca61151edee8253d9013b001a793f791bdd5271f
+oid sha256:fb63f6b905a337d3028844cf0b1a0f11cf90bbe2ae40b99c4134b4fd2e0a71b5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7352117cd5bb0d291b06da5c6eaeecf72863d98bb6f8d0278e0d0bf358b7b0c4
+oid sha256:0b42219166815d5324536ff3c1bbaf6c5d711c2e0def09e1228305c7e5a57bd9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf940684b9bc001cc793c7dcc52af61f304a84e29c41d0de2063d8e007d5016c
+oid sha256:d086b00605c04989d7494aedd26d4a0dd62a0050610c90dd7dac440ce76da1fc
 size 15024

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6619815826416016,
+  "best_metric": 0.6617953777313232,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
   "epoch": 0.23944926668662078,
   "eval_steps": 25,
@@ -10,376 +10,376 @@
   "log_history": [
     {
       "epoch": 0.004788985333732416,
-      "grad_norm": 9.139657974243164,
+      "grad_norm": 9.055534362792969,
       "learning_rate": 5e-05,
-      "loss": 0.9883,
+      "loss": 0.988,
       "step": 1
     },
     {
       "epoch": 0.004788985333732416,
-      "eval_loss": 1.3131486177444458,
-      "eval_runtime": 50.0467,
-      "eval_samples_per_second": 28.114,
-      "eval_steps_per_second": 3.517,
+      "eval_loss": 1.3129990100860596,
+      "eval_runtime": 89.8381,
+      "eval_samples_per_second": 15.662,
+      "eval_steps_per_second": 1.959,
       "step": 1
     },
     {
       "epoch": 0.009577970667464832,
-      "grad_norm": 10.1763334274292,
+      "grad_norm": 10.17972469329834,
       "learning_rate": 0.0001,
-      "loss": 1.0789,
+      "loss": 1.0788,
       "step": 2
     },
     {
       "epoch": 0.014366956001197246,
-      "grad_norm": 10.229259490966797,
+      "grad_norm": 10.148212432861328,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.1275,
+      "loss": 1.1269,
       "step": 3
     },
     {
       "epoch": 0.019155941334929663,
-      "grad_norm": 8.447587013244629,
+      "grad_norm": 8.283422470092773,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 1.0418,
+      "loss": 1.0397,
       "step": 4
     },
     {
       "epoch": 0.02394492666866208,
-      "grad_norm": 6.053240776062012,
+      "grad_norm": 6.014930725097656,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 0.9838,
+      "loss": 0.9835,
       "step": 5
     },
     {
       "epoch": 0.02873391200239449,
-      "grad_norm": 5.678994178771973,
+      "grad_norm": 5.637279033660889,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 0.9826,
+      "loss": 0.9822,
       "step": 6
     },
     {
       "epoch": 0.03352289733612691,
-      "grad_norm": 5.424116611480713,
+      "grad_norm": 5.371291160583496,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 0.907,
+      "loss": 0.9066,
       "step": 7
     },
     {
       "epoch": 0.038311882669859326,
-      "grad_norm": 5.176206588745117,
+      "grad_norm": 5.1611647605896,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 0.8721,
+      "loss": 0.8736,
       "step": 8
     },
     {
       "epoch": 0.04310086800359174,
-      "grad_norm": 5.132746696472168,
+      "grad_norm": 5.105460166931152,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.8634,
+      "loss": 0.8648,
       "step": 9
     },
     {
       "epoch": 0.04788985333732416,
-      "grad_norm": 4.970299243927002,
+      "grad_norm": 4.966892242431641,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 0.8958,
+      "loss": 0.8976,
       "step": 10
     },
     {
       "epoch": 0.05267883867105657,
-      "grad_norm": 5.442699909210205,
+      "grad_norm": 5.412621021270752,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 0.8947,
+      "loss": 0.8964,
       "step": 11
     },
     {
       "epoch": 0.05746782400478898,
-      "grad_norm": 10.588356018066406,
+      "grad_norm": 10.513104438781738,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 0.7673,
+      "loss": 0.7669,
       "step": 12
     },
     {
       "epoch": 0.0622568093385214,
-      "grad_norm": 5.640754699707031,
+      "grad_norm": 5.534309387207031,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 0.7415,
+      "loss": 0.7414,
       "step": 13
     },
     {
       "epoch": 0.06704579467225381,
-      "grad_norm": 3.7585272789001465,
+      "grad_norm": 3.6972882747650146,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 0.7878,
+      "loss": 0.7881,
       "step": 14
     },
     {
       "epoch": 0.07183478000598623,
-      "grad_norm": 3.351741075515747,
+      "grad_norm": 3.2626562118530273,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.7759,
+      "loss": 0.7764,
       "step": 15
     },
     {
       "epoch": 0.07662376533971865,
-      "grad_norm": 5.279153823852539,
+      "grad_norm": 3.4915661811828613,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.7632,
+      "loss": 0.7636,
       "step": 16
     },
     {
       "epoch": 0.08141275067345106,
-      "grad_norm": 2.6697967052459717,
+      "grad_norm": 2.549363374710083,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.7623,
+      "loss": 0.7617,
       "step": 17
     },
     {
       "epoch": 0.08620173600718348,
-      "grad_norm": 2.4722275733947754,
+      "grad_norm": 2.381659507751465,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.7504,
+      "loss": 0.7495,
       "step": 18
     },
     {
       "epoch": 0.09099072134091589,
-      "grad_norm": 2.5212650299072266,
+      "grad_norm": 2.6084702014923096,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.7132,
+      "loss": 0.7122,
       "step": 19
     },
     {
       "epoch": 0.09577970667464832,
-      "grad_norm": 2.689626932144165,
+      "grad_norm": 2.742548942565918,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.707,
+      "loss": 0.7071,
       "step": 20
     },
     {
       "epoch": 0.10056869200838073,
-      "grad_norm": 2.7140634059906006,
+      "grad_norm": 2.884613037109375,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.7209,
+      "loss": 0.7215,
       "step": 21
     },
     {
       "epoch": 0.10535767734211314,
-      "grad_norm": 3.371795654296875,
+      "grad_norm": 3.389320135116577,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.7428,
+      "loss": 0.7432,
       "step": 22
     },
     {
       "epoch": 0.11014666267584555,
-      "grad_norm": 4.396210670471191,
+      "grad_norm": 4.33539342880249,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.763,
+      "loss": 0.7635,
       "step": 23
     },
     {
       "epoch": 0.11493564800957796,
-      "grad_norm": 7.028194427490234,
+      "grad_norm": 7.149311542510986,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.6542,
+      "loss": 0.658,
       "step": 24
     },
     {
       "epoch": 0.11972463334331039,
-      "grad_norm": 9.474855422973633,
+      "grad_norm": 9.612565994262695,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.5116,
+      "loss": 0.5169,
       "step": 25
     },
     {
       "epoch": 0.11972463334331039,
-      "eval_loss": 0.6859295964241028,
-      "eval_runtime": 51.7306,
-      "eval_samples_per_second": 27.199,
-      "eval_steps_per_second": 3.402,
+      "eval_loss": 0.6865246295928955,
+      "eval_runtime": 89.8192,
+      "eval_samples_per_second": 15.665,
+      "eval_steps_per_second": 1.959,
       "step": 25
     },
     {
       "epoch": 0.1245136186770428,
-      "grad_norm": 2.8495266437530518,
+      "grad_norm": 2.2437281608581543,
       "learning_rate": 5e-05,
-      "loss": 0.7313,
+      "loss": 0.7308,
       "step": 26
     },
     {
       "epoch": 0.12930260401077523,
-      "grad_norm": 2.4230589866638184,
+      "grad_norm": 2.328535318374634,
       "learning_rate": 4.6729843538492847e-05,
-      "loss": 0.7152,
+      "loss": 0.7148,
       "step": 27
     },
     {
       "epoch": 0.13409158934450763,
-      "grad_norm": 2.371987819671631,
+      "grad_norm": 2.249345302581787,
       "learning_rate": 4.347369038899744e-05,
-      "loss": 0.7442,
+      "loss": 0.743,
       "step": 28
     },
     {
       "epoch": 0.13888057467824005,
-      "grad_norm": 2.205232858657837,
+      "grad_norm": 2.091951847076416,
       "learning_rate": 4.0245483899193595e-05,
-      "loss": 0.7313,
+      "loss": 0.7297,
       "step": 29
     },
     {
       "epoch": 0.14366956001197245,
-      "grad_norm": 2.417241096496582,
+      "grad_norm": 2.256178855895996,
       "learning_rate": 3.705904774487396e-05,
-      "loss": 0.7238,
+      "loss": 0.7213,
       "step": 30
     },
     {
       "epoch": 0.14845854534570488,
-      "grad_norm": 2.230722427368164,
+      "grad_norm": 2.5036637783050537,
       "learning_rate": 3.392802673484193e-05,
-      "loss": 0.7166,
+      "loss": 0.7151,
       "step": 31
     },
     {
       "epoch": 0.1532475306794373,
-      "grad_norm": 2.077070474624634,
+      "grad_norm": 2.000901222229004,
       "learning_rate": 3.086582838174551e-05,
-      "loss": 0.7191,
+      "loss": 0.7184,
       "step": 32
     },
     {
       "epoch": 0.1580365160131697,
-      "grad_norm": 2.1603822708129883,
+      "grad_norm": 2.140348196029663,
       "learning_rate": 2.7885565489049946e-05,
-      "loss": 0.6519,
+      "loss": 0.6517,
       "step": 33
     },
     {
       "epoch": 0.16282550134690213,
-      "grad_norm": 2.4969730377197266,
+      "grad_norm": 2.506681442260742,
       "learning_rate": 2.500000000000001e-05,
-      "loss": 0.6472,
+      "loss": 0.6467,
       "step": 34
     },
     {
       "epoch": 0.16761448668063453,
-      "grad_norm": 3.1127357482910156,
+      "grad_norm": 3.0968377590179443,
       "learning_rate": 2.2221488349019903e-05,
-      "loss": 0.7282,
+      "loss": 0.729,
       "step": 35
     },
     {
       "epoch": 0.17240347201436695,
-      "grad_norm": 4.340132236480713,
+      "grad_norm": 4.285067081451416,
       "learning_rate": 1.9561928549563968e-05,
-      "loss": 0.6882,
+      "loss": 0.6889,
       "step": 36
     },
     {
       "epoch": 0.17719245734809938,
-      "grad_norm": 6.205322265625,
+      "grad_norm": 6.125484466552734,
       "learning_rate": 1.703270924499656e-05,
-      "loss": 0.4678,
+      "loss": 0.4681,
       "step": 37
     },
     {
       "epoch": 0.18198144268183178,
-      "grad_norm": 4.504382133483887,
+      "grad_norm": 4.411527156829834,
       "learning_rate": 1.4644660940672627e-05,
-      "loss": 0.6262,
+      "loss": 0.6254,
       "step": 38
     },
     {
       "epoch": 0.1867704280155642,
-      "grad_norm": 1.453686237335205,
+      "grad_norm": 1.4111629724502563,
       "learning_rate": 1.2408009626051137e-05,
-      "loss": 0.6886,
+      "loss": 0.6884,
       "step": 39
     },
     {
       "epoch": 0.19155941334929663,
-      "grad_norm": 1.5423305034637451,
+      "grad_norm": 1.5426491498947144,
       "learning_rate": 1.0332332985438248e-05,
-      "loss": 0.7261,
+      "loss": 0.7264,
       "step": 40
     },
     {
       "epoch": 0.19634839868302903,
-      "grad_norm": 1.6292784214019775,
+      "grad_norm": 1.6077278852462769,
       "learning_rate": 8.426519384872733e-06,
-      "loss": 0.6999,
+      "loss": 0.6995,
       "step": 41
     },
     {
       "epoch": 0.20113738401676146,
-      "grad_norm": 1.777341365814209,
+      "grad_norm": 1.7078320980072021,
       "learning_rate": 6.698729810778065e-06,
-      "loss": 0.731,
+      "loss": 0.7309,
       "step": 42
     },
     {
       "epoch": 0.20592636935049385,
-      "grad_norm": 1.760827660560608,
+      "grad_norm": 1.7410907745361328,
       "learning_rate": 5.156362923365588e-06,
-      "loss": 0.7008,
+      "loss": 0.7004,
       "step": 43
     },
     {
       "epoch": 0.21071535468422628,
-      "grad_norm": 1.8341784477233887,
+      "grad_norm": 1.805100679397583,
       "learning_rate": 3.8060233744356633e-06,
-      "loss": 0.7237,
+      "loss": 0.7236,
       "step": 44
     },
     {
       "epoch": 0.2155043400179587,
-      "grad_norm": 2.0059590339660645,
+      "grad_norm": 1.9466443061828613,
       "learning_rate": 2.653493525244721e-06,
-      "loss": 0.6839,
+      "loss": 0.6835,
       "step": 45
     },
     {
       "epoch": 0.2202933253516911,
-      "grad_norm": 2.048092842102051,
+      "grad_norm": 2.037106990814209,
       "learning_rate": 1.70370868554659e-06,
-      "loss": 0.6488,
+      "loss": 0.6497,
       "step": 46
     },
     {
       "epoch": 0.22508231068542353,
-      "grad_norm": 2.2609188556671143,
+      "grad_norm": 2.251804828643799,
       "learning_rate": 9.607359798384785e-07,
-      "loss": 0.6132,
+      "loss": 0.614,
       "step": 47
     },
     {
       "epoch": 0.22987129601915593,
-      "grad_norm": 2.904057264328003,
+      "grad_norm": 2.8198914527893066,
       "learning_rate": 4.277569313094809e-07,
-      "loss": 0.683,
+      "loss": 0.6826,
       "step": 48
     },
     {
       "epoch": 0.23466028135288836,
-      "grad_norm": 4.419697284698486,
+      "grad_norm": 4.301578521728516,
       "learning_rate": 1.0705383806982606e-07,
-      "loss": 0.7001,
+      "loss": 0.7,
       "step": 49
     },
     {
       "epoch": 0.23944926668662078,
-      "grad_norm": 6.554656505584717,
+      "grad_norm": 6.325592041015625,
       "learning_rate": 0.0,
-      "loss": 0.4805,
+      "loss": 0.4808,
       "step": 50
     },
     {
       "epoch": 0.23944926668662078,
-      "eval_loss": 0.6619815826416016,
-      "eval_runtime": 49.7865,
-      "eval_samples_per_second": 28.261,
-      "eval_steps_per_second": 3.535,
+      "eval_loss": 0.6617953777313232,
+      "eval_runtime": 90.5077,
+      "eval_samples_per_second": 15.546,
+      "eval_steps_per_second": 1.945,
       "step": 50
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1b22d6c733c9ccb9696f6a38525cad499f4680848d8aa3eacd420d6adcd180c
+oid sha256:6a4f734ed6934bb9ee789a44bec97729b52b7fb6b1193460f5b177c980860df8
 size 6904