Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "o_proj",
+    "down_proj",
     "k_proj",
+    "q_proj",
     "up_proj",
     "v_proj",
-    "q_proj",
-    "down_proj",
-    "o_proj"
+    "gate_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:c85530c8829c972c803678f4e61f994ba11f32568c95b4ce7d189759a42c21ca
+oid sha256:de2f393ba7d3307f8201765e52ce0a815d5c2a1308f1d79b80c8b0a10eaf7505
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be4c182d0a59789e68ffb1c10dc74475d6f5676656825b0b691f5227f0492fb3
+oid sha256:355747ebcb892880883f348859a1427ce13bd528006f22bf5e453e46e5c1bf38
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb8d5c147ad9f15f58d642bd9a80dcfa788cef5f4c846030459c947252abe11
-size 15024
+oid sha256:87ed465b8131ade14ccc40a75420ec5291bdb48b0617b0af2e06cae9f1980e34
+size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691c181ae1aaa6fa73f587c7e924f10984925bc0671fca98e57f83b274ababe8
+oid sha256:937b3c763de285bf8e7976c73ee06ad859d8bffcb0e083004bb3c438d6bf5d1c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec17bc49e5b067fb69153fc378af21855884587be985ef4fdf200934460cc8a2
+oid sha256:f23b5c8be9c199811b18b21da2310d649f6bb783653318cb5d79b5bdb05a3478
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54eef41e231db63f3f2d49b345aa1a99ba729a652a120d8a8825f26878c98d0f
+oid sha256:8a2a6911123be9d1d2e369e6d11060a86b30a5641e6b182922c97d232b2ff96e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
+oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
 size 1064

last-checkpoint/trainer_state.json

@@ -1,386 +1,203 @@
 {
-  "best_metric": 2.1860828399658203,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.017588989292702768,
+  "best_metric": 2.192530632019043,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.008794494646351384,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00035177978585405537,
-      "grad_norm": 5.452480792999268,
+      "grad_norm": 5.538167476654053,
       "learning_rate": 5e-05,
-      "loss": 32.5319,
+      "loss": 32.5311,
       "step": 1
     },
     {
       "epoch": 0.00035177978585405537,
-      "eval_loss": 2.299668550491333,
-      "eval_runtime": 824.925,
-      "eval_samples_per_second": 23.215,
-      "eval_steps_per_second": 2.902,
+      "eval_loss": 2.2996881008148193,
+      "eval_runtime": 1602.8053,
+      "eval_samples_per_second": 11.948,
+      "eval_steps_per_second": 1.494,
       "step": 1
     },
     {
       "epoch": 0.0007035595717081107,
-      "grad_norm": 7.733003616333008,
+      "grad_norm": 7.6789164543151855,
       "learning_rate": 0.0001,
       "loss": 33.1713,
       "step": 2
     },
     {
       "epoch": 0.001055339357562166,
-      "grad_norm": 7.30857515335083,
+      "grad_norm": 7.3845014572143555,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 32.8704,
+      "loss": 32.8712,
       "step": 3
     },
     {
       "epoch": 0.0014071191434162215,
-      "grad_norm": 6.937483310699463,
+      "grad_norm": 6.956945419311523,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 33.1679,
+      "loss": 33.1673,
       "step": 4
     },
     {
       "epoch": 0.0017588989292702769,
-      "grad_norm": 7.842650890350342,
+      "grad_norm": 8.048707008361816,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 33.91,
+      "loss": 33.9079,
       "step": 5
     },
     {
       "epoch": 0.002110678715124332,
-      "grad_norm": 9.340250015258789,
+      "grad_norm": 9.416152000427246,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 33.5161,
+      "loss": 33.522,
       "step": 6
     },
     {
       "epoch": 0.0024624585009783875,
-      "grad_norm": 9.52157211303711,
+      "grad_norm": 9.693207740783691,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 33.634,
+      "loss": 33.6303,
       "step": 7
     },
     {
       "epoch": 0.002814238286832443,
-      "grad_norm": 9.34510612487793,
+      "grad_norm": 9.254134178161621,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 34.761,
+      "loss": 34.7466,
       "step": 8
     },
     {
       "epoch": 0.0031660180726864984,
-      "grad_norm": 13.48401165008545,
+      "grad_norm": 14.359371185302734,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 36.0081,
+      "loss": 36.0151,
       "step": 9
     },
     {
       "epoch": 0.0035177978585405538,
-      "grad_norm": 15.09841537475586,
+      "grad_norm": 15.26530933380127,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 36.3556,
+      "loss": 36.3619,
       "step": 10
     },
     {
       "epoch": 0.0038695776443946088,
-      "grad_norm": 17.29768180847168,
+      "grad_norm": 17.525087356567383,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 38.7349,
+      "loss": 38.7371,
       "step": 11
     },
     {
       "epoch": 0.004221357430248664,
-      "grad_norm": 22.131227493286133,
+      "grad_norm": 22.53554916381836,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 41.6837,
+      "loss": 41.6351,
       "step": 12
     },
     {
       "epoch": 0.00457313721610272,
-      "grad_norm": 23.215797424316406,
+      "grad_norm": 22.92333221435547,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 39.7892,
+      "loss": 39.7522,
       "step": 13
     },
     {
       "epoch": 0.004924917001956775,
-      "grad_norm": 9.220294952392578,
+      "grad_norm": 9.440299034118652,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 33.2681,
+      "loss": 33.28,
       "step": 14
     },
     {
       "epoch": 0.0052766967878108305,
-      "grad_norm": 9.76252555847168,
+      "grad_norm": 10.076234817504883,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 33.4629,
+      "loss": 33.4697,
       "step": 15
     },
     {
       "epoch": 0.005628476573664886,
-      "grad_norm": 8.49485969543457,
+      "grad_norm": 8.652132034301758,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 33.9832,
+      "loss": 33.9816,
       "step": 16
     },
     {
       "epoch": 0.005980256359518941,
-      "grad_norm": 8.919995307922363,
+      "grad_norm": 8.856562614440918,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 34.0772,
+      "loss": 34.08,
       "step": 17
     },
     {
       "epoch": 0.006332036145372997,
-      "grad_norm": 10.096283912658691,
+      "grad_norm": 9.761141777038574,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 32.312,
+      "loss": 32.3105,
       "step": 18
     },
     {
       "epoch": 0.006683815931227052,
-      "grad_norm": 9.981393814086914,
+      "grad_norm": 9.883894920349121,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 33.6215,
+      "loss": 33.6084,
       "step": 19
     },
     {
       "epoch": 0.0070355957170811076,
-      "grad_norm": 9.682584762573242,
+      "grad_norm": 9.651225090026855,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 34.3393,
+      "loss": 34.3374,
       "step": 20
     },
     {
       "epoch": 0.007387375502935163,
-      "grad_norm": 10.434945106506348,
+      "grad_norm": 10.468379974365234,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 34.8918,
+      "loss": 34.8942,
       "step": 21
     },
     {
       "epoch": 0.0077391552887892175,
-      "grad_norm": 11.270380973815918,
+      "grad_norm": 11.01174259185791,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 35.4063,
+      "loss": 35.4242,
       "step": 22
     },
     {
       "epoch": 0.008090935074643273,
-      "grad_norm": 14.67983341217041,
+      "grad_norm": 14.812124252319336,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 36.4115,
+      "loss": 36.4068,
       "step": 23
     },
     {
       "epoch": 0.008442714860497328,
-      "grad_norm": 14.8894681930542,
+      "grad_norm": 14.898117065429688,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 38.8561,
+      "loss": 38.8318,
       "step": 24
     },
     {
       "epoch": 0.008794494646351384,
-      "grad_norm": 24.04422378540039,
+      "grad_norm": 24.162452697753906,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 45.1928,
+      "loss": 45.2215,
       "step": 25
     },
     {
       "epoch": 0.008794494646351384,
-      "eval_loss": 2.192323923110962,
-      "eval_runtime": 826.0176,
-      "eval_samples_per_second": 23.185,
-      "eval_steps_per_second": 2.898,
+      "eval_loss": 2.192530632019043,
+      "eval_runtime": 1599.3943,
+      "eval_samples_per_second": 11.974,
+      "eval_steps_per_second": 1.497,
       "step": 25
-    },
-    {
-      "epoch": 0.00914627443220544,
-      "grad_norm": 3.8151047229766846,
-      "learning_rate": 5e-05,
-      "loss": 32.5243,
-      "step": 26
-    },
-    {
-      "epoch": 0.009498054218059495,
-      "grad_norm": 3.8212320804595947,
-      "learning_rate": 4.6729843538492847e-05,
-      "loss": 31.5323,
-      "step": 27
-    },
-    {
-      "epoch": 0.00984983400391355,
-      "grad_norm": 4.514546871185303,
-      "learning_rate": 4.347369038899744e-05,
-      "loss": 32.7899,
-      "step": 28
-    },
-    {
-      "epoch": 0.010201613789767605,
-      "grad_norm": 5.079270839691162,
-      "learning_rate": 4.0245483899193595e-05,
-      "loss": 33.4231,
-      "step": 29
-    },
-    {
-      "epoch": 0.010553393575621661,
-      "grad_norm": 5.683069705963135,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 31.9174,
-      "step": 30
-    },
-    {
-      "epoch": 0.010905173361475716,
-      "grad_norm": 7.779140949249268,
-      "learning_rate": 3.392802673484193e-05,
-      "loss": 32.5951,
-      "step": 31
-    },
-    {
-      "epoch": 0.011256953147329772,
-      "grad_norm": 7.834434986114502,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 33.5486,
-      "step": 32
-    },
-    {
-      "epoch": 0.011608732933183827,
-      "grad_norm": 8.553311347961426,
-      "learning_rate": 2.7885565489049946e-05,
-      "loss": 35.0256,
-      "step": 33
-    },
-    {
-      "epoch": 0.011960512719037883,
-      "grad_norm": 10.053312301635742,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 35.1863,
-      "step": 34
-    },
-    {
-      "epoch": 0.012312292504891938,
-      "grad_norm": 11.821266174316406,
-      "learning_rate": 2.2221488349019903e-05,
-      "loss": 36.9949,
-      "step": 35
-    },
-    {
-      "epoch": 0.012664072290745993,
-      "grad_norm": 14.664130210876465,
-      "learning_rate": 1.9561928549563968e-05,
-      "loss": 38.2195,
-      "step": 36
-    },
-    {
-      "epoch": 0.013015852076600049,
-      "grad_norm": 17.453157424926758,
-      "learning_rate": 1.703270924499656e-05,
-      "loss": 39.6056,
-      "step": 37
-    },
-    {
-      "epoch": 0.013367631862454104,
-      "grad_norm": 20.678699493408203,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 39.366,
-      "step": 38
-    },
-    {
-      "epoch": 0.01371941164830816,
-      "grad_norm": 3.5132977962493896,
-      "learning_rate": 1.2408009626051137e-05,
-      "loss": 33.041,
-      "step": 39
-    },
-    {
-      "epoch": 0.014071191434162215,
-      "grad_norm": 7.413121700286865,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 33.2397,
-      "step": 40
-    },
-    {
-      "epoch": 0.01442297122001627,
-      "grad_norm": 4.901597499847412,
-      "learning_rate": 8.426519384872733e-06,
-      "loss": 33.1532,
-      "step": 41
-    },
-    {
-      "epoch": 0.014774751005870326,
-      "grad_norm": 5.69987678527832,
-      "learning_rate": 6.698729810778065e-06,
-      "loss": 31.7657,
-      "step": 42
-    },
-    {
-      "epoch": 0.015126530791724381,
-      "grad_norm": 6.1713056564331055,
-      "learning_rate": 5.156362923365588e-06,
-      "loss": 32.1028,
-      "step": 43
-    },
-    {
-      "epoch": 0.015478310577578435,
-      "grad_norm": 6.70172119140625,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 34.2542,
-      "step": 44
-    },
-    {
-      "epoch": 0.01583009036343249,
-      "grad_norm": 7.707215309143066,
-      "learning_rate": 2.653493525244721e-06,
-      "loss": 33.1567,
-      "step": 45
-    },
-    {
-      "epoch": 0.016181870149286546,
-      "grad_norm": 8.802955627441406,
-      "learning_rate": 1.70370868554659e-06,
-      "loss": 34.1178,
-      "step": 46
-    },
-    {
-      "epoch": 0.0165336499351406,
-      "grad_norm": 10.024290084838867,
-      "learning_rate": 9.607359798384785e-07,
-      "loss": 35.9152,
-      "step": 47
-    },
-    {
-      "epoch": 0.016885429720994657,
-      "grad_norm": 11.615968704223633,
-      "learning_rate": 4.277569313094809e-07,
-      "loss": 37.0089,
-      "step": 48
-    },
-    {
-      "epoch": 0.017237209506848712,
-      "grad_norm": 14.557236671447754,
-      "learning_rate": 1.0705383806982606e-07,
-      "loss": 38.5182,
-      "step": 49
-    },
-    {
-      "epoch": 0.017588989292702768,
-      "grad_norm": 21.180112838745117,
-      "learning_rate": 0.0,
-      "loss": 45.6105,
-      "step": 50
-    },
-    {
-      "epoch": 0.017588989292702768,
-      "eval_loss": 2.1860828399658203,
-      "eval_runtime": 840.0113,
-      "eval_samples_per_second": 22.799,
-      "eval_steps_per_second": 2.85,
-      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -404,12 +221,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.658021338284032e+17,
+  "total_flos": 2.829010669142016e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f2b131c480d74238a837157ac676c7e56c9d6bee5aa1f992285c582f0217e2
+oid sha256:69bac34a33d8ba4e16c3a405dec0325e35527f02667dc56a89ad05189d58bea7
 size 6776