Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "v_proj",
-    "gate_proj",
     "o_proj",
+    "q_proj",
+    "gate_proj",
     "k_proj",
-    "up_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 sha256:368f92d9b73b84e30637dc9bc44224edf7c9879e589da952bc6b1997e93ecd9f
+oid sha256:cdfbfef24e2590958fa4d5023c3f410accd6403b8e0ea8042a7f98b8cddc6255
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b45c8a374bb4679fe8b66d169a7a43249fc4eebb6362b2c19b2a60e3b1b06921
+oid sha256:b52d8bfc7c2ed90e7f41e314fd1ab4bcba3040761ef93ef37d9b97e007d268b1
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3151b7e4d6e2f60996834310466937b7b15b8195c4bc92428d10b2a13c860d
+oid sha256:a0716f2bd846ab25a33e950d9cca30e303502e3d300ca4084147f0d2f21b817c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3edaf4972f1a1a4e43a6c4d114bf1604d7c2fe401276dd8d5dd50100a3fc5d
+oid sha256:9ae711fd14526246396c12f5c04b04231eee3258a04e850fd443293c43d3bef9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b44b2466268671db87f866d49713532cafedf8b9814423ec9913c6bef7d0c72
+oid sha256:7c22dd5dbf90b1e59af30d495f842504963e0e6c57c0f46f6f8bffd0c1cbb090
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed4a8257beb81ba1e47515024b2bc4b403def30ec1d9b29afb18656c8d816688
+oid sha256:434f4fd1d69bfa012480e7e71d691d24eed81234ecdaabb5949b8bcebbb8f3af
 size 15024

last-checkpoint/scheduler.pt

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

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
-  "best_metric": 0.41518697142601013,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02373887240356083,
+  "best_metric": 0.3918520212173462,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04747774480712166,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0009495548961424333,
-      "grad_norm": 7.661884307861328,
+      "grad_norm": 7.439890384674072,
       "learning_rate": 5e-05,
       "loss": 2.5959,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.0009495548961424333,
       "eval_loss": 4.306151866912842,
-      "eval_runtime": 93.0407,
-      "eval_samples_per_second": 76.257,
-      "eval_steps_per_second": 9.533,
+      "eval_runtime": 91.6663,
+      "eval_samples_per_second": 77.4,
+      "eval_steps_per_second": 9.676,
       "step": 1
     },
     {
       "epoch": 0.0018991097922848666,
-      "grad_norm": 11.511931419372559,
+      "grad_norm": 11.268596649169922,
       "learning_rate": 0.0001,
       "loss": 3.3436,
       "step": 2
     },
     {
       "epoch": 0.0028486646884273,
-      "grad_norm": 7.516351699829102,
+      "grad_norm": 7.319098949432373,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 2.3697,
+      "loss": 2.3813,
       "step": 3
     },
     {
       "epoch": 0.003798219584569733,
-      "grad_norm": 5.4108710289001465,
+      "grad_norm": 5.256196975708008,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 1.585,
+      "loss": 1.621,
       "step": 4
     },
     {
       "epoch": 0.004747774480712166,
-      "grad_norm": 3.9081742763519287,
+      "grad_norm": 3.84167218208313,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 1.0724,
+      "loss": 1.0992,
       "step": 5
     },
     {
       "epoch": 0.0056973293768546,
-      "grad_norm": 4.953296184539795,
+      "grad_norm": 4.822945594787598,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 0.9248,
+      "loss": 0.9423,
       "step": 6
     },
     {
       "epoch": 0.006646884272997033,
-      "grad_norm": 3.4243087768554688,
+      "grad_norm": 3.4690985679626465,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 0.7177,
+      "loss": 0.7374,
       "step": 7
     },
     {
       "epoch": 0.007596439169139466,
-      "grad_norm": 1.8715609312057495,
+      "grad_norm": 1.8934733867645264,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 0.5938,
+      "loss": 0.6049,
       "step": 8
     },
     {
       "epoch": 0.0085459940652819,
-      "grad_norm": 2.0616214275360107,
+      "grad_norm": 1.8843889236450195,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.6257,
+      "loss": 0.626,
       "step": 9
     },
     {
       "epoch": 0.009495548961424332,
-      "grad_norm": 1.8348668813705444,
+      "grad_norm": 1.7394013404846191,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 0.5286,
+      "loss": 0.5308,
       "step": 10
     },
     {
       "epoch": 0.010445103857566765,
-      "grad_norm": 1.3536250591278076,
+      "grad_norm": 1.3103629350662231,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 0.5025,
+      "loss": 0.5043,
       "step": 11
     },
     {
       "epoch": 0.0113946587537092,
-      "grad_norm": 1.6615864038467407,
+      "grad_norm": 1.6745845079421997,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 0.5754,
+      "loss": 0.578,
       "step": 12
     },
     {
       "epoch": 0.012344213649851632,
-      "grad_norm": 1.378383994102478,
+      "grad_norm": 1.3612757921218872,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 0.5091,
+      "loss": 0.5118,
       "step": 13
     },
     {
       "epoch": 0.013293768545994065,
-      "grad_norm": 1.4611592292785645,
+      "grad_norm": 1.4194831848144531,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 0.5618,
+      "loss": 0.5614,
       "step": 14
     },
     {
       "epoch": 0.014243323442136498,
-      "grad_norm": 1.462814211845398,
+      "grad_norm": 1.4411664009094238,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.6127,
+      "loss": 0.6148,
       "step": 15
     },
     {
       "epoch": 0.015192878338278933,
-      "grad_norm": 1.3176627159118652,
+      "grad_norm": 1.2932251691818237,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.4622,
+      "loss": 0.4638,
       "step": 16
     },
     {
       "epoch": 0.016142433234421365,
-      "grad_norm": 1.149091362953186,
+      "grad_norm": 1.1225634813308716,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.5356,
+      "loss": 0.5341,
       "step": 17
     },
     {
       "epoch": 0.0170919881305638,
-      "grad_norm": 1.1545970439910889,
+      "grad_norm": 1.115459680557251,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.5104,
+      "loss": 0.5072,
       "step": 18
     },
     {
       "epoch": 0.01804154302670623,
-      "grad_norm": 1.013222098350525,
+      "grad_norm": 0.9920904636383057,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.3924,
+      "loss": 0.3916,
       "step": 19
     },
     {
       "epoch": 0.018991097922848664,
-      "grad_norm": 1.1423275470733643,
+      "grad_norm": 1.1311784982681274,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.4742,
+      "loss": 0.4748,
       "step": 20
     },
     {
       "epoch": 0.019940652818991097,
-      "grad_norm": 1.0759767293930054,
+      "grad_norm": 1.0529801845550537,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.4157,
+      "loss": 0.4137,
       "step": 21
     },
     {
       "epoch": 0.02089020771513353,
-      "grad_norm": 1.0587694644927979,
+      "grad_norm": 1.0232025384902954,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.392,
+      "loss": 0.393,
       "step": 22
     },
     {
       "epoch": 0.021839762611275966,
-      "grad_norm": 1.3421058654785156,
+      "grad_norm": 1.290144681930542,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.4272,
+      "loss": 0.4288,
       "step": 23
     },
     {
       "epoch": 0.0227893175074184,
-      "grad_norm": 1.6769137382507324,
+      "grad_norm": 1.674687147140503,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.4728,
+      "loss": 0.4732,
       "step": 24
     },
     {
       "epoch": 0.02373887240356083,
-      "grad_norm": 1.447285771369934,
+      "grad_norm": 1.3398001194000244,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.4399,
+      "loss": 0.4374,
       "step": 25
     },
     {
       "epoch": 0.02373887240356083,
-      "eval_loss": 0.41518697142601013,
-      "eval_runtime": 93.1452,
-      "eval_samples_per_second": 76.171,
-      "eval_steps_per_second": 9.523,
+      "eval_loss": 0.4141256511211395,
+      "eval_runtime": 91.5273,
+      "eval_samples_per_second": 77.518,
+      "eval_steps_per_second": 9.691,
       "step": 25
+    },
+    {
+      "epoch": 0.024688427299703265,
+      "grad_norm": 1.6487070322036743,
+      "learning_rate": 5e-05,
+      "loss": 0.4644,
+      "step": 26
+    },
+    {
+      "epoch": 0.025637982195845697,
+      "grad_norm": 1.2411335706710815,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4067,
+      "step": 27
+    },
+    {
+      "epoch": 0.02658753709198813,
+      "grad_norm": 1.279060959815979,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4408,
+      "step": 28
+    },
+    {
+      "epoch": 0.027537091988130563,
+      "grad_norm": 1.0631486177444458,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4941,
+      "step": 29
+    },
+    {
+      "epoch": 0.028486646884272996,
+      "grad_norm": 1.0903637409210205,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4359,
+      "step": 30
+    },
+    {
+      "epoch": 0.02943620178041543,
+      "grad_norm": 1.2160718441009521,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4114,
+      "step": 31
+    },
+    {
+      "epoch": 0.030385756676557865,
+      "grad_norm": 1.050797462463379,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3263,
+      "step": 32
+    },
+    {
+      "epoch": 0.031335311572700295,
+      "grad_norm": 1.2560865879058838,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4473,
+      "step": 33
+    },
+    {
+      "epoch": 0.03228486646884273,
+      "grad_norm": 1.394460678100586,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.495,
+      "step": 34
+    },
+    {
+      "epoch": 0.03323442136498516,
+      "grad_norm": 1.2537908554077148,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3911,
+      "step": 35
+    },
+    {
+      "epoch": 0.0341839762611276,
+      "grad_norm": 1.2269549369812012,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4048,
+      "step": 36
+    },
+    {
+      "epoch": 0.03513353115727003,
+      "grad_norm": 1.258339524269104,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4062,
+      "step": 37
+    },
+    {
+      "epoch": 0.03608308605341246,
+      "grad_norm": 0.9876959919929504,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4156,
+      "step": 38
+    },
+    {
+      "epoch": 0.0370326409495549,
+      "grad_norm": 1.1021502017974854,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4423,
+      "step": 39
+    },
+    {
+      "epoch": 0.03798219584569733,
+      "grad_norm": 1.1865808963775635,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3848,
+      "step": 40
+    },
+    {
+      "epoch": 0.038931750741839764,
+      "grad_norm": 1.1538034677505493,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4178,
+      "step": 41
+    },
+    {
+      "epoch": 0.039881305637982194,
+      "grad_norm": 1.0449069738388062,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4413,
+      "step": 42
+    },
+    {
+      "epoch": 0.04083086053412463,
+      "grad_norm": 0.9766872525215149,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4192,
+      "step": 43
+    },
+    {
+      "epoch": 0.04178041543026706,
+      "grad_norm": 0.999814510345459,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4327,
+      "step": 44
+    },
+    {
+      "epoch": 0.042729970326409496,
+      "grad_norm": 1.0226655006408691,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3489,
+      "step": 45
+    },
+    {
+      "epoch": 0.04367952522255193,
+      "grad_norm": 1.0590505599975586,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4645,
+      "step": 46
+    },
+    {
+      "epoch": 0.04462908011869436,
+      "grad_norm": 0.9605615735054016,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4354,
+      "step": 47
+    },
+    {
+      "epoch": 0.0455786350148368,
+      "grad_norm": 1.1913832426071167,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3582,
+      "step": 48
+    },
+    {
+      "epoch": 0.04652818991097923,
+      "grad_norm": 1.1075249910354614,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.408,
+      "step": 49
+    },
+    {
+      "epoch": 0.04747774480712166,
+      "grad_norm": 1.1609270572662354,
+      "learning_rate": 0.0,
+      "loss": 0.4589,
+      "step": 50
+    },
+    {
+      "epoch": 0.04747774480712166,
+      "eval_loss": 0.3918520212173462,
+      "eval_runtime": 91.5631,
+      "eval_samples_per_second": 77.488,
+      "eval_steps_per_second": 9.687,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+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 sha256:9006c6c95c06a9fb103e6099c016804212a74da872759f8fd32e4e4a3ad1db63
+oid sha256:ec5b32eedda2bc615eaf0109911b868a90c6924faa5339ca304c04d27b03fce2
 size 6776