Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "up_proj",
     "down_proj",
-    "gate_proj",
-    "q_proj",
+    "k_proj",
     "o_proj",
-    "up_proj",
-    "k_proj"
+    "gate_proj",
+    "v_proj",
+    "q_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 sha256:6f222a1c4c489c9c91998165385fa6a8cca4505ef6b72b83a29f1ef9b4476dbd
+oid sha256:31a7d5fdd1388a98c30ce2b92bd7ce8c07eddd25429f3aaa19d1ad7a7ff0a1a7
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a7f682e8fe380804a7b69db82778ae81724f76d4bbc7ccc21b9a05753f5bed
+oid sha256:f146b42314babbf272c18a6a0a1e229d15716e312c551a8d093fd3ebbd7b1df9
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f32b24a025fd99a4774f254c729e6ea1d6653f5243edf7a461d966c3f9cfc90
+oid sha256:4bb9bd59dcd9b44e59614c1c8232046e7e9e1caebaf83fb1b0670f88f193cd6d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23001c42c640f89983758733dcfdb4e7daf6cce5a119ac7170fe88dbd18dd1b0
+oid sha256:c8ceb091103656fa4a13353c7f9c5fa1c6f42ee087495b52b0ff54267fb28bc0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1308bf92867c81ae09e5cb48fdc76fbfd6e32eecfad5332d4defae3a6af04703
+oid sha256:b4efdf6725885638b7d7ac22ea73d216339a42d524de3a299f6169334b40a2e4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676b7abf3456dcac426c8247f8ccdff0071875ec709c89ea4a819a457a82dd55
+oid sha256:9ad43da04f664a4b1afc5e2ec8bc883b432560b2810cd33fcf9c580425140814
 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": 0.3135169446468353,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.22148394241417496,
+  "best_metric": 0.4165385067462921,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.11074197120708748,
   "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": 0.004429678848283499,
-      "grad_norm": 90.43601989746094,
+      "grad_norm": 80.3771743774414,
       "learning_rate": 5e-05,
-      "loss": 186.7866,
+      "loss": 186.8504,
       "step": 1
     },
     {
       "epoch": 0.004429678848283499,
-      "eval_loss": 11.860960006713867,
-      "eval_runtime": 59.9491,
-      "eval_samples_per_second": 25.372,
-      "eval_steps_per_second": 3.186,
+      "eval_loss": 11.864986419677734,
+      "eval_runtime": 126.0276,
+      "eval_samples_per_second": 12.069,
+      "eval_steps_per_second": 1.516,
       "step": 1
     },
     {
       "epoch": 0.008859357696566999,
-      "grad_norm": 92.87113952636719,
+      "grad_norm": 83.50208282470703,
       "learning_rate": 0.0001,
-      "loss": 191.192,
+      "loss": 191.1957,
       "step": 2
     },
     {
       "epoch": 0.013289036544850499,
-      "grad_norm": 95.75019836425781,
+      "grad_norm": 89.58778381347656,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 186.3358,
+      "loss": 186.5678,
       "step": 3
     },
     {
       "epoch": 0.017718715393133997,
-      "grad_norm": 131.21568298339844,
+      "grad_norm": 129.3165740966797,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 169.4684,
+      "loss": 170.2373,
       "step": 4
     },
     {
       "epoch": 0.0221483942414175,
-      "grad_norm": 133.9580535888672,
+      "grad_norm": 139.35647583007812,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 140.7173,
+      "loss": 141.4767,
       "step": 5
     },
     {
       "epoch": 0.026578073089700997,
-      "grad_norm": 115.58403015136719,
+      "grad_norm": 118.65985107421875,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 116.9708,
+      "loss": 117.7925,
       "step": 6
     },
     {
       "epoch": 0.031007751937984496,
-      "grad_norm": 114.49787139892578,
+      "grad_norm": 117.44580078125,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 95.8174,
+      "loss": 96.8972,
       "step": 7
     },
     {
       "epoch": 0.035437430786267994,
-      "grad_norm": 112.3747329711914,
+      "grad_norm": 115.84791564941406,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 76.4804,
+      "loss": 77.6476,
       "step": 8
     },
     {
       "epoch": 0.03986710963455149,
-      "grad_norm": 134.6016845703125,
+      "grad_norm": 137.33387756347656,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 52.7218,
+      "loss": 54.0985,
       "step": 9
     },
     {
       "epoch": 0.044296788482835,
-      "grad_norm": 140.690673828125,
+      "grad_norm": 146.39991760253906,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 28.0401,
+      "loss": 29.7652,
       "step": 10
     },
     {
       "epoch": 0.048726467331118496,
-      "grad_norm": 73.04218292236328,
+      "grad_norm": 82.59661102294922,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 13.6756,
+      "loss": 14.8776,
       "step": 11
     },
     {
       "epoch": 0.053156146179401995,
-      "grad_norm": 81.19536590576172,
+      "grad_norm": 104.44115447998047,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 11.1729,
+      "loss": 12.1848,
       "step": 12
     },
     {
       "epoch": 0.05758582502768549,
-      "grad_norm": 56.66990661621094,
+      "grad_norm": 48.7734260559082,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 9.8869,
+      "loss": 9.9194,
       "step": 13
     },
     {
       "epoch": 0.06201550387596899,
-      "grad_norm": 28.945405960083008,
+      "grad_norm": 46.114593505859375,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 9.031,
+      "loss": 9.2692,
       "step": 14
     },
     {
       "epoch": 0.0664451827242525,
-      "grad_norm": 36.69380569458008,
+      "grad_norm": 31.456167221069336,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 8.7398,
+      "loss": 8.4696,
       "step": 15
     },
     {
       "epoch": 0.07087486157253599,
-      "grad_norm": 22.542613983154297,
+      "grad_norm": 69.29698944091797,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 8.2923,
+      "loss": 9.3606,
       "step": 16
     },
     {
       "epoch": 0.0753045404208195,
-      "grad_norm": 76.44745635986328,
+      "grad_norm": 41.587501525878906,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 9.5592,
+      "loss": 8.9985,
       "step": 17
     },
     {
       "epoch": 0.07973421926910298,
-      "grad_norm": 60.888092041015625,
+      "grad_norm": 32.481868743896484,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 7.8758,
+      "loss": 7.2757,
       "step": 18
     },
     {
       "epoch": 0.08416389811738649,
-      "grad_norm": 66.46916198730469,
+      "grad_norm": 41.32707214355469,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 6.9583,
+      "loss": 6.7443,
       "step": 19
     },
     {
       "epoch": 0.08859357696567,
-      "grad_norm": 67.2452163696289,
+      "grad_norm": 40.19483184814453,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 8.2272,
+      "loss": 7.1462,
       "step": 20
     },
     {
       "epoch": 0.09302325581395349,
-      "grad_norm": 53.93881607055664,
+      "grad_norm": 83.13573455810547,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 7.0548,
+      "loss": 7.713,
       "step": 21
     },
     {
       "epoch": 0.09745293466223699,
-      "grad_norm": 80.97118377685547,
+      "grad_norm": 55.984676361083984,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 7.2771,
+      "loss": 5.5221,
       "step": 22
     },
     {
       "epoch": 0.10188261351052048,
-      "grad_norm": 37.07639694213867,
+      "grad_norm": 29.221961975097656,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 6.2439,
+      "loss": 5.4771,
       "step": 23
     },
     {
       "epoch": 0.10631229235880399,
-      "grad_norm": 53.39252471923828,
+      "grad_norm": 37.901004791259766,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 6.0297,
+      "loss": 5.3382,
       "step": 24
     },
     {
       "epoch": 0.11074197120708748,
-      "grad_norm": 50.96709442138672,
+      "grad_norm": 29.54227066040039,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 5.7838,
+      "loss": 4.7856,
       "step": 25
     },
     {
       "epoch": 0.11074197120708748,
-      "eval_loss": 0.4496269226074219,
-      "eval_runtime": 59.8952,
-      "eval_samples_per_second": 25.394,
-      "eval_steps_per_second": 3.189,
+      "eval_loss": 0.4165385067462921,
+      "eval_runtime": 127.2616,
+      "eval_samples_per_second": 11.952,
+      "eval_steps_per_second": 1.501,
       "step": 25
-    },
-    {
-      "epoch": 0.11517165005537099,
-      "grad_norm": 43.56239318847656,
-      "learning_rate": 5e-05,
-      "loss": 8.002,
-      "step": 26
-    },
-    {
-      "epoch": 0.11960132890365449,
-      "grad_norm": 42.219730377197266,
-      "learning_rate": 4.6729843538492847e-05,
-      "loss": 7.7278,
-      "step": 27
-    },
-    {
-      "epoch": 0.12403100775193798,
-      "grad_norm": 51.25581741333008,
-      "learning_rate": 4.347369038899744e-05,
-      "loss": 7.8858,
-      "step": 28
-    },
-    {
-      "epoch": 0.12846068660022147,
-      "grad_norm": 28.833730697631836,
-      "learning_rate": 4.0245483899193595e-05,
-      "loss": 7.4616,
-      "step": 29
-    },
-    {
-      "epoch": 0.132890365448505,
-      "grad_norm": 36.36983108520508,
-      "learning_rate": 3.705904774487396e-05,
-      "loss": 5.8613,
-      "step": 30
-    },
-    {
-      "epoch": 0.13732004429678848,
-      "grad_norm": 24.915283203125,
-      "learning_rate": 3.392802673484193e-05,
-      "loss": 6.0989,
-      "step": 31
-    },
-    {
-      "epoch": 0.14174972314507198,
-      "grad_norm": 26.047985076904297,
-      "learning_rate": 3.086582838174551e-05,
-      "loss": 5.5893,
-      "step": 32
-    },
-    {
-      "epoch": 0.1461794019933555,
-      "grad_norm": 17.464637756347656,
-      "learning_rate": 2.7885565489049946e-05,
-      "loss": 5.6094,
-      "step": 33
-    },
-    {
-      "epoch": 0.150609080841639,
-      "grad_norm": 19.809972763061523,
-      "learning_rate": 2.500000000000001e-05,
-      "loss": 5.3021,
-      "step": 34
-    },
-    {
-      "epoch": 0.15503875968992248,
-      "grad_norm": 29.769086837768555,
-      "learning_rate": 2.2221488349019903e-05,
-      "loss": 5.5138,
-      "step": 35
-    },
-    {
-      "epoch": 0.15946843853820597,
-      "grad_norm": 25.799795150756836,
-      "learning_rate": 1.9561928549563968e-05,
-      "loss": 4.979,
-      "step": 36
-    },
-    {
-      "epoch": 0.1638981173864895,
-      "grad_norm": 25.358388900756836,
-      "learning_rate": 1.703270924499656e-05,
-      "loss": 3.709,
-      "step": 37
-    },
-    {
-      "epoch": 0.16832779623477298,
-      "grad_norm": 26.125646591186523,
-      "learning_rate": 1.4644660940672627e-05,
-      "loss": 4.5807,
-      "step": 38
-    },
-    {
-      "epoch": 0.17275747508305647,
-      "grad_norm": 20.812122344970703,
-      "learning_rate": 1.2408009626051137e-05,
-      "loss": 6.1171,
-      "step": 39
-    },
-    {
-      "epoch": 0.17718715393134,
-      "grad_norm": 20.470781326293945,
-      "learning_rate": 1.0332332985438248e-05,
-      "loss": 6.5875,
-      "step": 40
-    },
-    {
-      "epoch": 0.18161683277962348,
-      "grad_norm": 17.11683464050293,
-      "learning_rate": 8.426519384872733e-06,
-      "loss": 6.203,
-      "step": 41
-    },
-    {
-      "epoch": 0.18604651162790697,
-      "grad_norm": 15.608457565307617,
-      "learning_rate": 6.698729810778065e-06,
-      "loss": 4.9995,
-      "step": 42
-    },
-    {
-      "epoch": 0.19047619047619047,
-      "grad_norm": 14.48198127746582,
-      "learning_rate": 5.156362923365588e-06,
-      "loss": 5.2074,
-      "step": 43
-    },
-    {
-      "epoch": 0.19490586932447398,
-      "grad_norm": 17.412363052368164,
-      "learning_rate": 3.8060233744356633e-06,
-      "loss": 5.2764,
-      "step": 44
-    },
-    {
-      "epoch": 0.19933554817275748,
-      "grad_norm": 26.537670135498047,
-      "learning_rate": 2.653493525244721e-06,
-      "loss": 5.5755,
-      "step": 45
-    },
-    {
-      "epoch": 0.20376522702104097,
-      "grad_norm": 25.966537475585938,
-      "learning_rate": 1.70370868554659e-06,
-      "loss": 5.1873,
-      "step": 46
-    },
-    {
-      "epoch": 0.2081949058693245,
-      "grad_norm": 19.112852096557617,
-      "learning_rate": 9.607359798384785e-07,
-      "loss": 5.2322,
-      "step": 47
-    },
-    {
-      "epoch": 0.21262458471760798,
-      "grad_norm": 19.956279754638672,
-      "learning_rate": 4.277569313094809e-07,
-      "loss": 5.3597,
-      "step": 48
-    },
-    {
-      "epoch": 0.21705426356589147,
-      "grad_norm": 26.704853057861328,
-      "learning_rate": 1.0705383806982606e-07,
-      "loss": 4.1194,
-      "step": 49
-    },
-    {
-      "epoch": 0.22148394241417496,
-      "grad_norm": 22.032495498657227,
-      "learning_rate": 0.0,
-      "loss": 3.1469,
-      "step": 50
-    },
-    {
-      "epoch": 0.22148394241417496,
-      "eval_loss": 0.3135169446468353,
-      "eval_runtime": 59.89,
-      "eval_samples_per_second": 25.397,
-      "eval_steps_per_second": 3.189,
-      "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": 1.0205684108886016e+18,
+  "total_flos": 5.102842054443008e+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 sha256:119d39ddbc26862df059f1c46e9579f3f3c2231d69e1cd0cb71bc81e1445a849
+oid sha256:a07cb10832bd38400bef46779443665d988b8ed02bd1ef6fd2f90efabecd39f1
 size 6776