Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "down_proj",
     "gate_proj",
+    "q_proj",
+    "o_proj",
     "k_proj",
-    "down_proj",
     "v_proj",
-    "o_proj",
-    "q_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:bbbbf9ed39e52693c8037078b8794a0b56fb6d961974d6d6179e66b7879a5556
+oid sha256:5a3f12ee4e3436e79d183633ce2a2d047eedcd2b88e3a573844a350abf5640b0
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f80abe812ffacf2c4ae30c13d2279953e6d0f53ab607374eec86b8ccb8ef266
+oid sha256:ec5393af90272ac50088819599abc4db956c8fc1928788b2a77e6607e247710b
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef2a0a59e228201093d6fa0c4af7bb984a1ffba0969e11c60edf7c02ca7af58
+oid sha256:84f67b6ec72c1dd7ee0bd17866616af8ea6a63cb29d42e6157735badcfe76bc1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26390b9cd6abbe5c027fbf8965ecc75b6ccb0827f2d587a93c28673fe9a7a575
+oid sha256:a78fbc8fa226d0bf683b0696147bb1719e487c633ee76a660707ba592c8c69aa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37bc4be58a49e2a1cd5c6f3607c00b04002c9a7528adc15b713c261fe10aa35
+oid sha256:71240087e9a3fc6c48ace737384f68b8df525783b763ea16bc555c680cd8a671
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fc6c7878d8436ed3fd96f96e58f1c8a56d0baa7fdd0a0b58a54ee2e511d9f27
+oid sha256:1d385de266bce640545d7fc9f2a7da596c2d4a2a68b594c172a6c6ffd90c0f3a
 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": 0.43850070238113403,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3460207612456747,
+  "best_metric": 0.3484306335449219,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6920415224913494,
   "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": 0.01384083044982699,
-      "grad_norm": 5.880698204040527,
+      "grad_norm": 5.621618747711182,
       "learning_rate": 5e-05,
       "loss": 7.6368,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.01384083044982699,
       "eval_loss": 7.8842244148254395,
-      "eval_runtime": 14.7958,
-      "eval_samples_per_second": 32.915,
-      "eval_steps_per_second": 4.123,
+      "eval_runtime": 14.9672,
+      "eval_samples_per_second": 32.538,
+      "eval_steps_per_second": 4.076,
       "step": 1
     },
     {
       "epoch": 0.02768166089965398,
-      "grad_norm": 8.048609733581543,
+      "grad_norm": 7.752517223358154,
       "learning_rate": 0.0001,
       "loss": 7.5947,
       "step": 2
     },
     {
       "epoch": 0.04152249134948097,
-      "grad_norm": 5.903276443481445,
+      "grad_norm": 5.626784324645996,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 7.4678,
+      "loss": 7.4669,
       "step": 3
     },
     {
       "epoch": 0.05536332179930796,
-      "grad_norm": 6.215991020202637,
+      "grad_norm": 6.084512710571289,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 6.8011,
+      "loss": 6.8142,
       "step": 4
     },
     {
       "epoch": 0.06920415224913495,
-      "grad_norm": 6.165921211242676,
+      "grad_norm": 6.081336498260498,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 5.753,
+      "loss": 5.7758,
       "step": 5
     },
     {
       "epoch": 0.08304498269896193,
-      "grad_norm": 7.031081676483154,
+      "grad_norm": 6.943802356719971,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 4.7688,
+      "loss": 4.7993,
       "step": 6
     },
     {
       "epoch": 0.09688581314878893,
-      "grad_norm": 6.366204738616943,
+      "grad_norm": 6.29345178604126,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 4.0197,
+      "loss": 4.0527,
       "step": 7
     },
     {
       "epoch": 0.11072664359861592,
-      "grad_norm": 4.397291660308838,
+      "grad_norm": 4.292151927947998,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 3.249,
+      "loss": 3.2727,
       "step": 8
     },
     {
       "epoch": 0.1245674740484429,
-      "grad_norm": 5.513636589050293,
+      "grad_norm": 5.503575801849365,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 2.83,
+      "loss": 2.8503,
       "step": 9
     },
     {
       "epoch": 0.1384083044982699,
-      "grad_norm": 4.908700942993164,
+      "grad_norm": 4.841407775878906,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 2.4178,
+      "loss": 2.4343,
       "step": 10
     },
     {
       "epoch": 0.1522491349480969,
-      "grad_norm": 6.022943019866943,
+      "grad_norm": 6.313112258911133,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 2.1281,
+      "loss": 2.1632,
       "step": 11
     },
     {
       "epoch": 0.16608996539792387,
-      "grad_norm": 3.7920618057250977,
+      "grad_norm": 3.8577535152435303,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 1.5878,
+      "loss": 1.6195,
       "step": 12
     },
     {
       "epoch": 0.17993079584775087,
-      "grad_norm": 3.0949554443359375,
+      "grad_norm": 3.1162829399108887,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 1.5057,
+      "loss": 1.5276,
       "step": 13
     },
     {
       "epoch": 0.19377162629757785,
-      "grad_norm": 3.586160182952881,
+      "grad_norm": 3.4716217517852783,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 1.0358,
+      "loss": 1.0397,
       "step": 14
     },
     {
       "epoch": 0.20761245674740483,
-      "grad_norm": 3.107851982116699,
+      "grad_norm": 3.084270477294922,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.8187,
+      "loss": 0.8244,
       "step": 15
     },
     {
       "epoch": 0.22145328719723184,
-      "grad_norm": 2.730515956878662,
+      "grad_norm": 2.7555480003356934,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.7116,
+      "loss": 0.7128,
       "step": 16
     },
     {
       "epoch": 0.23529411764705882,
-      "grad_norm": 1.947086215019226,
+      "grad_norm": 1.8600603342056274,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.6138,
+      "loss": 0.6115,
       "step": 17
     },
     {
       "epoch": 0.2491349480968858,
-      "grad_norm": 2.442556142807007,
+      "grad_norm": 2.531231641769409,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.5869,
+      "loss": 0.5861,
       "step": 18
     },
     {
       "epoch": 0.2629757785467128,
-      "grad_norm": 2.137789726257324,
+      "grad_norm": 2.077843189239502,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.6223,
+      "loss": 0.6199,
       "step": 19
     },
     {
       "epoch": 0.2768166089965398,
-      "grad_norm": 1.5641061067581177,
+      "grad_norm": 1.583787202835083,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.4856,
+      "loss": 0.4894,
       "step": 20
     },
     {
       "epoch": 0.2906574394463668,
-      "grad_norm": 1.357182264328003,
+      "grad_norm": 1.3708211183547974,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.4392,
+      "loss": 0.4431,
       "step": 21
     },
     {
       "epoch": 0.3044982698961938,
-      "grad_norm": 1.2531371116638184,
+      "grad_norm": 1.2605596780776978,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.4463,
+      "loss": 0.4492,
       "step": 22
     },
     {
       "epoch": 0.31833910034602075,
-      "grad_norm": 1.172152042388916,
+      "grad_norm": 1.1777682304382324,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.4772,
+      "loss": 0.481,
       "step": 23
     },
     {
       "epoch": 0.33217993079584773,
-      "grad_norm": 1.490871787071228,
+      "grad_norm": 1.4885942935943604,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.4693,
+      "loss": 0.4696,
       "step": 24
     },
     {
       "epoch": 0.3460207612456747,
-      "grad_norm": 1.3255620002746582,
+      "grad_norm": 1.4242111444473267,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.55,
+      "loss": 0.5529,
       "step": 25
     },
     {
       "epoch": 0.3460207612456747,
-      "eval_loss": 0.43850070238113403,
-      "eval_runtime": 14.6517,
-      "eval_samples_per_second": 33.238,
-      "eval_steps_per_second": 4.163,
+      "eval_loss": 0.43912115693092346,
+      "eval_runtime": 15.14,
+      "eval_samples_per_second": 32.166,
+      "eval_steps_per_second": 4.029,
       "step": 25
+    },
+    {
+      "epoch": 0.35986159169550175,
+      "grad_norm": 1.7132164239883423,
+      "learning_rate": 5e-05,
+      "loss": 0.4416,
+      "step": 26
+    },
+    {
+      "epoch": 0.3737024221453287,
+      "grad_norm": 1.4002691507339478,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4363,
+      "step": 27
+    },
+    {
+      "epoch": 0.3875432525951557,
+      "grad_norm": 1.2369598150253296,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4154,
+      "step": 28
+    },
+    {
+      "epoch": 0.4013840830449827,
+      "grad_norm": 1.3835961818695068,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4338,
+      "step": 29
+    },
+    {
+      "epoch": 0.41522491349480967,
+      "grad_norm": 1.3330230712890625,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.397,
+      "step": 30
+    },
+    {
+      "epoch": 0.4290657439446367,
+      "grad_norm": 1.1802304983139038,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.357,
+      "step": 31
+    },
+    {
+      "epoch": 0.4429065743944637,
+      "grad_norm": 1.2367409467697144,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4034,
+      "step": 32
+    },
+    {
+      "epoch": 0.45674740484429066,
+      "grad_norm": 1.2130498886108398,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.405,
+      "step": 33
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 1.2608569860458374,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3353,
+      "step": 34
+    },
+    {
+      "epoch": 0.4844290657439446,
+      "grad_norm": 1.0305883884429932,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3415,
+      "step": 35
+    },
+    {
+      "epoch": 0.4982698961937716,
+      "grad_norm": 1.2544233798980713,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3868,
+      "step": 36
+    },
+    {
+      "epoch": 0.5121107266435986,
+      "grad_norm": 1.6862411499023438,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4628,
+      "step": 37
+    },
+    {
+      "epoch": 0.5259515570934256,
+      "grad_norm": 1.897385597229004,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.54,
+      "step": 38
+    },
+    {
+      "epoch": 0.5397923875432526,
+      "grad_norm": 2.4782629013061523,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3803,
+      "step": 39
+    },
+    {
+      "epoch": 0.5536332179930796,
+      "grad_norm": 1.555917501449585,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3567,
+      "step": 40
+    },
+    {
+      "epoch": 0.5674740484429066,
+      "grad_norm": 1.20793616771698,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3914,
+      "step": 41
+    },
+    {
+      "epoch": 0.5813148788927336,
+      "grad_norm": 1.0951979160308838,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3359,
+      "step": 42
+    },
+    {
+      "epoch": 0.5951557093425606,
+      "grad_norm": 1.0838958024978638,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3086,
+      "step": 43
+    },
+    {
+      "epoch": 0.6089965397923875,
+      "grad_norm": 1.0459932088851929,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3276,
+      "step": 44
+    },
+    {
+      "epoch": 0.6228373702422145,
+      "grad_norm": 0.9643223881721497,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3504,
+      "step": 45
+    },
+    {
+      "epoch": 0.6366782006920415,
+      "grad_norm": 0.7485679388046265,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.302,
+      "step": 46
+    },
+    {
+      "epoch": 0.6505190311418685,
+      "grad_norm": 1.1050732135772705,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3741,
+      "step": 47
+    },
+    {
+      "epoch": 0.6643598615916955,
+      "grad_norm": 1.0713732242584229,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3708,
+      "step": 48
+    },
+    {
+      "epoch": 0.6782006920415224,
+      "grad_norm": 1.1242785453796387,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.379,
+      "step": 49
+    },
+    {
+      "epoch": 0.6920415224913494,
+      "grad_norm": 1.2118394374847412,
+      "learning_rate": 0.0,
+      "loss": 0.4422,
+      "step": 50
+    },
+    {
+      "epoch": 0.6920415224913494,
+      "eval_loss": 0.3484306335449219,
+      "eval_runtime": 14.8805,
+      "eval_samples_per_second": 32.727,
+      "eval_steps_per_second": 4.099,
+      "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": 2.997096984524882e+17,
+  "total_flos": 5.988598893678428e+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 sha256:19ae2772d6870b4169589bf5c86f6169d7d232f7f1f7e8b68c04fdb0d4bc8620
+oid sha256:4578fc132968af2a4189cfb0752b1938b6f2efe71a595e6c70d949b67513381f
 size 6776