Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "dense",
+    "v_proj",
     "q_proj",
+    "fc2",
     "fc1",
-    "v_proj",
-    "fc2"
+    "k_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:c11319cf4a610482c0ad8a08c86c745223298427e8c17324cf085bce2bf3c9de
+oid sha256:2221398f139a64247098b0a0065522c53f283679afbe616899c16b432dbb90ac
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc31edda2632a672e9f8ab4a32dbf68b38a7d39b71c2447e1bf47840358a0138
+oid sha256:0cf14d4c88ba6d2b87a39bf064ddc7fa3347c6881454d2204167cad51f71f853
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc53c012da566556d99419068823b262a9c93d7d7e30dd7b739945aea15607eb
+oid sha256:919ed4d438ad94a772fe1f8d9209fc3a225e80a615e608ca84241e88a22d9e80
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5683b8497c71cbdd49024bbb701bdd7eced8fe7358f97f2d68f01cc2e3f4468c
+oid sha256:84c5c1774c312b48cd03647ce6960b4b50e262910f752b8c386f19ab0a1f42f6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5474960dccf849ad3bce7b772f017330d91f90d690403c609acaffefe853834a
+oid sha256:24802882abf54df50dcdbc226baddc0fd09951389017eb5782efaa5ee58ccf9d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a314a4e4b63b22e3f751b6766e60384ed83ced33ac8576ca6bd6176a7b5d3dc9
+oid sha256:fb18bfe1377a257a943c7b0083178fb1dce85925c99550c437d76d2aaca4b824
 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

@@ -1,203 +1,386 @@
 {
-  "best_metric": 6.919445037841797,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6611570247933884,
+  "best_metric": 6.912809371948242,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.3322314049586776,
   "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": 0.026446280991735537,
-      "grad_norm": 0.6766738891601562,
+      "grad_norm": 0.6606590151786804,
       "learning_rate": 5e-05,
-      "loss": 6.9199,
+      "loss": 6.9198,
       "step": 1
     },
     {
       "epoch": 0.026446280991735537,
-      "eval_loss": 6.939976215362549,
-      "eval_runtime": 0.19,
-      "eval_samples_per_second": 1341.97,
-      "eval_steps_per_second": 168.404,
+      "eval_loss": 6.939949989318848,
+      "eval_runtime": 0.2079,
+      "eval_samples_per_second": 1226.53,
+      "eval_steps_per_second": 153.917,
       "step": 1
     },
     {
       "epoch": 0.05289256198347107,
-      "grad_norm": 0.6871870756149292,
+      "grad_norm": 0.6681128144264221,
       "learning_rate": 0.0001,
       "loss": 6.9171,
       "step": 2
     },
     {
       "epoch": 0.07933884297520662,
-      "grad_norm": 0.2755799889564514,
+      "grad_norm": 0.27679502964019775,
       "learning_rate": 9.989294616193017e-05,
       "loss": 6.9456,
       "step": 3
     },
     {
       "epoch": 0.10578512396694215,
-      "grad_norm": 0.276292622089386,
+      "grad_norm": 0.2745823264122009,
       "learning_rate": 9.957224306869053e-05,
       "loss": 6.9391,
       "step": 4
     },
     {
       "epoch": 0.1322314049586777,
-      "grad_norm": 0.2206062525510788,
+      "grad_norm": 0.219028040766716,
       "learning_rate": 9.903926402016153e-05,
       "loss": 6.9458,
       "step": 5
     },
     {
       "epoch": 0.15867768595041323,
-      "grad_norm": 0.2578071057796478,
+      "grad_norm": 0.25739091634750366,
       "learning_rate": 9.829629131445342e-05,
       "loss": 6.9417,
       "step": 6
     },
     {
       "epoch": 0.18512396694214875,
-      "grad_norm": 0.31613314151763916,
+      "grad_norm": 0.3217504918575287,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 6.9346,
+      "loss": 6.9345,
       "step": 7
     },
     {
       "epoch": 0.2115702479338843,
-      "grad_norm": 0.316804975271225,
+      "grad_norm": 0.3200313448905945,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 6.936,
+      "loss": 6.9359,
       "step": 8
     },
     {
       "epoch": 0.23801652892561984,
-      "grad_norm": 0.31575196981430054,
+      "grad_norm": 0.3203120231628418,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 6.9337,
+      "loss": 6.9336,
       "step": 9
     },
     {
       "epoch": 0.2644628099173554,
-      "grad_norm": 0.6410444974899292,
+      "grad_norm": 0.6145105361938477,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 6.9081,
+      "loss": 6.9088,
       "step": 10
     },
     {
       "epoch": 0.2909090909090909,
-      "grad_norm": 0.6962993144989014,
+      "grad_norm": 0.6703035235404968,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 6.9004,
+      "loss": 6.901,
       "step": 11
     },
     {
       "epoch": 0.31735537190082647,
-      "grad_norm": 0.2695646286010742,
+      "grad_norm": 0.26121264696121216,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 6.93,
+      "loss": 6.9301,
       "step": 12
     },
     {
       "epoch": 0.343801652892562,
-      "grad_norm": 0.26575586199760437,
+      "grad_norm": 0.27104130387306213,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 6.9337,
+      "loss": 6.9334,
       "step": 13
     },
     {
       "epoch": 0.3702479338842975,
-      "grad_norm": 0.2219240367412567,
+      "grad_norm": 0.2263699471950531,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 6.9348,
+      "loss": 6.9346,
       "step": 14
     },
     {
       "epoch": 0.39669421487603307,
-      "grad_norm": 0.24326728284358978,
+      "grad_norm": 0.24379611015319824,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 6.9343,
+      "loss": 6.9342,
       "step": 15
     },
     {
       "epoch": 0.4231404958677686,
-      "grad_norm": 0.2914644479751587,
+      "grad_norm": 0.29605957865715027,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 6.9268,
+      "loss": 6.9266,
       "step": 16
     },
     {
       "epoch": 0.44958677685950416,
-      "grad_norm": 0.3105446696281433,
+      "grad_norm": 0.3095487952232361,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 6.9224,
+      "loss": 6.9225,
       "step": 17
     },
     {
       "epoch": 0.47603305785123967,
-      "grad_norm": 0.3269963562488556,
+      "grad_norm": 0.3249109089374542,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 6.9309,
+      "loss": 6.9311,
       "step": 18
     },
     {
       "epoch": 0.5024793388429752,
-      "grad_norm": 0.5097985863685608,
+      "grad_norm": 0.4838687777519226,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 6.904,
+      "loss": 6.9051,
       "step": 19
     },
     {
       "epoch": 0.5289256198347108,
-      "grad_norm": 0.7069076299667358,
+      "grad_norm": 0.6721590757369995,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 6.8889,
+      "loss": 6.8906,
       "step": 20
     },
     {
       "epoch": 0.5553719008264463,
-      "grad_norm": 0.3384103775024414,
+      "grad_norm": 0.31941476464271545,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 6.9151,
+      "loss": 6.9157,
       "step": 21
     },
     {
       "epoch": 0.5818181818181818,
-      "grad_norm": 0.24765978753566742,
+      "grad_norm": 0.24956785142421722,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 6.9245,
+      "loss": 6.9243,
       "step": 22
     },
     {
       "epoch": 0.6082644628099173,
-      "grad_norm": 0.25236260890960693,
+      "grad_norm": 0.2541434168815613,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 6.9264,
+      "loss": 6.9263,
       "step": 23
     },
     {
       "epoch": 0.6347107438016529,
-      "grad_norm": 0.2543906569480896,
+      "grad_norm": 0.251471608877182,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 6.9314,
+      "loss": 6.9317,
       "step": 24
     },
     {
       "epoch": 0.6611570247933884,
-      "grad_norm": 0.2705303132534027,
+      "grad_norm": 0.2736002206802368,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 6.9221,
+      "loss": 6.9218,
       "step": 25
     },
     {
       "epoch": 0.6611570247933884,
-      "eval_loss": 6.919445037841797,
-      "eval_runtime": 0.189,
-      "eval_samples_per_second": 1349.148,
-      "eval_steps_per_second": 169.305,
+      "eval_loss": 6.9197845458984375,
+      "eval_runtime": 0.2085,
+      "eval_samples_per_second": 1223.197,
+      "eval_steps_per_second": 153.499,
       "step": 25
+    },
+    {
+      "epoch": 0.687603305785124,
+      "grad_norm": 0.3520897328853607,
+      "learning_rate": 5e-05,
+      "loss": 6.9146,
+      "step": 26
+    },
+    {
+      "epoch": 0.7140495867768595,
+      "grad_norm": 0.36051222681999207,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 6.9212,
+      "step": 27
+    },
+    {
+      "epoch": 0.740495867768595,
+      "grad_norm": 0.36609479784965515,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 6.9077,
+      "step": 28
+    },
+    {
+      "epoch": 0.7669421487603306,
+      "grad_norm": 0.6825762391090393,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 6.8783,
+      "step": 29
+    },
+    {
+      "epoch": 0.7933884297520661,
+      "grad_norm": 0.4839974641799927,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 6.8943,
+      "step": 30
+    },
+    {
+      "epoch": 0.8198347107438017,
+      "grad_norm": 0.28504496812820435,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 6.9179,
+      "step": 31
+    },
+    {
+      "epoch": 0.8462809917355372,
+      "grad_norm": 0.3000105619430542,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 6.9187,
+      "step": 32
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 0.20943278074264526,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 6.9359,
+      "step": 33
+    },
+    {
+      "epoch": 0.8991735537190083,
+      "grad_norm": 0.26605117321014404,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.9216,
+      "step": 34
+    },
+    {
+      "epoch": 0.9256198347107438,
+      "grad_norm": 0.31303733587265015,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 6.914,
+      "step": 35
+    },
+    {
+      "epoch": 0.9520661157024793,
+      "grad_norm": 0.32604312896728516,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 6.9163,
+      "step": 36
+    },
+    {
+      "epoch": 0.9785123966942149,
+      "grad_norm": 0.32598012685775757,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 6.9243,
+      "step": 37
+    },
+    {
+      "epoch": 1.0148760330578512,
+      "grad_norm": 0.7397525906562805,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.6965,
+      "step": 38
+    },
+    {
+      "epoch": 1.0413223140495869,
+      "grad_norm": 0.6702333688735962,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 6.953,
+      "step": 39
+    },
+    {
+      "epoch": 1.0677685950413223,
+      "grad_norm": 0.3199296295642853,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 7.0705,
+      "step": 40
+    },
+    {
+      "epoch": 1.094214876033058,
+      "grad_norm": 0.28222858905792236,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 7.0668,
+      "step": 41
+    },
+    {
+      "epoch": 1.1206611570247933,
+      "grad_norm": 0.18209977447986603,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 5.656,
+      "step": 42
+    },
+    {
+      "epoch": 1.147107438016529,
+      "grad_norm": 0.2604251801967621,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 7.9056,
+      "step": 43
+    },
+    {
+      "epoch": 1.1735537190082646,
+      "grad_norm": 0.289387971162796,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.8854,
+      "step": 44
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.34119921922683716,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 7.1047,
+      "step": 45
+    },
+    {
+      "epoch": 1.2264462809917356,
+      "grad_norm": 0.3346429765224457,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 6.8513,
+      "step": 46
+    },
+    {
+      "epoch": 1.252892561983471,
+      "grad_norm": 0.32595688104629517,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 6.1413,
+      "step": 47
+    },
+    {
+      "epoch": 1.2793388429752066,
+      "grad_norm": 0.746822714805603,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 7.5015,
+      "step": 48
+    },
+    {
+      "epoch": 1.3057851239669422,
+      "grad_norm": 0.416890412569046,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 6.8391,
+      "step": 49
+    },
+    {
+      "epoch": 1.3322314049586776,
+      "grad_norm": 0.2753528952598572,
+      "learning_rate": 0.0,
+      "loss": 7.1526,
+      "step": 50
+    },
+    {
+      "epoch": 1.3322314049586776,
+      "eval_loss": 6.912809371948242,
+      "eval_runtime": 0.2069,
+      "eval_samples_per_second": 1232.763,
+      "eval_steps_per_second": 154.7,
+      "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": 2852978688000.0,
+  "total_flos": 5705957376000.0,
   "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 sha256:35f84cefbae9206f47a4308fd69e8fbec7509210dc2a4c6e6aa3830637bac8fa
+oid sha256:51e0c398dca0cd5d0cbfc1d39ace7ffd58d75e75e41ef4457b9f0d32d72eec7c
 size 6776