Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
+    "gate_proj",
+    "q_proj",
     "v_proj",
     "o_proj",
-    "q_proj",
-    "gate_proj",
+    "up_proj",
+    "down_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2abec29f33dbea96cabfaf8cd79839bea6ec494912eece249959f6601bc0c056
+oid sha256:3de2667e421e4c965989af254e94aa65121b2c682771bd3773741413c6472dc0
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a8243ce969f1fc7b1f0df2bc83dc2f5d8346f7c743e07a49b2ad7ab615e0ab0
+oid sha256:4b153b9028eb9101e45dd05debeb05b843edce9db7ed5111a7c8e9b1c31c5cca
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67bbae85891c3abdff708d110af864f53d01345b17dd294d1e625bad92cd1d4
+oid sha256:7674c2a5d96b7dd8617baf0ef4975eba2c266c0750292f6c60e107b6976f9929
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a72921ae91111ec6af6de54dadcceefdf32ba5503b8e8e85fc1e92517f90d611
+oid sha256:1379181e1c83c62ad2b5506363f1da74f0b64a838bf6df989f0a54e998c60a17
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e529c18453435be7df68f063171e955c5bfa48f4e99681c6125346c202dcc934
+oid sha256:cac8761e57a0871241834772015cc8a59e69fcd564a7d8a5fd4c5b2b7c85e707
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c99231f94cd3f5bd61d44d92a1f0adedd4e336a373b136fa3c6cfe9357387da4
+oid sha256:98b61e878afccaf9caea692f838043444693aa5a7550b7e00def46e61acfa071
 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": 1.2396924495697021,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.00549111126364198,
+  "best_metric": 1.1367937326431274,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01098222252728396,
   "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": 0.00021964445054567917,
-      "grad_norm": 128.1067352294922,
+      "grad_norm": 128.23704528808594,
       "learning_rate": 5e-05,
       "loss": 56.2272,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.00021964445054567917,
       "eval_loss": 4.680656433105469,
-      "eval_runtime": 1011.3172,
-      "eval_samples_per_second": 30.329,
-      "eval_steps_per_second": 3.791,
+      "eval_runtime": 993.785,
+      "eval_samples_per_second": 30.864,
+      "eval_steps_per_second": 3.858,
       "step": 1
     },
     {
       "epoch": 0.00043928890109135835,
-      "grad_norm": 143.234619140625,
+      "grad_norm": 143.4749755859375,
       "learning_rate": 0.0001,
       "loss": 60.1614,
       "step": 2
     },
     {
       "epoch": 0.0006589333516370375,
-      "grad_norm": 137.83009338378906,
+      "grad_norm": 137.1166229248047,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 49.6884,
+      "loss": 49.7424,
       "step": 3
     },
     {
       "epoch": 0.0008785778021827167,
-      "grad_norm": 149.57333374023438,
+      "grad_norm": 148.66978454589844,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 40.5463,
+      "loss": 40.6251,
       "step": 4
     },
     {
       "epoch": 0.001098222252728396,
-      "grad_norm": 126.31389617919922,
+      "grad_norm": 123.3190689086914,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 28.744,
+      "loss": 28.6644,
       "step": 5
     },
     {
       "epoch": 0.001317866703274075,
-      "grad_norm": 79.62859344482422,
+      "grad_norm": 96.45237731933594,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 24.7095,
+      "loss": 24.8699,
       "step": 6
     },
     {
       "epoch": 0.0015375111538197543,
-      "grad_norm": 80.24508666992188,
+      "grad_norm": 85.54580688476562,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 31.9621,
+      "loss": 32.3173,
       "step": 7
     },
     {
       "epoch": 0.0017571556043654334,
-      "grad_norm": 63.11004638671875,
+      "grad_norm": 62.83359909057617,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 34.5423,
+      "loss": 34.6373,
       "step": 8
     },
     {
       "epoch": 0.0019768000549111125,
-      "grad_norm": 57.706024169921875,
+      "grad_norm": 57.34482955932617,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 29.9541,
+      "loss": 30.0552,
       "step": 9
     },
     {
       "epoch": 0.002196444505456792,
-      "grad_norm": 54.863677978515625,
+      "grad_norm": 54.51626205444336,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 29.9576,
+      "loss": 30.001,
       "step": 10
     },
     {
       "epoch": 0.002416088956002471,
-      "grad_norm": 44.20351028442383,
+      "grad_norm": 42.708797454833984,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 26.8734,
+      "loss": 26.8644,
       "step": 11
     },
     {
       "epoch": 0.00263573340654815,
-      "grad_norm": 48.68452453613281,
+      "grad_norm": 49.291168212890625,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 24.3141,
+      "loss": 24.2909,
       "step": 12
     },
     {
       "epoch": 0.002855377857093829,
-      "grad_norm": 41.1622428894043,
+      "grad_norm": 41.978065490722656,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 21.5583,
+      "loss": 21.6199,
       "step": 13
     },
     {
       "epoch": 0.0030750223076395087,
-      "grad_norm": 33.06452941894531,
+      "grad_norm": 34.085784912109375,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 21.5232,
+      "loss": 21.6063,
       "step": 14
     },
     {
       "epoch": 0.0032946667581851877,
-      "grad_norm": 32.99700927734375,
+      "grad_norm": 32.29074478149414,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 21.1583,
+      "loss": 21.2135,
       "step": 15
     },
     {
       "epoch": 0.003514311208730867,
-      "grad_norm": 29.614459991455078,
+      "grad_norm": 29.822490692138672,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 19.3747,
+      "loss": 19.3972,
       "step": 16
     },
     {
       "epoch": 0.0037339556592765463,
-      "grad_norm": 30.350385665893555,
+      "grad_norm": 30.889225006103516,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 18.0964,
+      "loss": 18.1983,
       "step": 17
     },
     {
       "epoch": 0.003953600109822225,
-      "grad_norm": 32.349517822265625,
+      "grad_norm": 32.00242233276367,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 16.1271,
+      "loss": 16.1963,
       "step": 18
     },
     {
       "epoch": 0.004173244560367904,
-      "grad_norm": 32.42576599121094,
+      "grad_norm": 32.16281509399414,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 17.4368,
+      "loss": 17.5086,
       "step": 19
     },
     {
       "epoch": 0.004392889010913584,
-      "grad_norm": 34.648921966552734,
+      "grad_norm": 34.678836822509766,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 22.3387,
+      "loss": 22.4093,
       "step": 20
     },
     {
       "epoch": 0.0046125334614592626,
-      "grad_norm": 35.400508880615234,
+      "grad_norm": 34.99449157714844,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 24.7527,
+      "loss": 24.8476,
       "step": 21
     },
     {
       "epoch": 0.004832177912004942,
-      "grad_norm": 33.76140594482422,
+      "grad_norm": 33.277915954589844,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 24.1014,
+      "loss": 24.1189,
       "step": 22
     },
     {
       "epoch": 0.0050518223625506216,
-      "grad_norm": 34.995182037353516,
+      "grad_norm": 34.244911193847656,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 24.9544,
+      "loss": 24.978,
       "step": 23
     },
     {
       "epoch": 0.0052714668130963,
-      "grad_norm": 35.42438888549805,
+      "grad_norm": 34.834537506103516,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 21.6453,
+      "loss": 21.6183,
       "step": 24
     },
     {
       "epoch": 0.00549111126364198,
-      "grad_norm": 36.63457107543945,
+      "grad_norm": 36.37040710449219,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 19.3884,
+      "loss": 19.4469,
       "step": 25
     },
     {
       "epoch": 0.00549111126364198,
-      "eval_loss": 1.2396924495697021,
-      "eval_runtime": 1011.7714,
-      "eval_samples_per_second": 30.315,
-      "eval_steps_per_second": 3.789,
+      "eval_loss": 1.2408840656280518,
+      "eval_runtime": 997.0364,
+      "eval_samples_per_second": 30.763,
+      "eval_steps_per_second": 3.845,
       "step": 25
+    },
+    {
+      "epoch": 0.005710755714187658,
+      "grad_norm": 37.87440872192383,
+      "learning_rate": 5e-05,
+      "loss": 19.7613,
+      "step": 26
+    },
+    {
+      "epoch": 0.005930400164733338,
+      "grad_norm": 33.064544677734375,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 18.0642,
+      "step": 27
+    },
+    {
+      "epoch": 0.006150044615279017,
+      "grad_norm": 29.548095703125,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 17.3166,
+      "step": 28
+    },
+    {
+      "epoch": 0.006369689065824696,
+      "grad_norm": 26.16414451599121,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 15.5425,
+      "step": 29
+    },
+    {
+      "epoch": 0.0065893335163703754,
+      "grad_norm": 28.377233505249023,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 14.7725,
+      "step": 30
+    },
+    {
+      "epoch": 0.006808977966916055,
+      "grad_norm": 25.38302993774414,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 15.3178,
+      "step": 31
+    },
+    {
+      "epoch": 0.007028622417461734,
+      "grad_norm": 30.4620418548584,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 22.3925,
+      "step": 32
+    },
+    {
+      "epoch": 0.007248266868007413,
+      "grad_norm": 33.57545471191406,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 22.7248,
+      "step": 33
+    },
+    {
+      "epoch": 0.007467911318553093,
+      "grad_norm": 30.484207153320312,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 23.1463,
+      "step": 34
+    },
+    {
+      "epoch": 0.007687555769098771,
+      "grad_norm": 30.004377365112305,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 22.9688,
+      "step": 35
+    },
+    {
+      "epoch": 0.00790720021964445,
+      "grad_norm": 29.935291290283203,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 20.2948,
+      "step": 36
+    },
+    {
+      "epoch": 0.00812684467019013,
+      "grad_norm": 28.792709350585938,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 19.0507,
+      "step": 37
+    },
+    {
+      "epoch": 0.008346489120735809,
+      "grad_norm": 27.595048904418945,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 16.6061,
+      "step": 38
+    },
+    {
+      "epoch": 0.008566133571281487,
+      "grad_norm": 25.91175079345703,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 17.2893,
+      "step": 39
+    },
+    {
+      "epoch": 0.008785778021827168,
+      "grad_norm": 25.115896224975586,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 16.478,
+      "step": 40
+    },
+    {
+      "epoch": 0.009005422472372846,
+      "grad_norm": 25.421123504638672,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 15.2758,
+      "step": 41
+    },
+    {
+      "epoch": 0.009225066922918525,
+      "grad_norm": 24.610855102539062,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 15.0212,
+      "step": 42
+    },
+    {
+      "epoch": 0.009444711373464205,
+      "grad_norm": 25.012407302856445,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 12.7155,
+      "step": 43
+    },
+    {
+      "epoch": 0.009664355824009884,
+      "grad_norm": 27.121875762939453,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 18.6648,
+      "step": 44
+    },
+    {
+      "epoch": 0.009884000274555563,
+      "grad_norm": 26.64497947692871,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 22.6941,
+      "step": 45
+    },
+    {
+      "epoch": 0.010103644725101243,
+      "grad_norm": 28.527849197387695,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 23.0154,
+      "step": 46
+    },
+    {
+      "epoch": 0.010323289175646922,
+      "grad_norm": 28.003326416015625,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 20.9035,
+      "step": 47
+    },
+    {
+      "epoch": 0.0105429336261926,
+      "grad_norm": 27.89699935913086,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 19.9821,
+      "step": 48
+    },
+    {
+      "epoch": 0.01076257807673828,
+      "grad_norm": 31.022777557373047,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 21.9172,
+      "step": 49
+    },
+    {
+      "epoch": 0.01098222252728396,
+      "grad_norm": 28.083293914794922,
+      "learning_rate": 0.0,
+      "loss": 17.7392,
+      "step": 50
+    },
+    {
+      "epoch": 0.01098222252728396,
+      "eval_loss": 1.1367937326431274,
+      "eval_runtime": 1004.9057,
+      "eval_samples_per_second": 30.522,
+      "eval_steps_per_second": 3.815,
+      "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": 2.9561017256955085e+17,
+  "total_flos": 5.896147371137434e+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:a65880b754e7f84521433de3a80abd9cc044e2fb177ca6c0a8d5cc26dc281625
+oid sha256:520a3190afbaff4cd4b1377dcfd05b83cef3a7ef41fa7c660fd307b81cc80bf3
 size 6776