Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_up_proj",
-    "o_proj",
     "qkv_proj",
-    "down_proj"
+    "down_proj",
+    "gate_up_proj",
+    "o_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:c241f174145ad018a5542b556eb5707610678c36098e39bc309230dabd07c8df
+oid sha256:cd386869160576e247f818b418f34612f1c7896a0fbfa1c8145e8625aeb86c00
 size 445688440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d064825dd769bda137b127b7f7444cb07146d039bf2dbe54f7b0472329bb4e19
+oid sha256:4cd2ca765fa705d6a403bdf0586e8f24965872000346d2e8a1ce470d9d8e51ae
 size 891559354

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98bed804501c83a443212e698c81e2f59ae0593a94cbdae7c3c0926caa0ddda1
+oid sha256:d210f1b4508e0b14718aee8b474a75ef33e570d2742ab3213d64f0c8d649c4d0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f894f3bd0e6a7480a458b8103fd23e2f686650d9c5c430b236007af640eab3
+oid sha256:3eefb425294e5b1fb3776d7739e56463038021f05e6bdb62010a56abbef2a7d5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d49ee717dd8279a6e72085f7bf4733c9edf8d69e2fa0e890fbad97bee16a7720
+oid sha256:486130ae337c3a862a90c41b0ef19134915cd67ce9f9cc4459bdbfb9d2b1a8e2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea27066bf16d8be6a42b4d79014f645d6346e018cc0dfd87577f4cd12227571
+oid sha256:8e04d7b5c25e34a533abb24d633d6127ac51ab955d6bdabfdb43138f75172de6
 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": 1.7845427989959717,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.039012971813127864,
+  "best_metric": 1.7095980644226074,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07802594362625573,
   "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": 0.0015605188725251145,
-      "grad_norm": 27.093671798706055,
+      "grad_norm": 27.47134780883789,
       "learning_rate": 5e-05,
       "loss": 3.6352,
       "step": 1
@@ -18,186 +18,369 @@
     {
       "epoch": 0.0015605188725251145,
       "eval_loss": 5.159157752990723,
-      "eval_runtime": 284.5779,
-      "eval_samples_per_second": 15.17,
-      "eval_steps_per_second": 1.898,
+      "eval_runtime": 284.8757,
+      "eval_samples_per_second": 15.154,
+      "eval_steps_per_second": 1.896,
       "step": 1
     },
     {
       "epoch": 0.003121037745050229,
-      "grad_norm": 35.23081970214844,
+      "grad_norm": 36.22637939453125,
       "learning_rate": 0.0001,
       "loss": 3.9431,
       "step": 2
     },
     {
       "epoch": 0.004681556617575344,
-      "grad_norm": 47.64265823364258,
+      "grad_norm": 50.328521728515625,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 4.2257,
+      "loss": 4.2231,
       "step": 3
     },
     {
       "epoch": 0.006242075490100458,
-      "grad_norm": 49.69529724121094,
+      "grad_norm": 48.88551712036133,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 4.1541,
+      "loss": 4.1506,
       "step": 4
     },
     {
       "epoch": 0.007802594362625573,
-      "grad_norm": 62.94880676269531,
+      "grad_norm": 68.67530059814453,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 3.7494,
+      "loss": 3.7554,
       "step": 5
     },
     {
       "epoch": 0.009363113235150688,
-      "grad_norm": 58.486602783203125,
+      "grad_norm": 61.40333938598633,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 3.0434,
+      "loss": 3.0367,
       "step": 6
     },
     {
       "epoch": 0.010923632107675801,
-      "grad_norm": 47.32489776611328,
+      "grad_norm": 52.827537536621094,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 2.4626,
+      "loss": 2.4633,
       "step": 7
     },
     {
       "epoch": 0.012484150980200916,
-      "grad_norm": 28.48284912109375,
+      "grad_norm": 28.17048454284668,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 2.1683,
+      "loss": 2.1796,
       "step": 8
     },
     {
       "epoch": 0.014044669852726031,
-      "grad_norm": 36.46367645263672,
+      "grad_norm": 35.46862030029297,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 2.0081,
+      "loss": 2.0245,
       "step": 9
     },
     {
       "epoch": 0.015605188725251146,
-      "grad_norm": 31.903751373291016,
+      "grad_norm": 32.363494873046875,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 1.735,
+      "loss": 1.7505,
       "step": 10
     },
     {
       "epoch": 0.01716570759777626,
-      "grad_norm": 18.21411895751953,
+      "grad_norm": 17.789806365966797,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 1.5997,
+      "loss": 1.6077,
       "step": 11
     },
     {
       "epoch": 0.018726226470301376,
-      "grad_norm": 33.31740951538086,
+      "grad_norm": 33.911773681640625,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 2.0939,
+      "loss": 2.1027,
       "step": 12
     },
     {
       "epoch": 0.02028674534282649,
-      "grad_norm": 27.541213989257812,
+      "grad_norm": 27.88349723815918,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 2.3984,
+      "loss": 2.4112,
       "step": 13
     },
     {
       "epoch": 0.021847264215351603,
-      "grad_norm": 32.7118034362793,
+      "grad_norm": 30.37132453918457,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 2.366,
+      "loss": 2.3633,
       "step": 14
     },
     {
       "epoch": 0.023407783087876718,
-      "grad_norm": 28.815990447998047,
+      "grad_norm": 27.670595169067383,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 2.2951,
+      "loss": 2.2985,
       "step": 15
     },
     {
       "epoch": 0.024968301960401833,
-      "grad_norm": 22.008098602294922,
+      "grad_norm": 21.760271072387695,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 2.1483,
+      "loss": 2.1505,
       "step": 16
     },
     {
       "epoch": 0.026528820832926948,
-      "grad_norm": 19.000747680664062,
+      "grad_norm": 17.555070877075195,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 1.9089,
+      "loss": 1.908,
       "step": 17
     },
     {
       "epoch": 0.028089339705452063,
-      "grad_norm": 15.313111305236816,
+      "grad_norm": 13.887099266052246,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 1.7744,
+      "loss": 1.7718,
       "step": 18
     },
     {
       "epoch": 0.029649858577977178,
-      "grad_norm": 12.31628131866455,
+      "grad_norm": 11.893011093139648,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 1.7365,
+      "loss": 1.7384,
       "step": 19
     },
     {
       "epoch": 0.031210377450502293,
-      "grad_norm": 11.852285385131836,
+      "grad_norm": 11.991311073303223,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 1.5183,
+      "loss": 1.519,
       "step": 20
     },
     {
       "epoch": 0.032770896323027404,
-      "grad_norm": 11.74448299407959,
+      "grad_norm": 12.210515975952148,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 1.651,
+      "loss": 1.6556,
       "step": 21
     },
     {
       "epoch": 0.03433141519555252,
-      "grad_norm": 13.442978858947754,
+      "grad_norm": 13.891636848449707,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 1.5721,
+      "loss": 1.5797,
       "step": 22
     },
     {
       "epoch": 0.035891934068077634,
-      "grad_norm": 14.07254409790039,
+      "grad_norm": 14.036815643310547,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 1.4983,
+      "loss": 1.5168,
       "step": 23
     },
     {
       "epoch": 0.03745245294060275,
-      "grad_norm": 16.79251480102539,
+      "grad_norm": 17.62822914123535,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 1.4203,
+      "loss": 1.4325,
       "step": 24
     },
     {
       "epoch": 0.039012971813127864,
-      "grad_norm": 23.276710510253906,
+      "grad_norm": 23.006757736206055,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 2.2293,
+      "loss": 2.2311,
       "step": 25
     },
     {
       "epoch": 0.039012971813127864,
-      "eval_loss": 1.7845427989959717,
-      "eval_runtime": 284.5304,
-      "eval_samples_per_second": 15.172,
-      "eval_steps_per_second": 1.898,
+      "eval_loss": 1.7819569110870361,
+      "eval_runtime": 284.8265,
+      "eval_samples_per_second": 15.157,
+      "eval_steps_per_second": 1.896,
       "step": 25
+    },
+    {
+      "epoch": 0.04057349068565298,
+      "grad_norm": 11.565553665161133,
+      "learning_rate": 5e-05,
+      "loss": 2.165,
+      "step": 26
+    },
+    {
+      "epoch": 0.042134009558178094,
+      "grad_norm": 14.048898696899414,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.0494,
+      "step": 27
+    },
+    {
+      "epoch": 0.043694528430703206,
+      "grad_norm": 19.105083465576172,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.9045,
+      "step": 28
+    },
+    {
+      "epoch": 0.045255047303228324,
+      "grad_norm": 12.373530387878418,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.8103,
+      "step": 29
+    },
+    {
+      "epoch": 0.046815566175753436,
+      "grad_norm": 11.43731689453125,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.809,
+      "step": 30
+    },
+    {
+      "epoch": 0.048376085048278554,
+      "grad_norm": 10.184928894042969,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.7182,
+      "step": 31
+    },
+    {
+      "epoch": 0.049936603920803666,
+      "grad_norm": 7.965986251831055,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.555,
+      "step": 32
+    },
+    {
+      "epoch": 0.051497122793328784,
+      "grad_norm": 8.148660659790039,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.5228,
+      "step": 33
+    },
+    {
+      "epoch": 0.053057641665853895,
+      "grad_norm": 8.765047073364258,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6031,
+      "step": 34
+    },
+    {
+      "epoch": 0.054618160538379014,
+      "grad_norm": 10.645421981811523,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3356,
+      "step": 35
+    },
+    {
+      "epoch": 0.056178679410904125,
+      "grad_norm": 9.20206356048584,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4684,
+      "step": 36
+    },
+    {
+      "epoch": 0.05773919828342924,
+      "grad_norm": 18.52010726928711,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8632,
+      "step": 37
+    },
+    {
+      "epoch": 0.059299717155954355,
+      "grad_norm": 24.089401245117188,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.1842,
+      "step": 38
+    },
+    {
+      "epoch": 0.06086023602847947,
+      "grad_norm": 7.3534836769104,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.0029,
+      "step": 39
+    },
+    {
+      "epoch": 0.062420754901004585,
+      "grad_norm": 8.266510963439941,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0822,
+      "step": 40
+    },
+    {
+      "epoch": 0.0639812737735297,
+      "grad_norm": 7.034852981567383,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.8253,
+      "step": 41
+    },
+    {
+      "epoch": 0.06554179264605481,
+      "grad_norm": 7.051949977874756,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.8126,
+      "step": 42
+    },
+    {
+      "epoch": 0.06710231151857993,
+      "grad_norm": 8.679147720336914,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.8148,
+      "step": 43
+    },
+    {
+      "epoch": 0.06866283039110505,
+      "grad_norm": 7.149501323699951,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6592,
+      "step": 44
+    },
+    {
+      "epoch": 0.07022334926363016,
+      "grad_norm": 7.01240873336792,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.6468,
+      "step": 45
+    },
+    {
+      "epoch": 0.07178386813615527,
+      "grad_norm": 7.942070960998535,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5128,
+      "step": 46
+    },
+    {
+      "epoch": 0.07334438700868039,
+      "grad_norm": 10.752588272094727,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.4529,
+      "step": 47
+    },
+    {
+      "epoch": 0.0749049058812055,
+      "grad_norm": 9.855756759643555,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.4671,
+      "step": 48
+    },
+    {
+      "epoch": 0.07646542475373061,
+      "grad_norm": 12.484454154968262,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.5306,
+      "step": 49
+    },
+    {
+      "epoch": 0.07802594362625573,
+      "grad_norm": 30.089313507080078,
+      "learning_rate": 0.0,
+      "loss": 2.0822,
+      "step": 50
+    },
+    {
+      "epoch": 0.07802594362625573,
+      "eval_loss": 1.7095980644226074,
+      "eval_runtime": 284.8051,
+      "eval_samples_per_second": 15.158,
+      "eval_steps_per_second": 1.896,
+      "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": 5.468644419043328e+17,
+  "total_flos": 1.0937288838086656e+18,
   "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 sha256:0159e238933649e4b1712b80c029ece5145df05759de3a9be54b50d9c93a5826
+oid sha256:b095aab98c9d0f056114cfd27d18b2ae9c09fc7600a46ac9acc6ecf782b705ca
 size 6776