Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "qkv_proj",
-    "down_proj",
     "gate_up_proj",
-    "o_proj"
+    "o_proj",
+    "qkv_proj",
+    "down_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 sha256:6cc04517533795145589133fa331d3ae05820739f38c9c4f115e908b22cb88ad
+oid sha256:c241f174145ad018a5542b556eb5707610678c36098e39bc309230dabd07c8df
 size 445688440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a3335e4de86b5e42aa0781e28c3a5b5b25804ec52fc4597b208d7ffc04990b
+oid sha256:d064825dd769bda137b127b7f7444cb07146d039bf2dbe54f7b0472329bb4e19
 size 891559354

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.7819569110870361,
+  "best_metric": 1.7845427989959717,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 0.039012971813127864,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.0015605188725251145,
-      "grad_norm": 27.47134780883789,
+      "grad_norm": 27.093671798706055,
       "learning_rate": 5e-05,
       "loss": 3.6352,
       "step": 1
@@ -18,185 +18,185 @@
     {
       "epoch": 0.0015605188725251145,
       "eval_loss": 5.159157752990723,
-      "eval_runtime": 284.8757,
-      "eval_samples_per_second": 15.154,
-      "eval_steps_per_second": 1.896,
+      "eval_runtime": 284.5779,
+      "eval_samples_per_second": 15.17,
+      "eval_steps_per_second": 1.898,
       "step": 1
     },
     {
       "epoch": 0.003121037745050229,
-      "grad_norm": 36.22637939453125,
+      "grad_norm": 35.23081970214844,
       "learning_rate": 0.0001,
       "loss": 3.9431,
       "step": 2
     },
     {
       "epoch": 0.004681556617575344,
-      "grad_norm": 50.328521728515625,
+      "grad_norm": 47.64265823364258,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 4.2231,
+      "loss": 4.2257,
       "step": 3
     },
     {
       "epoch": 0.006242075490100458,
-      "grad_norm": 48.88551712036133,
+      "grad_norm": 49.69529724121094,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 4.1506,
+      "loss": 4.1541,
       "step": 4
     },
     {
       "epoch": 0.007802594362625573,
-      "grad_norm": 68.67530059814453,
+      "grad_norm": 62.94880676269531,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 3.7554,
+      "loss": 3.7494,
       "step": 5
     },
     {
       "epoch": 0.009363113235150688,
-      "grad_norm": 61.40333938598633,
+      "grad_norm": 58.486602783203125,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 3.0367,
+      "loss": 3.0434,
       "step": 6
     },
     {
       "epoch": 0.010923632107675801,
-      "grad_norm": 52.827537536621094,
+      "grad_norm": 47.32489776611328,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 2.4633,
+      "loss": 2.4626,
       "step": 7
     },
     {
       "epoch": 0.012484150980200916,
-      "grad_norm": 28.17048454284668,
+      "grad_norm": 28.48284912109375,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 2.1796,
+      "loss": 2.1683,
       "step": 8
     },
     {
       "epoch": 0.014044669852726031,
-      "grad_norm": 35.46862030029297,
+      "grad_norm": 36.46367645263672,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 2.0245,
+      "loss": 2.0081,
       "step": 9
     },
     {
       "epoch": 0.015605188725251146,
-      "grad_norm": 32.363494873046875,
+      "grad_norm": 31.903751373291016,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 1.7505,
+      "loss": 1.735,
       "step": 10
     },
     {
       "epoch": 0.01716570759777626,
-      "grad_norm": 17.789806365966797,
+      "grad_norm": 18.21411895751953,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 1.6077,
+      "loss": 1.5997,
       "step": 11
     },
     {
       "epoch": 0.018726226470301376,
-      "grad_norm": 33.911773681640625,
+      "grad_norm": 33.31740951538086,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 2.1027,
+      "loss": 2.0939,
       "step": 12
     },
     {
       "epoch": 0.02028674534282649,
-      "grad_norm": 27.88349723815918,
+      "grad_norm": 27.541213989257812,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 2.4112,
+      "loss": 2.3984,
       "step": 13
     },
     {
       "epoch": 0.021847264215351603,
-      "grad_norm": 30.37132453918457,
+      "grad_norm": 32.7118034362793,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 2.3633,
+      "loss": 2.366,
       "step": 14
     },
     {
       "epoch": 0.023407783087876718,
-      "grad_norm": 27.670595169067383,
+      "grad_norm": 28.815990447998047,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 2.2985,
+      "loss": 2.2951,
       "step": 15
     },
     {
       "epoch": 0.024968301960401833,
-      "grad_norm": 21.760271072387695,
+      "grad_norm": 22.008098602294922,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 2.1505,
+      "loss": 2.1483,
       "step": 16
     },
     {
       "epoch": 0.026528820832926948,
-      "grad_norm": 17.555070877075195,
+      "grad_norm": 19.000747680664062,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 1.908,
+      "loss": 1.9089,
       "step": 17
     },
     {
       "epoch": 0.028089339705452063,
-      "grad_norm": 13.887099266052246,
+      "grad_norm": 15.313111305236816,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 1.7718,
+      "loss": 1.7744,
       "step": 18
     },
     {
       "epoch": 0.029649858577977178,
-      "grad_norm": 11.893011093139648,
+      "grad_norm": 12.31628131866455,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 1.7384,
+      "loss": 1.7365,
       "step": 19
     },
     {
       "epoch": 0.031210377450502293,
-      "grad_norm": 11.991311073303223,
+      "grad_norm": 11.852285385131836,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 1.519,
+      "loss": 1.5183,
       "step": 20
     },
     {
       "epoch": 0.032770896323027404,
-      "grad_norm": 12.210515975952148,
+      "grad_norm": 11.74448299407959,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 1.6556,
+      "loss": 1.651,
       "step": 21
     },
     {
       "epoch": 0.03433141519555252,
-      "grad_norm": 13.891636848449707,
+      "grad_norm": 13.442978858947754,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 1.5797,
+      "loss": 1.5721,
       "step": 22
     },
     {
       "epoch": 0.035891934068077634,
-      "grad_norm": 14.036815643310547,
+      "grad_norm": 14.07254409790039,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 1.5168,
+      "loss": 1.4983,
       "step": 23
     },
     {
       "epoch": 0.03745245294060275,
-      "grad_norm": 17.62822914123535,
+      "grad_norm": 16.79251480102539,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 1.4325,
+      "loss": 1.4203,
       "step": 24
     },
     {
       "epoch": 0.039012971813127864,
-      "grad_norm": 23.006757736206055,
+      "grad_norm": 23.276710510253906,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 2.2311,
+      "loss": 2.2293,
       "step": 25
     },
     {
       "epoch": 0.039012971813127864,
-      "eval_loss": 1.7819569110870361,
-      "eval_runtime": 284.8265,
-      "eval_samples_per_second": 15.157,
-      "eval_steps_per_second": 1.896,
+      "eval_loss": 1.7845427989959717,
+      "eval_runtime": 284.5304,
+      "eval_samples_per_second": 15.172,
+      "eval_steps_per_second": 1.898,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b095aab98c9d0f056114cfd27d18b2ae9c09fc7600a46ac9acc6ecf782b705ca
+oid sha256:0159e238933649e4b1712b80c029ece5145df05759de3a9be54b50d9c93a5826
 size 6776