Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -21,10 +21,10 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "down_proj",
-    "gate_proj",
     "q_proj",
+    "gate_proj",
     "v_proj",
+    "down_proj",
     "up_proj",
     "o_proj"
   ],

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b129efb3e46f24c7651aaefaf6169be68892771d8e641d3a6112b32f2f4bf79
+oid sha256:5c55100978e8e86ced42b927ea5e128fb072afa9024f525538380bae0e7c50a6
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006425dd9ba25f4ad306f2b33680e755483a85f27be415ddaa0742d88bf40cad
+oid sha256:dfcc35de423f2dc5d273500b4fcac411bcf6c8da2c6ffcec902610912dd634c4
 size 671466706

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.11382482945919037,
+  "best_metric": 0.09059706330299377,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 1.3498349834983498,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.052805280528052806,
-      "grad_norm": 240.08116149902344,
+      "grad_norm": 241.61077880859375,
       "learning_rate": 5e-05,
       "loss": 61.3338,
       "step": 1
@@ -18,185 +18,185 @@
     {
       "epoch": 0.052805280528052806,
       "eval_loss": 3.5627546310424805,
-      "eval_runtime": 4.3057,
-      "eval_samples_per_second": 29.728,
-      "eval_steps_per_second": 3.716,
+      "eval_runtime": 4.3596,
+      "eval_samples_per_second": 29.361,
+      "eval_steps_per_second": 3.67,
       "step": 1
     },
     {
       "epoch": 0.10561056105610561,
-      "grad_norm": 311.3833923339844,
+      "grad_norm": 313.4629821777344,
       "learning_rate": 0.0001,
       "loss": 55.4131,
       "step": 2
     },
     {
       "epoch": 0.15841584158415842,
-      "grad_norm": 186.2847137451172,
+      "grad_norm": 185.32693481445312,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 35.886,
+      "loss": 35.7674,
       "step": 3
     },
     {
       "epoch": 0.21122112211221122,
-      "grad_norm": 109.15618896484375,
+      "grad_norm": 110.76226806640625,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 20.0972,
+      "loss": 20.0764,
       "step": 4
     },
     {
       "epoch": 0.264026402640264,
-      "grad_norm": 88.25745391845703,
+      "grad_norm": 87.55223846435547,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 24.9318,
+      "loss": 24.8683,
       "step": 5
     },
     {
       "epoch": 0.31683168316831684,
-      "grad_norm": 140.07655334472656,
+      "grad_norm": 139.35531616210938,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 18.6597,
+      "loss": 18.6656,
       "step": 6
     },
     {
       "epoch": 0.3696369636963696,
-      "grad_norm": 134.88388061523438,
+      "grad_norm": 132.13233947753906,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 14.9552,
+      "loss": 14.8754,
       "step": 7
     },
     {
       "epoch": 0.42244224422442245,
-      "grad_norm": 63.23054122924805,
+      "grad_norm": 63.427032470703125,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 10.7139,
+      "loss": 10.6936,
       "step": 8
     },
     {
       "epoch": 0.4752475247524752,
-      "grad_norm": 71.05472564697266,
+      "grad_norm": 70.66545104980469,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 9.8416,
+      "loss": 9.8106,
       "step": 9
     },
     {
       "epoch": 0.528052805280528,
-      "grad_norm": 97.5541763305664,
+      "grad_norm": 97.06773376464844,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 19.9574,
+      "loss": 19.9034,
       "step": 10
     },
     {
       "epoch": 0.5808580858085809,
-      "grad_norm": 69.11842346191406,
+      "grad_norm": 69.93522644042969,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 11.0275,
+      "loss": 10.8521,
       "step": 11
     },
     {
       "epoch": 0.6336633663366337,
-      "grad_norm": 56.24506759643555,
+      "grad_norm": 57.24028396606445,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 10.1437,
+      "loss": 10.1543,
       "step": 12
     },
     {
       "epoch": 0.6864686468646864,
-      "grad_norm": 54.2360954284668,
+      "grad_norm": 57.92759323120117,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 7.8817,
+      "loss": 7.9742,
       "step": 13
     },
     {
       "epoch": 0.7392739273927392,
-      "grad_norm": 65.11487579345703,
+      "grad_norm": 64.80909729003906,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 9.9734,
+      "loss": 9.9122,
       "step": 14
     },
     {
       "epoch": 0.7920792079207921,
-      "grad_norm": 63.567726135253906,
+      "grad_norm": 62.86793518066406,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 8.4856,
+      "loss": 8.432,
       "step": 15
     },
     {
       "epoch": 0.8448844884488449,
-      "grad_norm": 54.104248046875,
+      "grad_norm": 56.4834098815918,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 5.8322,
+      "loss": 5.9763,
       "step": 16
     },
     {
       "epoch": 0.8976897689768977,
-      "grad_norm": 41.041969299316406,
+      "grad_norm": 40.859291076660156,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 3.4734,
+      "loss": 3.4547,
       "step": 17
     },
     {
       "epoch": 0.9504950495049505,
-      "grad_norm": 51.88878631591797,
+      "grad_norm": 50.14191436767578,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 3.058,
+      "loss": 2.9626,
       "step": 18
     },
     {
       "epoch": 1.033003300330033,
-      "grad_norm": 63.439964294433594,
+      "grad_norm": 71.62645721435547,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 5.4253,
+      "loss": 5.432,
       "step": 19
     },
     {
       "epoch": 1.0858085808580857,
-      "grad_norm": 48.61954116821289,
+      "grad_norm": 51.751678466796875,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 2.854,
+      "loss": 2.9714,
       "step": 20
     },
     {
       "epoch": 1.1386138613861387,
-      "grad_norm": 55.616329193115234,
+      "grad_norm": 71.75513458251953,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 2.0837,
+      "loss": 2.1652,
       "step": 21
     },
     {
       "epoch": 1.1914191419141915,
-      "grad_norm": 50.29981231689453,
+      "grad_norm": 51.177284240722656,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 1.5129,
+      "loss": 1.4909,
       "step": 22
     },
     {
       "epoch": 1.2442244224422443,
-      "grad_norm": 48.272666931152344,
+      "grad_norm": 72.12232208251953,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 1.6346,
+      "loss": 1.4707,
       "step": 23
     },
     {
       "epoch": 1.297029702970297,
-      "grad_norm": 82.75598907470703,
+      "grad_norm": 81.59396362304688,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 2.8828,
+      "loss": 2.5601,
       "step": 24
     },
     {
       "epoch": 1.3498349834983498,
-      "grad_norm": 55.31129837036133,
+      "grad_norm": 44.115966796875,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.9758,
+      "loss": 0.8231,
       "step": 25
     },
     {
       "epoch": 1.3498349834983498,
-      "eval_loss": 0.11382482945919037,
-      "eval_runtime": 4.569,
-      "eval_samples_per_second": 28.015,
-      "eval_steps_per_second": 3.502,
+      "eval_loss": 0.09059706330299377,
+      "eval_runtime": 4.6098,
+      "eval_samples_per_second": 27.767,
+      "eval_steps_per_second": 3.471,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fce2681dc79991c6f33e2d27573b5f6d6f5cf0f1fcde8d296e5d63aeff6c313b
+oid sha256:5dd421ee496f84b943e667379d94c279e81d013b511fd3641f3973aa3000a968
 size 6776