Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "qkv_proj",
     "o_proj",
+    "down_proj",
     "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84ae780f75d0439f859b119d24ab01310419ab78f060cb4f95e2d37463210827
+oid sha256:ef7aa1ad3133f7c084d92b42411b3352f03041e55803e0729e6e094fe1999ee6
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8af342710945115f6f9ee024ac84f34199f726b4994ca8ecb904f139f8ef59
+oid sha256:ebc796025b869ce96594882df58f996e9964d53b03548ee20ace609fea30ab99
 size 402868986

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.235469788312912,
+  "best_metric": 0.23452582955360413,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 0.01297016861219196,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.0005188067444876783,
-      "grad_norm": 7.257709980010986,
+      "grad_norm": 7.088029384613037,
       "learning_rate": 5e-05,
       "loss": 0.8421,
       "step": 1
@@ -18,185 +18,185 @@
     {
       "epoch": 0.0005188067444876783,
       "eval_loss": 0.9019366502761841,
-      "eval_runtime": 437.3032,
-      "eval_samples_per_second": 29.693,
-      "eval_steps_per_second": 3.714,
+      "eval_runtime": 439.5345,
+      "eval_samples_per_second": 29.543,
+      "eval_steps_per_second": 3.695,
       "step": 1
     },
     {
       "epoch": 0.0010376134889753567,
-      "grad_norm": 9.514312744140625,
+      "grad_norm": 9.270331382751465,
       "learning_rate": 0.0001,
       "loss": 0.7793,
       "step": 2
     },
     {
       "epoch": 0.0015564202334630351,
-      "grad_norm": 13.657303810119629,
+      "grad_norm": 13.402799606323242,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 0.8538,
+      "loss": 0.8548,
       "step": 3
     },
     {
       "epoch": 0.0020752269779507134,
-      "grad_norm": 13.498005867004395,
+      "grad_norm": 13.478734016418457,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 0.7789,
+      "loss": 0.7784,
       "step": 4
     },
     {
       "epoch": 0.0025940337224383916,
-      "grad_norm": 15.755859375,
+      "grad_norm": 15.679061889648438,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 0.6017,
+      "loss": 0.596,
       "step": 5
     },
     {
       "epoch": 0.0031128404669260703,
-      "grad_norm": 13.434879302978516,
+      "grad_norm": 13.199936866760254,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 0.4315,
+      "loss": 0.4246,
       "step": 6
     },
     {
       "epoch": 0.0036316472114137485,
-      "grad_norm": 8.647991180419922,
+      "grad_norm": 8.329848289489746,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 0.2934,
+      "loss": 0.2895,
       "step": 7
     },
     {
       "epoch": 0.004150453955901427,
-      "grad_norm": 5.960851192474365,
+      "grad_norm": 5.857521057128906,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 0.2742,
+      "loss": 0.2731,
       "step": 8
     },
     {
       "epoch": 0.004669260700389105,
-      "grad_norm": 5.692524433135986,
+      "grad_norm": 5.562647342681885,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.254,
+      "loss": 0.2526,
       "step": 9
     },
     {
       "epoch": 0.005188067444876783,
-      "grad_norm": 6.573745250701904,
+      "grad_norm": 6.4964423179626465,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 0.266,
+      "loss": 0.2667,
       "step": 10
     },
     {
       "epoch": 0.005706874189364461,
-      "grad_norm": 7.913269996643066,
+      "grad_norm": 7.804101467132568,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 0.2703,
+      "loss": 0.2699,
       "step": 11
     },
     {
       "epoch": 0.0062256809338521405,
-      "grad_norm": 7.290318489074707,
+      "grad_norm": 7.244912147521973,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 0.202,
+      "loss": 0.2022,
       "step": 12
     },
     {
       "epoch": 0.006744487678339819,
-      "grad_norm": 10.77153491973877,
+      "grad_norm": 10.575514793395996,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 0.5624,
+      "loss": 0.5618,
       "step": 13
     },
     {
       "epoch": 0.007263294422827497,
-      "grad_norm": 13.511357307434082,
+      "grad_norm": 13.16678524017334,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 0.5687,
+      "loss": 0.564,
       "step": 14
     },
     {
       "epoch": 0.007782101167315175,
-      "grad_norm": 9.808670043945312,
+      "grad_norm": 9.636844635009766,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.4122,
+      "loss": 0.4095,
       "step": 15
     },
     {
       "epoch": 0.008300907911802853,
-      "grad_norm": 7.290343761444092,
+      "grad_norm": 7.153684139251709,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.2995,
+      "loss": 0.2974,
       "step": 16
     },
     {
       "epoch": 0.008819714656290532,
-      "grad_norm": 8.092347145080566,
+      "grad_norm": 7.988699913024902,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.3212,
+      "loss": 0.3181,
       "step": 17
     },
     {
       "epoch": 0.00933852140077821,
-      "grad_norm": 9.879920959472656,
+      "grad_norm": 9.76743221282959,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.2751,
+      "loss": 0.2727,
       "step": 18
     },
     {
       "epoch": 0.009857328145265888,
-      "grad_norm": 7.612329483032227,
+      "grad_norm": 7.5284318923950195,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.2201,
+      "loss": 0.2183,
       "step": 19
     },
     {
       "epoch": 0.010376134889753566,
-      "grad_norm": 5.5150322914123535,
+      "grad_norm": 5.3470563888549805,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.1909,
+      "loss": 0.1889,
       "step": 20
     },
     {
       "epoch": 0.010894941634241245,
-      "grad_norm": 3.7366225719451904,
+      "grad_norm": 3.7029356956481934,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.1765,
+      "loss": 0.1763,
       "step": 21
     },
     {
       "epoch": 0.011413748378728923,
-      "grad_norm": 4.036696434020996,
+      "grad_norm": 4.031704425811768,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.1671,
+      "loss": 0.1656,
       "step": 22
     },
     {
       "epoch": 0.011932555123216601,
-      "grad_norm": 5.270599365234375,
+      "grad_norm": 5.219779014587402,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.1808,
+      "loss": 0.1802,
       "step": 23
     },
     {
       "epoch": 0.012451361867704281,
-      "grad_norm": 8.023921012878418,
+      "grad_norm": 7.983980178833008,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.2025,
+      "loss": 0.2019,
       "step": 24
     },
     {
       "epoch": 0.01297016861219196,
-      "grad_norm": 8.021526336669922,
+      "grad_norm": 8.021879196166992,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.2274,
+      "loss": 0.2279,
       "step": 25
     },
     {
       "epoch": 0.01297016861219196,
-      "eval_loss": 0.235469788312912,
-      "eval_runtime": 437.5793,
-      "eval_samples_per_second": 29.675,
-      "eval_steps_per_second": 3.711,
+      "eval_loss": 0.23452582955360413,
+      "eval_runtime": 439.5012,
+      "eval_samples_per_second": 29.545,
+      "eval_steps_per_second": 3.695,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b4c867fc22c662d2eb55140f540ec9341dba7a58b87b7576d7182430af5852d
+oid sha256:32c9a617800bcf00617a974e9c1ac0e7ad0ab0a36eece5b682859f66cccab4d2
 size 6776