Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -22,8 +22,8 @@
   "target_modules": [
     "down_proj",
     "gate_up_proj",
-    "qkv_proj",
-    "o_proj"
+    "o_proj",
+    "qkv_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:da61ffd28a471bbd48d907eda6fcb8bca5d298867b170d0d914a9d7cf2875945
+oid sha256:357d35084e68617f7cdee2d4336d7568d5ee18d30b2ca4dc01ef3db5063be1f4
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba6b32acc56466e9f832d53cff699ec6351b17d1a635b397dcbf4b1b4eea59e2
+oid sha256:42dcfdb86818d4bd0894b7263487ba73283ec84b82a03b82409dedefab94fc21
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd2aaa457d929f461cdc1cea356aff643a761d7d75efe9fe19c192bf86f6928
+oid sha256:eea4de1cc4842f65adeacc3d4a3f7494157fc96b8a830e7266bb471df5d24409
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af4eb15f8fa6904c571192035c0d85b8f2a260ed1e5c31bdc91c1c16431f79ec
+oid sha256:d0e96d75f16313745b98055c980041ef43dd747de64cc92e2b020ac77f80c519
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5413ae07f66230c8b4942b62857f3047f6165ab092681ade342b7558f8e1133
+oid sha256:6b7e3da4d46cf1158634756d333b0fbe8991960ef54757ae7dff7193156407c7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:202bbb71bb01d11f862f4db4a44980327737ae98d39c52e3985f65547c8b7d40
+oid sha256:e5c05a533f4305c3ac7234753323d943feafef4ddb3d62bec8eecb4b254a7cfb
 size 15024

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.06485110521316528,
+  "best_metric": 0.06404294073581696,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 0.2107481559536354,
   "eval_steps": 25,
@@ -10,193 +10,193 @@
   "log_history": [
     {
       "epoch": 0.008429926238145416,
-      "grad_norm": 1.3518892526626587,
+      "grad_norm": 1.3341302871704102,
       "learning_rate": 5e-05,
-      "loss": 1.7474,
+      "loss": 1.7493,
       "step": 1
     },
     {
       "epoch": 0.008429926238145416,
-      "eval_loss": 0.21345072984695435,
-      "eval_runtime": 68.629,
-      "eval_samples_per_second": 11.657,
-      "eval_steps_per_second": 1.457,
+      "eval_loss": 0.21355804800987244,
+      "eval_runtime": 128.7109,
+      "eval_samples_per_second": 6.215,
+      "eval_steps_per_second": 0.777,
       "step": 1
     },
     {
       "epoch": 0.01685985247629083,
-      "grad_norm": 1.6836062669754028,
+      "grad_norm": 1.6189820766448975,
       "learning_rate": 0.0001,
-      "loss": 1.5145,
+      "loss": 1.5138,
       "step": 2
     },
     {
       "epoch": 0.02528977871443625,
-      "grad_norm": 1.508198618888855,
+      "grad_norm": 1.9272456169128418,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.3162,
+      "loss": 1.3181,
       "step": 3
     },
     {
       "epoch": 0.03371970495258166,
-      "grad_norm": 1.0490714311599731,
+      "grad_norm": 1.0431249141693115,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 1.8503,
+      "loss": 1.8563,
       "step": 4
     },
     {
       "epoch": 0.04214963119072708,
-      "grad_norm": 0.97480309009552,
+      "grad_norm": 1.2577431201934814,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 1.3278,
+      "loss": 1.3348,
       "step": 5
     },
     {
       "epoch": 0.0505795574288725,
-      "grad_norm": 0.7965978384017944,
+      "grad_norm": 0.8566964864730835,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 1.3214,
+      "loss": 1.3272,
       "step": 6
     },
     {
       "epoch": 0.059009483667017915,
-      "grad_norm": 1.3504085540771484,
+      "grad_norm": 0.9277756214141846,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 1.4296,
+      "loss": 1.4395,
       "step": 7
     },
     {
       "epoch": 0.06743940990516333,
-      "grad_norm": 3.461765766143799,
+      "grad_norm": 1.50494384765625,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 1.9774,
+      "loss": 1.9858,
       "step": 8
     },
     {
       "epoch": 0.07586933614330875,
-      "grad_norm": 7.153843879699707,
+      "grad_norm": 6.605533599853516,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 5.7443,
+      "loss": 5.6619,
       "step": 9
     },
     {
       "epoch": 0.08429926238145416,
-      "grad_norm": 3.3547306060791016,
+      "grad_norm": 3.0556588172912598,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 1.0362,
+      "loss": 0.9706,
       "step": 10
     },
     {
       "epoch": 0.09272918861959958,
-      "grad_norm": 5.1782450675964355,
+      "grad_norm": 4.112440586090088,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 0.9484,
+      "loss": 0.9054,
       "step": 11
     },
     {
       "epoch": 0.101159114857745,
-      "grad_norm": 2.743224859237671,
+      "grad_norm": 2.5288426876068115,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 0.498,
+      "loss": 0.44,
       "step": 12
     },
     {
       "epoch": 0.1095890410958904,
-      "grad_norm": 2.1662654876708984,
+      "grad_norm": 2.0018320083618164,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 1.0388,
+      "loss": 0.9965,
       "step": 13
     },
     {
       "epoch": 0.11801896733403583,
-      "grad_norm": 1.461312174797058,
+      "grad_norm": 1.453355073928833,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 0.6449,
+      "loss": 0.6349,
       "step": 14
     },
     {
       "epoch": 0.12644889357218125,
-      "grad_norm": 1.1520819664001465,
+      "grad_norm": 1.1725133657455444,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.9421,
+      "loss": 0.9425,
       "step": 15
     },
     {
       "epoch": 0.13487881981032665,
-      "grad_norm": 0.8277627229690552,
+      "grad_norm": 0.9537891745567322,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.9109,
+      "loss": 0.9102,
       "step": 16
     },
     {
       "epoch": 0.14330874604847207,
-      "grad_norm": 1.0022519826889038,
+      "grad_norm": 1.0789560079574585,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 1.0969,
+      "loss": 1.0972,
       "step": 17
     },
     {
       "epoch": 0.1517386722866175,
-      "grad_norm": 0.969890832901001,
+      "grad_norm": 2.126995801925659,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 1.0802,
+      "loss": 1.0853,
       "step": 18
     },
     {
       "epoch": 0.1601685985247629,
-      "grad_norm": 1.401827096939087,
+      "grad_norm": 1.467456340789795,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 1.6649,
+      "loss": 1.6946,
       "step": 19
     },
     {
       "epoch": 0.16859852476290832,
-      "grad_norm": 1.4785505533218384,
+      "grad_norm": 1.6159006357192993,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 1.0116,
+      "loss": 1.0233,
       "step": 20
     },
     {
       "epoch": 0.17702845100105374,
-      "grad_norm": 3.7158868312835693,
+      "grad_norm": 3.9295225143432617,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 2.2352,
+      "loss": 2.2685,
       "step": 21
     },
     {
       "epoch": 0.18545837723919917,
-      "grad_norm": 4.5050578117370605,
+      "grad_norm": 5.1888909339904785,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 1.9199,
+      "loss": 1.9563,
       "step": 22
     },
     {
       "epoch": 0.19388830347734456,
-      "grad_norm": 0.5490809679031372,
+      "grad_norm": 0.7670079469680786,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.0866,
+      "loss": 0.096,
       "step": 23
     },
     {
       "epoch": 0.20231822971549,
-      "grad_norm": 0.7847179770469666,
+      "grad_norm": 0.6988094449043274,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.0969,
+      "loss": 0.0889,
       "step": 24
     },
     {
       "epoch": 0.2107481559536354,
-      "grad_norm": 1.2605834007263184,
+      "grad_norm": 0.9281933307647705,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.1191,
+      "loss": 0.1051,
       "step": 25
     },
     {
       "epoch": 0.2107481559536354,
-      "eval_loss": 0.06485110521316528,
-      "eval_runtime": 68.626,
-      "eval_samples_per_second": 11.657,
-      "eval_steps_per_second": 1.457,
+      "eval_loss": 0.06404294073581696,
+      "eval_runtime": 121.7973,
+      "eval_samples_per_second": 6.568,
+      "eval_steps_per_second": 0.821,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d19f2eb19899cd285a1c786aa566276856c41c6665698ec6b31d3befdba6e632
+oid sha256:8399d9ccd5298114cbc3d90c6beef8c39db2b62b38db86fce7c63e656b9f1612
 size 6776