Training in progress, step 25, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "gate_proj",
-    "k_proj",
-    "down_proj",
-    "v_proj",
     "o_proj",
-    "up_proj"
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "k_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 sha256:78b8921a0648ccb25da27fe3a18667ee514feab63b3df1b7d0dc3b82acf43eac
+oid sha256:6f97f42f718855e4d8fa458df3b67f585a5008107acd016298a8510d9593379c
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f90a2e4a3b9d2b6030c18beadd9582382d85389dbe8d7ea44a2bc373a6f332a
+oid sha256:c10f96f94824ff813ac88d30e9c1057e14cbf6d57a95b43cd900c9340690db88
 size 202110330

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5078209638595581,
+  "best_metric": 0.506989598274231,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 1.1016483516483517,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.04395604395604396,
-      "grad_norm": 1.5371962785720825,
+      "grad_norm": 1.6147027015686035,
       "learning_rate": 5e-05,
       "loss": 0.9245,
       "step": 1
@@ -18,185 +18,185 @@
     {
       "epoch": 0.04395604395604396,
       "eval_loss": 1.125306487083435,
-      "eval_runtime": 1.5464,
-      "eval_samples_per_second": 98.942,
-      "eval_steps_per_second": 12.934,
+      "eval_runtime": 1.5098,
+      "eval_samples_per_second": 101.338,
+      "eval_steps_per_second": 13.247,
       "step": 1
     },
     {
       "epoch": 0.08791208791208792,
-      "grad_norm": 1.9072893857955933,
+      "grad_norm": 1.9983218908309937,
       "learning_rate": 0.0001,
       "loss": 1.0253,
       "step": 2
     },
     {
       "epoch": 0.13186813186813187,
-      "grad_norm": 1.8387856483459473,
+      "grad_norm": 1.9161258935928345,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.0753,
+      "loss": 1.0749,
       "step": 3
     },
     {
       "epoch": 0.17582417582417584,
-      "grad_norm": 1.3083786964416504,
+      "grad_norm": 1.3471875190734863,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 0.9815,
+      "loss": 0.9817,
       "step": 4
     },
     {
       "epoch": 0.21978021978021978,
-      "grad_norm": 1.2645456790924072,
+      "grad_norm": 1.3092931509017944,
       "learning_rate": 9.903926402016153e-05,
       "loss": 0.9245,
       "step": 5
     },
     {
       "epoch": 0.26373626373626374,
-      "grad_norm": 0.8451499342918396,
+      "grad_norm": 0.8603388071060181,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 0.6823,
+      "loss": 0.6806,
       "step": 6
     },
     {
       "epoch": 0.3076923076923077,
-      "grad_norm": 0.7806383371353149,
+      "grad_norm": 0.7902740240097046,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 0.5938,
+      "loss": 0.5908,
       "step": 7
     },
     {
       "epoch": 0.3516483516483517,
-      "grad_norm": 0.7988596558570862,
+      "grad_norm": 0.7974825501441956,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 0.6745,
+      "loss": 0.6714,
       "step": 8
     },
     {
       "epoch": 0.3956043956043956,
-      "grad_norm": 0.5786975622177124,
+      "grad_norm": 0.5884117484092712,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.6528,
+      "loss": 0.6504,
       "step": 9
     },
     {
       "epoch": 0.43956043956043955,
-      "grad_norm": 0.7035933136940002,
+      "grad_norm": 0.7321068048477173,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 0.6902,
+      "loss": 0.6882,
       "step": 10
     },
     {
       "epoch": 0.4835164835164835,
-      "grad_norm": 0.8232611417770386,
+      "grad_norm": 0.8219019174575806,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 0.79,
+      "loss": 0.7878,
       "step": 11
     },
     {
       "epoch": 0.5274725274725275,
-      "grad_norm": 0.7220979928970337,
+      "grad_norm": 0.7585610151290894,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 0.5096,
+      "loss": 0.509,
       "step": 12
     },
     {
       "epoch": 0.5714285714285714,
-      "grad_norm": 0.4586591422557831,
+      "grad_norm": 0.4833940267562866,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 0.5134,
+      "loss": 0.5126,
       "step": 13
     },
     {
       "epoch": 0.6153846153846154,
-      "grad_norm": 0.48070022463798523,
+      "grad_norm": 0.5011129379272461,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 0.5731,
+      "loss": 0.5713,
       "step": 14
     },
     {
       "epoch": 0.6593406593406593,
-      "grad_norm": 0.5730169415473938,
+      "grad_norm": 0.5959790945053101,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.6391,
+      "loss": 0.6383,
       "step": 15
     },
     {
       "epoch": 0.7032967032967034,
-      "grad_norm": 0.4397137761116028,
+      "grad_norm": 0.45197582244873047,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.6148,
+      "loss": 0.6132,
       "step": 16
     },
     {
       "epoch": 0.7472527472527473,
-      "grad_norm": 0.4415135085582733,
+      "grad_norm": 0.44793838262557983,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.527,
+      "loss": 0.5253,
       "step": 17
     },
     {
       "epoch": 0.7912087912087912,
-      "grad_norm": 0.47121483087539673,
+      "grad_norm": 0.47516193985939026,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.4637,
+      "loss": 0.4624,
       "step": 18
     },
     {
       "epoch": 0.8351648351648352,
-      "grad_norm": 0.35576266050338745,
+      "grad_norm": 0.3715343177318573,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.479,
+      "loss": 0.4779,
       "step": 19
     },
     {
       "epoch": 0.8791208791208791,
-      "grad_norm": 0.3464816212654114,
+      "grad_norm": 0.3526500165462494,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.5275,
+      "loss": 0.5268,
       "step": 20
     },
     {
       "epoch": 0.9230769230769231,
-      "grad_norm": 0.4190969169139862,
+      "grad_norm": 0.42601215839385986,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.613,
+      "loss": 0.6127,
       "step": 21
     },
     {
       "epoch": 0.967032967032967,
-      "grad_norm": 0.5241257548332214,
+      "grad_norm": 0.5091745257377625,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.6681,
+      "loss": 0.6665,
       "step": 22
     },
     {
       "epoch": 1.0137362637362637,
-      "grad_norm": 0.475443035364151,
+      "grad_norm": 0.49048399925231934,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.6159,
+      "loss": 0.6154,
       "step": 23
     },
     {
       "epoch": 1.0576923076923077,
-      "grad_norm": 0.36700522899627686,
+      "grad_norm": 0.3723498284816742,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.4199,
+      "loss": 0.4186,
       "step": 24
     },
     {
       "epoch": 1.1016483516483517,
-      "grad_norm": 0.32403191924095154,
+      "grad_norm": 0.33258843421936035,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.4759,
+      "loss": 0.4749,
       "step": 25
     },
     {
       "epoch": 1.1016483516483517,
-      "eval_loss": 0.5078209638595581,
-      "eval_runtime": 1.5369,
-      "eval_samples_per_second": 99.554,
-      "eval_steps_per_second": 13.014,
+      "eval_loss": 0.506989598274231,
+      "eval_runtime": 1.5047,
+      "eval_samples_per_second": 101.683,
+      "eval_steps_per_second": 13.292,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ab06be51039df455003f8feb3e74f379f65814e8310c29b4150b77286ba1778
+oid sha256:4e4d513a4abdd668e3a6ca19a017616fa49a05ff1c07caf387c8770c410e006d
 size 6776