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",
-    "o_proj",
-    "down_proj",
     "up_proj",
     "k_proj",
-    "v_proj"
+    "gate_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_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:ecbe4aa6759e37ce5ee40525bf9ab790ebdd33781d1e2000ebcb4d9483dcd2d8
+oid sha256:0ff36bf9c3d605bf4fd2f18ad5d7ba9a006eaf187d403e11fe9655678f2ccaaf
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5136dcf725297af4ab2f2ef0f45aa710e7d6e49e8271a64de6e99408406d4a70
+oid sha256:5f2db582d2898890a5a35f9ea78fe2eeb1738011c8d6ebbd89fdda3c22f73a42
 size 864785974

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.789313018321991,
+  "best_metric": 0.7922340035438538,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
   "epoch": 0.7326007326007326,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.029304029304029304,
-      "grad_norm": 42.63615417480469,
+      "grad_norm": 42.315101623535156,
       "learning_rate": 5e-05,
       "loss": 10.8108,
       "step": 1
@@ -18,185 +18,185 @@
     {
       "epoch": 0.029304029304029304,
       "eval_loss": 11.66943359375,
-      "eval_runtime": 12.0274,
-      "eval_samples_per_second": 19.123,
-      "eval_steps_per_second": 2.411,
+      "eval_runtime": 12.0921,
+      "eval_samples_per_second": 19.021,
+      "eval_steps_per_second": 2.398,
       "step": 1
     },
     {
       "epoch": 0.05860805860805861,
-      "grad_norm": 43.70536804199219,
+      "grad_norm": 43.577064514160156,
       "learning_rate": 0.0001,
       "loss": 11.4368,
       "step": 2
     },
     {
       "epoch": 0.08791208791208792,
-      "grad_norm": 30.874406814575195,
+      "grad_norm": 31.090862274169922,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 8.1072,
+      "loss": 8.1051,
       "step": 3
     },
     {
       "epoch": 0.11721611721611722,
-      "grad_norm": 17.766359329223633,
+      "grad_norm": 17.739784240722656,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 3.914,
+      "loss": 3.8912,
       "step": 4
     },
     {
       "epoch": 0.14652014652014653,
-      "grad_norm": 10.942605972290039,
+      "grad_norm": 10.802330017089844,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 2.2661,
+      "loss": 2.2566,
       "step": 5
     },
     {
       "epoch": 0.17582417582417584,
-      "grad_norm": 4.077508926391602,
+      "grad_norm": 4.046825408935547,
       "learning_rate": 9.829629131445342e-05,
-      "loss": 1.1809,
+      "loss": 1.178,
       "step": 6
     },
     {
       "epoch": 0.20512820512820512,
-      "grad_norm": 4.200634479522705,
+      "grad_norm": 4.262223720550537,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 1.0111,
+      "loss": 1.0102,
       "step": 7
     },
     {
       "epoch": 0.23443223443223443,
-      "grad_norm": 2.5703258514404297,
+      "grad_norm": 2.372178792953491,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 0.9798,
+      "loss": 0.9741,
       "step": 8
     },
     {
       "epoch": 0.26373626373626374,
-      "grad_norm": 1.4646650552749634,
+      "grad_norm": 1.6314536333084106,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 0.8646,
+      "loss": 0.8676,
       "step": 9
     },
     {
       "epoch": 0.29304029304029305,
-      "grad_norm": 1.0245696306228638,
+      "grad_norm": 1.1375904083251953,
       "learning_rate": 9.330127018922194e-05,
-      "loss": 0.7594,
+      "loss": 0.7656,
       "step": 10
     },
     {
       "epoch": 0.32234432234432236,
-      "grad_norm": 0.7607440948486328,
+      "grad_norm": 0.7322179675102234,
       "learning_rate": 9.157348061512727e-05,
-      "loss": 0.7369,
+      "loss": 0.738,
       "step": 11
     },
     {
       "epoch": 0.3516483516483517,
-      "grad_norm": 1.600371241569519,
+      "grad_norm": 1.6381927728652954,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 0.8084,
+      "loss": 0.8121,
       "step": 12
     },
     {
       "epoch": 0.38095238095238093,
-      "grad_norm": 1.577329397201538,
+      "grad_norm": 1.6779375076293945,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 0.7607,
+      "loss": 0.7658,
       "step": 13
     },
     {
       "epoch": 0.41025641025641024,
-      "grad_norm": 1.0018422603607178,
+      "grad_norm": 0.8208694458007812,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 0.8165,
+      "loss": 0.8118,
       "step": 14
     },
     {
       "epoch": 0.43956043956043955,
-      "grad_norm": 0.8424701690673828,
+      "grad_norm": 0.7266029119491577,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 0.8129,
+      "loss": 0.8152,
       "step": 15
     },
     {
       "epoch": 0.46886446886446886,
-      "grad_norm": 0.5086039900779724,
+      "grad_norm": 0.49156033992767334,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 0.8195,
+      "loss": 0.8198,
       "step": 16
     },
     {
       "epoch": 0.4981684981684982,
-      "grad_norm": 0.6842309236526489,
+      "grad_norm": 0.6357100009918213,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 0.8075,
+      "loss": 0.8063,
       "step": 17
     },
     {
       "epoch": 0.5274725274725275,
-      "grad_norm": 0.6705095767974854,
+      "grad_norm": 0.6192078590393066,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 0.7247,
+      "loss": 0.7221,
       "step": 18
     },
     {
       "epoch": 0.5567765567765568,
-      "grad_norm": 0.24981459975242615,
+      "grad_norm": 0.23790700733661652,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 0.741,
+      "loss": 0.7403,
       "step": 19
     },
     {
       "epoch": 0.5860805860805861,
-      "grad_norm": 0.3129333257675171,
+      "grad_norm": 0.3375350534915924,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 0.7393,
+      "loss": 0.7381,
       "step": 20
     },
     {
       "epoch": 0.6153846153846154,
-      "grad_norm": 0.7338513135910034,
+      "grad_norm": 0.7117923498153687,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 0.7904,
+      "loss": 0.7848,
       "step": 21
     },
     {
       "epoch": 0.6446886446886447,
-      "grad_norm": 1.3784418106079102,
+      "grad_norm": 1.3936290740966797,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 0.8909,
+      "loss": 0.8916,
       "step": 22
     },
     {
       "epoch": 0.673992673992674,
-      "grad_norm": 0.8394548296928406,
+      "grad_norm": 0.8301817178726196,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 0.8305,
+      "loss": 0.83,
       "step": 23
     },
     {
       "epoch": 0.7032967032967034,
-      "grad_norm": 0.29354768991470337,
+      "grad_norm": 0.2933414578437805,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 0.8116,
+      "loss": 0.8132,
       "step": 24
     },
     {
       "epoch": 0.7326007326007326,
-      "grad_norm": 0.3640207350254059,
+      "grad_norm": 0.3536495268344879,
       "learning_rate": 5.327015646150716e-05,
-      "loss": 0.8095,
+      "loss": 0.8106,
       "step": 25
     },
     {
       "epoch": 0.7326007326007326,
-      "eval_loss": 0.789313018321991,
-      "eval_runtime": 12.0233,
-      "eval_samples_per_second": 19.13,
-      "eval_steps_per_second": 2.412,
+      "eval_loss": 0.7922340035438538,
+      "eval_runtime": 12.0794,
+      "eval_samples_per_second": 19.041,
+      "eval_steps_per_second": 2.401,
       "step": 25
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768050f293879227102c7c91bc296e82e7ed39164763de483fc202082d0b9cf5
+oid sha256:071494bbe95931a08631bf47f2dba38f70b866d5bb370d5380baf7279eff516c
 size 6776