Training in progress, step 50, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "up_proj",
+    "o_proj",
     "down_proj",
-    "k_proj",
-    "q_proj",
     "gate_proj",
-    "up_proj",
-    "v_proj",
-    "o_proj"
+    "q_proj",
+    "k_proj",
+    "v_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 sha256:7b7d6717b6e5a10080e0402a8dc688f26cea0bbdf6305246d5ce4e732d87185c
+oid sha256:2457b8d3d9a9666343c17fe1ff37135875d254798359c1e9f3d7798ff54d1d00
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93c66886dc00818e0a2ad46050833941e9434a416bbd873066067865362ea227
+oid sha256:6a7ae23786a395cb7209262a87fe44f94b0ea72ef69b6aa9a41dfe600e83446d
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52d687f2290abf6a3c03da45fc431d7e94b763bb7bb57edd8b466963213dccfa
-size 15024
+oid sha256:98f30f9dc55e51536222b0fb6c0ad64960ffdd14f575f8e362fe66f12fd40b22
+size 14960

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 1.5106881856918335,
+  "best_metric": 1.5109426975250244,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
   "epoch": 2.6058631921824107,
   "eval_steps": 25,
@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.05211726384364821,
-      "grad_norm": 0.2577638030052185,
+      "grad_norm": 0.2549949288368225,
       "learning_rate": 5e-05,
       "loss": 1.5446,
       "step": 1
@@ -18,368 +18,368 @@
     {
       "epoch": 0.05211726384364821,
       "eval_loss": 1.7352440357208252,
-      "eval_runtime": 1.5453,
-      "eval_samples_per_second": 84.128,
-      "eval_steps_per_second": 11.001,
+      "eval_runtime": 1.567,
+      "eval_samples_per_second": 82.962,
+      "eval_steps_per_second": 10.849,
       "step": 1
     },
     {
       "epoch": 0.10423452768729642,
-      "grad_norm": 0.318787544965744,
+      "grad_norm": 0.31440269947052,
       "learning_rate": 0.0001,
       "loss": 1.67,
       "step": 2
     },
     {
       "epoch": 0.1563517915309446,
-      "grad_norm": 0.37061601877212524,
+      "grad_norm": 0.3652706742286682,
       "learning_rate": 9.989294616193017e-05,
-      "loss": 1.7674,
+      "loss": 1.7672,
       "step": 3
     },
     {
       "epoch": 0.20846905537459284,
-      "grad_norm": 0.40831488370895386,
+      "grad_norm": 0.4043881595134735,
       "learning_rate": 9.957224306869053e-05,
-      "loss": 1.7715,
+      "loss": 1.7733,
       "step": 4
     },
     {
       "epoch": 0.26058631921824105,
-      "grad_norm": 0.30434590578079224,
+      "grad_norm": 0.2993297278881073,
       "learning_rate": 9.903926402016153e-05,
-      "loss": 1.6535,
+      "loss": 1.6546,
       "step": 5
     },
     {
       "epoch": 0.3127035830618892,
-      "grad_norm": 0.23065593838691711,
+      "grad_norm": 0.2248372882604599,
       "learning_rate": 9.829629131445342e-05,
       "loss": 1.5188,
       "step": 6
     },
     {
       "epoch": 0.36482084690553745,
-      "grad_norm": 0.2754242718219757,
+      "grad_norm": 0.2682330906391144,
       "learning_rate": 9.73465064747553e-05,
-      "loss": 1.5627,
+      "loss": 1.5629,
       "step": 7
     },
     {
       "epoch": 0.4169381107491857,
-      "grad_norm": 0.29511553049087524,
+      "grad_norm": 0.2943899631500244,
       "learning_rate": 9.619397662556435e-05,
-      "loss": 1.6488,
+      "loss": 1.6496,
       "step": 8
     },
     {
       "epoch": 0.46905537459283386,
-      "grad_norm": 0.33961331844329834,
+      "grad_norm": 0.33675816655158997,
       "learning_rate": 9.484363707663442e-05,
-      "loss": 1.638,
+      "loss": 1.6385,
       "step": 9
     },
     {
       "epoch": 0.5211726384364821,
-      "grad_norm": 0.23454448580741882,
+      "grad_norm": 0.22509494423866272,
       "learning_rate": 9.330127018922194e-05,
       "loss": 1.5451,
       "step": 10
     },
     {
       "epoch": 0.5732899022801303,
-      "grad_norm": 0.22723951935768127,
+      "grad_norm": 0.22699198126792908,
       "learning_rate": 9.157348061512727e-05,
       "loss": 1.4938,
       "step": 11
     },
     {
       "epoch": 0.6254071661237784,
-      "grad_norm": 0.23099200427532196,
+      "grad_norm": 0.23530082404613495,
       "learning_rate": 8.966766701456177e-05,
-      "loss": 1.5569,
+      "loss": 1.5573,
       "step": 12
     },
     {
       "epoch": 0.6775244299674267,
-      "grad_norm": 0.2532730996608734,
+      "grad_norm": 0.2717456519603729,
       "learning_rate": 8.759199037394887e-05,
-      "loss": 1.6177,
+      "loss": 1.6186,
       "step": 13
     },
     {
       "epoch": 0.7296416938110749,
-      "grad_norm": 0.35024064779281616,
+      "grad_norm": 0.37839096784591675,
       "learning_rate": 8.535533905932738e-05,
-      "loss": 1.6219,
+      "loss": 1.6221,
       "step": 14
     },
     {
       "epoch": 0.7817589576547231,
-      "grad_norm": 0.19632823765277863,
+      "grad_norm": 0.19509711861610413,
       "learning_rate": 8.296729075500344e-05,
-      "loss": 1.5136,
+      "loss": 1.5138,
       "step": 15
     },
     {
       "epoch": 0.8338762214983714,
-      "grad_norm": 0.17742136120796204,
+      "grad_norm": 0.17660491168498993,
       "learning_rate": 8.043807145043604e-05,
-      "loss": 1.5131,
+      "loss": 1.5128,
       "step": 16
     },
     {
       "epoch": 0.8859934853420195,
-      "grad_norm": 0.173045814037323,
+      "grad_norm": 0.1734020709991455,
       "learning_rate": 7.777851165098012e-05,
-      "loss": 1.5647,
+      "loss": 1.5646,
       "step": 17
     },
     {
       "epoch": 0.9381107491856677,
-      "grad_norm": 0.2047812044620514,
+      "grad_norm": 0.20527638494968414,
       "learning_rate": 7.500000000000001e-05,
-      "loss": 1.5951,
+      "loss": 1.5953,
       "step": 18
     },
     {
       "epoch": 0.990228013029316,
-      "grad_norm": 0.2845378518104553,
+      "grad_norm": 0.2814466953277588,
       "learning_rate": 7.211443451095007e-05,
-      "loss": 1.5726,
+      "loss": 1.5729,
       "step": 19
     },
     {
       "epoch": 1.0423452768729642,
-      "grad_norm": 0.36903002858161926,
+      "grad_norm": 0.3659859001636505,
       "learning_rate": 6.91341716182545e-05,
-      "loss": 2.7558,
+      "loss": 2.7583,
       "step": 20
     },
     {
       "epoch": 1.0944625407166124,
-      "grad_norm": 0.15977373719215393,
+      "grad_norm": 0.1582447737455368,
       "learning_rate": 6.607197326515808e-05,
-      "loss": 1.491,
+      "loss": 1.4914,
       "step": 21
     },
     {
       "epoch": 1.1465798045602607,
-      "grad_norm": 0.17592281103134155,
+      "grad_norm": 0.17426688969135284,
       "learning_rate": 6.294095225512603e-05,
-      "loss": 1.5314,
+      "loss": 1.5322,
       "step": 22
     },
     {
       "epoch": 1.1986970684039089,
-      "grad_norm": 0.20101827383041382,
+      "grad_norm": 0.19917459785938263,
       "learning_rate": 5.9754516100806423e-05,
-      "loss": 1.5439,
+      "loss": 1.5445,
       "step": 23
     },
     {
       "epoch": 1.2508143322475571,
-      "grad_norm": 0.17436598241329193,
+      "grad_norm": 0.17322319746017456,
       "learning_rate": 5.6526309611002594e-05,
-      "loss": 1.1265,
+      "loss": 1.127,
       "step": 24
     },
     {
       "epoch": 1.3029315960912053,
-      "grad_norm": 0.1876562386751175,
+      "grad_norm": 0.18828198313713074,
       "learning_rate": 5.327015646150716e-05,
       "loss": 1.8535,
       "step": 25
     },
     {
       "epoch": 1.3029315960912053,
-      "eval_loss": 1.5216573476791382,
-      "eval_runtime": 1.5463,
-      "eval_samples_per_second": 84.073,
-      "eval_steps_per_second": 10.994,
+      "eval_loss": 1.5218009948730469,
+      "eval_runtime": 1.5723,
+      "eval_samples_per_second": 82.68,
+      "eval_steps_per_second": 10.812,
       "step": 25
     },
     {
       "epoch": 1.3550488599348534,
-      "grad_norm": 0.16081880033016205,
+      "grad_norm": 0.1617686152458191,
       "learning_rate": 5e-05,
-      "loss": 1.4835,
+      "loss": 1.4842,
       "step": 26
     },
     {
       "epoch": 1.4071661237785016,
-      "grad_norm": 0.18758077919483185,
+      "grad_norm": 0.18733806908130646,
       "learning_rate": 4.6729843538492847e-05,
-      "loss": 1.5511,
+      "loss": 1.5518,
       "step": 27
     },
     {
       "epoch": 1.4592833876221498,
-      "grad_norm": 0.2091963291168213,
+      "grad_norm": 0.2076980471611023,
       "learning_rate": 4.347369038899744e-05,
-      "loss": 1.5754,
+      "loss": 1.5763,
       "step": 28
     },
     {
       "epoch": 1.511400651465798,
-      "grad_norm": 0.15385547280311584,
+      "grad_norm": 0.15251806378364563,
       "learning_rate": 4.0245483899193595e-05,
-      "loss": 1.3026,
+      "loss": 1.3035,
       "step": 29
     },
     {
       "epoch": 1.5635179153094463,
-      "grad_norm": 0.1666935831308365,
+      "grad_norm": 0.16386252641677856,
       "learning_rate": 3.705904774487396e-05,
-      "loss": 1.6025,
+      "loss": 1.6028,
       "step": 30
     },
     {
       "epoch": 1.6156351791530945,
-      "grad_norm": 0.16534046828746796,
+      "grad_norm": 0.1646316945552826,
       "learning_rate": 3.392802673484193e-05,
-      "loss": 1.4696,
+      "loss": 1.4706,
       "step": 31
     },
     {
       "epoch": 1.6677524429967425,
-      "grad_norm": 0.19742794334888458,
+      "grad_norm": 0.197561576962471,
       "learning_rate": 3.086582838174551e-05,
-      "loss": 1.5445,
+      "loss": 1.5451,
       "step": 32
     },
     {
       "epoch": 1.7198697068403908,
-      "grad_norm": 0.22989995777606964,
+      "grad_norm": 0.22872388362884521,
       "learning_rate": 2.7885565489049946e-05,
-      "loss": 1.5685,
+      "loss": 1.5693,
       "step": 33
     },
     {
       "epoch": 1.771986970684039,
-      "grad_norm": 0.1536884307861328,
+      "grad_norm": 0.15276600420475006,
       "learning_rate": 2.500000000000001e-05,
-      "loss": 1.3685,
+      "loss": 1.3688,
       "step": 34
     },
     {
       "epoch": 1.8241042345276872,
-      "grad_norm": 0.1617068499326706,
+      "grad_norm": 0.15943904221057892,
       "learning_rate": 2.2221488349019903e-05,
-      "loss": 1.5156,
+      "loss": 1.5154,
       "step": 35
     },
     {
       "epoch": 1.8762214983713354,
-      "grad_norm": 0.17375367879867554,
+      "grad_norm": 0.1730474829673767,
       "learning_rate": 1.9561928549563968e-05,
-      "loss": 1.4867,
+      "loss": 1.4873,
       "step": 36
     },
     {
       "epoch": 1.9283387622149837,
-      "grad_norm": 0.19562163949012756,
+      "grad_norm": 0.19471915066242218,
       "learning_rate": 1.703270924499656e-05,
-      "loss": 1.5347,
+      "loss": 1.5353,
       "step": 37
     },
     {
       "epoch": 1.980456026058632,
-      "grad_norm": 0.27919065952301025,
+      "grad_norm": 0.27787989377975464,
       "learning_rate": 1.4644660940672627e-05,
-      "loss": 1.5318,
+      "loss": 1.5332,
       "step": 38
     },
     {
       "epoch": 2.03257328990228,
-      "grad_norm": 0.37415021657943726,
+      "grad_norm": 0.37134087085723877,
       "learning_rate": 1.2408009626051137e-05,
-      "loss": 2.6431,
+      "loss": 2.6427,
       "step": 39
     },
     {
       "epoch": 2.0846905537459284,
-      "grad_norm": 0.14578774571418762,
+      "grad_norm": 0.14338725805282593,
       "learning_rate": 1.0332332985438248e-05,
-      "loss": 1.3894,
+      "loss": 1.3897,
       "step": 40
     },
     {
       "epoch": 2.1368078175895766,
-      "grad_norm": 0.1634012907743454,
+      "grad_norm": 0.16175779700279236,
       "learning_rate": 8.426519384872733e-06,
-      "loss": 1.4961,
+      "loss": 1.4962,
       "step": 41
     },
     {
       "epoch": 2.188925081433225,
-      "grad_norm": 0.19175274670124054,
+      "grad_norm": 0.19053548574447632,
       "learning_rate": 6.698729810778065e-06,
-      "loss": 1.4962,
+      "loss": 1.4976,
       "step": 42
     },
     {
       "epoch": 2.241042345276873,
-      "grad_norm": 0.18947741389274597,
+      "grad_norm": 0.18777604401111603,
       "learning_rate": 5.156362923365588e-06,
-      "loss": 1.0892,
+      "loss": 1.0901,
       "step": 43
     },
     {
       "epoch": 2.2931596091205213,
-      "grad_norm": 0.20050141215324402,
+      "grad_norm": 0.1998460441827774,
       "learning_rate": 3.8060233744356633e-06,
-      "loss": 1.8695,
+      "loss": 1.8703,
       "step": 44
     },
     {
       "epoch": 2.3452768729641695,
-      "grad_norm": 0.1535215675830841,
+      "grad_norm": 0.1519627869129181,
       "learning_rate": 2.653493525244721e-06,
-      "loss": 1.4547,
+      "loss": 1.4546,
       "step": 45
     },
     {
       "epoch": 2.3973941368078178,
-      "grad_norm": 0.17014193534851074,
+      "grad_norm": 0.1694892942905426,
       "learning_rate": 1.70370868554659e-06,
-      "loss": 1.4896,
+      "loss": 1.4899,
       "step": 46
     },
     {
       "epoch": 2.449511400651466,
-      "grad_norm": 0.20422467589378357,
+      "grad_norm": 0.2037765234708786,
       "learning_rate": 9.607359798384785e-07,
-      "loss": 1.5507,
+      "loss": 1.5511,
       "step": 47
     },
     {
       "epoch": 2.5016286644951142,
-      "grad_norm": 0.16903725266456604,
+      "grad_norm": 0.16793659329414368,
       "learning_rate": 4.277569313094809e-07,
-      "loss": 1.0547,
+      "loss": 1.0556,
       "step": 48
     },
     {
       "epoch": 2.5537459283387625,
-      "grad_norm": 0.18690481781959534,
+      "grad_norm": 0.18593494594097137,
       "learning_rate": 1.0705383806982606e-07,
-      "loss": 1.8281,
+      "loss": 1.8283,
       "step": 49
     },
     {
       "epoch": 2.6058631921824107,
-      "grad_norm": 0.16421981155872345,
+      "grad_norm": 0.16320839524269104,
       "learning_rate": 0.0,
-      "loss": 1.4566,
+      "loss": 1.4568,
       "step": 50
     },
     {
       "epoch": 2.6058631921824107,
-      "eval_loss": 1.5106881856918335,
-      "eval_runtime": 1.5489,
-      "eval_samples_per_second": 83.931,
-      "eval_steps_per_second": 10.976,
+      "eval_loss": 1.5109426975250244,
+      "eval_runtime": 1.5706,
+      "eval_samples_per_second": 82.772,
+      "eval_steps_per_second": 10.824,
       "step": 50
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:083197ba65aafc31c05e970d5bb261f2b820c41cba8a95f470b8bd4a25560910
+oid sha256:cebc5e5b27fdeab60524468d1d81248313288b98f84295a55b46920331961701
 size 6776