Upload folder using huggingface_hub

adapter_config.json

@@ -23,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
+    "q_proj",
     "v_proj",
-    "o_proj",
-    "down_proj",
     "k_proj",
-    "up_proj",
-    "gate_proj",
-    "q_proj"
+    "down_proj",
+    "o_proj",
+    "up_proj"
   ],
   "task_type": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f12d3bb063fc19126b27a69ace5966a164e31befcec1b0912c36a4c3836efcbc
+oid sha256:6923740a2122c499a8b57fa0e72800dfb5ad897744ed4c72ce1b92e8d30f6395
 size 167829552

trainer_state.json

@@ -1,161 +1,371 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06411078343377356,
+  "epoch": 0.0837464826477288,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.003205539171688678,
-      "grad_norm": 0.43528684973716736,
-      "learning_rate": 2.9967944608283113e-05,
-      "loss": 1.7809,
+      "epoch": 0.001674929652954576,
+      "grad_norm": 0.30847179889678955,
+      "learning_rate": 2.9983250703470456e-05,
+      "loss": 0.5044,
       "step": 50
     },
     {
-      "epoch": 0.006411078343377356,
-      "grad_norm": 0.6100763082504272,
-      "learning_rate": 2.993588921656623e-05,
-      "loss": 1.0224,
+      "epoch": 0.003349859305909152,
+      "grad_norm": 0.04476890340447426,
+      "learning_rate": 2.9966501406940907e-05,
+      "loss": 0.0044,
       "step": 100
     },
     {
-      "epoch": 0.009616617515066034,
-      "grad_norm": 0.12871447205543518,
-      "learning_rate": 2.990383382484934e-05,
-      "loss": 1.0167,
+      "epoch": 0.005024788958863728,
+      "grad_norm": 0.08374588936567307,
+      "learning_rate": 2.9949752110411362e-05,
+      "loss": 0.0026,
       "step": 150
     },
     {
-      "epoch": 0.012822156686754712,
-      "grad_norm": 0.08891259878873825,
-      "learning_rate": 2.9871778433132457e-05,
-      "loss": 0.9958,
+      "epoch": 0.006699718611818304,
+      "grad_norm": 0.0017046213615685701,
+      "learning_rate": 2.9933002813881818e-05,
+      "loss": 0.0023,
       "step": 200
     },
     {
-      "epoch": 0.01602769585844339,
-      "grad_norm": 0.26497164368629456,
-      "learning_rate": 2.9839723041415565e-05,
-      "loss": 1.0257,
+      "epoch": 0.008374648264772879,
+      "grad_norm": 0.019402090460062027,
+      "learning_rate": 2.9916253517352273e-05,
+      "loss": 0.0013,
       "step": 250
     },
     {
-      "epoch": 0.01923323503013207,
-      "grad_norm": 0.10345622897148132,
-      "learning_rate": 2.9807667649698678e-05,
-      "loss": 1.0383,
+      "epoch": 0.010049577917727455,
+      "grad_norm": 0.010655886493623257,
+      "learning_rate": 2.9899504220822728e-05,
+      "loss": 0.002,
       "step": 300
     },
     {
-      "epoch": 0.022438774201820746,
-      "grad_norm": 0.31675589084625244,
-      "learning_rate": 2.9775612257981793e-05,
-      "loss": 1.0503,
+      "epoch": 0.011724507570682031,
+      "grad_norm": 0.006348441354930401,
+      "learning_rate": 2.9882754924293183e-05,
+      "loss": 0.0017,
       "step": 350
     },
     {
-      "epoch": 0.025644313373509423,
-      "grad_norm": 0.13149690628051758,
-      "learning_rate": 2.9743556866264905e-05,
-      "loss": 1.0373,
+      "epoch": 0.013399437223636608,
+      "grad_norm": 0.06810770183801651,
+      "learning_rate": 2.9866005627763634e-05,
+      "loss": 0.0015,
       "step": 400
     },
     {
-      "epoch": 0.0288498525451981,
-      "grad_norm": 0.45333313941955566,
-      "learning_rate": 2.971150147454802e-05,
-      "loss": 0.9785,
+      "epoch": 0.015074366876591184,
+      "grad_norm": 0.003874759189784527,
+      "learning_rate": 2.984925633123409e-05,
+      "loss": 0.0012,
       "step": 450
     },
     {
-      "epoch": 0.03205539171688678,
-      "grad_norm": 0.11852947622537613,
-      "learning_rate": 2.9679446082831133e-05,
-      "loss": 1.0165,
+      "epoch": 0.016749296529545758,
+      "grad_norm": 0.003985659219324589,
+      "learning_rate": 2.9832507034704544e-05,
+      "loss": 0.0012,
       "step": 500
     },
     {
-      "epoch": 0.03526093088857546,
-      "grad_norm": 0.13717707991600037,
-      "learning_rate": 2.9647390691114246e-05,
-      "loss": 0.9997,
+      "epoch": 0.018424226182500336,
+      "grad_norm": 0.01902610994875431,
+      "learning_rate": 2.9815757738174996e-05,
+      "loss": 0.0014,
       "step": 550
     },
     {
-      "epoch": 0.03846647006026414,
-      "grad_norm": 0.4000389277935028,
-      "learning_rate": 2.961533529939736e-05,
-      "loss": 1.012,
+      "epoch": 0.02009915583545491,
+      "grad_norm": 0.01615321636199951,
+      "learning_rate": 2.979900844164545e-05,
+      "loss": 0.0013,
       "step": 600
     },
     {
-      "epoch": 0.041672009231952814,
-      "grad_norm": 0.08108354359865189,
-      "learning_rate": 2.9583279907680473e-05,
-      "loss": 1.0151,
+      "epoch": 0.02177408548840949,
+      "grad_norm": 0.0055249775759875774,
+      "learning_rate": 2.9782259145115903e-05,
+      "loss": 0.0008,
       "step": 650
     },
     {
-      "epoch": 0.04487754840364149,
-      "grad_norm": 0.09668228775262833,
-      "learning_rate": 2.955122451596359e-05,
-      "loss": 0.9492,
+      "epoch": 0.023449015141364063,
+      "grad_norm": 0.0019460869953036308,
+      "learning_rate": 2.976550984858636e-05,
+      "loss": 0.0011,
       "step": 700
     },
     {
-      "epoch": 0.04808308757533017,
-      "grad_norm": 0.13635773956775665,
-      "learning_rate": 2.9519169124246698e-05,
-      "loss": 0.9951,
+      "epoch": 0.025123944794318637,
+      "grad_norm": 0.012369350530207157,
+      "learning_rate": 2.9748760552056816e-05,
+      "loss": 0.0011,
       "step": 750
     },
     {
-      "epoch": 0.051288626747018846,
-      "grad_norm": 0.1322096884250641,
-      "learning_rate": 2.948711373252981e-05,
-      "loss": 0.9404,
+      "epoch": 0.026798874447273215,
+      "grad_norm": 0.00836873333901167,
+      "learning_rate": 2.9732011255527268e-05,
+      "loss": 0.0013,
       "step": 800
     },
     {
-      "epoch": 0.054494165918707524,
-      "grad_norm": 0.30008432269096375,
-      "learning_rate": 2.9455058340812926e-05,
-      "loss": 0.9848,
+      "epoch": 0.02847380410022779,
+      "grad_norm": 0.0034731472842395306,
+      "learning_rate": 2.9715261958997723e-05,
+      "loss": 0.0016,
       "step": 850
     },
     {
-      "epoch": 0.0576997050903962,
-      "grad_norm": 0.16301093995571136,
-      "learning_rate": 2.9423002949096038e-05,
-      "loss": 1.04,
+      "epoch": 0.030148733753182368,
+      "grad_norm": 0.015365710482001305,
+      "learning_rate": 2.9698512662468178e-05,
+      "loss": 0.0013,
       "step": 900
     },
     {
-      "epoch": 0.060905244262084886,
-      "grad_norm": 0.1954452395439148,
-      "learning_rate": 2.939094755737915e-05,
-      "loss": 0.992,
+      "epoch": 0.031823663406136946,
+      "grad_norm": 0.017056584358215332,
+      "learning_rate": 2.968176336593863e-05,
+      "loss": 0.0013,
       "step": 950
     },
     {
-      "epoch": 0.06411078343377356,
-      "grad_norm": 0.34399452805519104,
-      "learning_rate": 2.9358892165662266e-05,
-      "loss": 0.967,
+      "epoch": 0.033498593059091517,
+      "grad_norm": 0.0038616659585386515,
+      "learning_rate": 2.9665014069409085e-05,
+      "loss": 0.0009,
       "step": 1000
+    },
+    {
+      "epoch": 0.035173522712046094,
+      "grad_norm": 0.0008767916006036103,
+      "learning_rate": 2.964826477287954e-05,
+      "loss": 0.0006,
+      "step": 1050
+    },
+    {
+      "epoch": 0.03684845236500067,
+      "grad_norm": 0.050677187740802765,
+      "learning_rate": 2.963151547634999e-05,
+      "loss": 0.0014,
+      "step": 1100
+    },
+    {
+      "epoch": 0.03852338201795524,
+      "grad_norm": 0.011451843194663525,
+      "learning_rate": 2.961476617982045e-05,
+      "loss": 0.0008,
+      "step": 1150
+    },
+    {
+      "epoch": 0.04019831167090982,
+      "grad_norm": 0.00335301854647696,
+      "learning_rate": 2.9598016883290905e-05,
+      "loss": 0.0013,
+      "step": 1200
+    },
+    {
+      "epoch": 0.0418732413238644,
+      "grad_norm": 0.01707889698445797,
+      "learning_rate": 2.9581267586761356e-05,
+      "loss": 0.0005,
+      "step": 1250
+    },
+    {
+      "epoch": 0.04354817097681898,
+      "grad_norm": 0.0004460318305063993,
+      "learning_rate": 2.956451829023181e-05,
+      "loss": 0.0011,
+      "step": 1300
+    },
+    {
+      "epoch": 0.04522310062977355,
+      "grad_norm": 0.00859643705189228,
+      "learning_rate": 2.9547768993702266e-05,
+      "loss": 0.0007,
+      "step": 1350
+    },
+    {
+      "epoch": 0.046898030282728126,
+      "grad_norm": 0.012995535507798195,
+      "learning_rate": 2.9531019697172718e-05,
+      "loss": 0.0009,
+      "step": 1400
+    },
+    {
+      "epoch": 0.048572959935682704,
+      "grad_norm": 0.004834771156311035,
+      "learning_rate": 2.9514270400643173e-05,
+      "loss": 0.0009,
+      "step": 1450
+    },
+    {
+      "epoch": 0.050247889588637275,
+      "grad_norm": 0.006121751386672258,
+      "learning_rate": 2.9497521104113628e-05,
+      "loss": 0.0009,
+      "step": 1500
+    },
+    {
+      "epoch": 0.05192281924159185,
+      "grad_norm": 0.004112472757697105,
+      "learning_rate": 2.9480771807584083e-05,
+      "loss": 0.0007,
+      "step": 1550
+    },
+    {
+      "epoch": 0.05359774889454643,
+      "grad_norm": 0.0025941322091966867,
+      "learning_rate": 2.9464022511054538e-05,
+      "loss": 0.0008,
+      "step": 1600
+    },
+    {
+      "epoch": 0.055272678547501,
+      "grad_norm": 0.0033354111947119236,
+      "learning_rate": 2.9447273214524993e-05,
+      "loss": 0.0014,
+      "step": 1650
+    },
+    {
+      "epoch": 0.05694760820045558,
+      "grad_norm": 0.0006163300131447613,
+      "learning_rate": 2.9430523917995445e-05,
+      "loss": 0.0013,
+      "step": 1700
+    },
+    {
+      "epoch": 0.05862253785341016,
+      "grad_norm": 0.03437214344739914,
+      "learning_rate": 2.94137746214659e-05,
+      "loss": 0.0011,
+      "step": 1750
+    },
+    {
+      "epoch": 0.060297467506364735,
+      "grad_norm": 0.004870133940130472,
+      "learning_rate": 2.939702532493635e-05,
+      "loss": 0.0011,
+      "step": 1800
+    },
+    {
+      "epoch": 0.061972397159319306,
+      "grad_norm": 0.011027672328054905,
+      "learning_rate": 2.9380276028406807e-05,
+      "loss": 0.0011,
+      "step": 1850
+    },
+    {
+      "epoch": 0.06364732681227389,
+      "grad_norm": 0.005804801359772682,
+      "learning_rate": 2.936352673187726e-05,
+      "loss": 0.0009,
+      "step": 1900
+    },
+    {
+      "epoch": 0.06532225646522846,
+      "grad_norm": 0.001421495107933879,
+      "learning_rate": 2.9346777435347713e-05,
+      "loss": 0.0007,
+      "step": 1950
+    },
+    {
+      "epoch": 0.06699718611818303,
+      "grad_norm": 0.00775284506380558,
+      "learning_rate": 2.9330028138818172e-05,
+      "loss": 0.0008,
+      "step": 2000
+    },
+    {
+      "epoch": 0.06867211577113762,
+      "grad_norm": 0.009989109821617603,
+      "learning_rate": 2.9313278842288627e-05,
+      "loss": 0.0013,
+      "step": 2050
+    },
+    {
+      "epoch": 0.07034704542409219,
+      "grad_norm": 0.004933220334351063,
+      "learning_rate": 2.929652954575908e-05,
+      "loss": 0.0008,
+      "step": 2100
+    },
+    {
+      "epoch": 0.07202197507704676,
+      "grad_norm": 0.0003998636966571212,
+      "learning_rate": 2.9279780249229533e-05,
+      "loss": 0.0005,
+      "step": 2150
+    },
+    {
+      "epoch": 0.07369690473000134,
+      "grad_norm": 0.00017748262325767428,
+      "learning_rate": 2.926303095269999e-05,
+      "loss": 0.0006,
+      "step": 2200
+    },
+    {
+      "epoch": 0.07537183438295592,
+      "grad_norm": 0.0009646079852245748,
+      "learning_rate": 2.924628165617044e-05,
+      "loss": 0.0007,
+      "step": 2250
+    },
+    {
+      "epoch": 0.07704676403591049,
+      "grad_norm": 0.004842822439968586,
+      "learning_rate": 2.9229532359640895e-05,
+      "loss": 0.0011,
+      "step": 2300
+    },
+    {
+      "epoch": 0.07872169368886507,
+      "grad_norm": 0.010380016639828682,
+      "learning_rate": 2.921278306311135e-05,
+      "loss": 0.001,
+      "step": 2350
+    },
+    {
+      "epoch": 0.08039662334181964,
+      "grad_norm": 0.0021645210217684507,
+      "learning_rate": 2.9196033766581802e-05,
+      "loss": 0.0009,
+      "step": 2400
+    },
+    {
+      "epoch": 0.08207155299477421,
+      "grad_norm": 0.0019599520601332188,
+      "learning_rate": 2.917928447005226e-05,
+      "loss": 0.0009,
+      "step": 2450
+    },
+    {
+      "epoch": 0.0837464826477288,
+      "grad_norm": 0.03942473977804184,
+      "learning_rate": 2.9162535173522715e-05,
+      "loss": 0.0011,
+      "step": 2500
     }
   ],
   "logging_steps": 50,
-  "max_steps": 46794,
+  "max_steps": 89556,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
-  "save_steps": 200,
+  "save_steps": 500,
   "total_flos": 0.0,
-  "train_batch_size": 100,
+  "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a3016ede18977651f64e35e7937a6eedad1efb5f8d5b0283902a432b80950ff
+oid sha256:740c8229cdedb3d1d6b326158ea54f02a778419a7c50fd4a45de07c549a9e9fe
 size 5048