Training Examples: 10-20k

README.md

@@ -1,8 +1,6 @@
 ---
 base_model: unsloth/Phi-3.5-mini-instruct
 library_name: peft
-tags:
-- unsloth
 ---
 
 # Model Card for Model ID

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f863b9077713f0e757fcdcacee68ba1dcf99ea980774246b3554039ed33fffdb
+oid sha256:7f343725d809da4ffaf684a244a4100eecaa26a54d067b93505a4ea66f68b319
 size 61227348

scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93c597eb03d2515505b488c57afff1198972d636568623b2424b16127e41db5
+oid sha256:57acdb1f05c51c1c33f6ebed56a52d6cf566d8a89c725b24e17cf2ddc63a1a1f
 size 988

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f40383c44c7538547fd9cf2b2d066e1e62a7c77bd533c66118ed64f4b2c883d
+oid sha256:c65471f2a90c88eeb3b60677a5a2bfebe038a7e13f123565e2531cb20a70783a
 size 1064

trainer_state.json

@@ -3,357 +3,357 @@
   "best_model_checkpoint": null,
   "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 4820,
+  "global_step": 4825,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0002074688796680498,
-      "grad_norm": 0.655322790145874,
-      "learning_rate": 2.074688796680498e-07,
-      "loss": 1.8621,
+      "epoch": 0.0002072538860103627,
+      "grad_norm": 0.5270228385925293,
+      "learning_rate": 4.140786749482402e-07,
+      "loss": 0.7597,
       "step": 1
     },
     {
-      "epoch": 0.02074688796680498,
-      "grad_norm": 0.2854801118373871,
-      "learning_rate": 2.0746887966804982e-05,
-      "loss": 1.2556,
+      "epoch": 0.02072538860103627,
+      "grad_norm": 0.3120118975639343,
+      "learning_rate": 4.140786749482402e-05,
+      "loss": 0.8058,
       "step": 100
     },
     {
-      "epoch": 0.04149377593360996,
-      "grad_norm": 0.3198237419128418,
-      "learning_rate": 4.1493775933609964e-05,
-      "loss": 1.003,
+      "epoch": 0.04145077720207254,
+      "grad_norm": 0.3838038146495819,
+      "learning_rate": 8.281573498964804e-05,
+      "loss": 0.8085,
       "step": 200
     },
     {
-      "epoch": 0.06224066390041494,
-      "grad_norm": 0.40545061230659485,
-      "learning_rate": 6.224066390041494e-05,
-      "loss": 0.9348,
+      "epoch": 0.06217616580310881,
+      "grad_norm": 0.33677420020103455,
+      "learning_rate": 0.00012422360248447205,
+      "loss": 0.8452,
       "step": 300
     },
     {
-      "epoch": 0.08298755186721991,
-      "grad_norm": 0.18410639464855194,
-      "learning_rate": 8.298755186721993e-05,
-      "loss": 0.9333,
+      "epoch": 0.08290155440414508,
+      "grad_norm": 0.2833797335624695,
+      "learning_rate": 0.00016563146997929608,
+      "loss": 0.7836,
       "step": 400
     },
     {
-      "epoch": 0.1037344398340249,
-      "grad_norm": 0.21944168210029602,
-      "learning_rate": 0.00010373443983402491,
-      "loss": 0.9156,
+      "epoch": 0.10362694300518134,
+      "grad_norm": 0.3029078245162964,
+      "learning_rate": 0.0001999924354607825,
+      "loss": 0.8032,
       "step": 500
     },
     {
-      "epoch": 0.12448132780082988,
-      "grad_norm": 0.20224255323410034,
-      "learning_rate": 0.00012448132780082987,
-      "loss": 0.9411,
+      "epoch": 0.12435233160621761,
+      "grad_norm": 0.30878347158432007,
+      "learning_rate": 0.00019964190153093613,
+      "loss": 0.8034,
       "step": 600
     },
     {
-      "epoch": 0.14522821576763487,
-      "grad_norm": 0.33025670051574707,
-      "learning_rate": 0.00014522821576763486,
-      "loss": 0.8919,
+      "epoch": 0.14507772020725387,
+      "grad_norm": 0.1962185502052307,
+      "learning_rate": 0.00019878125322990773,
+      "loss": 0.8069,
       "step": 700
     },
     {
-      "epoch": 0.16597510373443983,
-      "grad_norm": 0.13862663507461548,
-      "learning_rate": 0.00016597510373443986,
-      "loss": 0.8931,
+      "epoch": 0.16580310880829016,
+      "grad_norm": 0.2113143652677536,
+      "learning_rate": 0.00019739761494902327,
+      "loss": 0.8239,
       "step": 800
     },
     {
-      "epoch": 0.18672199170124482,
-      "grad_norm": 0.41121917963027954,
-      "learning_rate": 0.00018672199170124482,
-      "loss": 0.912,
+      "epoch": 0.18652849740932642,
+      "grad_norm": 0.36496707797050476,
+      "learning_rate": 0.00019550431853565577,
+      "loss": 0.7952,
       "step": 900
     },
     {
-      "epoch": 0.2074688796680498,
-      "grad_norm": 0.25411322712898254,
-      "learning_rate": 0.00019995698998770956,
-      "loss": 0.9075,
+      "epoch": 0.20725388601036268,
+      "grad_norm": 0.4117984175682068,
+      "learning_rate": 0.00019311127115144138,
+      "loss": 0.8159,
       "step": 1000
     },
     {
-      "epoch": 0.22821576763485477,
-      "grad_norm": 0.3547718822956085,
-      "learning_rate": 0.00019938676188562863,
-      "loss": 0.9199,
+      "epoch": 0.22797927461139897,
+      "grad_norm": 0.25097981095314026,
+      "learning_rate": 0.00019023099503382319,
+      "loss": 0.8295,
       "step": 1100
     },
     {
-      "epoch": 0.24896265560165975,
-      "grad_norm": 0.4020107388496399,
-      "learning_rate": 0.00019815718684822688,
-      "loss": 0.9164,
+      "epoch": 0.24870466321243523,
+      "grad_norm": 0.2996521592140198,
+      "learning_rate": 0.00018687856197021518,
+      "loss": 0.8071,
       "step": 1200
     },
     {
-      "epoch": 0.2697095435684647,
-      "grad_norm": 0.21474340558052063,
-      "learning_rate": 0.00019627642206381863,
-      "loss": 0.881,
+      "epoch": 0.2694300518134715,
+      "grad_norm": 0.2897460162639618,
+      "learning_rate": 0.0001830715144309886,
+      "loss": 0.8338,
       "step": 1300
     },
     {
-      "epoch": 0.29045643153526973,
-      "grad_norm": 0.18409068882465363,
-      "learning_rate": 0.00019375694481280965,
-      "loss": 0.8793,
+      "epoch": 0.29015544041450775,
+      "grad_norm": 0.5588517785072327,
+      "learning_rate": 0.0001788297737739727,
+      "loss": 0.7572,
       "step": 1400
     },
     {
-      "epoch": 0.3112033195020747,
-      "grad_norm": 0.4158700704574585,
-      "learning_rate": 0.0001906154696915157,
-      "loss": 0.8633,
+      "epoch": 0.31088082901554404,
+      "grad_norm": 0.47002148628234863,
+      "learning_rate": 0.00017417553600081358,
+      "loss": 0.809,
       "step": 1500
     },
     {
-      "epoch": 0.33195020746887965,
-      "grad_norm": 0.3469320237636566,
-      "learning_rate": 0.00018687283772498206,
-      "loss": 0.897,
+      "epoch": 0.3316062176165803,
+      "grad_norm": 0.3224999010562897,
+      "learning_rate": 0.00016913315561067264,
+      "loss": 0.7942,
       "step": 1600
     },
     {
-      "epoch": 0.35269709543568467,
-      "grad_norm": 0.4698736369609833,
-      "learning_rate": 0.00018255387810444448,
-      "loss": 0.8829,
+      "epoch": 0.35233160621761656,
+      "grad_norm": 0.5584061145782471,
+      "learning_rate": 0.0001637290181590304,
+      "loss": 0.8329,
       "step": 1700
     },
     {
-      "epoch": 0.37344398340248963,
-      "grad_norm": 0.3711629807949066,
-      "learning_rate": 0.0001776872434666882,
-      "loss": 0.8862,
+      "epoch": 0.37305699481865284,
+      "grad_norm": 0.3566969633102417,
+      "learning_rate": 0.00015799140218846435,
+      "loss": 0.7901,
       "step": 1800
     },
     {
-      "epoch": 0.3941908713692946,
-      "grad_norm": 0.2403649389743805,
-      "learning_rate": 0.000172305219808086,
-      "loss": 0.8799,
+      "epoch": 0.39378238341968913,
+      "grad_norm": 0.27286580204963684,
+      "learning_rate": 0.00015195033125388395,
+      "loss": 0.8138,
       "step": 1900
     },
     {
-      "epoch": 0.4149377593360996,
-      "grad_norm": 0.45258045196533203,
-      "learning_rate": 0.00016644351229437416,
-      "loss": 0.8671,
+      "epoch": 0.41450777202072536,
+      "grad_norm": 0.3148711621761322,
+      "learning_rate": 0.00014563741681653824,
+      "loss": 0.7867,
       "step": 2000
     },
     {
-      "epoch": 0.43568464730290457,
-      "grad_norm": 0.19893667101860046,
-      "learning_rate": 0.00016014100838713797,
-      "loss": 0.8391,
+      "epoch": 0.43523316062176165,
+      "grad_norm": 0.3646707832813263,
+      "learning_rate": 0.0001390856928288946,
+      "loss": 0.7681,
       "step": 2100
     },
     {
-      "epoch": 0.45643153526970953,
-      "grad_norm": 0.44036027789115906,
-      "learning_rate": 0.00015343951985846095,
-      "loss": 0.847,
+      "epoch": 0.45595854922279794,
+      "grad_norm": 0.32302677631378174,
+      "learning_rate": 0.00013232944287596522,
+      "loss": 0.8134,
       "step": 2200
     },
     {
-      "epoch": 0.47717842323651455,
-      "grad_norm": 0.17648863792419434,
-      "learning_rate": 0.00014638350540525246,
-      "loss": 0.8721,
+      "epoch": 0.47668393782383417,
+      "grad_norm": 0.7468949556350708,
+      "learning_rate": 0.000125404020777609,
+      "loss": 0.7862,
       "step": 2300
     },
     {
-      "epoch": 0.4979253112033195,
-      "grad_norm": 0.39910203218460083,
-      "learning_rate": 0.0001390197757034721,
-      "loss": 0.8791,
+      "epoch": 0.49740932642487046,
+      "grad_norm": 0.36616334319114685,
+      "learning_rate": 0.00011834566559055394,
+      "loss": 0.7675,
       "step": 2400
     },
     {
-      "epoch": 0.5186721991701245,
-      "grad_norm": 0.39837658405303955,
-      "learning_rate": 0.00013139718285896655,
-      "loss": 0.8557,
+      "epoch": 0.5181347150259067,
+      "grad_norm": 0.3042179346084595,
+      "learning_rate": 0.00011119131197818904,
+      "loss": 0.7824,
       "step": 2500
     },
     {
-      "epoch": 0.5394190871369294,
-      "grad_norm": 0.3242895305156708,
-      "learning_rate": 0.00012356629631514929,
-      "loss": 0.8634,
+      "epoch": 0.538860103626943,
+      "grad_norm": 0.6282315850257874,
+      "learning_rate": 0.0001039783969404153,
+      "loss": 0.8008,
       "step": 2600
     },
     {
-      "epoch": 0.5601659751037344,
-      "grad_norm": 0.260079562664032,
-      "learning_rate": 0.0001156595402508126,
-      "loss": 0.8228,
+      "epoch": 0.5595854922279793,
+      "grad_norm": 0.309589147567749,
+      "learning_rate": 9.674466391489112e-05,
+      "loss": 0.7918,
       "step": 2700
     },
     {
-      "epoch": 0.5809128630705395,
-      "grad_norm": 0.19493329524993896,
-      "learning_rate": 0.00010756972609502109,
-      "loss": 0.8483,
+      "epoch": 0.5803108808290155,
+      "grad_norm": 0.6195072531700134,
+      "learning_rate": 8.952796527476341e-05,
+      "loss": 0.7714,
       "step": 2800
     },
     {
-      "epoch": 0.6016597510373444,
-      "grad_norm": 0.4152539372444153,
-      "learning_rate": 9.942969322189461e-05,
-      "loss": 0.7983,
+      "epoch": 0.6010362694300518,
+      "grad_norm": 0.5037879943847656,
+      "learning_rate": 8.236606425636553e-05,
+      "loss": 0.8098,
       "step": 2900
     },
     {
-      "epoch": 0.6224066390041494,
-      "grad_norm": 0.28217726945877075,
-      "learning_rate": 9.129344385090869e-05,
-      "loss": 0.8174,
+      "epoch": 0.6217616580310881,
+      "grad_norm": 0.3202759325504303,
+      "learning_rate": 7.529643735334646e-05,
+      "loss": 0.7303,
       "step": 3000
     },
     {
-      "epoch": 0.6431535269709544,
-      "grad_norm": 0.25863170623779297,
-      "learning_rate": 8.321495510120858e-05,
-      "loss": 0.829,
+      "epoch": 0.6424870466321243,
+      "grad_norm": 0.4311729669570923,
+      "learning_rate": 6.835607821125519e-05,
+      "loss": 0.7717,
       "step": 3100
     },
     {
-      "epoch": 0.6639004149377593,
-      "grad_norm": 0.33922916650772095,
-      "learning_rate": 7.524782089916924e-05,
-      "loss": 0.828,
+      "epoch": 0.6632124352331606,
+      "grad_norm": 0.28787970542907715,
+      "learning_rate": 6.158130404875231e-05,
+      "loss": 0.7748,
       "step": 3200
     },
     {
-      "epoch": 0.6846473029045643,
-      "grad_norm": 0.2833387851715088,
-      "learning_rate": 6.744489642811432e-05,
-      "loss": 0.8211,
+      "epoch": 0.6839378238341969,
+      "grad_norm": 0.28564584255218506,
+      "learning_rate": 5.5007565618399506e-05,
+      "loss": 0.8161,
       "step": 3300
     },
     {
-      "epoch": 0.7053941908713693,
-      "grad_norm": 0.44776320457458496,
-      "learning_rate": 5.9857947478969156e-05,
-      "loss": 0.8534,
+      "epoch": 0.7046632124352331,
+      "grad_norm": 0.5357826352119446,
+      "learning_rate": 4.873136932795313e-05,
+      "loss": 0.7594,
       "step": 3400
     },
     {
-      "epoch": 0.7261410788381742,
-      "grad_norm": 0.4343676269054413,
-      "learning_rate": 5.253730702810957e-05,
-      "loss": 0.8126,
+      "epoch": 0.7253886010362695,
+      "grad_norm": 0.292579710483551,
+      "learning_rate": 4.265882101960175e-05,
+      "loss": 0.7572,
       "step": 3500
     },
     {
-      "epoch": 0.7468879668049793,
-      "grad_norm": 0.2133251577615738,
-      "learning_rate": 4.553154132072044e-05,
-      "loss": 0.8514,
+      "epoch": 0.7461139896373057,
+      "grad_norm": 0.29901111125946045,
+      "learning_rate": 3.688632521467985e-05,
+      "loss": 0.7514,
       "step": 3600
     },
     {
-      "epoch": 0.7676348547717843,
-      "grad_norm": 0.4406150281429291,
-      "learning_rate": 3.88871276749183e-05,
-      "loss": 0.8379,
+      "epoch": 0.7668393782383419,
+      "grad_norm": 0.3171032667160034,
+      "learning_rate": 3.144408798582336e-05,
+      "loss": 0.7862,
       "step": 3700
     },
     {
-      "epoch": 0.7883817427385892,
-      "grad_norm": 0.48208776116371155,
-      "learning_rate": 3.264814614413537e-05,
-      "loss": 0.8325,
+      "epoch": 0.7875647668393783,
+      "grad_norm": 0.43368250131607056,
+      "learning_rate": 2.636058724251739e-05,
+      "loss": 0.7994,
       "step": 3800
     },
     {
-      "epoch": 0.8091286307053942,
-      "grad_norm": 0.2793184220790863,
-      "learning_rate": 2.68559870833223e-05,
-      "loss": 0.8116,
+      "epoch": 0.8082901554404145,
+      "grad_norm": 0.4301137924194336,
+      "learning_rate": 2.1662423713092516e-05,
+      "loss": 0.7646,
       "step": 3900
     },
     {
-      "epoch": 0.8298755186721992,
-      "grad_norm": 0.354342520236969,
-      "learning_rate": 2.154907655902131e-05,
-      "loss": 0.806,
+      "epoch": 0.8290155440414507,
+      "grad_norm": 0.20049989223480225,
+      "learning_rate": 1.737418174955542e-05,
+      "loss": 0.7742,
       "step": 4000
     },
     {
-      "epoch": 0.8506224066390041,
-      "grad_norm": 0.2756762206554413,
-      "learning_rate": 1.6762621424980718e-05,
-      "loss": 0.8254,
+      "epoch": 0.8497409326424871,
+      "grad_norm": 0.5148625373840332,
+      "learning_rate": 1.3518300683627982e-05,
+      "loss": 0.7357,
       "step": 4100
     },
     {
-      "epoch": 0.8713692946058091,
-      "grad_norm": 0.551670491695404,
-      "learning_rate": 1.252837575451774e-05,
-      "loss": 0.8275,
+      "epoch": 0.8704663212435233,
+      "grad_norm": 0.38820308446884155,
+      "learning_rate": 1.011495740715882e-05,
+      "loss": 0.7536,
       "step": 4200
     },
     {
-      "epoch": 0.8921161825726142,
-      "grad_norm": 0.3675282597541809,
-      "learning_rate": 8.874430179153592e-06,
-      "loss": 0.7922,
+      "epoch": 0.8911917098445595,
+      "grad_norm": 0.6004698276519775,
+      "learning_rate": 7.1819607913342745e-06,
+      "loss": 0.7238,
       "step": 4300
     },
     {
-      "epoch": 0.9128630705394191,
-      "grad_norm": 0.24929411709308624,
-      "learning_rate": 5.825025531079997e-06,
-      "loss": 0.8274,
+      "epoch": 0.9119170984455959,
+      "grad_norm": 0.30640721321105957,
+      "learning_rate": 4.734658497168276e-06,
+      "loss": 0.7669,
       "step": 4400
     },
     {
-      "epoch": 0.9336099585062241,
-      "grad_norm": 0.296157568693161,
-      "learning_rate": 3.4003920257815068e-06,
-      "loss": 0.8172,
+      "epoch": 0.9326424870466321,
+      "grad_norm": 0.23962052166461945,
+      "learning_rate": 2.7858566649088814e-06,
+      "loss": 0.7329,
       "step": 4500
     },
     {
-      "epoch": 0.9543568464730291,
-      "grad_norm": 0.3886050879955292,
-      "learning_rate": 1.6166150517008316e-06,
-      "loss": 0.7862,
+      "epoch": 0.9533678756476683,
+      "grad_norm": 0.2379899024963379,
+      "learning_rate": 1.3457529026076777e-06,
+      "loss": 0.7845,
       "step": 4600
     },
     {
-      "epoch": 0.975103734439834,
-      "grad_norm": 0.21001334488391876,
-      "learning_rate": 4.85528457318829e-07,
-      "loss": 0.8318,
+      "epoch": 0.9740932642487047,
+      "grad_norm": 0.291648268699646,
+      "learning_rate": 4.218829245063227e-07,
+      "loss": 0.773,
       "step": 4700
     },
     {
-      "epoch": 0.995850622406639,
-      "grad_norm": 0.42969635128974915,
-      "learning_rate": 1.4636043598914572e-08,
-      "loss": 0.8309,
+      "epoch": 0.9948186528497409,
+      "grad_norm": 0.7486833930015564,
+      "learning_rate": 1.9081118468888824e-08,
+      "loss": 0.8057,
       "step": 4800
     }
   ],
   "logging_steps": 100,
-  "max_steps": 4820,
+  "max_steps": 4825,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
@@ -369,7 +369,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.298519682425856e+17,
+  "total_flos": 1.3151301866366976e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3f58fe7d64d267d98f39cbabdd040fd1cebc479f214ef573c983f87829e472
+oid sha256:97682e56ca9cafdee97b6d5ed5984ff75c9fc1563ca7b651bdb1cd346643b028
 size 5624