Upload folder using huggingface_hub

outputs/tiny-50M/checkpoint-94/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae96028076b6e140e06e513f753332301f0815540e99342614f848b0b5f0890a
+oid sha256:c2ec8c3e2a1273864162c61aab7bfd4ecbd577f70dcb0e843192fee8ec0637c3
 size 223914096

outputs/tiny-50M/checkpoint-94/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7733ea084c434ec579f2f3cc4aee34b44190325f6f48362cfa246a0b6e81a92a
+oid sha256:0a8c4e7b7b959237905206c30f6607df8beb4d0b0cfb3e651c1386e077153d52
 size 447876619

outputs/tiny-50M/checkpoint-94/trainer_state.json

@@ -11,331 +11,331 @@
   "log_history": [
     {
       "epoch": 0.021333333333333333,
-      "grad_norm": 19.857784271240234,
+      "grad_norm": 20.886064529418945,
       "learning_rate": 0.00029680851063829784,
-      "loss": 8.839614868164062,
+      "loss": 9.117223739624023,
       "step": 2
     },
     {
       "epoch": 0.042666666666666665,
-      "grad_norm": 8.053306579589844,
+      "grad_norm": 9.685882568359375,
       "learning_rate": 0.0002904255319148936,
-      "loss": 4.259130954742432,
+      "loss": 4.377265453338623,
       "step": 4
     },
     {
       "epoch": 0.064,
-      "grad_norm": 7.085880279541016,
+      "grad_norm": 7.4572367668151855,
       "learning_rate": 0.00028404255319148934,
-      "loss": 4.260076999664307,
+      "loss": 4.354522228240967,
       "step": 6
     },
     {
       "epoch": 0.08533333333333333,
-      "grad_norm": 5.618923664093018,
+      "grad_norm": 6.9209370613098145,
       "learning_rate": 0.00027765957446808506,
-      "loss": 3.5047478675842285,
+      "loss": 3.705888271331787,
       "step": 8
     },
     {
       "epoch": 0.10666666666666667,
-      "grad_norm": 6.0084614753723145,
+      "grad_norm": 4.850710868835449,
       "learning_rate": 0.00027127659574468084,
-      "loss": 3.2548251152038574,
+      "loss": 3.117213249206543,
       "step": 10
     },
     {
       "epoch": 0.128,
-      "grad_norm": 3.2026114463806152,
+      "grad_norm": 3.311143636703491,
       "learning_rate": 0.00026489361702127656,
-      "loss": 2.6681971549987793,
+      "loss": 2.82865571975708,
       "step": 12
     },
     {
       "epoch": 0.14933333333333335,
-      "grad_norm": 2.4880897998809814,
+      "grad_norm": 3.6059303283691406,
       "learning_rate": 0.0002585106382978723,
-      "loss": 2.908954620361328,
+      "loss": 3.0487096309661865,
       "step": 14
     },
     {
       "epoch": 0.17066666666666666,
-      "grad_norm": 2.081550121307373,
+      "grad_norm": 2.1480607986450195,
       "learning_rate": 0.00025212765957446806,
-      "loss": 2.3955461978912354,
+      "loss": 2.4057984352111816,
       "step": 16
     },
     {
       "epoch": 0.192,
-      "grad_norm": 2.23256254196167,
+      "grad_norm": 2.106024980545044,
       "learning_rate": 0.00024574468085106384,
-      "loss": 1.9950157403945923,
+      "loss": 1.9920709133148193,
       "step": 18
     },
     {
       "epoch": 0.21333333333333335,
-      "grad_norm": 1.2642862796783447,
+      "grad_norm": 1.3735127449035645,
       "learning_rate": 0.00023936170212765956,
-      "loss": 2.406209945678711,
+      "loss": 2.4057974815368652,
       "step": 20
     },
     {
       "epoch": 0.23466666666666666,
-      "grad_norm": 1.0684170722961426,
+      "grad_norm": 1.1117502450942993,
       "learning_rate": 0.00023297872340425529,
-      "loss": 1.4826658964157104,
+      "loss": 1.4768301248550415,
       "step": 22
     },
     {
       "epoch": 0.256,
-      "grad_norm": 1.1620922088623047,
+      "grad_norm": 1.1720795631408691,
       "learning_rate": 0.00022659574468085106,
-      "loss": 1.7480285167694092,
+      "loss": 1.74120032787323,
       "step": 24
     },
     {
       "epoch": 0.2773333333333333,
-      "grad_norm": 1.057904839515686,
+      "grad_norm": 0.933724582195282,
       "learning_rate": 0.00022021276595744679,
-      "loss": 1.8112417459487915,
+      "loss": 1.8157235383987427,
       "step": 26
     },
     {
       "epoch": 0.2986666666666667,
-      "grad_norm": 1.139146327972412,
+      "grad_norm": 1.2087736129760742,
       "learning_rate": 0.00021382978723404254,
-      "loss": 1.962647795677185,
+      "loss": 1.966804027557373,
       "step": 28
     },
     {
       "epoch": 0.32,
-      "grad_norm": 0.7921020984649658,
+      "grad_norm": 0.7714659571647644,
       "learning_rate": 0.0002074468085106383,
-      "loss": 1.338681936264038,
+      "loss": 1.3380244970321655,
       "step": 30
     },
     {
       "epoch": 0.3413333333333333,
-      "grad_norm": 0.5229901671409607,
+      "grad_norm": 0.5713186860084534,
       "learning_rate": 0.00020106382978723404,
-      "loss": 1.2959659099578857,
+      "loss": 1.2967045307159424,
       "step": 32
     },
     {
       "epoch": 0.3626666666666667,
-      "grad_norm": 0.5313481092453003,
+      "grad_norm": 0.520260214805603,
       "learning_rate": 0.00019468085106382976,
-      "loss": 1.3124475479125977,
+      "loss": 1.3104149103164673,
       "step": 34
     },
     {
       "epoch": 0.384,
-      "grad_norm": 0.29172077775001526,
+      "grad_norm": 0.32929661870002747,
       "learning_rate": 0.0001882978723404255,
-      "loss": 1.4122732877731323,
+      "loss": 1.4126676321029663,
       "step": 36
     },
     {
       "epoch": 0.4053333333333333,
-      "grad_norm": 0.4614223837852478,
+      "grad_norm": 0.4052687883377075,
       "learning_rate": 0.00018191489361702126,
-      "loss": 1.14182710647583,
+      "loss": 1.1403084993362427,
       "step": 38
     },
     {
       "epoch": 0.4266666666666667,
-      "grad_norm": 0.3804754912853241,
+      "grad_norm": 0.38564684987068176,
       "learning_rate": 0.000175531914893617,
-      "loss": 1.2516833543777466,
+      "loss": 1.2476884126663208,
       "step": 40
     },
     {
       "epoch": 0.448,
-      "grad_norm": 0.33474111557006836,
+      "grad_norm": 0.48461219668388367,
       "learning_rate": 0.00016914893617021274,
-      "loss": 1.2273238897323608,
+      "loss": 1.2218774557113647,
       "step": 42
     },
     {
       "epoch": 0.4693333333333333,
-      "grad_norm": 0.39935603737831116,
+      "grad_norm": 0.45225775241851807,
       "learning_rate": 0.00016276595744680849,
-      "loss": 0.9951828122138977,
+      "loss": 0.9925822019577026,
       "step": 44
     },
     {
       "epoch": 0.49066666666666664,
-      "grad_norm": 0.23251356184482574,
+      "grad_norm": 1.3031398057937622,
       "learning_rate": 0.00015638297872340426,
-      "loss": 1.0770968198776245,
+      "loss": 1.0708966255187988,
       "step": 46
     },
     {
       "epoch": 0.512,
-      "grad_norm": 0.262003093957901,
+      "grad_norm": 0.4108118414878845,
       "learning_rate": 0.00015,
-      "loss": 1.340306043624878,
+      "loss": 1.328290343284607,
       "step": 48
     },
     {
       "epoch": 0.5333333333333333,
-      "grad_norm": 0.3379991352558136,
+      "grad_norm": 0.445605993270874,
       "learning_rate": 0.00014361702127659574,
-      "loss": 1.1250380277633667,
+      "loss": 1.112563133239746,
       "step": 50
     },
     {
       "epoch": 0.5546666666666666,
-      "grad_norm": 0.25868967175483704,
+      "grad_norm": 0.33703047037124634,
       "learning_rate": 0.0001372340425531915,
-      "loss": 1.2347091436386108,
+      "loss": 1.2103136777877808,
       "step": 52
     },
     {
       "epoch": 0.576,
-      "grad_norm": 0.2983493506908417,
+      "grad_norm": 0.4313303232192993,
       "learning_rate": 0.00013085106382978724,
-      "loss": 1.0739911794662476,
+      "loss": 1.0557019710540771,
       "step": 54
     },
     {
       "epoch": 0.5973333333333334,
-      "grad_norm": 0.3253922760486603,
+      "grad_norm": 0.6436446905136108,
       "learning_rate": 0.00012446808510638296,
-      "loss": 0.986941397190094,
+      "loss": 0.972583532333374,
       "step": 56
     },
     {
       "epoch": 0.6186666666666667,
-      "grad_norm": 0.32209739089012146,
+      "grad_norm": 0.545637309551239,
       "learning_rate": 0.00011808510638297871,
-      "loss": 1.1307929754257202,
+      "loss": 1.1087357997894287,
       "step": 58
     },
     {
       "epoch": 0.64,
-      "grad_norm": 0.2041606307029724,
+      "grad_norm": 0.26695331931114197,
       "learning_rate": 0.00011170212765957445,
-      "loss": 0.9198997616767883,
+      "loss": 0.9045885801315308,
       "step": 60
     },
     {
       "epoch": 0.6613333333333333,
-      "grad_norm": 0.20420902967453003,
+      "grad_norm": 0.22084178030490875,
       "learning_rate": 0.0001053191489361702,
-      "loss": 0.7641400694847107,
+      "loss": 0.7554645538330078,
       "step": 62
     },
     {
       "epoch": 0.6826666666666666,
-      "grad_norm": 0.3539799451828003,
+      "grad_norm": 0.4161592721939087,
       "learning_rate": 9.893617021276594e-05,
-      "loss": 1.109285593032837,
+      "loss": 1.088483214378357,
       "step": 64
     },
     {
       "epoch": 0.704,
-      "grad_norm": 0.3249659836292267,
+      "grad_norm": 0.35406050086021423,
       "learning_rate": 9.25531914893617e-05,
-      "loss": 1.0656695365905762,
+      "loss": 1.0480642318725586,
       "step": 66
     },
     {
       "epoch": 0.7253333333333334,
-      "grad_norm": 0.283320814371109,
+      "grad_norm": 0.3608798682689667,
       "learning_rate": 8.617021276595745e-05,
-      "loss": 1.0882402658462524,
+      "loss": 1.069770336151123,
       "step": 68
     },
     {
       "epoch": 0.7466666666666667,
-      "grad_norm": 0.4081163704395294,
+      "grad_norm": 0.48737776279449463,
       "learning_rate": 7.978723404255319e-05,
-      "loss": 0.8739507794380188,
+      "loss": 0.8581401705741882,
       "step": 70
     },
     {
       "epoch": 0.768,
-      "grad_norm": 0.4886767864227295,
+      "grad_norm": 0.6724710464477539,
       "learning_rate": 7.340425531914892e-05,
-      "loss": 1.099593162536621,
+      "loss": 1.077805757522583,
       "step": 72
     },
     {
       "epoch": 0.7893333333333333,
-      "grad_norm": 0.38340282440185547,
+      "grad_norm": 0.3901081383228302,
       "learning_rate": 6.702127659574467e-05,
-      "loss": 1.378351092338562,
+      "loss": 1.348370909690857,
       "step": 74
     },
     {
       "epoch": 0.8106666666666666,
-      "grad_norm": 0.39620906114578247,
+      "grad_norm": 0.6735767126083374,
       "learning_rate": 6.063829787234042e-05,
-      "loss": 1.1076319217681885,
+      "loss": 1.0873925685882568,
       "step": 76
     },
     {
       "epoch": 0.832,
-      "grad_norm": 0.30094316601753235,
+      "grad_norm": 0.4087413251399994,
       "learning_rate": 5.425531914893617e-05,
-      "loss": 0.768018901348114,
+      "loss": 0.7546330690383911,
       "step": 78
     },
     {
       "epoch": 0.8533333333333334,
-      "grad_norm": 0.4080992639064789,
+      "grad_norm": 0.48011866211891174,
       "learning_rate": 4.787234042553191e-05,
-      "loss": 0.9190238118171692,
+      "loss": 0.8991920948028564,
       "step": 80
     },
     {
       "epoch": 0.8746666666666667,
-      "grad_norm": 0.22875891625881195,
+      "grad_norm": 0.25723037123680115,
       "learning_rate": 4.1489361702127656e-05,
-      "loss": 0.6930217146873474,
+      "loss": 0.6794441342353821,
       "step": 82
     },
     {
       "epoch": 0.896,
-      "grad_norm": 0.4183938801288605,
+      "grad_norm": 0.4201943278312683,
       "learning_rate": 3.51063829787234e-05,
-      "loss": 0.9895132780075073,
+      "loss": 0.9654682278633118,
       "step": 84
     },
     {
       "epoch": 0.9173333333333333,
-      "grad_norm": 0.5136104822158813,
+      "grad_norm": 0.6856644749641418,
       "learning_rate": 2.8723404255319147e-05,
-      "loss": 0.9970792531967163,
+      "loss": 0.971971333026886,
       "step": 86
     },
     {
       "epoch": 0.9386666666666666,
-      "grad_norm": 0.39408519864082336,
+      "grad_norm": 0.3479587137699127,
       "learning_rate": 2.234042553191489e-05,
-      "loss": 0.8527765870094299,
+      "loss": 0.8317626118659973,
       "step": 88
     },
     {
       "epoch": 0.96,
-      "grad_norm": 0.3212464153766632,
+      "grad_norm": 0.4632757604122162,
       "learning_rate": 1.5957446808510637e-05,
-      "loss": 1.1280995607376099,
+      "loss": 1.1008682250976562,
       "step": 90
     },
     {
       "epoch": 0.9813333333333333,
-      "grad_norm": 0.37641191482543945,
+      "grad_norm": 0.47290000319480896,
       "learning_rate": 9.574468085106381e-06,
-      "loss": 1.1669095754623413,
+      "loss": 1.1374844312667847,
       "step": 92
     },
     {
       "epoch": 1.0,
-      "grad_norm": 0.3149685263633728,
+      "grad_norm": 0.332586407661438,
       "learning_rate": 3.1914893617021273e-06,
-      "loss": 0.982663631439209,
+      "loss": 0.9553995132446289,
       "step": 94
     }
   ],

outputs/tiny-50M/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae96028076b6e140e06e513f753332301f0815540e99342614f848b0b5f0890a
+oid sha256:c2ec8c3e2a1273864162c61aab7bfd4ecbd577f70dcb0e843192fee8ec0637c3
 size 223914096