hin2kan_model / trainer_state.json
shubham-das-coder's picture
Add files using upload-large-folder tool
3c2307e verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 37460,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.13347570742124934,
"grad_norm": 3.1733596324920654,
"learning_rate": 4.933395621996797e-05,
"loss": 1.4561,
"step": 500
},
{
"epoch": 0.2669514148424987,
"grad_norm": 2.9853200912475586,
"learning_rate": 4.866657768286172e-05,
"loss": 1.2371,
"step": 1000
},
{
"epoch": 0.400427122263748,
"grad_norm": 2.6459007263183594,
"learning_rate": 4.7999199145755475e-05,
"loss": 1.1388,
"step": 1500
},
{
"epoch": 0.5339028296849974,
"grad_norm": 2.6050009727478027,
"learning_rate": 4.733182060864923e-05,
"loss": 1.1141,
"step": 2000
},
{
"epoch": 0.6673785371062466,
"grad_norm": 2.1738457679748535,
"learning_rate": 4.666444207154298e-05,
"loss": 1.086,
"step": 2500
},
{
"epoch": 0.800854244527496,
"grad_norm": 2.692978620529175,
"learning_rate": 4.599706353443674e-05,
"loss": 1.0676,
"step": 3000
},
{
"epoch": 0.9343299519487454,
"grad_norm": 2.072795867919922,
"learning_rate": 4.532968499733049e-05,
"loss": 0.9895,
"step": 3500
},
{
"epoch": 1.0678056593699947,
"grad_norm": 2.18379282951355,
"learning_rate": 4.466230646022424e-05,
"loss": 0.9155,
"step": 4000
},
{
"epoch": 1.201281366791244,
"grad_norm": 2.4531776905059814,
"learning_rate": 4.3994927923117995e-05,
"loss": 0.8136,
"step": 4500
},
{
"epoch": 1.3347570742124932,
"grad_norm": 2.8264808654785156,
"learning_rate": 4.332754938601175e-05,
"loss": 0.8129,
"step": 5000
},
{
"epoch": 1.4682327816337426,
"grad_norm": 1.746168851852417,
"learning_rate": 4.26601708489055e-05,
"loss": 0.8581,
"step": 5500
},
{
"epoch": 1.601708489054992,
"grad_norm": 2.722280740737915,
"learning_rate": 4.199279231179926e-05,
"loss": 0.7905,
"step": 6000
},
{
"epoch": 1.7351841964762413,
"grad_norm": 2.4873287677764893,
"learning_rate": 4.1325413774693004e-05,
"loss": 0.8327,
"step": 6500
},
{
"epoch": 1.8686599038974907,
"grad_norm": 2.6175665855407715,
"learning_rate": 4.0658035237586763e-05,
"loss": 0.8191,
"step": 7000
},
{
"epoch": 2.00213561131874,
"grad_norm": 1.2910939455032349,
"learning_rate": 3.9990656700480516e-05,
"loss": 0.8359,
"step": 7500
},
{
"epoch": 2.1356113187399894,
"grad_norm": 2.5565571784973145,
"learning_rate": 3.932327816337427e-05,
"loss": 0.6788,
"step": 8000
},
{
"epoch": 2.269087026161239,
"grad_norm": 2.173668146133423,
"learning_rate": 3.865589962626802e-05,
"loss": 0.6669,
"step": 8500
},
{
"epoch": 2.402562733582488,
"grad_norm": 1.9133882522583008,
"learning_rate": 3.798852108916178e-05,
"loss": 0.6696,
"step": 9000
},
{
"epoch": 2.536038441003737,
"grad_norm": 1.3470282554626465,
"learning_rate": 3.7321142552055525e-05,
"loss": 0.6803,
"step": 9500
},
{
"epoch": 2.6695141484249865,
"grad_norm": 2.3730781078338623,
"learning_rate": 3.6653764014949284e-05,
"loss": 0.6684,
"step": 10000
},
{
"epoch": 2.802989855846236,
"grad_norm": 2.106994390487671,
"learning_rate": 3.598638547784303e-05,
"loss": 0.6717,
"step": 10500
},
{
"epoch": 2.936465563267485,
"grad_norm": 1.7302494049072266,
"learning_rate": 3.531900694073679e-05,
"loss": 0.676,
"step": 11000
},
{
"epoch": 3.0699412706887346,
"grad_norm": 1.477286458015442,
"learning_rate": 3.465162840363054e-05,
"loss": 0.586,
"step": 11500
},
{
"epoch": 3.203416978109984,
"grad_norm": 1.818613052368164,
"learning_rate": 3.398424986652429e-05,
"loss": 0.5467,
"step": 12000
},
{
"epoch": 3.3368926855312333,
"grad_norm": 1.6314208507537842,
"learning_rate": 3.3316871329418045e-05,
"loss": 0.556,
"step": 12500
},
{
"epoch": 3.4703683929524827,
"grad_norm": 2.8924617767333984,
"learning_rate": 3.2649492792311804e-05,
"loss": 0.5567,
"step": 13000
},
{
"epoch": 3.603844100373732,
"grad_norm": 2.6945688724517822,
"learning_rate": 3.198211425520555e-05,
"loss": 0.5568,
"step": 13500
},
{
"epoch": 3.7373198077949814,
"grad_norm": 2.092221736907959,
"learning_rate": 3.131473571809931e-05,
"loss": 0.5567,
"step": 14000
},
{
"epoch": 3.8707955152162308,
"grad_norm": 1.6795735359191895,
"learning_rate": 3.064735718099306e-05,
"loss": 0.5764,
"step": 14500
},
{
"epoch": 4.00427122263748,
"grad_norm": 2.4606454372406006,
"learning_rate": 2.9979978643886814e-05,
"loss": 0.5716,
"step": 15000
},
{
"epoch": 4.1377469300587295,
"grad_norm": 4.759591102600098,
"learning_rate": 2.931260010678057e-05,
"loss": 0.4671,
"step": 15500
},
{
"epoch": 4.271222637479979,
"grad_norm": 1.4791502952575684,
"learning_rate": 2.8645221569674318e-05,
"loss": 0.4719,
"step": 16000
},
{
"epoch": 4.404698344901228,
"grad_norm": 1.2884821891784668,
"learning_rate": 2.7977843032568074e-05,
"loss": 0.465,
"step": 16500
},
{
"epoch": 4.538174052322478,
"grad_norm": 3.4914660453796387,
"learning_rate": 2.731046449546183e-05,
"loss": 0.4572,
"step": 17000
},
{
"epoch": 4.671649759743727,
"grad_norm": 1.9152294397354126,
"learning_rate": 2.664308595835558e-05,
"loss": 0.4685,
"step": 17500
},
{
"epoch": 4.805125467164976,
"grad_norm": 2.193741798400879,
"learning_rate": 2.5975707421249334e-05,
"loss": 0.4751,
"step": 18000
},
{
"epoch": 4.938601174586225,
"grad_norm": 1.8435180187225342,
"learning_rate": 2.530832888414309e-05,
"loss": 0.4671,
"step": 18500
},
{
"epoch": 5.072076882007474,
"grad_norm": 2.184936761856079,
"learning_rate": 2.464095034703684e-05,
"loss": 0.4342,
"step": 19000
},
{
"epoch": 5.205552589428724,
"grad_norm": 1.9590941667556763,
"learning_rate": 2.3973571809930594e-05,
"loss": 0.3865,
"step": 19500
},
{
"epoch": 5.339028296849973,
"grad_norm": 2.4979445934295654,
"learning_rate": 2.3306193272824347e-05,
"loss": 0.3983,
"step": 20000
},
{
"epoch": 5.472504004271222,
"grad_norm": 2.703019142150879,
"learning_rate": 2.26388147357181e-05,
"loss": 0.3951,
"step": 20500
},
{
"epoch": 5.605979711692472,
"grad_norm": 2.801893711090088,
"learning_rate": 2.197143619861185e-05,
"loss": 0.3996,
"step": 21000
},
{
"epoch": 5.739455419113721,
"grad_norm": 1.1886452436447144,
"learning_rate": 2.1304057661505607e-05,
"loss": 0.4042,
"step": 21500
},
{
"epoch": 5.87293112653497,
"grad_norm": 2.024179458618164,
"learning_rate": 2.063667912439936e-05,
"loss": 0.4081,
"step": 22000
},
{
"epoch": 6.00640683395622,
"grad_norm": 1.3413245677947998,
"learning_rate": 1.996930058729311e-05,
"loss": 0.3917,
"step": 22500
},
{
"epoch": 6.139882541377469,
"grad_norm": 1.4281545877456665,
"learning_rate": 1.9301922050186867e-05,
"loss": 0.34,
"step": 23000
},
{
"epoch": 6.2733582487987185,
"grad_norm": 2.500412702560425,
"learning_rate": 1.863454351308062e-05,
"loss": 0.3327,
"step": 23500
},
{
"epoch": 6.406833956219968,
"grad_norm": 2.666672945022583,
"learning_rate": 1.7967164975974375e-05,
"loss": 0.3399,
"step": 24000
},
{
"epoch": 6.540309663641217,
"grad_norm": 2.352971076965332,
"learning_rate": 1.7299786438868128e-05,
"loss": 0.331,
"step": 24500
},
{
"epoch": 6.673785371062467,
"grad_norm": 3.2518150806427,
"learning_rate": 1.663240790176188e-05,
"loss": 0.3576,
"step": 25000
},
{
"epoch": 6.807261078483716,
"grad_norm": 1.363599181175232,
"learning_rate": 1.5965029364655636e-05,
"loss": 0.3572,
"step": 25500
},
{
"epoch": 6.940736785904965,
"grad_norm": 2.377072811126709,
"learning_rate": 1.5297650827549388e-05,
"loss": 0.3538,
"step": 26000
},
{
"epoch": 7.074212493326215,
"grad_norm": 2.4149889945983887,
"learning_rate": 1.463027229044314e-05,
"loss": 0.32,
"step": 26500
},
{
"epoch": 7.207688200747464,
"grad_norm": 2.2141239643096924,
"learning_rate": 1.3962893753336892e-05,
"loss": 0.2894,
"step": 27000
},
{
"epoch": 7.3411639081687134,
"grad_norm": 1.6364160776138306,
"learning_rate": 1.3295515216230648e-05,
"loss": 0.2914,
"step": 27500
},
{
"epoch": 7.474639615589963,
"grad_norm": 2.363274097442627,
"learning_rate": 1.26281366791244e-05,
"loss": 0.2963,
"step": 28000
},
{
"epoch": 7.608115323011212,
"grad_norm": 3.750777006149292,
"learning_rate": 1.1960758142018154e-05,
"loss": 0.299,
"step": 28500
},
{
"epoch": 7.7415910304324616,
"grad_norm": 3.3002822399139404,
"learning_rate": 1.1293379604911907e-05,
"loss": 0.2956,
"step": 29000
},
{
"epoch": 7.875066737853711,
"grad_norm": 3.4351253509521484,
"learning_rate": 1.062600106780566e-05,
"loss": 0.3213,
"step": 29500
},
{
"epoch": 8.00854244527496,
"grad_norm": 2.195547103881836,
"learning_rate": 9.958622530699413e-06,
"loss": 0.2988,
"step": 30000
},
{
"epoch": 8.14201815269621,
"grad_norm": 2.4596967697143555,
"learning_rate": 9.291243993593167e-06,
"loss": 0.2702,
"step": 30500
},
{
"epoch": 8.275493860117459,
"grad_norm": 3.5012736320495605,
"learning_rate": 8.62386545648692e-06,
"loss": 0.2609,
"step": 31000
},
{
"epoch": 8.408969567538708,
"grad_norm": 1.7438409328460693,
"learning_rate": 7.956486919380673e-06,
"loss": 0.2605,
"step": 31500
},
{
"epoch": 8.542445274959958,
"grad_norm": 2.4345345497131348,
"learning_rate": 7.289108382274426e-06,
"loss": 0.2611,
"step": 32000
},
{
"epoch": 8.675920982381207,
"grad_norm": 3.1137731075286865,
"learning_rate": 6.62172984516818e-06,
"loss": 0.2688,
"step": 32500
},
{
"epoch": 8.809396689802456,
"grad_norm": 1.2621135711669922,
"learning_rate": 5.9543513080619334e-06,
"loss": 0.2732,
"step": 33000
},
{
"epoch": 8.942872397223706,
"grad_norm": 1.6983531713485718,
"learning_rate": 5.286972770955687e-06,
"loss": 0.2805,
"step": 33500
},
{
"epoch": 9.076348104644955,
"grad_norm": 1.4236127138137817,
"learning_rate": 4.61959423384944e-06,
"loss": 0.2668,
"step": 34000
},
{
"epoch": 9.209823812066205,
"grad_norm": 2.3351385593414307,
"learning_rate": 3.952215696743193e-06,
"loss": 0.2437,
"step": 34500
},
{
"epoch": 9.343299519487454,
"grad_norm": 2.2198843955993652,
"learning_rate": 3.2848371596369464e-06,
"loss": 0.2459,
"step": 35000
},
{
"epoch": 9.476775226908703,
"grad_norm": 2.087069272994995,
"learning_rate": 2.6174586225306996e-06,
"loss": 0.2415,
"step": 35500
},
{
"epoch": 9.610250934329953,
"grad_norm": 1.8616083860397339,
"learning_rate": 1.9500800854244527e-06,
"loss": 0.2453,
"step": 36000
},
{
"epoch": 9.743726641751202,
"grad_norm": 1.3939635753631592,
"learning_rate": 1.282701548318206e-06,
"loss": 0.2369,
"step": 36500
},
{
"epoch": 9.877202349172451,
"grad_norm": 2.0491538047790527,
"learning_rate": 6.153230112119594e-07,
"loss": 0.2489,
"step": 37000
},
{
"epoch": 10.0,
"step": 37460,
"total_flos": 1.2944564446789632e+16,
"train_loss": 0.5224577584498334,
"train_runtime": 9349.5182,
"train_samples_per_second": 16.026,
"train_steps_per_second": 4.007
}
],
"logging_steps": 500,
"max_steps": 37460,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 10000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.2944564446789632e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}