Colin1337X's picture
Upload folder using huggingface_hub
b18428f verified
Raw History Blame Contribute Delete
12.2 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.02256734834524918,
"eval_steps": 500,
"global_step": 6500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00034718997454229514,
"grad_norm": 0.8856930732727051,
"learning_rate": 0.00019999994169931,
"loss": 2.4069,
"step": 100
},
{
"epoch": 0.0006943799490845903,
"grad_norm": 0.8890424966812134,
"learning_rate": 0.0001999997644357777,
"loss": 2.3882,
"step": 200
},
{
"epoch": 0.0010415699236268853,
"grad_norm": 0.8619076013565063,
"learning_rate": 0.00019999946820366553,
"loss": 2.4208,
"step": 300
},
{
"epoch": 0.0013887598981691806,
"grad_norm": 0.8981874585151672,
"learning_rate": 0.00019999905300332595,
"loss": 2.3859,
"step": 400
},
{
"epoch": 0.0017359498727114757,
"grad_norm": 1.1088451147079468,
"learning_rate": 0.0001999985188352529,
"loss": 2.4031,
"step": 500
},
{
"epoch": 0.0020831398472537705,
"grad_norm": 0.8845599889755249,
"learning_rate": 0.00019999786570008187,
"loss": 2.3765,
"step": 600
},
{
"epoch": 0.002430329821796066,
"grad_norm": 1.1892898082733154,
"learning_rate": 0.0001999970935985899,
"loss": 2.4083,
"step": 700
},
{
"epoch": 0.002777519796338361,
"grad_norm": 1.2907609939575195,
"learning_rate": 0.00019999620253169554,
"loss": 2.4262,
"step": 800
},
{
"epoch": 0.003124709770880656,
"grad_norm": 1.511342167854309,
"learning_rate": 0.00019999519250045886,
"loss": 2.4077,
"step": 900
},
{
"epoch": 0.0034718997454229513,
"grad_norm": 1.2708256244659424,
"learning_rate": 0.00019999406350608152,
"loss": 2.4238,
"step": 1000
},
{
"epoch": 0.003819089719965246,
"grad_norm": 1.380018949508667,
"learning_rate": 0.00019999281554990668,
"loss": 2.4429,
"step": 1100
},
{
"epoch": 0.004166279694507541,
"grad_norm": 1.5074928998947144,
"learning_rate": 0.000199991448633419,
"loss": 2.4212,
"step": 1200
},
{
"epoch": 0.004513469669049836,
"grad_norm": 1.20973801612854,
"learning_rate": 0.00019998996275824465,
"loss": 2.4092,
"step": 1300
},
{
"epoch": 0.004860659643592132,
"grad_norm": 1.4226404428482056,
"learning_rate": 0.0001999883579261514,
"loss": 2.3977,
"step": 1400
},
{
"epoch": 0.005207849618134427,
"grad_norm": 1.437606930732727,
"learning_rate": 0.0001999866341390485,
"loss": 2.4527,
"step": 1500
},
{
"epoch": 0.005555039592676722,
"grad_norm": 1.4428914785385132,
"learning_rate": 0.00019998479139898668,
"loss": 2.4495,
"step": 1600
},
{
"epoch": 0.005902229567219017,
"grad_norm": 2.573493719100952,
"learning_rate": 0.00019998282970815832,
"loss": 2.4216,
"step": 1700
},
{
"epoch": 0.006249419541761312,
"grad_norm": 1.491316795349121,
"learning_rate": 0.00019998074906889715,
"loss": 2.4209,
"step": 1800
},
{
"epoch": 0.006596609516303607,
"grad_norm": 1.9518392086029053,
"learning_rate": 0.00019997854948367846,
"loss": 2.4081,
"step": 1900
},
{
"epoch": 0.006943799490845903,
"grad_norm": 1.6811418533325195,
"learning_rate": 0.0001999762309551191,
"loss": 2.4255,
"step": 2000
},
{
"epoch": 0.007290989465388197,
"grad_norm": 1.316292643547058,
"learning_rate": 0.00019997379348597744,
"loss": 2.4039,
"step": 2100
},
{
"epoch": 0.007638179439930492,
"grad_norm": 1.297400712966919,
"learning_rate": 0.00019997123707915325,
"loss": 2.4193,
"step": 2200
},
{
"epoch": 0.007985369414472789,
"grad_norm": 1.5318177938461304,
"learning_rate": 0.00019996856173768785,
"loss": 2.4258,
"step": 2300
},
{
"epoch": 0.008332559389015082,
"grad_norm": 2.240832567214966,
"learning_rate": 0.00019996576746476413,
"loss": 2.4457,
"step": 2400
},
{
"epoch": 0.008679749363557377,
"grad_norm": 1.50482976436615,
"learning_rate": 0.00019996285426370636,
"loss": 2.4521,
"step": 2500
},
{
"epoch": 0.009026939338099673,
"grad_norm": 1.1736887693405151,
"learning_rate": 0.00019995982213798035,
"loss": 2.4226,
"step": 2600
},
{
"epoch": 0.009374129312641968,
"grad_norm": 1.489713430404663,
"learning_rate": 0.00019995667109119335,
"loss": 2.4314,
"step": 2700
},
{
"epoch": 0.009721319287184263,
"grad_norm": 2.00687313079834,
"learning_rate": 0.00019995340112709422,
"loss": 2.4389,
"step": 2800
},
{
"epoch": 0.010068509261726559,
"grad_norm": 1.5748944282531738,
"learning_rate": 0.00019995001224957308,
"loss": 2.4483,
"step": 2900
},
{
"epoch": 0.010415699236268854,
"grad_norm": 1.7045289278030396,
"learning_rate": 0.00019994650446266175,
"loss": 2.4407,
"step": 3000
},
{
"epoch": 0.01076288921081115,
"grad_norm": 1.3988068103790283,
"learning_rate": 0.0001999428777705333,
"loss": 2.462,
"step": 3100
},
{
"epoch": 0.011110079185353445,
"grad_norm": 1.3608533143997192,
"learning_rate": 0.00019993913217750245,
"loss": 2.4472,
"step": 3200
},
{
"epoch": 0.011457269159895738,
"grad_norm": 1.2952604293823242,
"learning_rate": 0.00019993526768802525,
"loss": 2.4427,
"step": 3300
},
{
"epoch": 0.011804459134438033,
"grad_norm": 2.3562355041503906,
"learning_rate": 0.0001999312843066992,
"loss": 2.4659,
"step": 3400
},
{
"epoch": 0.012151649108980329,
"grad_norm": 2.296459913253784,
"learning_rate": 0.00019992718203826337,
"loss": 2.4795,
"step": 3500
},
{
"epoch": 0.012498839083522624,
"grad_norm": 1.3606270551681519,
"learning_rate": 0.00019992296088759814,
"loss": 2.463,
"step": 3600
},
{
"epoch": 0.01284602905806492,
"grad_norm": 1.6714372634887695,
"learning_rate": 0.00019991862085972536,
"loss": 2.43,
"step": 3700
},
{
"epoch": 0.013193219032607215,
"grad_norm": 2.1929798126220703,
"learning_rate": 0.0001999141619598083,
"loss": 2.4513,
"step": 3800
},
{
"epoch": 0.01354040900714951,
"grad_norm": 1.7777063846588135,
"learning_rate": 0.00019990958419315166,
"loss": 2.472,
"step": 3900
},
{
"epoch": 0.013887598981691805,
"grad_norm": 1.5554057359695435,
"learning_rate": 0.00019990488756520164,
"loss": 2.4663,
"step": 4000
},
{
"epoch": 0.0142347889562341,
"grad_norm": 1.551933765411377,
"learning_rate": 0.00019990007208154565,
"loss": 2.5033,
"step": 4100
},
{
"epoch": 0.014581978930776394,
"grad_norm": 1.9665030241012573,
"learning_rate": 0.00019989513774791267,
"loss": 2.4518,
"step": 4200
},
{
"epoch": 0.01492916890531869,
"grad_norm": 1.5771666765213013,
"learning_rate": 0.000199890084570173,
"loss": 2.4703,
"step": 4300
},
{
"epoch": 0.015276358879860985,
"grad_norm": 1.750036597251892,
"learning_rate": 0.0001998849125543384,
"loss": 2.495,
"step": 4400
},
{
"epoch": 0.01562354885440328,
"grad_norm": 1.4305938482284546,
"learning_rate": 0.00019987962170656188,
"loss": 2.473,
"step": 4500
},
{
"epoch": 0.015970738828945577,
"grad_norm": 1.410703420639038,
"learning_rate": 0.00019987421203313799,
"loss": 2.4629,
"step": 4600
},
{
"epoch": 0.01631792880348787,
"grad_norm": 1.448388695716858,
"learning_rate": 0.0001998686835405025,
"loss": 2.4591,
"step": 4700
},
{
"epoch": 0.016665118778030164,
"grad_norm": 1.7654149532318115,
"learning_rate": 0.00019986303623523258,
"loss": 2.4754,
"step": 4800
},
{
"epoch": 0.01701230875257246,
"grad_norm": 1.8118611574172974,
"learning_rate": 0.0001998572701240468,
"loss": 2.4657,
"step": 4900
},
{
"epoch": 0.017359498727114755,
"grad_norm": 1.8808069229125977,
"learning_rate": 0.00019985138521380505,
"loss": 2.4736,
"step": 5000
},
{
"epoch": 0.01770668870165705,
"grad_norm": 1.5441018342971802,
"learning_rate": 0.00019984538151150846,
"loss": 2.4785,
"step": 5100
},
{
"epoch": 0.018053878676199345,
"grad_norm": 1.6582081317901611,
"learning_rate": 0.00019983925902429967,
"loss": 2.4841,
"step": 5200
},
{
"epoch": 0.01840106865074164,
"grad_norm": 1.5702968835830688,
"learning_rate": 0.00019983301775946245,
"loss": 2.4868,
"step": 5300
},
{
"epoch": 0.018748258625283936,
"grad_norm": 2.0732314586639404,
"learning_rate": 0.00019982665772442205,
"loss": 2.4601,
"step": 5400
},
{
"epoch": 0.01909544859982623,
"grad_norm": 1.4423972368240356,
"learning_rate": 0.00019982017892674483,
"loss": 2.4773,
"step": 5500
},
{
"epoch": 0.019442638574368527,
"grad_norm": 1.9959121942520142,
"learning_rate": 0.00019981358137413863,
"loss": 2.4989,
"step": 5600
},
{
"epoch": 0.019789828548910822,
"grad_norm": 1.7514522075653076,
"learning_rate": 0.0001998068650744524,
"loss": 2.4689,
"step": 5700
},
{
"epoch": 0.020137018523453117,
"grad_norm": 1.6253585815429688,
"learning_rate": 0.00019980003003567653,
"loss": 2.4683,
"step": 5800
},
{
"epoch": 0.020484208497995413,
"grad_norm": 1.9775470495224,
"learning_rate": 0.0001997930762659425,
"loss": 2.4787,
"step": 5900
},
{
"epoch": 0.020831398472537708,
"grad_norm": 1.4767321348190308,
"learning_rate": 0.00019978600377352324,
"loss": 2.4865,
"step": 6000
},
{
"epoch": 0.021178588447080003,
"grad_norm": 2.2066593170166016,
"learning_rate": 0.00019977881256683273,
"loss": 2.4826,
"step": 6100
},
{
"epoch": 0.0215257784216223,
"grad_norm": 1.9816187620162964,
"learning_rate": 0.00019977150265442626,
"loss": 2.486,
"step": 6200
},
{
"epoch": 0.021872968396164594,
"grad_norm": 1.573564052581787,
"learning_rate": 0.0001997640740450004,
"loss": 2.4893,
"step": 6300
},
{
"epoch": 0.02222015837070689,
"grad_norm": 2.1582605838775635,
"learning_rate": 0.00019975652674739285,
"loss": 2.4896,
"step": 6400
},
{
"epoch": 0.02256734834524918,
"grad_norm": 1.991675615310669,
"learning_rate": 0.00019974886077058255,
"loss": 2.5041,
"step": 6500
}
],
"logging_steps": 100,
"max_steps": 288027,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.7839791959124787e+18,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}