382 lines
11 KiB
JSON
382 lines
11 KiB
JSON
|
{
|
||
|
|
"best_global_step": null,
|
||
|
|
"best_metric": null,
|
||
|
|
"best_model_checkpoint": null,
|
||
|
|
"epoch": 3.0,
|
||
|
|
"eval_steps": 20,
|
||
|
|
"global_step": 135,
|
||
|
|
"is_hyper_param_search": false,
|
||
|
|
"is_local_process_zero": true,
|
||
|
|
"is_world_process_zero": true,
|
||
|
|
"log_history": [
|
||
|
|
{
|
||
|
|
"entropy": 0.46982616782188413,
|
||
|
|
"epoch": 0.1111111111111111,
|
||
|
|
"grad_norm": 1.9415351152420044,
|
||
|
|
"learning_rate": 0.00023999999999999998,
|
||
|
|
"loss": 1.166135025024414,
|
||
|
|
"mean_token_accuracy": 0.8076520800590515,
|
||
|
|
"num_tokens": 59002.0,
|
||
|
|
"step": 5
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.681049507856369,
|
||
|
|
"epoch": 0.2222222222222222,
|
||
|
|
"grad_norm": 0.8071348071098328,
|
||
|
|
"learning_rate": 0.00029929974520764727,
|
||
|
|
"loss": 0.7030046463012696,
|
||
|
|
"mean_token_accuracy": 0.849864411354065,
|
||
|
|
"num_tokens": 120432.0,
|
||
|
|
"step": 10
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.9322404026985168,
|
||
|
|
"epoch": 0.3333333333333333,
|
||
|
|
"grad_norm": 0.6664227247238159,
|
||
|
|
"learning_rate": 0.0002964661618243908,
|
||
|
|
"loss": 0.878734016418457,
|
||
|
|
"mean_token_accuracy": 0.8135401248931885,
|
||
|
|
"num_tokens": 179678.0,
|
||
|
|
"step": 15
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8074370503425599,
|
||
|
|
"epoch": 0.4444444444444444,
|
||
|
|
"grad_norm": 0.6451402306556702,
|
||
|
|
"learning_rate": 0.0002914967719886614,
|
||
|
|
"loss": 0.8701633453369141,
|
||
|
|
"mean_token_accuracy": 0.8204897165298461,
|
||
|
|
"num_tokens": 240600.0,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.4444444444444444,
|
||
|
|
"eval_entropy": 0.8143169482549032,
|
||
|
|
"eval_loss": 0.924848735332489,
|
||
|
|
"eval_mean_token_accuracy": 0.803371528784434,
|
||
|
|
"eval_num_tokens": 240600.0,
|
||
|
|
"eval_runtime": 1.6201,
|
||
|
|
"eval_samples_per_second": 45.676,
|
||
|
|
"eval_steps_per_second": 1.852,
|
||
|
|
"step": 20
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.7912694752216339,
|
||
|
|
"epoch": 0.5555555555555556,
|
||
|
|
"grad_norm": 0.4144524037837982,
|
||
|
|
"learning_rate": 0.0002844640405943555,
|
||
|
|
"loss": 0.8696941375732422,
|
||
|
|
"mean_token_accuracy": 0.8263819813728333,
|
||
|
|
"num_tokens": 301638.0,
|
||
|
|
"step": 25
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.9237359523773193,
|
||
|
|
"epoch": 0.6666666666666666,
|
||
|
|
"grad_norm": 0.5862515568733215,
|
||
|
|
"learning_rate": 0.00027547052070153396,
|
||
|
|
"loss": 0.9361928939819336,
|
||
|
|
"mean_token_accuracy": 0.8028241634368897,
|
||
|
|
"num_tokens": 359243.0,
|
||
|
|
"step": 30
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.6837044417858124,
|
||
|
|
"epoch": 0.7777777777777778,
|
||
|
|
"grad_norm": 0.4594927728176117,
|
||
|
|
"learning_rate": 0.0002646473580818772,
|
||
|
|
"loss": 0.6992801666259766,
|
||
|
|
"mean_token_accuracy": 0.8513208270072937,
|
||
|
|
"num_tokens": 417098.0,
|
||
|
|
"step": 35
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8795680403709412,
|
||
|
|
"epoch": 0.8888888888888888,
|
||
|
|
"grad_norm": 0.5710228681564331,
|
||
|
|
"learning_rate": 0.00025215237881801955,
|
||
|
|
"loss": 0.9085055351257324,
|
||
|
|
"mean_token_accuracy": 0.8098101854324341,
|
||
|
|
"num_tokens": 480008.0,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 0.8888888888888888,
|
||
|
|
"eval_entropy": 0.8618650635083517,
|
||
|
|
"eval_loss": 0.9124361872673035,
|
||
|
|
"eval_mean_token_accuracy": 0.8028692404429117,
|
||
|
|
"eval_num_tokens": 480008.0,
|
||
|
|
"eval_runtime": 1.6251,
|
||
|
|
"eval_samples_per_second": 45.535,
|
||
|
|
"eval_steps_per_second": 1.846,
|
||
|
|
"step": 40
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8452938675880433,
|
||
|
|
"epoch": 1.0,
|
||
|
|
"grad_norm": 0.789717972278595,
|
||
|
|
"learning_rate": 0.00023816778784387094,
|
||
|
|
"loss": 0.8828925132751465,
|
||
|
|
"mean_token_accuracy": 0.8208261251449585,
|
||
|
|
"num_tokens": 530794.0,
|
||
|
|
"step": 45
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5805854141712189,
|
||
|
|
"epoch": 1.1111111111111112,
|
||
|
|
"grad_norm": 0.4138790965080261,
|
||
|
|
"learning_rate": 0.00022289751198639087,
|
||
|
|
"loss": 0.5360542297363281,
|
||
|
|
"mean_token_accuracy": 0.8808212757110596,
|
||
|
|
"num_tokens": 589773.0,
|
||
|
|
"step": 50
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8660945177078248,
|
||
|
|
"epoch": 1.2222222222222223,
|
||
|
|
"grad_norm": 0.4917871356010437,
|
||
|
|
"learning_rate": 0.00020656422625324805,
|
||
|
|
"loss": 0.8303131103515625,
|
||
|
|
"mean_token_accuracy": 0.8197528839111328,
|
||
|
|
"num_tokens": 644861.0,
|
||
|
|
"step": 55
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5908387929201127,
|
||
|
|
"epoch": 1.3333333333333333,
|
||
|
|
"grad_norm": 0.5149257779121399,
|
||
|
|
"learning_rate": 0.00018940610672978802,
|
||
|
|
"loss": 0.5536936283111572,
|
||
|
|
"mean_token_accuracy": 0.8759726524353028,
|
||
|
|
"num_tokens": 707064.0,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.3333333333333333,
|
||
|
|
"eval_entropy": 0.7562275131543478,
|
||
|
|
"eval_loss": 0.9295161366462708,
|
||
|
|
"eval_mean_token_accuracy": 0.8002562522888184,
|
||
|
|
"eval_num_tokens": 707064.0,
|
||
|
|
"eval_runtime": 1.6273,
|
||
|
|
"eval_samples_per_second": 45.475,
|
||
|
|
"eval_steps_per_second": 1.844,
|
||
|
|
"step": 60
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.7860998153686524,
|
||
|
|
"epoch": 1.4444444444444444,
|
||
|
|
"grad_norm": 0.6012740731239319,
|
||
|
|
"learning_rate": 0.00017167335743538317,
|
||
|
|
"loss": 0.7982378482818604,
|
||
|
|
"mean_token_accuracy": 0.8309973835945129,
|
||
|
|
"num_tokens": 763959.0,
|
||
|
|
"step": 65
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.6057170808315278,
|
||
|
|
"epoch": 1.5555555555555556,
|
||
|
|
"grad_norm": 0.7193827629089355,
|
||
|
|
"learning_rate": 0.00015362456178541982,
|
||
|
|
"loss": 0.6322322368621827,
|
||
|
|
"mean_token_accuracy": 0.8604895114898682,
|
||
|
|
"num_tokens": 826139.0,
|
||
|
|
"step": 70
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.8781150817871094,
|
||
|
|
"epoch": 1.6666666666666665,
|
||
|
|
"grad_norm": 0.5556202530860901,
|
||
|
|
"learning_rate": 0.00013552291186282273,
|
||
|
|
"loss": 0.8648699760437012,
|
||
|
|
"mean_token_accuracy": 0.8099217295646668,
|
||
|
|
"num_tokens": 883964.0,
|
||
|
|
"step": 75
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.7820337891578675,
|
||
|
|
"epoch": 1.7777777777777777,
|
||
|
|
"grad_norm": 0.626190721988678,
|
||
|
|
"learning_rate": 0.00011763237048482908,
|
||
|
|
"loss": 0.7500524520874023,
|
||
|
|
"mean_token_accuracy": 0.8313877940177917,
|
||
|
|
"num_tokens": 942825.0,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 1.7777777777777777,
|
||
|
|
"eval_entropy": 0.7708820303281149,
|
||
|
|
"eval_loss": 0.9428374767303467,
|
||
|
|
"eval_mean_token_accuracy": 0.7990738352139791,
|
||
|
|
"eval_num_tokens": 942825.0,
|
||
|
|
"eval_runtime": 1.6267,
|
||
|
|
"eval_samples_per_second": 45.49,
|
||
|
|
"eval_steps_per_second": 1.844,
|
||
|
|
"step": 80
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.6434245944023133,
|
||
|
|
"epoch": 1.8888888888888888,
|
||
|
|
"grad_norm": 0.7037157416343689,
|
||
|
|
"learning_rate": 0.00010021382203072075,
|
||
|
|
"loss": 0.6138159275054932,
|
||
|
|
"mean_token_accuracy": 0.8665528893470764,
|
||
|
|
"num_tokens": 1005474.0,
|
||
|
|
"step": 85
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.44103629887104034,
|
||
|
|
"epoch": 2.0,
|
||
|
|
"grad_norm": 0.5344287753105164,
|
||
|
|
"learning_rate": 8.352126816011381e-05,
|
||
|
|
"loss": 0.441878604888916,
|
||
|
|
"mean_token_accuracy": 0.9036641597747803,
|
||
|
|
"num_tokens": 1061588.0,
|
||
|
|
"step": 90
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.7921009421348572,
|
||
|
|
"epoch": 2.111111111111111,
|
||
|
|
"grad_norm": 0.5275471210479736,
|
||
|
|
"learning_rate": 6.779812389679952e-05,
|
||
|
|
"loss": 0.7220367431640625,
|
||
|
|
"mean_token_accuracy": 0.8374058127403259,
|
||
|
|
"num_tokens": 1119675.0,
|
||
|
|
"step": 95
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.6127014696598053,
|
||
|
|
"epoch": 2.2222222222222223,
|
||
|
|
"grad_norm": 0.6188642382621765,
|
||
|
|
"learning_rate": 5.327366808957444e-05,
|
||
|
|
"loss": 0.545912790298462,
|
||
|
|
"mean_token_accuracy": 0.8728284955024719,
|
||
|
|
"num_tokens": 1178607.0,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.2222222222222223,
|
||
|
|
"eval_entropy": 0.6974611083666483,
|
||
|
|
"eval_loss": 0.9652960300445557,
|
||
|
|
"eval_mean_token_accuracy": 0.799143652121226,
|
||
|
|
"eval_num_tokens": 1178607.0,
|
||
|
|
"eval_runtime": 1.6275,
|
||
|
|
"eval_samples_per_second": 45.469,
|
||
|
|
"eval_steps_per_second": 1.843,
|
||
|
|
"step": 100
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5584009617567063,
|
||
|
|
"epoch": 2.3333333333333335,
|
||
|
|
"grad_norm": 0.2800925076007843,
|
||
|
|
"learning_rate": 4.015970001033401e-05,
|
||
|
|
"loss": 0.5415268421173096,
|
||
|
|
"mean_token_accuracy": 0.8769876599311829,
|
||
|
|
"num_tokens": 1239996.0,
|
||
|
|
"step": 105
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.40896390080451966,
|
||
|
|
"epoch": 2.4444444444444446,
|
||
|
|
"grad_norm": 0.38913053274154663,
|
||
|
|
"learning_rate": 2.8647450843757897e-05,
|
||
|
|
"loss": 0.4072125434875488,
|
||
|
|
"mean_token_accuracy": 0.9056331634521484,
|
||
|
|
"num_tokens": 1303203.0,
|
||
|
|
"step": 110
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5653573453426362,
|
||
|
|
"epoch": 2.5555555555555554,
|
||
|
|
"grad_norm": 0.7067868709564209,
|
||
|
|
"learning_rate": 1.8904795106022313e-05,
|
||
|
|
"loss": 0.5507754325866699,
|
||
|
|
"mean_token_accuracy": 0.8763858556747437,
|
||
|
|
"num_tokens": 1361238.0,
|
||
|
|
"step": 115
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5153138220310212,
|
||
|
|
"epoch": 2.6666666666666665,
|
||
|
|
"grad_norm": 0.7621523141860962,
|
||
|
|
"learning_rate": 1.1073802656333546e-05,
|
||
|
|
"loss": 0.507559871673584,
|
||
|
|
"mean_token_accuracy": 0.8800268650054932,
|
||
|
|
"num_tokens": 1423474.0,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 2.6666666666666665,
|
||
|
|
"eval_entropy": 0.6664723753929138,
|
||
|
|
"eval_loss": 0.9865095615386963,
|
||
|
|
"eval_mean_token_accuracy": 0.7970906893412272,
|
||
|
|
"eval_num_tokens": 1423474.0,
|
||
|
|
"eval_runtime": 1.6278,
|
||
|
|
"eval_samples_per_second": 45.46,
|
||
|
|
"eval_steps_per_second": 1.843,
|
||
|
|
"step": 120
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.634662801027298,
|
||
|
|
"epoch": 2.7777777777777777,
|
||
|
|
"grad_norm": 0.5899237394332886,
|
||
|
|
"learning_rate": 5.268666998467297e-06,
|
||
|
|
"loss": 0.5941447734832763,
|
||
|
|
"mean_token_accuracy": 0.8620630621910095,
|
||
|
|
"num_tokens": 1479493.0,
|
||
|
|
"step": 125
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.5771006941795349,
|
||
|
|
"epoch": 2.888888888888889,
|
||
|
|
"grad_norm": 0.6653247475624084,
|
||
|
|
"learning_rate": 1.5740400823423316e-06,
|
||
|
|
"loss": 0.5706047534942627,
|
||
|
|
"mean_token_accuracy": 0.874986720085144,
|
||
|
|
"num_tokens": 1539267.0,
|
||
|
|
"step": 130
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"entropy": 0.603338897228241,
|
||
|
|
"epoch": 3.0,
|
||
|
|
"grad_norm": 0.9464746713638306,
|
||
|
|
"learning_rate": 4.379788797105877e-08,
|
||
|
|
"loss": 0.5793191909790039,
|
||
|
|
"mean_token_accuracy": 0.8678125262260437,
|
||
|
|
"num_tokens": 1592382.0,
|
||
|
|
"step": 135
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"epoch": 3.0,
|
||
|
|
"eval_entropy": 0.6672613223393759,
|
||
|
|
"eval_loss": 0.9868772625923157,
|
||
|
|
"eval_mean_token_accuracy": 0.7981111407279968,
|
||
|
|
"eval_num_tokens": 1592382.0,
|
||
|
|
"eval_runtime": 1.6294,
|
||
|
|
"eval_samples_per_second": 45.415,
|
||
|
|
"eval_steps_per_second": 1.841,
|
||
|
|
"step": 135
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"logging_steps": 5,
|
||
|
|
"max_steps": 135,
|
||
|
|
"num_input_tokens_seen": 0,
|
||
|
|
"num_train_epochs": 3,
|
||
|
|
"save_steps": 500,
|
||
|
|
"stateful_callbacks": {
|
||
|
|
"TrainerControl": {
|
||
|
|
"args": {
|
||
|
|
"should_epoch_stop": false,
|
||
|
|
"should_evaluate": false,
|
||
|
|
"should_log": false,
|
||
|
|
"should_save": true,
|
||
|
|
"should_training_stop": true
|
||
|
|
},
|
||
|
|
"attributes": {}
|
||
|
|
}
|
||
|
|
},
|
||
|
|
"total_flos": 5851882291200000.0,
|
||
|
|
"train_batch_size": 32,
|
||
|
|
"trial_name": null,
|
||
|
|
"trial_params": null
|
||
|
|
}
|