dada22231's picture
Training in progress, step 50, checkpoint
12ea4a0 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.37860861334595364,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007572172266919072,
"grad_norm": 2.4073128700256348,
"learning_rate": 5e-05,
"loss": 3.0444,
"step": 1
},
{
"epoch": 0.007572172266919072,
"eval_loss": 4.418989658355713,
"eval_runtime": 3.2607,
"eval_samples_per_second": 15.334,
"eval_steps_per_second": 3.987,
"step": 1
},
{
"epoch": 0.015144344533838144,
"grad_norm": 3.72934627532959,
"learning_rate": 0.0001,
"loss": 3.6067,
"step": 2
},
{
"epoch": 0.022716516800757217,
"grad_norm": 4.2463226318359375,
"learning_rate": 9.990365154573717e-05,
"loss": 3.5081,
"step": 3
},
{
"epoch": 0.03028868906767629,
"grad_norm": 3.8385074138641357,
"learning_rate": 9.961501876182148e-05,
"loss": 3.2803,
"step": 4
},
{
"epoch": 0.03786086133459536,
"grad_norm": 2.1566147804260254,
"learning_rate": 9.913533761814537e-05,
"loss": 3.0277,
"step": 5
},
{
"epoch": 0.04543303360151443,
"grad_norm": 2.4533753395080566,
"learning_rate": 9.846666218300807e-05,
"loss": 3.0663,
"step": 6
},
{
"epoch": 0.053005205868433505,
"grad_norm": 3.8815910816192627,
"learning_rate": 9.761185582727977e-05,
"loss": 2.9878,
"step": 7
},
{
"epoch": 0.06057737813535258,
"grad_norm": 1.6462730169296265,
"learning_rate": 9.657457896300791e-05,
"loss": 2.9207,
"step": 8
},
{
"epoch": 0.06814955040227165,
"grad_norm": 0.9676688313484192,
"learning_rate": 9.535927336897098e-05,
"loss": 2.8042,
"step": 9
},
{
"epoch": 0.07572172266919072,
"grad_norm": 3.804490566253662,
"learning_rate": 9.397114317029975e-05,
"loss": 2.7335,
"step": 10
},
{
"epoch": 0.0832938949361098,
"grad_norm": 1.113680124282837,
"learning_rate": 9.241613255361455e-05,
"loss": 2.7169,
"step": 11
},
{
"epoch": 0.09086606720302887,
"grad_norm": 1.01719069480896,
"learning_rate": 9.070090031310558e-05,
"loss": 2.4422,
"step": 12
},
{
"epoch": 0.09843823946994794,
"grad_norm": 0.8143924474716187,
"learning_rate": 8.883279133655399e-05,
"loss": 2.5477,
"step": 13
},
{
"epoch": 0.10601041173686701,
"grad_norm": 1.0786701440811157,
"learning_rate": 8.681980515339464e-05,
"loss": 2.6932,
"step": 14
},
{
"epoch": 0.11358258400378608,
"grad_norm": 1.154252529144287,
"learning_rate": 8.467056167950311e-05,
"loss": 2.7261,
"step": 15
},
{
"epoch": 0.12115475627070516,
"grad_norm": 1.010557770729065,
"learning_rate": 8.239426430539243e-05,
"loss": 2.8172,
"step": 16
},
{
"epoch": 0.12872692853762424,
"grad_norm": 0.6834193468093872,
"learning_rate": 8.000066048588211e-05,
"loss": 2.7133,
"step": 17
},
{
"epoch": 0.1362991008045433,
"grad_norm": 0.8263300657272339,
"learning_rate": 7.75e-05,
"loss": 2.778,
"step": 18
},
{
"epoch": 0.14387127307146239,
"grad_norm": 0.9877240657806396,
"learning_rate": 7.490299105985507e-05,
"loss": 2.8338,
"step": 19
},
{
"epoch": 0.15144344533838144,
"grad_norm": 1.397219181060791,
"learning_rate": 7.222075445642904e-05,
"loss": 2.8442,
"step": 20
},
{
"epoch": 0.15901561760530053,
"grad_norm": 1.878542184829712,
"learning_rate": 6.946477593864228e-05,
"loss": 2.6447,
"step": 21
},
{
"epoch": 0.1665877898722196,
"grad_norm": 2.025350332260132,
"learning_rate": 6.664685702961344e-05,
"loss": 2.7511,
"step": 22
},
{
"epoch": 0.17415996213913867,
"grad_norm": 2.2214548587799072,
"learning_rate": 6.377906449072578e-05,
"loss": 2.6628,
"step": 23
},
{
"epoch": 0.18173213440605773,
"grad_norm": 2.252363681793213,
"learning_rate": 6.087367864990233e-05,
"loss": 2.7163,
"step": 24
},
{
"epoch": 0.18930430667297682,
"grad_norm": 6.229862689971924,
"learning_rate": 5.794314081535644e-05,
"loss": 2.6675,
"step": 25
},
{
"epoch": 0.18930430667297682,
"eval_loss": 2.6197311878204346,
"eval_runtime": 3.2948,
"eval_samples_per_second": 15.175,
"eval_steps_per_second": 3.946,
"step": 25
},
{
"epoch": 0.19687647893989588,
"grad_norm": 0.5425540208816528,
"learning_rate": 5.500000000000001e-05,
"loss": 2.4719,
"step": 26
},
{
"epoch": 0.20444865120681496,
"grad_norm": 0.835626482963562,
"learning_rate": 5.205685918464356e-05,
"loss": 2.6482,
"step": 27
},
{
"epoch": 0.21202082347373402,
"grad_norm": 1.7947323322296143,
"learning_rate": 4.912632135009769e-05,
"loss": 2.7267,
"step": 28
},
{
"epoch": 0.2195929957406531,
"grad_norm": 4.438429832458496,
"learning_rate": 4.6220935509274235e-05,
"loss": 2.6783,
"step": 29
},
{
"epoch": 0.22716516800757217,
"grad_norm": 4.250818252563477,
"learning_rate": 4.3353142970386564e-05,
"loss": 2.7994,
"step": 30
},
{
"epoch": 0.23473734027449125,
"grad_norm": 2.890430450439453,
"learning_rate": 4.053522406135775e-05,
"loss": 2.8081,
"step": 31
},
{
"epoch": 0.2423095125414103,
"grad_norm": 2.2607815265655518,
"learning_rate": 3.777924554357096e-05,
"loss": 2.6962,
"step": 32
},
{
"epoch": 0.2498816848083294,
"grad_norm": 0.9068285822868347,
"learning_rate": 3.509700894014496e-05,
"loss": 2.6694,
"step": 33
},
{
"epoch": 0.2574538570752485,
"grad_norm": 0.7581325173377991,
"learning_rate": 3.250000000000001e-05,
"loss": 2.661,
"step": 34
},
{
"epoch": 0.2650260293421675,
"grad_norm": 0.9279335737228394,
"learning_rate": 2.9999339514117912e-05,
"loss": 2.6437,
"step": 35
},
{
"epoch": 0.2725982016090866,
"grad_norm": 0.7952417731285095,
"learning_rate": 2.760573569460757e-05,
"loss": 2.5672,
"step": 36
},
{
"epoch": 0.2801703738760057,
"grad_norm": 1.2510565519332886,
"learning_rate": 2.53294383204969e-05,
"loss": 2.4211,
"step": 37
},
{
"epoch": 0.28774254614292477,
"grad_norm": 0.6021161675453186,
"learning_rate": 2.3180194846605367e-05,
"loss": 2.4254,
"step": 38
},
{
"epoch": 0.2953147184098438,
"grad_norm": 0.6810365319252014,
"learning_rate": 2.1167208663446025e-05,
"loss": 2.6075,
"step": 39
},
{
"epoch": 0.3028868906767629,
"grad_norm": 0.8788719177246094,
"learning_rate": 1.9299099686894423e-05,
"loss": 2.6724,
"step": 40
},
{
"epoch": 0.310459062943682,
"grad_norm": 0.9619131088256836,
"learning_rate": 1.758386744638546e-05,
"loss": 2.647,
"step": 41
},
{
"epoch": 0.31803123521060106,
"grad_norm": 0.925391435623169,
"learning_rate": 1.602885682970026e-05,
"loss": 2.6874,
"step": 42
},
{
"epoch": 0.3256034074775201,
"grad_norm": 0.825603723526001,
"learning_rate": 1.464072663102903e-05,
"loss": 2.7573,
"step": 43
},
{
"epoch": 0.3331755797444392,
"grad_norm": 0.6580988764762878,
"learning_rate": 1.3425421036992098e-05,
"loss": 2.7402,
"step": 44
},
{
"epoch": 0.34074775201135826,
"grad_norm": 0.567483127117157,
"learning_rate": 1.2388144172720251e-05,
"loss": 2.6631,
"step": 45
},
{
"epoch": 0.34831992427827735,
"grad_norm": 0.555555522441864,
"learning_rate": 1.1533337816991932e-05,
"loss": 2.7038,
"step": 46
},
{
"epoch": 0.3558920965451964,
"grad_norm": 0.7060038447380066,
"learning_rate": 1.0864662381854632e-05,
"loss": 2.5818,
"step": 47
},
{
"epoch": 0.36346426881211547,
"grad_norm": 0.8900313377380371,
"learning_rate": 1.0384981238178534e-05,
"loss": 2.5252,
"step": 48
},
{
"epoch": 0.37103644107903455,
"grad_norm": 1.1769415140151978,
"learning_rate": 1.0096348454262845e-05,
"loss": 2.4474,
"step": 49
},
{
"epoch": 0.37860861334595364,
"grad_norm": 2.9755210876464844,
"learning_rate": 1e-05,
"loss": 2.4783,
"step": 50
},
{
"epoch": 0.37860861334595364,
"eval_loss": 2.5627858638763428,
"eval_runtime": 3.3177,
"eval_samples_per_second": 15.071,
"eval_steps_per_second": 3.918,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.32019209568256e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}