|
{ |
|
"best_metric": null, |
|
"best_model_checkpoint": null, |
|
"epoch": 2.155226558995065, |
|
"eval_steps": 500, |
|
"global_step": 300, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.07178106774338268, |
|
"grad_norm": 0.46034833788871765, |
|
"learning_rate": 2.380952380952381e-06, |
|
"loss": 1.2735, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.14356213548676536, |
|
"grad_norm": 0.17795707285404205, |
|
"learning_rate": 4.761904761904762e-06, |
|
"loss": 0.9311, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.21534320323014805, |
|
"grad_norm": 0.07722567766904831, |
|
"learning_rate": 7.1428571428571436e-06, |
|
"loss": 0.7258, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.2871242709735307, |
|
"grad_norm": 0.058059412986040115, |
|
"learning_rate": 9.523809523809525e-06, |
|
"loss": 0.6562, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.35890533871691344, |
|
"grad_norm": 0.05688474327325821, |
|
"learning_rate": 9.786666666666667e-06, |
|
"loss": 0.6236, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.4306864064602961, |
|
"grad_norm": 0.0652860477566719, |
|
"learning_rate": 9.52e-06, |
|
"loss": 0.6011, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.5024674742036788, |
|
"grad_norm": 0.09465105831623077, |
|
"learning_rate": 9.253333333333333e-06, |
|
"loss": 0.5775, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.5742485419470614, |
|
"grad_norm": 0.16655535995960236, |
|
"learning_rate": 8.986666666666666e-06, |
|
"loss": 0.5588, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.6460296096904441, |
|
"grad_norm": 0.11725710332393646, |
|
"learning_rate": 8.720000000000001e-06, |
|
"loss": 0.537, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.7178106774338269, |
|
"grad_norm": 0.044058505445718765, |
|
"learning_rate": 8.453333333333334e-06, |
|
"loss": 0.5187, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.7895917451772095, |
|
"grad_norm": 0.022063592448830605, |
|
"learning_rate": 8.186666666666667e-06, |
|
"loss": 0.51, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 0.8613728129205922, |
|
"grad_norm": 0.021037070080637932, |
|
"learning_rate": 7.92e-06, |
|
"loss": 0.5043, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 0.9331538806639749, |
|
"grad_norm": 0.01985151134431362, |
|
"learning_rate": 7.653333333333333e-06, |
|
"loss": 0.4985, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.0058322117541498, |
|
"grad_norm": 0.04843816161155701, |
|
"learning_rate": 7.386666666666667e-06, |
|
"loss": 0.5345, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.0776132794975326, |
|
"grad_norm": 0.02092103101313114, |
|
"learning_rate": 7.1200000000000004e-06, |
|
"loss": 0.4855, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.1493943472409152, |
|
"grad_norm": 0.020286045968532562, |
|
"learning_rate": 6.853333333333334e-06, |
|
"loss": 0.4794, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.221175414984298, |
|
"grad_norm": 0.020133651793003082, |
|
"learning_rate": 6.5866666666666666e-06, |
|
"loss": 0.4779, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.2929564827276807, |
|
"grad_norm": 0.020597418770194054, |
|
"learning_rate": 6.3200000000000005e-06, |
|
"loss": 0.4738, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.3647375504710633, |
|
"grad_norm": 0.020543133839964867, |
|
"learning_rate": 6.0533333333333335e-06, |
|
"loss": 0.4713, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.4365186182144458, |
|
"grad_norm": 0.0203793253749609, |
|
"learning_rate": 5.7866666666666674e-06, |
|
"loss": 0.4665, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.5082996859578286, |
|
"grad_norm": 0.020146360620856285, |
|
"learning_rate": 5.5200000000000005e-06, |
|
"loss": 0.4627, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.5800807537012114, |
|
"grad_norm": 0.020714716985821724, |
|
"learning_rate": 5.2533333333333336e-06, |
|
"loss": 0.4609, |
|
"step": 220 |
|
}, |
|
{ |
|
"epoch": 1.651861821444594, |
|
"grad_norm": 0.020331306383013725, |
|
"learning_rate": 4.986666666666667e-06, |
|
"loss": 0.458, |
|
"step": 230 |
|
}, |
|
{ |
|
"epoch": 1.7236428891879767, |
|
"grad_norm": 0.019636554643511772, |
|
"learning_rate": 4.7200000000000005e-06, |
|
"loss": 0.4559, |
|
"step": 240 |
|
}, |
|
{ |
|
"epoch": 1.7954239569313595, |
|
"grad_norm": 0.020189929753541946, |
|
"learning_rate": 4.453333333333334e-06, |
|
"loss": 0.454, |
|
"step": 250 |
|
}, |
|
{ |
|
"epoch": 1.867205024674742, |
|
"grad_norm": 0.020626794546842575, |
|
"learning_rate": 4.1866666666666675e-06, |
|
"loss": 0.4507, |
|
"step": 260 |
|
}, |
|
{ |
|
"epoch": 1.9389860924181246, |
|
"grad_norm": 0.02100289985537529, |
|
"learning_rate": 3.920000000000001e-06, |
|
"loss": 0.4498, |
|
"step": 270 |
|
}, |
|
{ |
|
"epoch": 2.0116644235082997, |
|
"grad_norm": 0.020512910559773445, |
|
"learning_rate": 3.6533333333333336e-06, |
|
"loss": 0.4824, |
|
"step": 280 |
|
}, |
|
{ |
|
"epoch": 2.083445491251682, |
|
"grad_norm": 0.02125644125044346, |
|
"learning_rate": 3.386666666666667e-06, |
|
"loss": 0.4383, |
|
"step": 290 |
|
}, |
|
{ |
|
"epoch": 2.155226558995065, |
|
"grad_norm": 0.021306023001670837, |
|
"learning_rate": 3.12e-06, |
|
"loss": 0.4377, |
|
"step": 300 |
|
} |
|
], |
|
"logging_steps": 10, |
|
"max_steps": 417, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 100, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": false |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 8.035788892038758e+17, |
|
"train_batch_size": 14, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|