| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.5112474437627812, | |
| "eval_steps": 500, | |
| "global_step": 25500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01002445968162316, | |
| "grad_norm": 0.27810075879096985, | |
| "learning_rate": 2.969926620955131e-05, | |
| "loss": 0.0283, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.02004891936324632, | |
| "grad_norm": 0.32781505584716797, | |
| "learning_rate": 2.939853241910261e-05, | |
| "loss": 0.0244, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.03007337904486948, | |
| "grad_norm": 0.21168646216392517, | |
| "learning_rate": 2.9097798628653917e-05, | |
| "loss": 0.0235, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.04009783872649264, | |
| "grad_norm": 0.15510809421539307, | |
| "learning_rate": 2.879706483820522e-05, | |
| "loss": 0.0225, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.0501222984081158, | |
| "grad_norm": 0.2416733056306839, | |
| "learning_rate": 2.849633104775653e-05, | |
| "loss": 0.0221, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.06014675808973896, | |
| "grad_norm": 0.19131343066692352, | |
| "learning_rate": 2.819559725730783e-05, | |
| "loss": 0.021, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.07017121777136212, | |
| "grad_norm": 0.14675654470920563, | |
| "learning_rate": 2.7894863466859138e-05, | |
| "loss": 0.0209, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.08019567745298528, | |
| "grad_norm": 0.1758842021226883, | |
| "learning_rate": 2.7594129676410442e-05, | |
| "loss": 0.0205, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.09022013713460844, | |
| "grad_norm": 0.14844126999378204, | |
| "learning_rate": 2.729339588596175e-05, | |
| "loss": 0.0203, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.1002445968162316, | |
| "grad_norm": 0.25966688990592957, | |
| "learning_rate": 2.699266209551305e-05, | |
| "loss": 0.02, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.11026905649785476, | |
| "grad_norm": 0.15259282290935516, | |
| "learning_rate": 2.6691928305064358e-05, | |
| "loss": 0.0201, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.12029351617947792, | |
| "grad_norm": 0.2339366376399994, | |
| "learning_rate": 2.6391194514615663e-05, | |
| "loss": 0.0197, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.13031797586110108, | |
| "grad_norm": 0.19134366512298584, | |
| "learning_rate": 2.609046072416697e-05, | |
| "loss": 0.0195, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.14034243554272424, | |
| "grad_norm": 0.18384341895580292, | |
| "learning_rate": 2.578972693371827e-05, | |
| "loss": 0.0195, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.1503668952243474, | |
| "grad_norm": 0.12643477320671082, | |
| "learning_rate": 2.548899314326958e-05, | |
| "loss": 0.0189, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.16039135490597056, | |
| "grad_norm": 0.1328970193862915, | |
| "learning_rate": 2.5188259352820883e-05, | |
| "loss": 0.0189, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.17041581458759372, | |
| "grad_norm": 0.11257112771272659, | |
| "learning_rate": 2.488752556237219e-05, | |
| "loss": 0.0188, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.18044027426921688, | |
| "grad_norm": 0.1610465794801712, | |
| "learning_rate": 2.4586791771923492e-05, | |
| "loss": 0.0185, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.19046473395084004, | |
| "grad_norm": 0.19272467494010925, | |
| "learning_rate": 2.42860579814748e-05, | |
| "loss": 0.0186, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.2004891936324632, | |
| "grad_norm": 0.14881977438926697, | |
| "learning_rate": 2.3985324191026104e-05, | |
| "loss": 0.0185, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.21051365331408636, | |
| "grad_norm": 0.1241874098777771, | |
| "learning_rate": 2.368459040057741e-05, | |
| "loss": 0.0183, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.22053811299570952, | |
| "grad_norm": 0.13214462995529175, | |
| "learning_rate": 2.3383856610128712e-05, | |
| "loss": 0.0178, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.23056257267733268, | |
| "grad_norm": 0.1579483300447464, | |
| "learning_rate": 2.308312281968002e-05, | |
| "loss": 0.018, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.24058703235895584, | |
| "grad_norm": 0.15338820219039917, | |
| "learning_rate": 2.2782389029231324e-05, | |
| "loss": 0.0179, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.25061149204057903, | |
| "grad_norm": 0.25933489203453064, | |
| "learning_rate": 2.2481655238782632e-05, | |
| "loss": 0.018, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.26063595172220216, | |
| "grad_norm": 0.14008085429668427, | |
| "learning_rate": 2.2180921448333933e-05, | |
| "loss": 0.0178, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.27066041140382535, | |
| "grad_norm": 0.17158617079257965, | |
| "learning_rate": 2.188018765788524e-05, | |
| "loss": 0.0176, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.2806848710854485, | |
| "grad_norm": 0.1249169260263443, | |
| "learning_rate": 2.1579453867436545e-05, | |
| "loss": 0.0176, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.29070933076707167, | |
| "grad_norm": 0.15336212515830994, | |
| "learning_rate": 2.1278720076987853e-05, | |
| "loss": 0.0174, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.3007337904486948, | |
| "grad_norm": 0.17169423401355743, | |
| "learning_rate": 2.0977986286539154e-05, | |
| "loss": 0.0171, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.310758250130318, | |
| "grad_norm": 0.12056533992290497, | |
| "learning_rate": 2.067725249609046e-05, | |
| "loss": 0.0175, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.3207827098119411, | |
| "grad_norm": 0.15232908725738525, | |
| "learning_rate": 2.0376518705641766e-05, | |
| "loss": 0.017, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.3308071694935643, | |
| "grad_norm": 0.12425834685564041, | |
| "learning_rate": 2.0075784915193073e-05, | |
| "loss": 0.0173, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.34083162917518744, | |
| "grad_norm": 0.09441632032394409, | |
| "learning_rate": 1.9775051124744374e-05, | |
| "loss": 0.0171, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.35085608885681063, | |
| "grad_norm": 0.11303837597370148, | |
| "learning_rate": 1.9474317334295682e-05, | |
| "loss": 0.017, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.36088054853843377, | |
| "grad_norm": 0.13934484124183655, | |
| "learning_rate": 1.9173583543846986e-05, | |
| "loss": 0.0166, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.37090500822005695, | |
| "grad_norm": 0.17438557744026184, | |
| "learning_rate": 1.8872849753398294e-05, | |
| "loss": 0.0168, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.3809294679016801, | |
| "grad_norm": 0.10365904122591019, | |
| "learning_rate": 1.8572115962949595e-05, | |
| "loss": 0.0166, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.3909539275833033, | |
| "grad_norm": 0.10702642053365707, | |
| "learning_rate": 1.8271382172500902e-05, | |
| "loss": 0.0165, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.4009783872649264, | |
| "grad_norm": 0.08877725899219513, | |
| "learning_rate": 1.7970648382052207e-05, | |
| "loss": 0.0165, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.4110028469465496, | |
| "grad_norm": 0.1188698559999466, | |
| "learning_rate": 1.7669914591603514e-05, | |
| "loss": 0.0168, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.4210273066281727, | |
| "grad_norm": 0.08468133956193924, | |
| "learning_rate": 1.7369180801154815e-05, | |
| "loss": 0.0164, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.4310517663097959, | |
| "grad_norm": 0.09056028723716736, | |
| "learning_rate": 1.7068447010706123e-05, | |
| "loss": 0.0163, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.44107622599141905, | |
| "grad_norm": 0.14430883526802063, | |
| "learning_rate": 1.6767713220257427e-05, | |
| "loss": 0.0166, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.45110068567304223, | |
| "grad_norm": 0.0935540571808815, | |
| "learning_rate": 1.6466979429808735e-05, | |
| "loss": 0.0163, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.46112514535466537, | |
| "grad_norm": 0.08878663927316666, | |
| "learning_rate": 1.616624563936004e-05, | |
| "loss": 0.0163, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.47114960503628855, | |
| "grad_norm": 0.11340079456567764, | |
| "learning_rate": 1.5865511848911344e-05, | |
| "loss": 0.016, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.4811740647179117, | |
| "grad_norm": 0.1878892481327057, | |
| "learning_rate": 1.556477805846265e-05, | |
| "loss": 0.0163, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.4911985243995349, | |
| "grad_norm": 0.06906645745038986, | |
| "learning_rate": 1.5264044268013956e-05, | |
| "loss": 0.0164, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.5012229840811581, | |
| "grad_norm": 0.11366972327232361, | |
| "learning_rate": 1.496331047756526e-05, | |
| "loss": 0.0162, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.5112474437627812, | |
| "grad_norm": 0.10021985322237015, | |
| "learning_rate": 1.4662576687116564e-05, | |
| "loss": 0.016, | |
| "step": 25500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 49878, | |
| "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": 0.0, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |