| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.932811944543192, | |
| "eval_steps": 500, | |
| "global_step": 16500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08887308922858159, | |
| "grad_norm": 20.37746810913086, | |
| "learning_rate": 4.851878184619031e-05, | |
| "loss": 0.6617, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.17774617845716317, | |
| "grad_norm": 8.832418441772461, | |
| "learning_rate": 4.703756369238061e-05, | |
| "loss": 0.5007, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.26661926768574473, | |
| "grad_norm": 112.71693420410156, | |
| "learning_rate": 4.555634553857092e-05, | |
| "loss": 0.4867, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.35549235691432635, | |
| "grad_norm": 0.7494603991508484, | |
| "learning_rate": 4.407512738476123e-05, | |
| "loss": 0.5113, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.4443654461429079, | |
| "grad_norm": 0.5181692838668823, | |
| "learning_rate": 4.259390923095153e-05, | |
| "loss": 0.557, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.5332385353714895, | |
| "grad_norm": 0.8127353191375732, | |
| "learning_rate": 4.1112691077141844e-05, | |
| "loss": 0.4746, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.6221116246000711, | |
| "grad_norm": 52.21469497680664, | |
| "learning_rate": 3.9631472923332156e-05, | |
| "loss": 0.4848, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.7109847138286527, | |
| "grad_norm": 3.922440767288208, | |
| "learning_rate": 3.815025476952246e-05, | |
| "loss": 0.4689, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.7998578030572343, | |
| "grad_norm": 39.936492919921875, | |
| "learning_rate": 3.6669036615712765e-05, | |
| "loss": 0.4724, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.8887308922858158, | |
| "grad_norm": 3.033518075942993, | |
| "learning_rate": 3.518781846190307e-05, | |
| "loss": 0.4384, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.9776039815143974, | |
| "grad_norm": 8.464579582214355, | |
| "learning_rate": 3.370660030809338e-05, | |
| "loss": 0.4534, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.066477070742979, | |
| "grad_norm": 0.24204222857952118, | |
| "learning_rate": 3.2225382154283686e-05, | |
| "loss": 0.3978, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.1553501599715605, | |
| "grad_norm": 0.057052597403526306, | |
| "learning_rate": 3.074416400047399e-05, | |
| "loss": 0.3852, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 1.2442232492001422, | |
| "grad_norm": 0.15880955755710602, | |
| "learning_rate": 2.92629458466643e-05, | |
| "loss": 0.3915, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 1.3330963384287238, | |
| "grad_norm": 0.09902948141098022, | |
| "learning_rate": 2.7781727692854603e-05, | |
| "loss": 0.3785, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 1.4219694276573054, | |
| "grad_norm": 0.15144290030002594, | |
| "learning_rate": 2.6300509539044908e-05, | |
| "loss": 0.3587, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 1.510842516885887, | |
| "grad_norm": 0.22604715824127197, | |
| "learning_rate": 2.481929138523522e-05, | |
| "loss": 0.3811, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 1.5997156061144686, | |
| "grad_norm": 14.215106964111328, | |
| "learning_rate": 2.3338073231425524e-05, | |
| "loss": 0.3591, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 1.68858869534305, | |
| "grad_norm": 0.2168210744857788, | |
| "learning_rate": 2.1856855077615832e-05, | |
| "loss": 0.37, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 1.7774617845716318, | |
| "grad_norm": 0.15380479395389557, | |
| "learning_rate": 2.0375636923806137e-05, | |
| "loss": 0.3492, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 1.8663348738002132, | |
| "grad_norm": 0.09666112810373306, | |
| "learning_rate": 1.889441876999645e-05, | |
| "loss": 0.3922, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 1.9552079630287948, | |
| "grad_norm": 0.7467890381813049, | |
| "learning_rate": 1.7413200616186753e-05, | |
| "loss": 0.3786, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 2.0440810522573765, | |
| "grad_norm": 1.9722317457199097, | |
| "learning_rate": 1.593198246237706e-05, | |
| "loss": 0.3258, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 2.132954141485958, | |
| "grad_norm": 0.07470700144767761, | |
| "learning_rate": 1.4450764308567366e-05, | |
| "loss": 0.2807, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 2.2218272307145397, | |
| "grad_norm": 0.11256339401006699, | |
| "learning_rate": 1.2969546154757672e-05, | |
| "loss": 0.2751, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 2.310700319943121, | |
| "grad_norm": 0.010098825208842754, | |
| "learning_rate": 1.148832800094798e-05, | |
| "loss": 0.2385, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 2.399573409171703, | |
| "grad_norm": 0.15252766013145447, | |
| "learning_rate": 1.0007109847138287e-05, | |
| "loss": 0.2379, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 2.4884464984002843, | |
| "grad_norm": 17.05082130432129, | |
| "learning_rate": 8.525891693328595e-06, | |
| "loss": 0.2706, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 2.5773195876288657, | |
| "grad_norm": 0.11130794882774353, | |
| "learning_rate": 7.0446735395189e-06, | |
| "loss": 0.2591, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 2.6661926768574475, | |
| "grad_norm": 74.68379974365234, | |
| "learning_rate": 5.5634553857092076e-06, | |
| "loss": 0.3314, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 2.7550657660860294, | |
| "grad_norm": 15.91612434387207, | |
| "learning_rate": 4.082237231899514e-06, | |
| "loss": 0.2514, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 2.8439388553146108, | |
| "grad_norm": 39.0718994140625, | |
| "learning_rate": 2.601019078089821e-06, | |
| "loss": 0.2358, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 2.932811944543192, | |
| "grad_norm": 0.09988761693239212, | |
| "learning_rate": 1.119800924280128e-06, | |
| "loss": 0.2359, | |
| "step": 16500 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 16878, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4794112531464192.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |