| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0010590639992374739, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.118127998474948e-05, | |
| "grad_norm": 0.2101120799779892, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3942, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.118127998474948e-05, | |
| "eval_loss": 10.403708457946777, | |
| "eval_runtime": 268.1681, | |
| "eval_samples_per_second": 148.258, | |
| "eval_steps_per_second": 74.129, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.236255996949896e-05, | |
| "grad_norm": 0.20717068016529083, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3948, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.354383995424843e-05, | |
| "grad_norm": 0.2090730518102646, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.409, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.472511993899791e-05, | |
| "grad_norm": 0.21802741289138794, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3764, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0001059063999237474, | |
| "grad_norm": 0.21404823660850525, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3959, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00012708767990849687, | |
| "grad_norm": 0.20767731964588165, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.376, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014826895989324636, | |
| "grad_norm": 0.22036834061145782, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3979, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00016945023987799583, | |
| "grad_norm": 0.2219642698764801, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3815, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001906315198627453, | |
| "grad_norm": 0.21895252168178558, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3867, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002118127998474948, | |
| "grad_norm": 0.21666066348552704, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.399, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00023299407983224426, | |
| "grad_norm": 0.21962043642997742, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3959, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00025417535981699373, | |
| "grad_norm": 0.27812445163726807, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3602, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0002753566398017432, | |
| "grad_norm": 0.22255368530750275, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3785, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0002965379197864927, | |
| "grad_norm": 0.2322796732187271, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3698, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0003177191997712422, | |
| "grad_norm": 0.267484575510025, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3784, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00033890047975599166, | |
| "grad_norm": 0.3014521300792694, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.367, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.00036008175974074113, | |
| "grad_norm": 0.2773747444152832, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.386, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0003812630397254906, | |
| "grad_norm": 0.23313163220882416, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3712, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00040244431971024006, | |
| "grad_norm": 0.2613055109977722, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3915, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0004236255996949896, | |
| "grad_norm": 0.277883917093277, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3587, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00044480687967973906, | |
| "grad_norm": 0.2852385938167572, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3558, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0004659881596644885, | |
| "grad_norm": 0.3128252625465393, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.3685, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.000487169439649238, | |
| "grad_norm": 0.2944328784942627, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3631, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0005083507196339875, | |
| "grad_norm": 0.2717386484146118, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3978, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005295319996187369, | |
| "grad_norm": 0.3077712655067444, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3605, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005295319996187369, | |
| "eval_loss": 10.377364158630371, | |
| "eval_runtime": 268.1587, | |
| "eval_samples_per_second": 148.263, | |
| "eval_steps_per_second": 74.131, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0005507132796034864, | |
| "grad_norm": 0.29744622111320496, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3543, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0005718945595882359, | |
| "grad_norm": 0.3198077380657196, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3582, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0005930758395729854, | |
| "grad_norm": 0.3042125105857849, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.3503, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0006142571195577349, | |
| "grad_norm": 0.31835922598838806, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3759, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0006354383995424844, | |
| "grad_norm": 0.3096944987773895, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3664, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0006566196795272338, | |
| "grad_norm": 0.32308197021484375, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3584, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0006778009595119833, | |
| "grad_norm": 0.343171626329422, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3525, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0006989822394967328, | |
| "grad_norm": 0.32908880710601807, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.374, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0007201635194814823, | |
| "grad_norm": 0.34512171149253845, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.391, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0007413447994662317, | |
| "grad_norm": 0.30201077461242676, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3747, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0007625260794509812, | |
| "grad_norm": 0.32104218006134033, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3582, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0007837073594357307, | |
| "grad_norm": 0.3781031370162964, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3578, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0008048886394204801, | |
| "grad_norm": 0.3561527729034424, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3755, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0008260699194052297, | |
| "grad_norm": 0.37884965538978577, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3643, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0008472511993899792, | |
| "grad_norm": 0.3193395435810089, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3406, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0008684324793747286, | |
| "grad_norm": 0.34663599729537964, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3519, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0008896137593594781, | |
| "grad_norm": 0.3503679931163788, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3813, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0009107950393442276, | |
| "grad_norm": 0.3438533544540405, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3496, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.000931976319328977, | |
| "grad_norm": 0.3700442314147949, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3515, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0009531575993137265, | |
| "grad_norm": 0.35162249207496643, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3779, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.000974338879298476, | |
| "grad_norm": 0.37360620498657227, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.363, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0009955201592832255, | |
| "grad_norm": 0.4056940972805023, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3698, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.001016701439267975, | |
| "grad_norm": 0.36040621995925903, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3676, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0010378827192527244, | |
| "grad_norm": 0.43919169902801514, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.3687, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0010590639992374739, | |
| "grad_norm": 0.482573539018631, | |
| "learning_rate": 0.0, | |
| "loss": 10.4012, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0010590639992374739, | |
| "eval_loss": 10.36749267578125, | |
| "eval_runtime": 268.1107, | |
| "eval_samples_per_second": 148.289, | |
| "eval_steps_per_second": 74.145, | |
| "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": 5346007449600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |