| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9991235758106923, | |
| "eval_steps": 500, | |
| "global_step": 285, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.017528483786152498, | |
| "grad_norm": 2.3260412216186523, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4745, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.035056967572304996, | |
| "grad_norm": 2.4670772552490234, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5049, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05258545135845749, | |
| "grad_norm": 2.598940372467041, | |
| "learning_rate": 2e-05, | |
| "loss": 0.509, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07011393514460999, | |
| "grad_norm": 2.3951876163482666, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4642, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0876424189307625, | |
| "grad_norm": 2.50634765625, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4899, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10517090271691498, | |
| "grad_norm": 2.51271390914917, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5057, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12269938650306748, | |
| "grad_norm": 2.2455062866210938, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4374, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.14022787028921999, | |
| "grad_norm": 2.7102108001708984, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4747, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.15775635407537247, | |
| "grad_norm": 2.5008888244628906, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4686, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.175284837861525, | |
| "grad_norm": 2.638371467590332, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4867, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.19281332164767748, | |
| "grad_norm": 2.447908878326416, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4578, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.21034180543382996, | |
| "grad_norm": 3.2303571701049805, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4797, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.22787028921998248, | |
| "grad_norm": 2.4729976654052734, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4778, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.24539877300613497, | |
| "grad_norm": 2.7793662548065186, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4679, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.26292725679228746, | |
| "grad_norm": 2.6131370067596436, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4866, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.28045574057843997, | |
| "grad_norm": 2.5630428791046143, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4802, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.2979842243645925, | |
| "grad_norm": 2.7526726722717285, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4572, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.31551270815074495, | |
| "grad_norm": 2.934720993041992, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4557, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.33304119193689746, | |
| "grad_norm": 2.7996726036071777, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4692, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.35056967572305, | |
| "grad_norm": 3.004939079284668, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4786, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.36809815950920244, | |
| "grad_norm": 2.67604660987854, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4955, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.38562664329535495, | |
| "grad_norm": 2.9146041870117188, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4509, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.40315512708150747, | |
| "grad_norm": 2.9048011302948, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4457, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.42068361086765993, | |
| "grad_norm": 2.4492969512939453, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4572, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.43821209465381245, | |
| "grad_norm": 2.833976984024048, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4538, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.45574057843996496, | |
| "grad_norm": 2.866576671600342, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4817, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4732690622261174, | |
| "grad_norm": 3.0097880363464355, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4555, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.49079754601226994, | |
| "grad_norm": 2.912531852722168, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5023, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5083260297984225, | |
| "grad_norm": 2.936351776123047, | |
| "learning_rate": 2e-05, | |
| "loss": 0.48, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.5258545135845749, | |
| "grad_norm": 2.962674856185913, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4526, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5433829973707275, | |
| "grad_norm": 2.743187189102173, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4774, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.5609114811568799, | |
| "grad_norm": 2.742067575454712, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4789, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5784399649430324, | |
| "grad_norm": 3.111201047897339, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4877, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.595968448729185, | |
| "grad_norm": 2.6774637699127197, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4867, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6134969325153374, | |
| "grad_norm": 3.2346479892730713, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4781, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.6310254163014899, | |
| "grad_norm": 2.714986801147461, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5008, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6485539000876425, | |
| "grad_norm": 2.6662895679473877, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4053, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.6660823838737949, | |
| "grad_norm": 3.0469818115234375, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4482, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6836108676599474, | |
| "grad_norm": 2.78334379196167, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4731, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.7011393514461, | |
| "grad_norm": 2.9470932483673096, | |
| "learning_rate": 2e-05, | |
| "loss": 0.444, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.7186678352322524, | |
| "grad_norm": 3.256516218185425, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4826, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.7361963190184049, | |
| "grad_norm": 3.080620765686035, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4561, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.7537248028045574, | |
| "grad_norm": 3.4312586784362793, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4471, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.7712532865907099, | |
| "grad_norm": 2.649163246154785, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4449, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.7887817703768624, | |
| "grad_norm": 2.7402210235595703, | |
| "learning_rate": 2e-05, | |
| "loss": 0.469, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.8063102541630149, | |
| "grad_norm": 3.1415464878082275, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4706, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.8238387379491674, | |
| "grad_norm": 3.1218481063842773, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4754, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.8413672217353199, | |
| "grad_norm": 3.197633743286133, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4614, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.8588957055214724, | |
| "grad_norm": 2.9509947299957275, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5037, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.8764241893076249, | |
| "grad_norm": 3.126260995864868, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4472, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.8939526730937774, | |
| "grad_norm": 3.562556028366089, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4515, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.9114811568799299, | |
| "grad_norm": 3.086526870727539, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5097, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.9290096406660824, | |
| "grad_norm": 3.190669059753418, | |
| "learning_rate": 2e-05, | |
| "loss": 0.462, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.9465381244522348, | |
| "grad_norm": 3.133270263671875, | |
| "learning_rate": 2e-05, | |
| "loss": 0.445, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.9640666082383874, | |
| "grad_norm": 3.3561840057373047, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4711, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.9815950920245399, | |
| "grad_norm": 3.056903123855591, | |
| "learning_rate": 2e-05, | |
| "loss": 0.5028, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.9991235758106923, | |
| "grad_norm": 2.7743754386901855, | |
| "learning_rate": 2e-05, | |
| "loss": 0.4612, | |
| "step": 285 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 285, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 285, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.111992390689751e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |