| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016418204505155316, | |
| "eval_steps": 9, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.2836409010310635e-05, | |
| "grad_norm": 0.039061568677425385, | |
| "learning_rate": 1e-05, | |
| "loss": 10.374, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.2836409010310635e-05, | |
| "eval_loss": 10.37774658203125, | |
| "eval_runtime": 169.5857, | |
| "eval_samples_per_second": 151.227, | |
| "eval_steps_per_second": 18.905, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.567281802062127e-05, | |
| "grad_norm": 0.04970359802246094, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3808, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.85092270309319e-05, | |
| "grad_norm": 0.051377296447753906, | |
| "learning_rate": 3e-05, | |
| "loss": 10.3791, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013134563604124254, | |
| "grad_norm": 0.040986333042383194, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3831, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00016418204505155317, | |
| "grad_norm": 0.04276856407523155, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3766, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001970184540618638, | |
| "grad_norm": 0.03917916491627693, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3777, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00022985486307217442, | |
| "grad_norm": 0.054591104388237, | |
| "learning_rate": 7e-05, | |
| "loss": 10.3798, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002626912720824851, | |
| "grad_norm": 0.04181118682026863, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3828, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002955276810927957, | |
| "grad_norm": 0.039910946041345596, | |
| "learning_rate": 9e-05, | |
| "loss": 10.3794, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002955276810927957, | |
| "eval_loss": 10.377296447753906, | |
| "eval_runtime": 170.6195, | |
| "eval_samples_per_second": 150.311, | |
| "eval_steps_per_second": 18.79, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00032836409010310633, | |
| "grad_norm": 0.057242438197135925, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3841, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00036120049911341694, | |
| "grad_norm": 0.06191801652312279, | |
| "learning_rate": 9.99695413509548e-05, | |
| "loss": 10.3803, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0003940369081237276, | |
| "grad_norm": 0.06025468185544014, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 10.3891, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00042687331713403825, | |
| "grad_norm": 0.04083796963095665, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 10.3679, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00045970972614434885, | |
| "grad_norm": 0.04752117395401001, | |
| "learning_rate": 9.951340343707852e-05, | |
| "loss": 10.3791, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0004925461351546594, | |
| "grad_norm": 0.063045933842659, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 10.383, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0005253825441649702, | |
| "grad_norm": 0.03456421196460724, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 10.3785, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0005582189531752808, | |
| "grad_norm": 0.04961790144443512, | |
| "learning_rate": 9.851478631379982e-05, | |
| "loss": 10.3833, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0005910553621855914, | |
| "grad_norm": 0.05567217618227005, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 10.3881, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0005910553621855914, | |
| "eval_loss": 10.37619400024414, | |
| "eval_runtime": 170.4028, | |
| "eval_samples_per_second": 150.502, | |
| "eval_steps_per_second": 18.814, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0006238917711959021, | |
| "grad_norm": 0.038412440568208694, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.3748, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0006567281802062127, | |
| "grad_norm": 0.04399815946817398, | |
| "learning_rate": 9.698463103929542e-05, | |
| "loss": 10.3757, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006895645892165233, | |
| "grad_norm": 0.03764853626489639, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 10.3762, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0007224009982268339, | |
| "grad_norm": 0.052127059549093246, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 10.3771, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0007552374072371446, | |
| "grad_norm": 0.03697521612048149, | |
| "learning_rate": 9.493970231495835e-05, | |
| "loss": 10.374, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0007880738162474552, | |
| "grad_norm": 0.04965825751423836, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 10.3714, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0008209102252577658, | |
| "grad_norm": 0.038044273853302, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3757, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0008537466342680765, | |
| "grad_norm": 0.04307650402188301, | |
| "learning_rate": 9.24024048078213e-05, | |
| "loss": 10.3715, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0008865830432783871, | |
| "grad_norm": 0.041188716888427734, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 10.3712, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0008865830432783871, | |
| "eval_loss": 10.375112533569336, | |
| "eval_runtime": 170.1694, | |
| "eval_samples_per_second": 150.709, | |
| "eval_steps_per_second": 18.84, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0009194194522886977, | |
| "grad_norm": 0.03614542633295059, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 10.3765, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0009522558612990083, | |
| "grad_norm": 0.0354689322412014, | |
| "learning_rate": 8.940053768033609e-05, | |
| "loss": 10.3743, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.000985092270309319, | |
| "grad_norm": 0.0464780293405056, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 10.3809, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0010179286793196296, | |
| "grad_norm": 0.05983458459377289, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 10.3758, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0010507650883299403, | |
| "grad_norm": 0.04344520345330238, | |
| "learning_rate": 8.596699001693255e-05, | |
| "loss": 10.3735, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0010836014973402508, | |
| "grad_norm": 0.041173264384269714, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 10.3722, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0011164379063505615, | |
| "grad_norm": 0.041133031249046326, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 10.3769, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0011492743153608722, | |
| "grad_norm": 0.06315415352582932, | |
| "learning_rate": 8.213938048432697e-05, | |
| "loss": 10.378, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0011821107243711827, | |
| "grad_norm": 0.04024801030755043, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 10.373, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0011821107243711827, | |
| "eval_loss": 10.374061584472656, | |
| "eval_runtime": 170.5991, | |
| "eval_samples_per_second": 150.329, | |
| "eval_steps_per_second": 18.793, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0012149471333814934, | |
| "grad_norm": 0.042859919369220734, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 10.3751, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0012477835423918041, | |
| "grad_norm": 0.04361676052212715, | |
| "learning_rate": 7.795964517353735e-05, | |
| "loss": 10.3766, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0012806199514021146, | |
| "grad_norm": 0.053741976618766785, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 10.3753, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0013134563604124253, | |
| "grad_norm": 0.0702785924077034, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3751, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0013462927694227358, | |
| "grad_norm": 0.06600352376699448, | |
| "learning_rate": 7.347357813929454e-05, | |
| "loss": 10.3788, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0013791291784330465, | |
| "grad_norm": 0.037580136209726334, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 10.3778, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0014119655874433572, | |
| "grad_norm": 0.05780002847313881, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 10.375, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0014448019964536677, | |
| "grad_norm": 0.04174739867448807, | |
| "learning_rate": 6.873032967079561e-05, | |
| "loss": 10.3758, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0014776384054639784, | |
| "grad_norm": 0.053912002593278885, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 10.3738, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0014776384054639784, | |
| "eval_loss": 10.373043060302734, | |
| "eval_runtime": 170.5618, | |
| "eval_samples_per_second": 150.362, | |
| "eval_steps_per_second": 18.797, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0015104748144742892, | |
| "grad_norm": 0.044272515922784805, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.3758, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0015433112234845997, | |
| "grad_norm": 0.04709697142243385, | |
| "learning_rate": 6.378186779084995e-05, | |
| "loss": 10.3749, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0015761476324949104, | |
| "grad_norm": 0.04305019602179527, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 10.364, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.001608984041505221, | |
| "grad_norm": 0.049739986658096313, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 10.3708, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0016418204505155316, | |
| "grad_norm": 0.04268916696310043, | |
| "learning_rate": 5.868240888334653e-05, | |
| "loss": 10.3697, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2615122329600.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |