| { | |
| "best_metric": 2.28448224067688, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.018947019397011107, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00037894038794022213, | |
| "grad_norm": 41.42342758178711, | |
| "learning_rate": 5e-05, | |
| "loss": 5.0871, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00037894038794022213, | |
| "eval_loss": 6.468197822570801, | |
| "eval_runtime": 948.8603, | |
| "eval_samples_per_second": 18.736, | |
| "eval_steps_per_second": 2.343, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007578807758804443, | |
| "grad_norm": 49.051673889160156, | |
| "learning_rate": 0.0001, | |
| "loss": 5.6547, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0011368211638206665, | |
| "grad_norm": 53.116275787353516, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 5.7698, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0015157615517608885, | |
| "grad_norm": 67.34286499023438, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 5.3108, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0018947019397011107, | |
| "grad_norm": 84.63033294677734, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 4.9954, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002273642327641333, | |
| "grad_norm": 92.24832916259766, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.0311, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002652582715581555, | |
| "grad_norm": 92.74950408935547, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 3.4383, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.003031523103521777, | |
| "grad_norm": 55.20710372924805, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.6935, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0034104634914619994, | |
| "grad_norm": 31.44512939453125, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.6105, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0037894038794022214, | |
| "grad_norm": 31.56848907470703, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.6512, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004168344267342443, | |
| "grad_norm": 26.10360336303711, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.7422, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.004547284655282666, | |
| "grad_norm": 22.286645889282227, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.6847, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.004926225043222888, | |
| "grad_norm": 33.60494613647461, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.5989, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.00530516543116311, | |
| "grad_norm": 57.28451156616211, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.7178, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.005684105819103332, | |
| "grad_norm": 30.965965270996094, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.4546, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006063046207043554, | |
| "grad_norm": 19.96285629272461, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.412, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.006441986594983777, | |
| "grad_norm": 19.304079055786133, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.4099, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.006820926982923999, | |
| "grad_norm": 26.206418991088867, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3938, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.007199867370864221, | |
| "grad_norm": 27.039033889770508, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.4971, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.007578807758804443, | |
| "grad_norm": 27.811473846435547, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.4299, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007957748146744666, | |
| "grad_norm": 24.03557777404785, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.4618, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.008336688534684887, | |
| "grad_norm": 20.3538818359375, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.3906, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.00871562892262511, | |
| "grad_norm": 18.857227325439453, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.4056, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.009094569310565332, | |
| "grad_norm": 18.808645248413086, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.4523, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.009473509698505553, | |
| "grad_norm": 19.10662269592285, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.4367, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009473509698505553, | |
| "eval_loss": 2.3853487968444824, | |
| "eval_runtime": 1485.5718, | |
| "eval_samples_per_second": 11.967, | |
| "eval_steps_per_second": 1.496, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009852450086445776, | |
| "grad_norm": 41.54273223876953, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5266, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.010231390474385997, | |
| "grad_norm": 37.918094635009766, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.3561, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.01061033086232622, | |
| "grad_norm": 32.39877700805664, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.3502, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.010989271250266443, | |
| "grad_norm": 33.80083465576172, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.4292, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.011368211638206664, | |
| "grad_norm": 24.64554786682129, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.4089, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011747152026146887, | |
| "grad_norm": 21.70261573791504, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.3391, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.012126092414087108, | |
| "grad_norm": 20.256654739379883, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.262, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.012505032802027331, | |
| "grad_norm": 15.916815757751465, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.2547, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.012883973189967554, | |
| "grad_norm": 19.03730010986328, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.3206, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.013262913577907775, | |
| "grad_norm": 21.43941307067871, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.2924, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013641853965847998, | |
| "grad_norm": 22.336946487426758, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.3934, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.014020794353788219, | |
| "grad_norm": 37.155521392822266, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.5508, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.014399734741728442, | |
| "grad_norm": 24.519384384155273, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.4562, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.014778675129668664, | |
| "grad_norm": 16.592533111572266, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.1991, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.015157615517608886, | |
| "grad_norm": 16.430328369140625, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.2824, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015536555905549108, | |
| "grad_norm": 16.076345443725586, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.2632, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.01591549629348933, | |
| "grad_norm": 15.423989295959473, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.2627, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.016294436681429554, | |
| "grad_norm": 17.79759979248047, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.3937, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.016673377069369773, | |
| "grad_norm": 17.390098571777344, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.3232, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.017052317457309996, | |
| "grad_norm": 16.93052864074707, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.2348, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01743125784525022, | |
| "grad_norm": 17.974763870239258, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.3418, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.017810198233190442, | |
| "grad_norm": 20.516761779785156, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.2928, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.018189138621130665, | |
| "grad_norm": 19.835205078125, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.4389, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.018568079009070884, | |
| "grad_norm": 30.226259231567383, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.348, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.018947019397011107, | |
| "grad_norm": 38.83269119262695, | |
| "learning_rate": 0.0, | |
| "loss": 2.4241, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018947019397011107, | |
| "eval_loss": 2.28448224067688, | |
| "eval_runtime": 1485.3063, | |
| "eval_samples_per_second": 11.969, | |
| "eval_steps_per_second": 1.497, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.967137622687744e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |