| { | |
| "best_metric": 0.224692702293396, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.556420233463035, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0311284046692607, | |
| "grad_norm": 52.70968246459961, | |
| "learning_rate": 5e-05, | |
| "loss": 8.0843, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0311284046692607, | |
| "eval_loss": 8.973531723022461, | |
| "eval_runtime": 1.5439, | |
| "eval_samples_per_second": 32.385, | |
| "eval_steps_per_second": 8.42, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0622568093385214, | |
| "grad_norm": 53.89131164550781, | |
| "learning_rate": 0.0001, | |
| "loss": 8.5925, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0933852140077821, | |
| "grad_norm": 37.69356155395508, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 8.0115, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1245136186770428, | |
| "grad_norm": 15.508984565734863, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.6474, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.1556420233463035, | |
| "grad_norm": 22.018217086791992, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.004, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1867704280155642, | |
| "grad_norm": 12.03746509552002, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.3792, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2178988326848249, | |
| "grad_norm": 10.574116706848145, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 4.733, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2490272373540856, | |
| "grad_norm": 11.999857902526855, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 4.1143, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2801556420233463, | |
| "grad_norm": 13.117135047912598, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.1396, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.311284046692607, | |
| "grad_norm": 11.065128326416016, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.5544, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3424124513618677, | |
| "grad_norm": 8.749752044677734, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.1875, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3735408560311284, | |
| "grad_norm": 16.695640563964844, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 2.7578, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.4046692607003891, | |
| "grad_norm": 10.788463592529297, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 2.4173, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4357976653696498, | |
| "grad_norm": 9.146074295043945, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.9589, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.4669260700389105, | |
| "grad_norm": 8.945752143859863, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 1.5098, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4980544747081712, | |
| "grad_norm": 10.399638175964355, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.1905, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5291828793774319, | |
| "grad_norm": 9.355493545532227, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.4249, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5603112840466926, | |
| "grad_norm": 8.332611083984375, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.3049, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5914396887159533, | |
| "grad_norm": 6.5103864669799805, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.9483, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.622568093385214, | |
| "grad_norm": 5.166444301605225, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.748, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6536964980544747, | |
| "grad_norm": 3.8692352771759033, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.592, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6848249027237354, | |
| "grad_norm": 4.719802379608154, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.521, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.7159533073929961, | |
| "grad_norm": 4.014556407928467, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4679, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7470817120622568, | |
| "grad_norm": 5.582361698150635, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4608, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.7782101167315175, | |
| "grad_norm": 6.946940898895264, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.5128, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7782101167315175, | |
| "eval_loss": 0.3729974329471588, | |
| "eval_runtime": 1.0103, | |
| "eval_samples_per_second": 49.488, | |
| "eval_steps_per_second": 12.867, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.8093385214007782, | |
| "grad_norm": 6.1687211990356445, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.4149, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8404669260700389, | |
| "grad_norm": 4.363428115844727, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.3586, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8715953307392996, | |
| "grad_norm": 2.75276255607605, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.3073, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.9027237354085603, | |
| "grad_norm": 2.7687063217163086, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.3206, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.933852140077821, | |
| "grad_norm": 3.324737787246704, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.3263, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9649805447470817, | |
| "grad_norm": 3.30027174949646, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.3295, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9961089494163424, | |
| "grad_norm": 4.5243635177612305, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.353, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.027237354085603, | |
| "grad_norm": 7.758679389953613, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.589, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0583657587548638, | |
| "grad_norm": 3.8175582885742188, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.2994, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.0894941634241244, | |
| "grad_norm": 2.687283992767334, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.2773, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.1206225680933852, | |
| "grad_norm": 2.0834670066833496, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.2474, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1517509727626458, | |
| "grad_norm": 2.1409308910369873, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.2538, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.1828793774319066, | |
| "grad_norm": 2.018048048019409, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.2499, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.2140077821011672, | |
| "grad_norm": 2.7065320014953613, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.2588, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.245136186770428, | |
| "grad_norm": 3.8568458557128906, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.2751, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2762645914396886, | |
| "grad_norm": 1.778807520866394, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.2381, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.3073929961089494, | |
| "grad_norm": 1.6081846952438354, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.234, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.3385214007782102, | |
| "grad_norm": 1.3087798357009888, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.2232, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.3696498054474708, | |
| "grad_norm": 1.1397979259490967, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.2191, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.4007782101167314, | |
| "grad_norm": 1.1176964044570923, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.2301, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.4319066147859922, | |
| "grad_norm": 2.2158350944519043, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.2631, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.463035019455253, | |
| "grad_norm": 2.2761166095733643, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.248, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.4941634241245136, | |
| "grad_norm": 4.002376556396484, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.2715, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.5252918287937742, | |
| "grad_norm": 1.4426534175872803, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.2277, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.556420233463035, | |
| "grad_norm": 1.8565995693206787, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2096, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.556420233463035, | |
| "eval_loss": 0.224692702293396, | |
| "eval_runtime": 1.0263, | |
| "eval_samples_per_second": 48.717, | |
| "eval_steps_per_second": 12.666, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |