| { | |
| "best_metric": 0.8562852740287781, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.125, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0025, | |
| "grad_norm": 0.3971959948539734, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5395, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0025, | |
| "eval_loss": 1.1322004795074463, | |
| "eval_runtime": 3.9712, | |
| "eval_samples_per_second": 12.591, | |
| "eval_steps_per_second": 3.274, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005, | |
| "grad_norm": 0.4969935119152069, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6558, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0075, | |
| "grad_norm": 0.4038621783256531, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.6895, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "grad_norm": 1.0576386451721191, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.7636, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0125, | |
| "grad_norm": 0.685674786567688, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.7734, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.015, | |
| "grad_norm": 0.6992109417915344, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.8644, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0175, | |
| "grad_norm": 0.3900702893733978, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.7884, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "grad_norm": 0.4977249205112457, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.8432, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0225, | |
| "grad_norm": 0.5239284634590149, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.9342, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.025, | |
| "grad_norm": 0.6216078400611877, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 1.0346, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0275, | |
| "grad_norm": 0.6671596765518188, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 1.0471, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "grad_norm": 0.8819237947463989, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.1599, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0325, | |
| "grad_norm": 0.4116205871105194, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.5751, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.035, | |
| "grad_norm": 0.41587910056114197, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.5604, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0375, | |
| "grad_norm": 0.34116992354393005, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.5859, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.429836630821228, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.6672, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0425, | |
| "grad_norm": 0.37650197744369507, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.6814, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.045, | |
| "grad_norm": 0.3543069362640381, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.6907, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0475, | |
| "grad_norm": 0.3654783070087433, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.7604, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "grad_norm": 0.3880738914012909, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7461, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0525, | |
| "grad_norm": 0.44006282091140747, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.8202, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.055, | |
| "grad_norm": 0.49291035532951355, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.8413, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0575, | |
| "grad_norm": 0.5791784524917603, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.8998, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "grad_norm": 0.6938871741294861, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 1.045, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "grad_norm": 0.9933279156684875, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 1.2349, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0625, | |
| "eval_loss": 0.8781389594078064, | |
| "eval_runtime": 4.0776, | |
| "eval_samples_per_second": 12.262, | |
| "eval_steps_per_second": 3.188, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.065, | |
| "grad_norm": 0.270175963640213, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.489, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0675, | |
| "grad_norm": 0.2893918454647064, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6359, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "grad_norm": 0.3046613335609436, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.6455, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0725, | |
| "grad_norm": 0.3335619568824768, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.6744, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.075, | |
| "grad_norm": 0.3445623517036438, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.6907, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0775, | |
| "grad_norm": 0.3691665232181549, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.7053, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3850746750831604, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.7444, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0825, | |
| "grad_norm": 0.4230135381221771, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.7554, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.085, | |
| "grad_norm": 0.5101211071014404, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.8672, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0875, | |
| "grad_norm": 0.616494357585907, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.8741, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "grad_norm": 0.7683385610580444, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.885, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0925, | |
| "grad_norm": 0.8297840356826782, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 1.1771, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.095, | |
| "grad_norm": 0.3354261517524719, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.5277, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0975, | |
| "grad_norm": 0.33234667778015137, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.5691, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "grad_norm": 0.36417073011398315, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.6006, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1025, | |
| "grad_norm": 0.37846243381500244, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.6895, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.105, | |
| "grad_norm": 0.3880544900894165, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.7326, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.1075, | |
| "grad_norm": 0.365140825510025, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.6952, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "grad_norm": 0.38633495569229126, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.7239, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.1125, | |
| "grad_norm": 0.3560256063938141, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.6973, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.115, | |
| "grad_norm": 0.40417200326919556, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.7619, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.1175, | |
| "grad_norm": 0.48786085844039917, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.8403, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.5909727811813354, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.9017, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.1225, | |
| "grad_norm": 0.7687093615531921, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 1.0387, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "grad_norm": 1.0339679718017578, | |
| "learning_rate": 1e-05, | |
| "loss": 1.1475, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.125, | |
| "eval_loss": 0.8562852740287781, | |
| "eval_runtime": 4.0326, | |
| "eval_samples_per_second": 12.399, | |
| "eval_steps_per_second": 3.224, | |
| "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": 6.189915553566556e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |