| { | |
| "best_metric": 0.04461386054754257, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.08278145695364239, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0016556291390728477, | |
| "grad_norm": 60.55550003051758, | |
| "learning_rate": 5e-05, | |
| "loss": 9.6147, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016556291390728477, | |
| "eval_loss": 1.729671835899353, | |
| "eval_runtime": 2.7379, | |
| "eval_samples_per_second": 18.262, | |
| "eval_steps_per_second": 4.748, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0033112582781456954, | |
| "grad_norm": 88.10015106201172, | |
| "learning_rate": 0.0001, | |
| "loss": 14.1212, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004966887417218543, | |
| "grad_norm": 78.02826690673828, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 9.2619, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006622516556291391, | |
| "grad_norm": 75.08650207519531, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 5.3035, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.008278145695364239, | |
| "grad_norm": 48.65683364868164, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.7546, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009933774834437087, | |
| "grad_norm": 51.727535247802734, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.3214, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011589403973509934, | |
| "grad_norm": 44.52106475830078, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 2.439, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.013245033112582781, | |
| "grad_norm": 38.45843505859375, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 1.5849, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014900662251655629, | |
| "grad_norm": 23.558330535888672, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 1.1648, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.016556291390728478, | |
| "grad_norm": 14.836483001708984, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.5373, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.018211920529801324, | |
| "grad_norm": 10.093094825744629, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.3844, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.019867549668874173, | |
| "grad_norm": 14.989266395568848, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.2357, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02152317880794702, | |
| "grad_norm": 23.200645446777344, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.6601, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.023178807947019868, | |
| "grad_norm": 22.931533813476562, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 2.4081, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.024834437086092714, | |
| "grad_norm": 35.96150588989258, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 2.2575, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.026490066225165563, | |
| "grad_norm": 22.532569885253906, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 1.8754, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.028145695364238412, | |
| "grad_norm": 13.657093048095703, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 1.4515, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.029801324503311258, | |
| "grad_norm": 12.508075714111328, | |
| "learning_rate": 7.75e-05, | |
| "loss": 1.2775, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.03145695364238411, | |
| "grad_norm": 10.395607948303223, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 1.1712, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.033112582781456956, | |
| "grad_norm": 10.008374214172363, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 1.0409, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0347682119205298, | |
| "grad_norm": 9.688435554504395, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.52, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03642384105960265, | |
| "grad_norm": 6.625133037567139, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.3953, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0380794701986755, | |
| "grad_norm": 7.011756896972656, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.3715, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.039735099337748346, | |
| "grad_norm": 6.321486949920654, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.231, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.041390728476821195, | |
| "grad_norm": 6.622514247894287, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.0867, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.041390728476821195, | |
| "eval_loss": 0.05529414117336273, | |
| "eval_runtime": 2.8552, | |
| "eval_samples_per_second": 17.512, | |
| "eval_steps_per_second": 4.553, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04304635761589404, | |
| "grad_norm": 15.081778526306152, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 1.8354, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.04470198675496689, | |
| "grad_norm": 13.045018196105957, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 1.4958, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.046357615894039736, | |
| "grad_norm": 10.834997177124023, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 1.3995, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.048013245033112585, | |
| "grad_norm": 10.475743293762207, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 1.1832, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04966887417218543, | |
| "grad_norm": 10.040482521057129, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.8479, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05132450331125828, | |
| "grad_norm": 9.801156044006348, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.9541, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.052980132450331126, | |
| "grad_norm": 9.155835151672363, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.8973, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.054635761589403975, | |
| "grad_norm": 9.182353019714355, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.6259, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.056291390728476824, | |
| "grad_norm": 8.900016784667969, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.5571, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.057947019867549666, | |
| "grad_norm": 6.651839733123779, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.2958, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.059602649006622516, | |
| "grad_norm": 9.37293815612793, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.2097, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.061258278145695365, | |
| "grad_norm": 3.1808083057403564, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.1149, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.06291390728476821, | |
| "grad_norm": 6.839907646179199, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.731, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06456953642384106, | |
| "grad_norm": 10.234563827514648, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 1.3803, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.06622516556291391, | |
| "grad_norm": 10.767460823059082, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 1.2713, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06788079470198675, | |
| "grad_norm": 13.208647727966309, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 1.0011, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0695364238410596, | |
| "grad_norm": 9.809880256652832, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.8504, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.07119205298013245, | |
| "grad_norm": 7.994148254394531, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.6678, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0728476821192053, | |
| "grad_norm": 10.173336029052734, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.7144, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07450331125827815, | |
| "grad_norm": 11.309749603271484, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.6579, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.076158940397351, | |
| "grad_norm": 12.104318618774414, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.5522, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07781456953642384, | |
| "grad_norm": 9.264493942260742, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.5053, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.07947019867549669, | |
| "grad_norm": 3.8863046169281006, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.1143, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.08112582781456953, | |
| "grad_norm": 8.043832778930664, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.2191, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.08278145695364239, | |
| "grad_norm": 3.410689115524292, | |
| "learning_rate": 1e-05, | |
| "loss": 0.0447, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08278145695364239, | |
| "eval_loss": 0.04461386054754257, | |
| "eval_runtime": 2.8406, | |
| "eval_samples_per_second": 17.602, | |
| "eval_steps_per_second": 4.577, | |
| "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": 5.659789468945613e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |