| { | |
| "best_metric": 0.22630853950977325, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.30337504740235116, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006067500948047023, | |
| "grad_norm": 2.3925507068634033, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6663, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.006067500948047023, | |
| "eval_loss": 0.8734264373779297, | |
| "eval_runtime": 3.9541, | |
| "eval_samples_per_second": 12.645, | |
| "eval_steps_per_second": 3.288, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012135001896094046, | |
| "grad_norm": 1.986020565032959, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6833, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01820250284414107, | |
| "grad_norm": 1.0565606355667114, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 0.4843, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02427000379218809, | |
| "grad_norm": 1.0573176145553589, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 0.4526, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.030337504740235114, | |
| "grad_norm": 0.9442809224128723, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 0.4474, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03640500568828214, | |
| "grad_norm": 1.3014634847640991, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 0.458, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04247250663632916, | |
| "grad_norm": 1.3589190244674683, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 0.382, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04854000758437618, | |
| "grad_norm": 0.6996656060218811, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 0.4638, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05460750853242321, | |
| "grad_norm": 0.9042606949806213, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 0.3659, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06067500948047023, | |
| "grad_norm": 1.435241460800171, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 0.34, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06674251042851725, | |
| "grad_norm": 1.6041172742843628, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 0.4521, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.07281001137656427, | |
| "grad_norm": 2.595395565032959, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 0.5519, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0788775123246113, | |
| "grad_norm": 2.3777811527252197, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 0.3176, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08494501327265833, | |
| "grad_norm": 1.6618249416351318, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 0.3969, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.09101251422070535, | |
| "grad_norm": 1.199908971786499, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.3355, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09708001516875236, | |
| "grad_norm": 0.6158227920532227, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.2947, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.1031475161167994, | |
| "grad_norm": 0.6150046586990356, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.3583, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10921501706484642, | |
| "grad_norm": 0.5712833404541016, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.3118, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11528251801289344, | |
| "grad_norm": 0.6288195848464966, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.3097, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.12135001896094046, | |
| "grad_norm": 0.5716285109519958, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.3623, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12741751990898748, | |
| "grad_norm": 0.6264747977256775, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.3175, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1334850208570345, | |
| "grad_norm": 0.7028448581695557, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.3243, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13955252180508154, | |
| "grad_norm": 1.1365748643875122, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.3676, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.14562002275312855, | |
| "grad_norm": 1.3793036937713623, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.4114, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.15168752370117558, | |
| "grad_norm": 1.4198849201202393, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.274, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15168752370117558, | |
| "eval_loss": 0.23994900286197662, | |
| "eval_runtime": 4.0482, | |
| "eval_samples_per_second": 12.351, | |
| "eval_steps_per_second": 3.211, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1577550246492226, | |
| "grad_norm": 0.7292701005935669, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.1866, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.16382252559726962, | |
| "grad_norm": 0.46785980463027954, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.3407, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16989002654531665, | |
| "grad_norm": 0.39624592661857605, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.2456, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.17595752749336366, | |
| "grad_norm": 0.5996044874191284, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.2868, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1820250284414107, | |
| "grad_norm": 0.6050768494606018, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.3026, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.18809252938945772, | |
| "grad_norm": 0.5520008206367493, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.3086, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.19416003033750473, | |
| "grad_norm": 0.5303773283958435, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.342, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.20022753128555176, | |
| "grad_norm": 0.6441546678543091, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.3525, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.2062950322335988, | |
| "grad_norm": 0.5183490514755249, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.2628, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2123625331816458, | |
| "grad_norm": 0.5794525146484375, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.2773, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.21843003412969283, | |
| "grad_norm": 1.2633119821548462, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.3883, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.22449753507773987, | |
| "grad_norm": 2.0984978675842285, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.422, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.23056503602578687, | |
| "grad_norm": 0.7109975814819336, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.1681, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2366325369738339, | |
| "grad_norm": 0.4398191273212433, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.2961, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2427000379218809, | |
| "grad_norm": 0.2695257365703583, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.2445, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.24876753886992795, | |
| "grad_norm": 0.4018322825431824, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.2565, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.25483503981797495, | |
| "grad_norm": 0.44669589400291443, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.3254, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.260902540766022, | |
| "grad_norm": 0.3876776397228241, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.2492, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.266970041714069, | |
| "grad_norm": 0.44162696599960327, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.2914, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.27303754266211605, | |
| "grad_norm": 0.401747465133667, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.2792, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2791050436101631, | |
| "grad_norm": 0.3714073598384857, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.296, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.28517254455821006, | |
| "grad_norm": 0.39308562874794006, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.2146, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2912400455062571, | |
| "grad_norm": 0.49879807233810425, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.2932, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.29730754645430413, | |
| "grad_norm": 0.8610867261886597, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.3741, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.30337504740235116, | |
| "grad_norm": 0.6880888342857361, | |
| "learning_rate": 1e-05, | |
| "loss": 0.2975, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.30337504740235116, | |
| "eval_loss": 0.22630853950977325, | |
| "eval_runtime": 4.0151, | |
| "eval_samples_per_second": 12.453, | |
| "eval_steps_per_second": 3.238, | |
| "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": 6.174479344467968e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |