| { | |
| "best_metric": 2.4227938652038574, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.0534550195567145, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.020860495436766623, | |
| "grad_norm": 9.733530044555664, | |
| "learning_rate": 5e-05, | |
| "loss": 6.9458, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.020860495436766623, | |
| "eval_loss": 9.503127098083496, | |
| "eval_runtime": 2.0464, | |
| "eval_samples_per_second": 24.433, | |
| "eval_steps_per_second": 6.353, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.041720990873533245, | |
| "grad_norm": 10.49179744720459, | |
| "learning_rate": 0.0001, | |
| "loss": 7.877, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06258148631029987, | |
| "grad_norm": 9.120818138122559, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 7.3715, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08344198174706649, | |
| "grad_norm": 6.438422203063965, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 6.5731, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10430247718383312, | |
| "grad_norm": 6.40809965133667, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 6.0948, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.12516297262059975, | |
| "grad_norm": 7.464506149291992, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 5.9117, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.14602346805736635, | |
| "grad_norm": 7.578457832336426, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 5.5103, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.16688396349413298, | |
| "grad_norm": 6.015934944152832, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 5.5119, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1877444589308996, | |
| "grad_norm": 11.263550758361816, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 4.9997, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.20860495436766624, | |
| "grad_norm": 12.682040214538574, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.9157, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22946544980443284, | |
| "grad_norm": 16.877872467041016, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.5108, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2503259452411995, | |
| "grad_norm": 20.40404510498047, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 5.0812, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.2711864406779661, | |
| "grad_norm": 14.97578239440918, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 4.9984, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.2920469361147327, | |
| "grad_norm": 6.86972713470459, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 4.5982, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.31290743155149936, | |
| "grad_norm": 4.815412998199463, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 4.3926, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.33376792698826596, | |
| "grad_norm": 4.70793342590332, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 4.336, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3546284224250326, | |
| "grad_norm": 4.900488376617432, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.998, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.3754889178617992, | |
| "grad_norm": 4.3667521476745605, | |
| "learning_rate": 7.75e-05, | |
| "loss": 4.0995, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.3963494132985658, | |
| "grad_norm": 3.6821374893188477, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 4.1878, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4172099087353325, | |
| "grad_norm": 3.6842868328094482, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.901, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4380704041720991, | |
| "grad_norm": 3.5541388988494873, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 2.8489, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.4589308996088657, | |
| "grad_norm": 4.352834701538086, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6377, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.47979139504563234, | |
| "grad_norm": 4.775582790374756, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.4793, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.500651890482399, | |
| "grad_norm": 4.74364709854126, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.8634, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5215123859191656, | |
| "grad_norm": 4.812182426452637, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.4721, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5215123859191656, | |
| "eval_loss": 2.924403190612793, | |
| "eval_runtime": 2.0621, | |
| "eval_samples_per_second": 24.248, | |
| "eval_steps_per_second": 6.304, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5423728813559322, | |
| "grad_norm": 4.208644866943359, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.495, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.5632333767926988, | |
| "grad_norm": 3.7513959407806396, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 3.5881, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.5840938722294654, | |
| "grad_norm": 3.0269153118133545, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.5614, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6049543676662321, | |
| "grad_norm": 3.4557063579559326, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.5098, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6258148631029987, | |
| "grad_norm": 3.736849308013916, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.4906, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6466753585397653, | |
| "grad_norm": 4.803586006164551, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.6127, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.6675358539765319, | |
| "grad_norm": 6.40614652633667, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.7518, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.6883963494132985, | |
| "grad_norm": 4.483238220214844, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 1.7023, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7092568448500652, | |
| "grad_norm": 1.4310004711151123, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.2358, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7301173402868318, | |
| "grad_norm": 2.1178836822509766, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.07, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7509778357235984, | |
| "grad_norm": 3.472343683242798, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.0525, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.771838331160365, | |
| "grad_norm": 3.5565571784973145, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 3.2537, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.7926988265971316, | |
| "grad_norm": 3.446967601776123, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.1724, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8135593220338984, | |
| "grad_norm": 3.225677490234375, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.2635, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.834419817470665, | |
| "grad_norm": 3.0172581672668457, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.2634, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.8552803129074316, | |
| "grad_norm": 3.3737077713012695, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.4262, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.8761408083441982, | |
| "grad_norm": 3.4301564693450928, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.4815, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.8970013037809648, | |
| "grad_norm": 3.4359047412872314, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.4434, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9178617992177314, | |
| "grad_norm": 3.938171148300171, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.3815, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.9387222946544981, | |
| "grad_norm": 1.9196503162384033, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.7353, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9595827900912647, | |
| "grad_norm": 1.731357455253601, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.3883, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.9804432855280313, | |
| "grad_norm": 1.4864057302474976, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.0512, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0117340286831813, | |
| "grad_norm": 4.474582195281982, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 5.1054, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.032594524119948, | |
| "grad_norm": 2.65756893157959, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 2.9023, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.0534550195567145, | |
| "grad_norm": 2.487783432006836, | |
| "learning_rate": 1e-05, | |
| "loss": 2.6625, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.0534550195567145, | |
| "eval_loss": 2.4227938652038574, | |
| "eval_runtime": 2.066, | |
| "eval_samples_per_second": 24.201, | |
| "eval_steps_per_second": 6.292, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |