| { | |
| "best_metric": 0.39716607332229614, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2898550724637681, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005797101449275362, | |
| "grad_norm": 10.208795547485352, | |
| "learning_rate": 5e-05, | |
| "loss": 16.0627, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005797101449275362, | |
| "eval_loss": 16.929000854492188, | |
| "eval_runtime": 1.1119, | |
| "eval_samples_per_second": 44.969, | |
| "eval_steps_per_second": 11.692, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011594202898550725, | |
| "grad_norm": 10.654747009277344, | |
| "learning_rate": 0.0001, | |
| "loss": 16.069, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.017391304347826087, | |
| "grad_norm": 9.603225708007812, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 15.8954, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02318840579710145, | |
| "grad_norm": 9.658941268920898, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 14.9997, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.028985507246376812, | |
| "grad_norm": 9.447863578796387, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 12.737, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.034782608695652174, | |
| "grad_norm": 9.92809772491455, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 10.9932, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04057971014492753, | |
| "grad_norm": 10.60568904876709, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 9.9986, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0463768115942029, | |
| "grad_norm": 11.535539627075195, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 8.0154, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05217391304347826, | |
| "grad_norm": 13.508352279663086, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 6.612, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.057971014492753624, | |
| "grad_norm": 14.02491283416748, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 4.7346, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06376811594202898, | |
| "grad_norm": 12.741116523742676, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.1989, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06956521739130435, | |
| "grad_norm": 8.461541175842285, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 1.9065, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07536231884057971, | |
| "grad_norm": 5.787874221801758, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 1.5115, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.08115942028985507, | |
| "grad_norm": 6.2908244132995605, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 1.2384, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08695652173913043, | |
| "grad_norm": 4.603776454925537, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 0.9015, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0927536231884058, | |
| "grad_norm": 3.331716299057007, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 0.7981, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09855072463768116, | |
| "grad_norm": 4.428544044494629, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 0.7916, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10434782608695652, | |
| "grad_norm": 2.488654375076294, | |
| "learning_rate": 7.75e-05, | |
| "loss": 0.6879, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.11014492753623188, | |
| "grad_norm": 4.0563249588012695, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 0.7179, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11594202898550725, | |
| "grad_norm": 4.581613063812256, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 0.7083, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.12173913043478261, | |
| "grad_norm": 4.776706695556641, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 0.7742, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12753623188405797, | |
| "grad_norm": 3.9252874851226807, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 0.6682, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13333333333333333, | |
| "grad_norm": 2.8567593097686768, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 0.6622, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.1391304347826087, | |
| "grad_norm": 2.9367213249206543, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 0.619, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14492753623188406, | |
| "grad_norm": 3.3056252002716064, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 0.6961, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14492753623188406, | |
| "eval_loss": 0.6495192050933838, | |
| "eval_runtime": 1.1115, | |
| "eval_samples_per_second": 44.983, | |
| "eval_steps_per_second": 11.696, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.15072463768115943, | |
| "grad_norm": 3.3572421073913574, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 0.6819, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.1565217391304348, | |
| "grad_norm": 2.560725212097168, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 0.6434, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.16231884057971013, | |
| "grad_norm": 2.2695226669311523, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 0.6025, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.1681159420289855, | |
| "grad_norm": 2.8875999450683594, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 0.6578, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 2.134882688522339, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 0.5826, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17971014492753623, | |
| "grad_norm": 1.8630090951919556, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 0.5471, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1855072463768116, | |
| "grad_norm": 3.8702120780944824, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 0.5753, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.19130434782608696, | |
| "grad_norm": 1.330750584602356, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 0.5259, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19710144927536233, | |
| "grad_norm": 1.5397303104400635, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 0.5233, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2028985507246377, | |
| "grad_norm": 1.617982268333435, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 0.5063, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.20869565217391303, | |
| "grad_norm": 1.4378247261047363, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 0.4855, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2144927536231884, | |
| "grad_norm": 1.699135661125183, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 0.5608, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.22028985507246376, | |
| "grad_norm": 1.7574081420898438, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 0.5302, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.22608695652173913, | |
| "grad_norm": 1.6374109983444214, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 0.4257, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2318840579710145, | |
| "grad_norm": 2.2475686073303223, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 0.5505, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.23768115942028986, | |
| "grad_norm": 2.40238881111145, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 0.5059, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.24347826086956523, | |
| "grad_norm": 2.1908628940582275, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 0.4962, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2492753623188406, | |
| "grad_norm": 2.013533592224121, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 0.5273, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.25507246376811593, | |
| "grad_norm": 2.148557186126709, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 0.447, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2608695652173913, | |
| "grad_norm": 1.5102720260620117, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 0.4032, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 1.6244993209838867, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 0.4339, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.27246376811594203, | |
| "grad_norm": 1.256397008895874, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 0.4239, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.2782608695652174, | |
| "grad_norm": 2.4411745071411133, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 0.5304, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.28405797101449276, | |
| "grad_norm": 1.6444889307022095, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 0.4382, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2898550724637681, | |
| "grad_norm": 2.026066303253174, | |
| "learning_rate": 1e-05, | |
| "loss": 0.4483, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2898550724637681, | |
| "eval_loss": 0.39716607332229614, | |
| "eval_runtime": 1.1118, | |
| "eval_samples_per_second": 44.974, | |
| "eval_steps_per_second": 11.693, | |
| "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": 2.229252309123072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |