| { | |
| "best_metric": 3.096146821975708, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.03226456946965114, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006452913893930228, | |
| "grad_norm": 0.574839174747467, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3162, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006452913893930228, | |
| "eval_loss": 3.6529152393341064, | |
| "eval_runtime": 2.3223, | |
| "eval_samples_per_second": 21.531, | |
| "eval_steps_per_second": 5.598, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012905827787860456, | |
| "grad_norm": 0.7847986221313477, | |
| "learning_rate": 0.0001, | |
| "loss": 3.3277, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0019358741681790683, | |
| "grad_norm": 0.7542749643325806, | |
| "learning_rate": 9.990365154573717e-05, | |
| "loss": 3.3816, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002581165557572091, | |
| "grad_norm": 0.7341458201408386, | |
| "learning_rate": 9.961501876182148e-05, | |
| "loss": 3.3093, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003226456946965114, | |
| "grad_norm": 0.7249818444252014, | |
| "learning_rate": 9.913533761814537e-05, | |
| "loss": 3.2996, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0038717483363581366, | |
| "grad_norm": 0.7715960741043091, | |
| "learning_rate": 9.846666218300807e-05, | |
| "loss": 3.2916, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004517039725751159, | |
| "grad_norm": 0.6721057295799255, | |
| "learning_rate": 9.761185582727977e-05, | |
| "loss": 3.2502, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.005162331115144182, | |
| "grad_norm": 0.7479740977287292, | |
| "learning_rate": 9.657457896300791e-05, | |
| "loss": 3.2657, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005807622504537205, | |
| "grad_norm": 0.9009524583816528, | |
| "learning_rate": 9.535927336897098e-05, | |
| "loss": 3.4405, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006452913893930228, | |
| "grad_norm": 0.8615654706954956, | |
| "learning_rate": 9.397114317029975e-05, | |
| "loss": 3.5466, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.007098205283323251, | |
| "grad_norm": 0.7970622777938843, | |
| "learning_rate": 9.241613255361455e-05, | |
| "loss": 3.452, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007743496672716273, | |
| "grad_norm": 1.7848974466323853, | |
| "learning_rate": 9.070090031310558e-05, | |
| "loss": 3.4924, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.008388788062109296, | |
| "grad_norm": 2.9138290882110596, | |
| "learning_rate": 8.883279133655399e-05, | |
| "loss": 3.3885, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.009034079451502319, | |
| "grad_norm": 2.8835642337799072, | |
| "learning_rate": 8.681980515339464e-05, | |
| "loss": 3.3483, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009679370840895343, | |
| "grad_norm": 1.9729639291763306, | |
| "learning_rate": 8.467056167950311e-05, | |
| "loss": 3.207, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010324662230288365, | |
| "grad_norm": 0.8947727084159851, | |
| "learning_rate": 8.239426430539243e-05, | |
| "loss": 3.1475, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010969953619681387, | |
| "grad_norm": 1.0026689767837524, | |
| "learning_rate": 8.000066048588211e-05, | |
| "loss": 3.1175, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01161524500907441, | |
| "grad_norm": 1.1229300498962402, | |
| "learning_rate": 7.75e-05, | |
| "loss": 3.1363, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.012260536398467433, | |
| "grad_norm": 1.087923526763916, | |
| "learning_rate": 7.490299105985507e-05, | |
| "loss": 3.1274, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012905827787860456, | |
| "grad_norm": 0.49753323197364807, | |
| "learning_rate": 7.222075445642904e-05, | |
| "loss": 3.1879, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013551119177253478, | |
| "grad_norm": 0.7116471529006958, | |
| "learning_rate": 6.946477593864228e-05, | |
| "loss": 3.1611, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.014196410566646502, | |
| "grad_norm": 0.8382435441017151, | |
| "learning_rate": 6.664685702961344e-05, | |
| "loss": 3.361, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014841701956039524, | |
| "grad_norm": 0.8177525401115417, | |
| "learning_rate": 6.377906449072578e-05, | |
| "loss": 3.439, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.015486993345432546, | |
| "grad_norm": 0.8859652280807495, | |
| "learning_rate": 6.087367864990233e-05, | |
| "loss": 3.448, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.01613228473482557, | |
| "grad_norm": 1.3049736022949219, | |
| "learning_rate": 5.794314081535644e-05, | |
| "loss": 3.5132, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01613228473482557, | |
| "eval_loss": 3.1355321407318115, | |
| "eval_runtime": 1.9595, | |
| "eval_samples_per_second": 25.516, | |
| "eval_steps_per_second": 6.634, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016777576124218593, | |
| "grad_norm": 0.24698567390441895, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 3.0764, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.017422867513611617, | |
| "grad_norm": 0.24421782791614532, | |
| "learning_rate": 5.205685918464356e-05, | |
| "loss": 3.0893, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.018068158903004637, | |
| "grad_norm": 0.28326475620269775, | |
| "learning_rate": 4.912632135009769e-05, | |
| "loss": 3.1001, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.01871345029239766, | |
| "grad_norm": 0.308344304561615, | |
| "learning_rate": 4.6220935509274235e-05, | |
| "loss": 3.0855, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.019358741681790685, | |
| "grad_norm": 0.3393581807613373, | |
| "learning_rate": 4.3353142970386564e-05, | |
| "loss": 3.0941, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020004033071183706, | |
| "grad_norm": 0.36885160207748413, | |
| "learning_rate": 4.053522406135775e-05, | |
| "loss": 3.1291, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.02064932446057673, | |
| "grad_norm": 0.40527042746543884, | |
| "learning_rate": 3.777924554357096e-05, | |
| "loss": 3.1255, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.021294615849969754, | |
| "grad_norm": 0.39910948276519775, | |
| "learning_rate": 3.509700894014496e-05, | |
| "loss": 3.1406, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.021939907239362774, | |
| "grad_norm": 0.5128020644187927, | |
| "learning_rate": 3.250000000000001e-05, | |
| "loss": 3.2373, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.022585198628755798, | |
| "grad_norm": 0.5385227203369141, | |
| "learning_rate": 2.9999339514117912e-05, | |
| "loss": 3.3137, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02323049001814882, | |
| "grad_norm": 0.4920327663421631, | |
| "learning_rate": 2.760573569460757e-05, | |
| "loss": 3.3304, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.023875781407541843, | |
| "grad_norm": 0.927702009677887, | |
| "learning_rate": 2.53294383204969e-05, | |
| "loss": 3.3799, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.024521072796934867, | |
| "grad_norm": 0.3272736668586731, | |
| "learning_rate": 2.3180194846605367e-05, | |
| "loss": 3.1169, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.025166364186327887, | |
| "grad_norm": 0.4105949401855469, | |
| "learning_rate": 2.1167208663446025e-05, | |
| "loss": 3.1145, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.02581165557572091, | |
| "grad_norm": 0.4404626786708832, | |
| "learning_rate": 1.9299099686894423e-05, | |
| "loss": 3.0417, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.026456946965113935, | |
| "grad_norm": 0.4399726390838623, | |
| "learning_rate": 1.758386744638546e-05, | |
| "loss": 3.0397, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.027102238354506956, | |
| "grad_norm": 0.39927875995635986, | |
| "learning_rate": 1.602885682970026e-05, | |
| "loss": 3.0521, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.02774752974389998, | |
| "grad_norm": 0.4015970528125763, | |
| "learning_rate": 1.464072663102903e-05, | |
| "loss": 3.0857, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.028392821133293004, | |
| "grad_norm": 0.3402881324291229, | |
| "learning_rate": 1.3425421036992098e-05, | |
| "loss": 3.115, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.029038112522686024, | |
| "grad_norm": 0.330485999584198, | |
| "learning_rate": 1.2388144172720251e-05, | |
| "loss": 3.0711, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02968340391207905, | |
| "grad_norm": 0.3675265610218048, | |
| "learning_rate": 1.1533337816991932e-05, | |
| "loss": 3.1623, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.030328695301472072, | |
| "grad_norm": 0.5795705318450928, | |
| "learning_rate": 1.0864662381854632e-05, | |
| "loss": 3.3602, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.030973986690865093, | |
| "grad_norm": 0.5248962044715881, | |
| "learning_rate": 1.0384981238178534e-05, | |
| "loss": 3.3047, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03161927808025811, | |
| "grad_norm": 1.0681005716323853, | |
| "learning_rate": 1.0096348454262845e-05, | |
| "loss": 3.3858, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.03226456946965114, | |
| "grad_norm": 1.1730180978775024, | |
| "learning_rate": 1e-05, | |
| "loss": 3.455, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03226456946965114, | |
| "eval_loss": 3.096146821975708, | |
| "eval_runtime": 1.9568, | |
| "eval_samples_per_second": 25.552, | |
| "eval_steps_per_second": 6.644, | |
| "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 | |
| } | |