| { | |
| "best_metric": 10.375041007995605, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.0963159162051529, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001926318324103058, | |
| "grad_norm": 0.017134863883256912, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3772, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001926318324103058, | |
| "eval_loss": 10.376731872558594, | |
| "eval_runtime": 4.3149, | |
| "eval_samples_per_second": 810.683, | |
| "eval_steps_per_second": 101.509, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003852636648206116, | |
| "grad_norm": 0.01785031147301197, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3775, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005778954972309174, | |
| "grad_norm": 0.018595920875668526, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 10.3776, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007705273296412232, | |
| "grad_norm": 0.01824306882917881, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 10.3772, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00963159162051529, | |
| "grad_norm": 0.017736271023750305, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 10.3768, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.011557909944618349, | |
| "grad_norm": 0.01673169620335102, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 10.3766, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013484228268721405, | |
| "grad_norm": 0.01604505628347397, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 10.3769, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.015410546592824464, | |
| "grad_norm": 0.013165425509214401, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.3766, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.017336864916927524, | |
| "grad_norm": 0.013424793258309364, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 10.3761, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01926318324103058, | |
| "grad_norm": 0.012556428089737892, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3756, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021189501565133637, | |
| "grad_norm": 0.017751269042491913, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 10.3751, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.023115819889236697, | |
| "grad_norm": 0.03788875415921211, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 10.3754, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.025042138213339754, | |
| "grad_norm": 0.014531556516885757, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 10.3755, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.02696845653744281, | |
| "grad_norm": 0.018963413313031197, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.3761, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.02889477486154587, | |
| "grad_norm": 0.0179679486900568, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 10.3756, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.030821093185648928, | |
| "grad_norm": 0.018420385196805, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 10.3764, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.03274741150975199, | |
| "grad_norm": 0.01803528517484665, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 10.3763, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.03467372983385505, | |
| "grad_norm": 0.017887067049741745, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 10.3761, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0366000481579581, | |
| "grad_norm": 0.01678159460425377, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 10.3757, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.03852636648206116, | |
| "grad_norm": 0.016594473272562027, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.376, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04045268480616422, | |
| "grad_norm": 0.012984883040189743, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 10.3756, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.042379003130267275, | |
| "grad_norm": 0.014251720160245895, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 10.376, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.044305321454370335, | |
| "grad_norm": 0.014976712875068188, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 10.3756, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.046231639778473395, | |
| "grad_norm": 0.029554875567555428, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 10.3746, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.04815795810257645, | |
| "grad_norm": 0.04060554876923561, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 10.3748, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04815795810257645, | |
| "eval_loss": 10.375431060791016, | |
| "eval_runtime": 4.5126, | |
| "eval_samples_per_second": 775.167, | |
| "eval_steps_per_second": 97.062, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05008427642667951, | |
| "grad_norm": 0.017374927178025246, | |
| "learning_rate": 5e-05, | |
| "loss": 10.3758, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.05201059475078257, | |
| "grad_norm": 0.01883726380765438, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 10.3753, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.05393691307488562, | |
| "grad_norm": 0.0194549597799778, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 10.375, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.05586323139898868, | |
| "grad_norm": 0.02029833383858204, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 10.3754, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.05778954972309174, | |
| "grad_norm": 0.02029760368168354, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3755, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0597158680471948, | |
| "grad_norm": 0.019594980403780937, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 10.3748, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.061642186371297855, | |
| "grad_norm": 0.016207123175263405, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 10.3758, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.06356850469540092, | |
| "grad_norm": 0.014481107704341412, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 10.3754, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.06549482301950398, | |
| "grad_norm": 0.01565168984234333, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 10.3749, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.06742114134360704, | |
| "grad_norm": 0.01421188935637474, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 10.3751, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0693474596677101, | |
| "grad_norm": 0.020938636735081673, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 10.3757, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.07127377799181314, | |
| "grad_norm": 0.03991640731692314, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 10.3748, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0732000963159162, | |
| "grad_norm": 0.017153754830360413, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 10.3752, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.07512641464001926, | |
| "grad_norm": 0.020170168951153755, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 10.3758, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.07705273296412232, | |
| "grad_norm": 0.02071978710591793, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.3752, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07897905128822538, | |
| "grad_norm": 0.021749036386609077, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 10.3754, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.08090536961232844, | |
| "grad_norm": 0.02003314718604088, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 10.3752, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.08283168793643149, | |
| "grad_norm": 0.02103583887219429, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 10.3756, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.08475800626053455, | |
| "grad_norm": 0.01838034950196743, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 10.3757, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.08668432458463761, | |
| "grad_norm": 0.017888696864247322, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 10.3758, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08861064290874067, | |
| "grad_norm": 0.014699080027639866, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 10.375, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.09053696123284373, | |
| "grad_norm": 0.014515848830342293, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 10.3747, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.09246327955694679, | |
| "grad_norm": 0.01529916375875473, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 10.3752, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.09438959788104985, | |
| "grad_norm": 0.030164409428834915, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 10.3744, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0963159162051529, | |
| "grad_norm": 0.03701487183570862, | |
| "learning_rate": 0.0, | |
| "loss": 10.375, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0963159162051529, | |
| "eval_loss": 10.375041007995605, | |
| "eval_runtime": 4.3206, | |
| "eval_samples_per_second": 809.616, | |
| "eval_steps_per_second": 101.376, | |
| "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": 43369485434880.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |