| { | |
| "best_metric": 2.295586347579956, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.031069167734669306, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006213833546933862, | |
| "grad_norm": 20.18564796447754, | |
| "learning_rate": 5e-05, | |
| "loss": 6.7432, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006213833546933862, | |
| "eval_loss": 8.449797630310059, | |
| "eval_runtime": 99.453, | |
| "eval_samples_per_second": 109.016, | |
| "eval_steps_per_second": 13.635, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012427667093867724, | |
| "grad_norm": 33.745121002197266, | |
| "learning_rate": 0.0001, | |
| "loss": 7.6447, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0018641500640801585, | |
| "grad_norm": 34.93381881713867, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.7703, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0024855334187735448, | |
| "grad_norm": 14.993317604064941, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 6.4022, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0031069167734669306, | |
| "grad_norm": 13.611467361450195, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.1388, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.003728300128160317, | |
| "grad_norm": 6.870720863342285, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 6.0277, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.004349683482853703, | |
| "grad_norm": 11.345956802368164, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 5.8643, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0049710668375470895, | |
| "grad_norm": 5.781732559204102, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.6858, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.005592450192240475, | |
| "grad_norm": 5.978038311004639, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 5.5732, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.006213833546933861, | |
| "grad_norm": 5.235627174377441, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 5.2231, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0068352169016272476, | |
| "grad_norm": 6.350806713104248, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 5.2827, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.007456600256320634, | |
| "grad_norm": 5.949211120605469, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 5.2801, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00807798361101402, | |
| "grad_norm": 5.284346580505371, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 4.3414, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.008699366965707406, | |
| "grad_norm": 5.39470100402832, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 4.4207, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.009320750320400792, | |
| "grad_norm": 5.765320777893066, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 4.3219, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009942133675094179, | |
| "grad_norm": 10.471980094909668, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 4.5284, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.010563517029787564, | |
| "grad_norm": 7.325485706329346, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 4.4177, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01118490038448095, | |
| "grad_norm": 7.271228790283203, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 4.1735, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.011806283739174337, | |
| "grad_norm": 6.641774654388428, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 4.1708, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.012427667093867723, | |
| "grad_norm": 10.327823638916016, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.9731, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01304905044856111, | |
| "grad_norm": 9.504193305969238, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 3.6202, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.013670433803254495, | |
| "grad_norm": 8.062225341796875, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 3.5678, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.014291817157947882, | |
| "grad_norm": 10.836487770080566, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 3.3968, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.014913200512641268, | |
| "grad_norm": 19.103179931640625, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 3.3893, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.015534583867334653, | |
| "grad_norm": 13.378957748413086, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.4375, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.015534583867334653, | |
| "eval_loss": 3.0447850227355957, | |
| "eval_runtime": 99.5049, | |
| "eval_samples_per_second": 108.96, | |
| "eval_steps_per_second": 13.627, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01615596722202804, | |
| "grad_norm": 6.254918575286865, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7294, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.016777350576721427, | |
| "grad_norm": 7.319060802459717, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.8813, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.017398733931414813, | |
| "grad_norm": 8.43337345123291, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.8859, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0180201172861082, | |
| "grad_norm": 8.820302963256836, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 3.0777, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.018641500640801584, | |
| "grad_norm": 7.4783854484558105, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.5522, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01926288399549497, | |
| "grad_norm": 7.428519248962402, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.7819, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.019884267350188358, | |
| "grad_norm": 7.079680442810059, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.6707, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.020505650704881744, | |
| "grad_norm": 6.271028995513916, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.4942, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.02112703405957513, | |
| "grad_norm": 8.533285140991211, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.8131, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.021748417414268514, | |
| "grad_norm": 7.770425796508789, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.6253, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0223698007689619, | |
| "grad_norm": 7.423771381378174, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.7925, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.02299118412365529, | |
| "grad_norm": 8.581366539001465, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.6777, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.023612567478348674, | |
| "grad_norm": 7.073851108551025, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.3883, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.02423395083304206, | |
| "grad_norm": 6.073333740234375, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.2233, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.024855334187735445, | |
| "grad_norm": 7.236076354980469, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.2824, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.025476717542428834, | |
| "grad_norm": 8.7551851272583, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.2064, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.02609810089712222, | |
| "grad_norm": 7.784063339233398, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.2192, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.026719484251815605, | |
| "grad_norm": 7.144655227661133, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.3833, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.02734086760650899, | |
| "grad_norm": 6.632129669189453, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.1774, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.027962250961202376, | |
| "grad_norm": 6.696552276611328, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.2596, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.028583634315895765, | |
| "grad_norm": 6.228443622589111, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.3508, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02920501767058915, | |
| "grad_norm": 7.7984538078308105, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.3823, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.029826401025282535, | |
| "grad_norm": 9.903982162475586, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.5122, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.03044778437997592, | |
| "grad_norm": 7.956427097320557, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.5993, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.031069167734669306, | |
| "grad_norm": 8.152593612670898, | |
| "learning_rate": 0.0, | |
| "loss": 2.592, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.031069167734669306, | |
| "eval_loss": 2.295586347579956, | |
| "eval_runtime": 99.4875, | |
| "eval_samples_per_second": 108.979, | |
| "eval_steps_per_second": 13.63, | |
| "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": 8.33416392081408e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |