| { | |
| "best_metric": 1.5863984823226929, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.5536332179930796, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.011072664359861591, | |
| "grad_norm": 3.085151433944702, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0965, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011072664359861591, | |
| "eval_loss": 2.226940631866455, | |
| "eval_runtime": 7.9021, | |
| "eval_samples_per_second": 77.068, | |
| "eval_steps_per_second": 9.744, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022145328719723183, | |
| "grad_norm": 2.4434478282928467, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1067, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.03321799307958478, | |
| "grad_norm": 1.3165335655212402, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.1499, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.044290657439446365, | |
| "grad_norm": 0.9989780187606812, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.1183, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.05536332179930796, | |
| "grad_norm": 0.7292075753211975, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0738, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.06643598615916955, | |
| "grad_norm": 1.1118435859680176, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.1048, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07750865051903114, | |
| "grad_norm": 2.3716795444488525, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.0179, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.08858131487889273, | |
| "grad_norm": 1.524487853050232, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.0181, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.09965397923875433, | |
| "grad_norm": 1.016344428062439, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9666, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.11072664359861592, | |
| "grad_norm": 1.953541874885559, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.7658, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12179930795847752, | |
| "grad_norm": 2.0307700634002686, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.7502, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.1328719723183391, | |
| "grad_norm": 2.3972978591918945, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.8412, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.1439446366782007, | |
| "grad_norm": 1.575653076171875, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.8075, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.15501730103806227, | |
| "grad_norm": 0.6672093272209167, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.8219, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.16608996539792387, | |
| "grad_norm": 0.5373260378837585, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.8665, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17716262975778546, | |
| "grad_norm": 0.5511289238929749, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.8291, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": 0.4291207194328308, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.8075, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.19930795847750865, | |
| "grad_norm": 0.457125186920166, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.7697, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.21038062283737025, | |
| "grad_norm": 0.4102403223514557, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.7076, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.22145328719723184, | |
| "grad_norm": 0.3947022557258606, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.6706, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23252595155709344, | |
| "grad_norm": 0.4045722186565399, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.694, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.24359861591695503, | |
| "grad_norm": 0.5666907429695129, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5357, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2546712802768166, | |
| "grad_norm": 0.8208253383636475, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.5144, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.2657439446366782, | |
| "grad_norm": 0.9341422319412231, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5001, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2768166089965398, | |
| "grad_norm": 1.0937079191207886, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 1.6608, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2768166089965398, | |
| "eval_loss": 1.6505544185638428, | |
| "eval_runtime": 7.8911, | |
| "eval_samples_per_second": 77.176, | |
| "eval_steps_per_second": 9.758, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2878892733564014, | |
| "grad_norm": 0.7896848320960999, | |
| "learning_rate": 5e-05, | |
| "loss": 1.7627, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.29896193771626295, | |
| "grad_norm": 2.765718460083008, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.7096, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.31003460207612454, | |
| "grad_norm": 0.9219654202461243, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.7509, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.32110726643598614, | |
| "grad_norm": 0.45888030529022217, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.6932, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.33217993079584773, | |
| "grad_norm": 0.438749223947525, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.7275, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.34325259515570933, | |
| "grad_norm": 0.4799425005912781, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.6746, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.3543252595155709, | |
| "grad_norm": 0.4412655830383301, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.6737, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.3653979238754325, | |
| "grad_norm": 0.43257012963294983, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.637, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3764705882352941, | |
| "grad_norm": 0.4603326618671417, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6152, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.3875432525951557, | |
| "grad_norm": 0.3942500948905945, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.4533, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3986159169550173, | |
| "grad_norm": 0.5060563683509827, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4186, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4096885813148789, | |
| "grad_norm": 0.635962724685669, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.3692, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.4207612456747405, | |
| "grad_norm": 0.46357303857803345, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.6341, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4318339100346021, | |
| "grad_norm": 0.351576566696167, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.6602, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.4429065743944637, | |
| "grad_norm": 0.31902870535850525, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.6347, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4539792387543253, | |
| "grad_norm": 0.34050145745277405, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.6312, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.46505190311418687, | |
| "grad_norm": 0.33912649750709534, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.6503, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.47612456747404847, | |
| "grad_norm": 0.3392663896083832, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.6453, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.48719723183391006, | |
| "grad_norm": 0.34437981247901917, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.6424, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.4982698961937716, | |
| "grad_norm": 0.3915778398513794, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.6141, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5093425605536333, | |
| "grad_norm": 0.4128722548484802, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.6223, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.5204152249134948, | |
| "grad_norm": 0.37415212392807007, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.4766, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.5314878892733564, | |
| "grad_norm": 0.475273996591568, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.4923, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.542560553633218, | |
| "grad_norm": 0.6358432173728943, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.3999, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.5536332179930796, | |
| "grad_norm": 0.7917025089263916, | |
| "learning_rate": 0.0, | |
| "loss": 1.5597, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5536332179930796, | |
| "eval_loss": 1.5863984823226929, | |
| "eval_runtime": 8.4179, | |
| "eval_samples_per_second": 72.346, | |
| "eval_steps_per_second": 9.147, | |
| "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": 1.29516617859072e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |