| { | |
| "best_metric": 1.3719125986099243, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.013988948730502902, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0002797789746100581, | |
| "grad_norm": 0.6457531452178955, | |
| "learning_rate": 5e-05, | |
| "loss": 2.118, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002797789746100581, | |
| "eval_loss": 4.790634632110596, | |
| "eval_runtime": 290.7116, | |
| "eval_samples_per_second": 82.831, | |
| "eval_steps_per_second": 10.354, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005595579492201162, | |
| "grad_norm": 2.5176806449890137, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6891, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0008393369238301741, | |
| "grad_norm": 0.9567082524299622, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 2.05, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0011191158984402323, | |
| "grad_norm": 2.075179100036621, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 2.4286, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0013988948730502902, | |
| "grad_norm": 1.5577850341796875, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.4824, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0016786738476603483, | |
| "grad_norm": 1.5086711645126343, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.7467, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0019584528222704066, | |
| "grad_norm": 1.5570716857910156, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.4736, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0022382317968804646, | |
| "grad_norm": 1.768438696861267, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3928, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0025180107714905223, | |
| "grad_norm": 2.5458669662475586, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.7248, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0027977897461005804, | |
| "grad_norm": 2.0986435413360596, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.7086, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0030775687207106384, | |
| "grad_norm": 2.463690996170044, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.9833, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0033573476953206965, | |
| "grad_norm": 2.4661600589752197, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.7851, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0036371266699307546, | |
| "grad_norm": 0.5250707864761353, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.2392, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.003916905644540813, | |
| "grad_norm": 1.2579808235168457, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.9034, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.004196684619150871, | |
| "grad_norm": 1.0845015048980713, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.303, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.004476463593760929, | |
| "grad_norm": 1.1315339803695679, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.0852, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0047562425683709865, | |
| "grad_norm": 0.6806582808494568, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.3763, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.005036021542981045, | |
| "grad_norm": 1.0810201168060303, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4589, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.005315800517591103, | |
| "grad_norm": 0.8670059442520142, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.4309, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.005595579492201161, | |
| "grad_norm": 0.8074933290481567, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.8018, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.005875358466811219, | |
| "grad_norm": 1.1735812425613403, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.3628, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.006155137441421277, | |
| "grad_norm": 1.394433617591858, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.4953, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.006434916416031335, | |
| "grad_norm": 1.1334067583084106, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.6903, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.006714695390641393, | |
| "grad_norm": 1.4898574352264404, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.5683, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.006994474365251451, | |
| "grad_norm": 2.480189323425293, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.313, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.006994474365251451, | |
| "eval_loss": 1.4263904094696045, | |
| "eval_runtime": 289.3918, | |
| "eval_samples_per_second": 83.209, | |
| "eval_steps_per_second": 10.401, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.007274253339861509, | |
| "grad_norm": 0.41041114926338196, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0975, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.007554032314471567, | |
| "grad_norm": 1.5040510892868042, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.939, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.007833811289081626, | |
| "grad_norm": 0.6277198791503906, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.6496, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.008113590263691683, | |
| "grad_norm": 0.8916029334068298, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.8643, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.008393369238301742, | |
| "grad_norm": 0.7794185876846313, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.0262, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0086731482129118, | |
| "grad_norm": 0.9928082227706909, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.1687, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.008952927187521859, | |
| "grad_norm": 0.9538123607635498, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2194, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.009232706162131916, | |
| "grad_norm": 1.2503325939178467, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.179, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.009512485136741973, | |
| "grad_norm": 1.0158066749572754, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.2768, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.009792264111352032, | |
| "grad_norm": 1.1659492254257202, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.5504, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01007204308596209, | |
| "grad_norm": 1.3990727663040161, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.7014, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.010351822060572148, | |
| "grad_norm": 1.8722199201583862, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.9507, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.010631601035182205, | |
| "grad_norm": 0.545448362827301, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.2116, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.010911380009792264, | |
| "grad_norm": 0.848518967628479, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.7857, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.011191158984402321, | |
| "grad_norm": 0.7432922124862671, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.6847, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01147093795901238, | |
| "grad_norm": 0.6820698976516724, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.2811, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.011750716933622438, | |
| "grad_norm": 0.8533961772918701, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.6261, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.012030495908232497, | |
| "grad_norm": 0.8349013328552246, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.5641, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.012310274882842554, | |
| "grad_norm": 0.8028209209442139, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3012, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.012590053857452613, | |
| "grad_norm": 0.8586874604225159, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.4158, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01286983283206267, | |
| "grad_norm": 1.2300059795379639, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.2818, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.013149611806672729, | |
| "grad_norm": 1.4779167175292969, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.1995, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.013429390781282786, | |
| "grad_norm": 1.1225005388259888, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.682, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.013709169755892845, | |
| "grad_norm": 1.845724105834961, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.7847, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.013988948730502902, | |
| "grad_norm": 2.089684009552002, | |
| "learning_rate": 0.0, | |
| "loss": 1.8361, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.013988948730502902, | |
| "eval_loss": 1.3719125986099243, | |
| "eval_runtime": 289.049, | |
| "eval_samples_per_second": 83.308, | |
| "eval_steps_per_second": 10.413, | |
| "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": 1.0741049715379405e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |