| { | |
| "best_metric": 11.928548812866211, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04092699647004656, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008185399294009311, | |
| "grad_norm": 0.03302260860800743, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9308, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008185399294009311, | |
| "eval_loss": 11.931392669677734, | |
| "eval_runtime": 18.7218, | |
| "eval_samples_per_second": 439.595, | |
| "eval_steps_per_second": 54.963, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016370798588018621, | |
| "grad_norm": 0.03007926419377327, | |
| "learning_rate": 0.0001, | |
| "loss": 11.9312, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0024556197882027934, | |
| "grad_norm": 0.03515538573265076, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 11.9309, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0032741597176037243, | |
| "grad_norm": 0.03678855299949646, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 11.9305, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004092699647004656, | |
| "grad_norm": 0.033681780099868774, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 11.9309, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004911239576405587, | |
| "grad_norm": 0.027831466868519783, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 11.93, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005729779505806517, | |
| "grad_norm": 0.03375954180955887, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 11.9309, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0065483194352074486, | |
| "grad_norm": 0.030696505680680275, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.9306, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00736685936460838, | |
| "grad_norm": 0.030666222795844078, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 11.9304, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008185399294009311, | |
| "grad_norm": 0.03268038108944893, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 11.9298, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009003939223410242, | |
| "grad_norm": 0.03586149215698242, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 11.9305, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009822479152811174, | |
| "grad_norm": 0.03411286696791649, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 11.9298, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010641019082212105, | |
| "grad_norm": 0.03174988552927971, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 11.9308, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011459559011613035, | |
| "grad_norm": 0.03703003004193306, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.9298, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012278098941013966, | |
| "grad_norm": 0.04582355543971062, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 11.9302, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013096638870414897, | |
| "grad_norm": 0.039099063724279404, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 11.9304, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013915178799815828, | |
| "grad_norm": 0.04335886612534523, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 11.9302, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01473371872921676, | |
| "grad_norm": 0.03939344733953476, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 11.9303, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015552258658617691, | |
| "grad_norm": 0.042626477777957916, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 11.9296, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016370798588018622, | |
| "grad_norm": 0.040842197835445404, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.9306, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017189338517419554, | |
| "grad_norm": 0.039784859865903854, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 11.9304, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018007878446820485, | |
| "grad_norm": 0.04021400585770607, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 11.9298, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018826418376221416, | |
| "grad_norm": 0.0478106252849102, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 11.9294, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019644958305622347, | |
| "grad_norm": 0.04421238228678703, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 11.9307, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.02046349823502328, | |
| "grad_norm": 0.04299471527338028, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 11.9308, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02046349823502328, | |
| "eval_loss": 11.929377555847168, | |
| "eval_runtime": 18.7793, | |
| "eval_samples_per_second": 438.248, | |
| "eval_steps_per_second": 54.794, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02128203816442421, | |
| "grad_norm": 0.056903108954429626, | |
| "learning_rate": 5e-05, | |
| "loss": 11.9294, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.022100578093825138, | |
| "grad_norm": 0.053392358124256134, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 11.9288, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02291911802322607, | |
| "grad_norm": 0.05559993535280228, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 11.9294, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.023737657952627, | |
| "grad_norm": 0.05701728165149689, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 11.9294, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.02455619788202793, | |
| "grad_norm": 0.057807229459285736, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 11.9305, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025374737811428863, | |
| "grad_norm": 0.05711260065436363, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 11.9283, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.026193277740829794, | |
| "grad_norm": 0.0587916374206543, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.9296, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.027011817670230726, | |
| "grad_norm": 0.06173417717218399, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 11.9291, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.027830357599631657, | |
| "grad_norm": 0.05909475311636925, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 11.9293, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.028648897529032588, | |
| "grad_norm": 0.058725230395793915, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 11.9288, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02946743745843352, | |
| "grad_norm": 0.05278372764587402, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 11.93, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03028597738783445, | |
| "grad_norm": 0.058989524841308594, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 11.9286, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.031104517317235382, | |
| "grad_norm": 0.0682770386338234, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.9284, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.03192305724663631, | |
| "grad_norm": 0.06626476347446442, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 11.9283, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.032741597176037245, | |
| "grad_norm": 0.0669265016913414, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 11.9275, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.033560137105438176, | |
| "grad_norm": 0.06591495126485825, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 11.929, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.03437867703483911, | |
| "grad_norm": 0.06877961754798889, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 11.9275, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.03519721696424004, | |
| "grad_norm": 0.06533712148666382, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 11.9286, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.03601575689364097, | |
| "grad_norm": 0.06201931834220886, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.929, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0368342968230419, | |
| "grad_norm": 0.061079900711774826, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 11.9282, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03765283675244283, | |
| "grad_norm": 0.06090058758854866, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 11.928, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.038471376681843764, | |
| "grad_norm": 0.06689566373825073, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 11.9286, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.039289916611244695, | |
| "grad_norm": 0.06943468004465103, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 11.928, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.040108456540645626, | |
| "grad_norm": 0.05866420269012451, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 11.9288, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04092699647004656, | |
| "grad_norm": 0.05418151617050171, | |
| "learning_rate": 0.0, | |
| "loss": 11.929, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04092699647004656, | |
| "eval_loss": 11.928548812866211, | |
| "eval_runtime": 18.8301, | |
| "eval_samples_per_second": 437.065, | |
| "eval_steps_per_second": 54.646, | |
| "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": 1045100494848.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |