| { | |
| "best_metric": 0.20316138863563538, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.002056597564988483, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.113195129976966e-05, | |
| "grad_norm": 19.256942749023438, | |
| "learning_rate": 5e-06, | |
| "loss": 12.9006, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.113195129976966e-05, | |
| "eval_loss": 12.973265647888184, | |
| "eval_runtime": 5580.0626, | |
| "eval_samples_per_second": 7.338, | |
| "eval_steps_per_second": 0.917, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 8.226390259953932e-05, | |
| "grad_norm": 20.658445358276367, | |
| "learning_rate": 1e-05, | |
| "loss": 13.0794, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00012339585389930897, | |
| "grad_norm": 22.79210662841797, | |
| "learning_rate": 1.5e-05, | |
| "loss": 13.135, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00016452780519907864, | |
| "grad_norm": 22.022035598754883, | |
| "learning_rate": 2e-05, | |
| "loss": 12.7988, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0002056597564988483, | |
| "grad_norm": 17.91415786743164, | |
| "learning_rate": 2.5e-05, | |
| "loss": 11.8402, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00024679170779861795, | |
| "grad_norm": 19.318565368652344, | |
| "learning_rate": 3e-05, | |
| "loss": 10.7828, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0002879236590983876, | |
| "grad_norm": 20.40044593811035, | |
| "learning_rate": 3.5e-05, | |
| "loss": 9.6432, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0003290556103981573, | |
| "grad_norm": 19.99835205078125, | |
| "learning_rate": 4e-05, | |
| "loss": 7.9933, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00037018756169792695, | |
| "grad_norm": 21.982711791992188, | |
| "learning_rate": 4.5e-05, | |
| "loss": 6.2512, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0004113195129976966, | |
| "grad_norm": 20.890398025512695, | |
| "learning_rate": 5e-05, | |
| "loss": 5.3094, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004524514642974663, | |
| "grad_norm": 19.561426162719727, | |
| "learning_rate": 5.500000000000001e-05, | |
| "loss": 4.2817, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0004935834155972359, | |
| "grad_norm": 11.958085060119629, | |
| "learning_rate": 6e-05, | |
| "loss": 3.2946, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0005347153668970056, | |
| "grad_norm": 24.05998420715332, | |
| "learning_rate": 6.500000000000001e-05, | |
| "loss": 2.6703, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0005758473181967752, | |
| "grad_norm": 16.159927368164062, | |
| "learning_rate": 7e-05, | |
| "loss": 1.7678, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0006169792694965449, | |
| "grad_norm": 14.88825798034668, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.1081, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0006581112207963146, | |
| "grad_norm": 14.109820365905762, | |
| "learning_rate": 8e-05, | |
| "loss": 0.5209, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0006992431720960842, | |
| "grad_norm": 8.61984920501709, | |
| "learning_rate": 8.5e-05, | |
| "loss": 0.2652, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0007403751233958539, | |
| "grad_norm": 7.315117835998535, | |
| "learning_rate": 9e-05, | |
| "loss": 0.5351, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0007815070746956236, | |
| "grad_norm": 2.942542552947998, | |
| "learning_rate": 9.5e-05, | |
| "loss": 0.2552, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0008226390259953932, | |
| "grad_norm": 11.162988662719727, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8851, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008637709772951629, | |
| "grad_norm": 11.123847961425781, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.8391, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0009049029285949326, | |
| "grad_norm": 3.1932854652404785, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.3039, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0009460348798947022, | |
| "grad_norm": 1.8381555080413818, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.2274, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.0009871668311944718, | |
| "grad_norm": 1.7383055686950684, | |
| "learning_rate": 9.567727288213005e-05, | |
| "loss": 0.2197, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0010282987824942415, | |
| "grad_norm": 1.562986135482788, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.2192, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010282987824942415, | |
| "eval_loss": 0.2792419195175171, | |
| "eval_runtime": 5613.0531, | |
| "eval_samples_per_second": 7.295, | |
| "eval_steps_per_second": 0.912, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0010694307337940111, | |
| "grad_norm": 4.635091781616211, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.3612, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0011105626850937808, | |
| "grad_norm": 2.413482904434204, | |
| "learning_rate": 8.715724127386972e-05, | |
| "loss": 0.2537, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0011516946363935505, | |
| "grad_norm": 2.4534168243408203, | |
| "learning_rate": 8.345653031794292e-05, | |
| "loss": 0.2547, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0011928265876933201, | |
| "grad_norm": 4.514098644256592, | |
| "learning_rate": 7.938926261462366e-05, | |
| "loss": 0.3676, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0012339585389930898, | |
| "grad_norm": 5.916527271270752, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.5274, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012750904902928595, | |
| "grad_norm": 5.45999813079834, | |
| "learning_rate": 7.033683215379002e-05, | |
| "loss": 0.4659, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.0013162224415926291, | |
| "grad_norm": 4.046067237854004, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.311, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0013573543928923988, | |
| "grad_norm": 0.2217586785554886, | |
| "learning_rate": 6.0395584540887963e-05, | |
| "loss": 0.2055, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.0013984863441921685, | |
| "grad_norm": 2.0084125995635986, | |
| "learning_rate": 5.522642316338268e-05, | |
| "loss": 0.262, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0014396182954919381, | |
| "grad_norm": 2.1569504737854004, | |
| "learning_rate": 5e-05, | |
| "loss": 0.2769, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0014807502467917078, | |
| "grad_norm": 2.107754945755005, | |
| "learning_rate": 4.477357683661734e-05, | |
| "loss": 0.2857, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0015218821980914775, | |
| "grad_norm": 0.5223035216331482, | |
| "learning_rate": 3.960441545911204e-05, | |
| "loss": 0.1738, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0015630141493912471, | |
| "grad_norm": 0.17265839874744415, | |
| "learning_rate": 3.4549150281252636e-05, | |
| "loss": 0.2089, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0016041461006910168, | |
| "grad_norm": 0.9179982542991638, | |
| "learning_rate": 2.9663167846209998e-05, | |
| "loss": 0.2048, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0016452780519907865, | |
| "grad_norm": 0.45841121673583984, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.2062, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016864100032905561, | |
| "grad_norm": 0.1439216583967209, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.2099, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0017275419545903258, | |
| "grad_norm": 0.22398719191551208, | |
| "learning_rate": 1.6543469682057106e-05, | |
| "loss": 0.2121, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0017686739058900955, | |
| "grad_norm": 0.5332353711128235, | |
| "learning_rate": 1.2842758726130283e-05, | |
| "loss": 0.2314, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.0018098058571898651, | |
| "grad_norm": 0.13061563670635223, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.2174, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0018509378084896348, | |
| "grad_norm": 0.3310577869415283, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.21, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0018920697597894045, | |
| "grad_norm": 1.527039885520935, | |
| "learning_rate": 4.322727117869951e-06, | |
| "loss": 0.1943, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0019332017110891741, | |
| "grad_norm": 0.961459755897522, | |
| "learning_rate": 2.4471741852423237e-06, | |
| "loss": 0.1982, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0019743336623889436, | |
| "grad_norm": 0.12971656024456024, | |
| "learning_rate": 1.0926199633097157e-06, | |
| "loss": 0.1915, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0020154656136887133, | |
| "grad_norm": 0.8849334120750427, | |
| "learning_rate": 2.7390523158633554e-07, | |
| "loss": 0.2229, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.002056597564988483, | |
| "grad_norm": 0.23174209892749786, | |
| "learning_rate": 0.0, | |
| "loss": 0.2113, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002056597564988483, | |
| "eval_loss": 0.20316138863563538, | |
| "eval_runtime": 5612.293, | |
| "eval_samples_per_second": 7.296, | |
| "eval_steps_per_second": 0.912, | |
| "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": 3, | |
| "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": 1.402475366055936e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |