| { | |
| "best_metric": 0.5250022411346436, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.1142061281337048, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022284122562674095, | |
| "grad_norm": 30.49173927307129, | |
| "learning_rate": 5e-05, | |
| "loss": 9.0729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.022284122562674095, | |
| "eval_loss": 8.730381965637207, | |
| "eval_runtime": 8.1751, | |
| "eval_samples_per_second": 37.064, | |
| "eval_steps_per_second": 4.648, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04456824512534819, | |
| "grad_norm": 34.60056686401367, | |
| "learning_rate": 0.0001, | |
| "loss": 8.9334, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.06685236768802229, | |
| "grad_norm": 28.790254592895508, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 7.1646, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.08913649025069638, | |
| "grad_norm": 17.176443099975586, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.5561, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11142061281337047, | |
| "grad_norm": 9.993888854980469, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.0962, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.13370473537604458, | |
| "grad_norm": 6.4263596534729, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.3272, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.15598885793871867, | |
| "grad_norm": 4.858709335327148, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.9065, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.17827298050139276, | |
| "grad_norm": 2.9489457607269287, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.7016, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.20055710306406685, | |
| "grad_norm": 8.086634635925293, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.6285, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22284122562674094, | |
| "grad_norm": 6.957271099090576, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.6165, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.24512534818941503, | |
| "grad_norm": 2.8947906494140625, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.546, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.26740947075208915, | |
| "grad_norm": 10.271145820617676, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.6261, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.28969359331476324, | |
| "grad_norm": 6.051088809967041, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.6014, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.31197771587743733, | |
| "grad_norm": 5.635314464569092, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.5633, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.3342618384401114, | |
| "grad_norm": 5.927159309387207, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.6042, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3565459610027855, | |
| "grad_norm": 1.467381477355957, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.5585, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.3788300835654596, | |
| "grad_norm": 12.164403915405273, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.6605, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.4011142061281337, | |
| "grad_norm": 11.079755783081055, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.6287, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.4233983286908078, | |
| "grad_norm": 5.293990612030029, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.5424, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.4456824512534819, | |
| "grad_norm": 4.628940105438232, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5815, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.467966573816156, | |
| "grad_norm": 5.81827974319458, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.6098, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.49025069637883006, | |
| "grad_norm": 5.480099201202393, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.5606, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.5125348189415042, | |
| "grad_norm": 2.7813830375671387, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.5137, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.5348189415041783, | |
| "grad_norm": 4.324994087219238, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.5278, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.5571030640668524, | |
| "grad_norm": 5.292835235595703, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.5243, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5571030640668524, | |
| "eval_loss": 0.5735299587249756, | |
| "eval_runtime": 8.2869, | |
| "eval_samples_per_second": 36.564, | |
| "eval_steps_per_second": 4.586, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5793871866295265, | |
| "grad_norm": 6.091929912567139, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5637, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.6016713091922006, | |
| "grad_norm": 1.8379416465759277, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.5558, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.6239554317548747, | |
| "grad_norm": 1.373220682144165, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.5139, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.6462395543175488, | |
| "grad_norm": 3.242717742919922, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.5975, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.6685236768802229, | |
| "grad_norm": 1.5490792989730835, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.5589, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6908077994428969, | |
| "grad_norm": 1.0958337783813477, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.5849, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.713091922005571, | |
| "grad_norm": 1.335720181465149, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5244, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.7353760445682451, | |
| "grad_norm": 1.8901203870773315, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4989, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.7576601671309192, | |
| "grad_norm": 1.3303558826446533, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.5267, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.7799442896935933, | |
| "grad_norm": 0.8487653136253357, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4921, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8022284122562674, | |
| "grad_norm": 1.4701528549194336, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4972, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.8245125348189415, | |
| "grad_norm": 3.763484001159668, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.5617, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.8467966573816156, | |
| "grad_norm": 3.6227574348449707, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5396, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.8690807799442897, | |
| "grad_norm": 0.6843830943107605, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.5328, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.8913649025069638, | |
| "grad_norm": 2.871105432510376, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.5647, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9136490250696379, | |
| "grad_norm": 1.7284497022628784, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.5141, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.935933147632312, | |
| "grad_norm": 2.233738422393799, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.5297, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.958217270194986, | |
| "grad_norm": 0.8520792722702026, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.5582, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.9805013927576601, | |
| "grad_norm": 2.821225881576538, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5086, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.0027855153203342, | |
| "grad_norm": 3.3593173027038574, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.6117, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0250696378830084, | |
| "grad_norm": 1.817628026008606, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.5412, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.0473537604456824, | |
| "grad_norm": 1.0740711688995361, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.5352, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.0696378830083566, | |
| "grad_norm": 4.573311805725098, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.5294, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.0919220055710306, | |
| "grad_norm": 2.1602420806884766, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4741, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.1142061281337048, | |
| "grad_norm": 3.4920172691345215, | |
| "learning_rate": 0.0, | |
| "loss": 0.5032, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.1142061281337048, | |
| "eval_loss": 0.5250022411346436, | |
| "eval_runtime": 8.3188, | |
| "eval_samples_per_second": 36.423, | |
| "eval_steps_per_second": 4.568, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "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": 1.6068485461311488e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |