| { | |
| "best_metric": 1.9779502153396606, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 1.495344506517691, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0297951582867784, | |
| "grad_norm": 5.255026817321777, | |
| "learning_rate": 5e-05, | |
| "loss": 3.7359, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0297951582867784, | |
| "eval_loss": 4.239082336425781, | |
| "eval_runtime": 2.9162, | |
| "eval_samples_per_second": 77.842, | |
| "eval_steps_per_second": 9.945, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0595903165735568, | |
| "grad_norm": 6.154642581939697, | |
| "learning_rate": 0.0001, | |
| "loss": 4.0273, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0893854748603352, | |
| "grad_norm": 6.228611469268799, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.1499, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.1191806331471136, | |
| "grad_norm": 5.3180623054504395, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.1502, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.148975791433892, | |
| "grad_norm": 5.917397499084473, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.9261, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1787709497206704, | |
| "grad_norm": 5.27532434463501, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.4381, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.2085661080074488, | |
| "grad_norm": 3.5522358417510986, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.8911, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.2383612662942272, | |
| "grad_norm": 3.5772132873535156, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.2964, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2681564245810056, | |
| "grad_norm": 5.116891384124756, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.6329, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.297951582867784, | |
| "grad_norm": 4.258176326751709, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.8402, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.32774674115456237, | |
| "grad_norm": 3.147491931915283, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.6133, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.3575418994413408, | |
| "grad_norm": 2.7201478481292725, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.5179, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.38733705772811916, | |
| "grad_norm": 3.547346591949463, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.41, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.4171322160148976, | |
| "grad_norm": 2.9750421047210693, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.3717, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.44692737430167595, | |
| "grad_norm": 2.5824129581451416, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.5694, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.4767225325884544, | |
| "grad_norm": 2.871670722961426, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.909, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.5065176908752328, | |
| "grad_norm": 2.181304931640625, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.238, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.5363128491620112, | |
| "grad_norm": 2.4061832427978516, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.3752, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.5661080074487895, | |
| "grad_norm": 1.8905714750289917, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.2268, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.595903165735568, | |
| "grad_norm": 1.8679147958755493, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.1416, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6256983240223464, | |
| "grad_norm": 3.0014896392822266, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.0755, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.6554934823091247, | |
| "grad_norm": 4.232528209686279, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.2963, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.6852886405959032, | |
| "grad_norm": 2.2052879333496094, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.8984, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.7150837988826816, | |
| "grad_norm": 2.3755292892456055, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.8503, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.74487895716946, | |
| "grad_norm": 2.062422513961792, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.0566, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.74487895716946, | |
| "eval_loss": 2.1353137493133545, | |
| "eval_runtime": 2.9818, | |
| "eval_samples_per_second": 76.128, | |
| "eval_steps_per_second": 9.726, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.7746741154562383, | |
| "grad_norm": 2.946615695953369, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0212, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.8044692737430168, | |
| "grad_norm": 2.3928239345550537, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.0514, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.8342644320297952, | |
| "grad_norm": 2.0668535232543945, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.1217, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.8640595903165735, | |
| "grad_norm": 1.8767576217651367, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.8756, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.8938547486033519, | |
| "grad_norm": 3.1248583793640137, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.9879, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.9236499068901304, | |
| "grad_norm": 2.4403278827667236, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.9678, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.9534450651769087, | |
| "grad_norm": 2.0304882526397705, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.3779, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.9832402234636871, | |
| "grad_norm": 2.2402291297912598, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.5861, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.0186219739292366, | |
| "grad_norm": 3.376228094100952, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 3.2541, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 1.048417132216015, | |
| "grad_norm": 1.9267646074295044, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.9487, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 1.0782122905027933, | |
| "grad_norm": 1.7760834693908691, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.8374, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 1.1080074487895717, | |
| "grad_norm": 1.5164313316345215, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.8834, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 1.13780260707635, | |
| "grad_norm": 2.668070077896118, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.7881, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 1.1675977653631284, | |
| "grad_norm": 2.745457887649536, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.4016, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 1.197392923649907, | |
| "grad_norm": 2.1074106693267822, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.9102, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.2271880819366854, | |
| "grad_norm": 2.2203242778778076, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.6533, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 1.2569832402234637, | |
| "grad_norm": 1.5127211809158325, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.8591, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 1.2867783985102421, | |
| "grad_norm": 2.127408027648926, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.0432, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 1.3165735567970205, | |
| "grad_norm": 1.5922434329986572, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.8363, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 1.3463687150837989, | |
| "grad_norm": 1.5293318033218384, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.9234, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.3761638733705772, | |
| "grad_norm": 1.7801039218902588, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.6588, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 1.4059590316573556, | |
| "grad_norm": 2.720064640045166, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.6795, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 1.435754189944134, | |
| "grad_norm": 2.2383999824523926, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.1166, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 1.4655493482309125, | |
| "grad_norm": 2.0387301445007324, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.3229, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 1.495344506517691, | |
| "grad_norm": 1.6231642961502075, | |
| "learning_rate": 0.0, | |
| "loss": 1.8016, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.495344506517691, | |
| "eval_loss": 1.9779502153396606, | |
| "eval_runtime": 2.9043, | |
| "eval_samples_per_second": 78.16, | |
| "eval_steps_per_second": 9.985, | |
| "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": 4.927833981845504e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |