| { | |
| "best_metric": 1.9690523147583008, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.6389776357827476, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.012779552715654952, | |
| "grad_norm": 8.877751350402832, | |
| "learning_rate": 5e-05, | |
| "loss": 4.9321, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012779552715654952, | |
| "eval_loss": 6.123461723327637, | |
| "eval_runtime": 10.5802, | |
| "eval_samples_per_second": 49.81, | |
| "eval_steps_per_second": 6.238, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.025559105431309903, | |
| "grad_norm": 10.304305076599121, | |
| "learning_rate": 0.0001, | |
| "loss": 5.1275, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.038338658146964855, | |
| "grad_norm": 8.709698677062988, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.6715, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.051118210862619806, | |
| "grad_norm": 5.1918158531188965, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 3.7957, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.06389776357827476, | |
| "grad_norm": 4.481715679168701, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.2292, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.07667731629392971, | |
| "grad_norm": 3.8522226810455322, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 2.9605, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.08945686900958466, | |
| "grad_norm": 3.353649616241455, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.9539, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.10223642172523961, | |
| "grad_norm": 3.3866119384765625, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.7747, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.11501597444089456, | |
| "grad_norm": 3.164320468902588, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.481, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.12779552715654952, | |
| "grad_norm": 3.258185863494873, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.2717, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.14057507987220447, | |
| "grad_norm": 3.4878883361816406, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.1277, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.15335463258785942, | |
| "grad_norm": 8.28603458404541, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.6454, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.16613418530351437, | |
| "grad_norm": 10.599574089050293, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 3.1577, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.17891373801916932, | |
| "grad_norm": 8.967954635620117, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.4868, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.19169329073482427, | |
| "grad_norm": 6.120244979858398, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 3.0674, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.20447284345047922, | |
| "grad_norm": 3.495366096496582, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.7325, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.21725239616613418, | |
| "grad_norm": 2.693588972091675, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 2.5184, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.23003194888178913, | |
| "grad_norm": 2.7409822940826416, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 2.6186, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.24281150159744408, | |
| "grad_norm": 3.185375213623047, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 2.4666, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.25559105431309903, | |
| "grad_norm": 3.1198649406433105, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.3674, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.268370607028754, | |
| "grad_norm": 2.870100975036621, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 2.2704, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.28115015974440893, | |
| "grad_norm": 2.4920003414154053, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 2.1803, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.2939297124600639, | |
| "grad_norm": 2.7012813091278076, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.8492, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.30670926517571884, | |
| "grad_norm": 3.0564913749694824, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.4749, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.3194888178913738, | |
| "grad_norm": 5.215954303741455, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.659, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.3194888178913738, | |
| "eval_loss": 2.1801815032958984, | |
| "eval_runtime": 10.6002, | |
| "eval_samples_per_second": 49.716, | |
| "eval_steps_per_second": 6.226, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.33226837060702874, | |
| "grad_norm": 3.1555850505828857, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7737, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.3450479233226837, | |
| "grad_norm": 3.189253330230713, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.6303, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.35782747603833864, | |
| "grad_norm": 2.7232983112335205, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 2.3977, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.3706070287539936, | |
| "grad_norm": 2.5928525924682617, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.4877, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.38338658146964855, | |
| "grad_norm": 2.2546591758728027, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 2.4363, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3961661341853035, | |
| "grad_norm": 2.2360236644744873, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 2.2867, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.40894568690095845, | |
| "grad_norm": 2.709982395172119, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.265, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.4217252396166134, | |
| "grad_norm": 2.5096139907836914, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 2.1913, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.43450479233226835, | |
| "grad_norm": 2.7589054107666016, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 2.1013, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.4472843450479233, | |
| "grad_norm": 2.6283981800079346, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.8382, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.46006389776357826, | |
| "grad_norm": 2.599478244781494, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.476, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.4728434504792332, | |
| "grad_norm": 3.168750524520874, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.1022, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.48562300319488816, | |
| "grad_norm": 2.388570785522461, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.2588, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.4984025559105431, | |
| "grad_norm": 1.9153763055801392, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 2.3374, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.5111821086261981, | |
| "grad_norm": 2.0474133491516113, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.3056, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.5239616613418531, | |
| "grad_norm": 2.0961573123931885, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 2.4279, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.536741214057508, | |
| "grad_norm": 1.869411826133728, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 2.2039, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.549520766773163, | |
| "grad_norm": 2.0868279933929443, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 2.3414, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.5623003194888179, | |
| "grad_norm": 2.301476240158081, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.4253, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.5750798722044729, | |
| "grad_norm": 2.090371608734131, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 2.1862, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.5878594249201278, | |
| "grad_norm": 2.2954154014587402, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 2.0252, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.6006389776357828, | |
| "grad_norm": 2.319589138031006, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.8494, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.6134185303514377, | |
| "grad_norm": 2.208622932434082, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.5522, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.6261980830670927, | |
| "grad_norm": 2.477149248123169, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.5403, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.6389776357827476, | |
| "grad_norm": 2.278909206390381, | |
| "learning_rate": 0.0, | |
| "loss": 0.4689, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.6389776357827476, | |
| "eval_loss": 1.9690523147583008, | |
| "eval_runtime": 10.6008, | |
| "eval_samples_per_second": 49.713, | |
| "eval_steps_per_second": 6.226, | |
| "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": 1.62480894509056e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |