| { | |
| "best_metric": 0.44486159086227417, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.02250098441806829, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004500196883613658, | |
| "grad_norm": 14.422728538513184, | |
| "learning_rate": 5e-05, | |
| "loss": 0.4203, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004500196883613658, | |
| "eval_loss": 0.5684293508529663, | |
| "eval_runtime": 455.5935, | |
| "eval_samples_per_second": 32.858, | |
| "eval_steps_per_second": 4.109, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0009000393767227316, | |
| "grad_norm": 19.22362518310547, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5523, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0013500590650840974, | |
| "grad_norm": 7.609604358673096, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 0.5326, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0018000787534454632, | |
| "grad_norm": 8.216272354125977, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 0.508, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0022500984418068293, | |
| "grad_norm": 8.645339012145996, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 0.5229, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.002700118130168195, | |
| "grad_norm": 6.784003734588623, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 0.5124, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003150137818529561, | |
| "grad_norm": 6.9004106521606445, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 0.4839, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0036001575068909265, | |
| "grad_norm": 7.402937889099121, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.4642, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004050177195252292, | |
| "grad_norm": 7.011044025421143, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 0.4852, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0045001968836136585, | |
| "grad_norm": 6.2018961906433105, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 0.479, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004950216571975024, | |
| "grad_norm": 6.468971252441406, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 0.4569, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.00540023626033639, | |
| "grad_norm": 8.639153480529785, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 0.5582, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.005850255948697755, | |
| "grad_norm": 7.218179702758789, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 0.5095, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.006300275637059122, | |
| "grad_norm": 4.941307067871094, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4468, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.006750295325420487, | |
| "grad_norm": 4.753408908843994, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 0.4704, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.007200315013781853, | |
| "grad_norm": 4.523560047149658, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 0.4383, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0076503347021432185, | |
| "grad_norm": 4.823092460632324, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 0.4565, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.008100354390504584, | |
| "grad_norm": 5.255280017852783, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.4712, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.00855037407886595, | |
| "grad_norm": 5.276516437530518, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 0.4372, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.009000393767227317, | |
| "grad_norm": 5.404825687408447, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.4581, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009450413455588683, | |
| "grad_norm": 5.321479320526123, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 0.4392, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.009900433143950048, | |
| "grad_norm": 5.3940253257751465, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 0.4586, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.010350452832311414, | |
| "grad_norm": 5.638725280761719, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 0.4332, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01080047252067278, | |
| "grad_norm": 6.029419422149658, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 0.4774, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011250492209034145, | |
| "grad_norm": 7.096339225769043, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 0.536, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.011250492209034145, | |
| "eval_loss": 0.45366477966308594, | |
| "eval_runtime": 456.5638, | |
| "eval_samples_per_second": 32.788, | |
| "eval_steps_per_second": 4.1, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01170051189739551, | |
| "grad_norm": 3.5797367095947266, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3567, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.012150531585756876, | |
| "grad_norm": 4.528767108917236, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 0.4475, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012600551274118243, | |
| "grad_norm": 4.389427661895752, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 0.4494, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.013050570962479609, | |
| "grad_norm": 4.565876007080078, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 0.4593, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.013500590650840975, | |
| "grad_norm": 4.244178771972656, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 0.433, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01395061033920234, | |
| "grad_norm": 4.859099388122559, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 0.4386, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.014400630027563706, | |
| "grad_norm": 4.869718551635742, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.472, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.014850649715925071, | |
| "grad_norm": 5.395300388336182, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 0.4698, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.015300669404286437, | |
| "grad_norm": 6.101658344268799, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.443, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.015750689092647804, | |
| "grad_norm": 5.844554901123047, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 0.4324, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016200708781009168, | |
| "grad_norm": 6.385544300079346, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 0.4312, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.016650728469370536, | |
| "grad_norm": 7.2580461502075195, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 0.4674, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0171007481577319, | |
| "grad_norm": 6.991725444793701, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.4949, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.017550767846093267, | |
| "grad_norm": 3.6845273971557617, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 0.4213, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.018000787534454634, | |
| "grad_norm": 4.191789627075195, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 0.4935, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018450807222815998, | |
| "grad_norm": 5.070094108581543, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 0.4547, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.018900826911177365, | |
| "grad_norm": 4.569336414337158, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 0.4384, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.01935084659953873, | |
| "grad_norm": 4.306663513183594, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 0.4513, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.019800866287900096, | |
| "grad_norm": 4.363531589508057, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4405, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.02025088597626146, | |
| "grad_norm": 4.676458358764648, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 0.4528, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.020700905664622828, | |
| "grad_norm": 4.858545780181885, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 0.4823, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.02115092535298419, | |
| "grad_norm": 5.037557125091553, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 0.4299, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.02160094504134556, | |
| "grad_norm": 5.234649658203125, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 0.4471, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.022050964729706926, | |
| "grad_norm": 5.939426422119141, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 0.4684, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.02250098441806829, | |
| "grad_norm": 7.509469509124756, | |
| "learning_rate": 0.0, | |
| "loss": 0.5282, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02250098441806829, | |
| "eval_loss": 0.44486159086227417, | |
| "eval_runtime": 459.9762, | |
| "eval_samples_per_second": 32.545, | |
| "eval_steps_per_second": 4.07, | |
| "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": 5.6941044108047155e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |