| { | |
| "best_metric": 0.44632911682128906, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.04105933073290905, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000821186614658181, | |
| "grad_norm": 2.0305542945861816, | |
| "learning_rate": 1e-05, | |
| "loss": 0.7261, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000821186614658181, | |
| "eval_loss": 1.465772271156311, | |
| "eval_runtime": 288.2262, | |
| "eval_samples_per_second": 7.116, | |
| "eval_steps_per_second": 1.78, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001642373229316362, | |
| "grad_norm": 2.114654541015625, | |
| "learning_rate": 2e-05, | |
| "loss": 0.7726, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.002463559843974543, | |
| "grad_norm": 2.2381458282470703, | |
| "learning_rate": 3e-05, | |
| "loss": 0.8371, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.003284746458632724, | |
| "grad_norm": 1.9415267705917358, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7885, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0041059330732909054, | |
| "grad_norm": 1.484900712966919, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7522, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004927119687949086, | |
| "grad_norm": 1.259929895401001, | |
| "learning_rate": 6e-05, | |
| "loss": 0.7248, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005748306302607267, | |
| "grad_norm": 0.9762012958526611, | |
| "learning_rate": 7e-05, | |
| "loss": 0.5922, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006569492917265448, | |
| "grad_norm": 1.0204635858535767, | |
| "learning_rate": 8e-05, | |
| "loss": 0.5452, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00739067953192363, | |
| "grad_norm": 0.8520223498344421, | |
| "learning_rate": 9e-05, | |
| "loss": 0.4675, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008211866146581811, | |
| "grad_norm": 1.470017433166504, | |
| "learning_rate": 0.0001, | |
| "loss": 0.4164, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.009033052761239991, | |
| "grad_norm": 0.8858131766319275, | |
| "learning_rate": 9.99983777858264e-05, | |
| "loss": 0.3847, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009854239375898173, | |
| "grad_norm": 1.0039604902267456, | |
| "learning_rate": 9.999351124856874e-05, | |
| "loss": 0.3836, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010675425990556354, | |
| "grad_norm": 0.6317289471626282, | |
| "learning_rate": 9.998540070400966e-05, | |
| "loss": 0.3325, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011496612605214535, | |
| "grad_norm": 0.680807888507843, | |
| "learning_rate": 9.997404667843075e-05, | |
| "loss": 0.3493, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.012317799219872716, | |
| "grad_norm": 0.6124119758605957, | |
| "learning_rate": 9.995944990857849e-05, | |
| "loss": 0.3204, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013138985834530896, | |
| "grad_norm": 0.6300580501556396, | |
| "learning_rate": 9.994161134161634e-05, | |
| "loss": 0.3341, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013960172449189078, | |
| "grad_norm": 0.608344554901123, | |
| "learning_rate": 9.992053213506334e-05, | |
| "loss": 0.3386, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01478135906384726, | |
| "grad_norm": 0.5785073041915894, | |
| "learning_rate": 9.989621365671902e-05, | |
| "loss": 0.3035, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.01560254567850544, | |
| "grad_norm": 0.6188136339187622, | |
| "learning_rate": 9.986865748457457e-05, | |
| "loss": 0.3162, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.016423732293163622, | |
| "grad_norm": 0.5587109923362732, | |
| "learning_rate": 9.983786540671051e-05, | |
| "loss": 0.273, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017244918907821802, | |
| "grad_norm": 0.5472216606140137, | |
| "learning_rate": 9.980383942118066e-05, | |
| "loss": 0.3215, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.018066105522479982, | |
| "grad_norm": 0.4810258150100708, | |
| "learning_rate": 9.976658173588244e-05, | |
| "loss": 0.307, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018887292137138165, | |
| "grad_norm": 0.5424895882606506, | |
| "learning_rate": 9.972609476841367e-05, | |
| "loss": 0.3065, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.019708478751796345, | |
| "grad_norm": 0.5074129700660706, | |
| "learning_rate": 9.968238114591566e-05, | |
| "loss": 0.2774, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.020529665366454525, | |
| "grad_norm": 0.5599948167800903, | |
| "learning_rate": 9.96354437049027e-05, | |
| "loss": 0.2691, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.02135085198111271, | |
| "grad_norm": 0.6742061972618103, | |
| "learning_rate": 9.95852854910781e-05, | |
| "loss": 0.2898, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.02217203859577089, | |
| "grad_norm": 0.5526089072227478, | |
| "learning_rate": 9.953190975913647e-05, | |
| "loss": 0.3071, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.02299322521042907, | |
| "grad_norm": 0.5390534996986389, | |
| "learning_rate": 9.947531997255256e-05, | |
| "loss": 0.2906, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.023814411825087253, | |
| "grad_norm": 0.504539430141449, | |
| "learning_rate": 9.941551980335652e-05, | |
| "loss": 0.2688, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.024635598439745433, | |
| "grad_norm": 0.4898300766944885, | |
| "learning_rate": 9.935251313189564e-05, | |
| "loss": 0.2845, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.025456785054403613, | |
| "grad_norm": 0.49974775314331055, | |
| "learning_rate": 9.928630404658255e-05, | |
| "loss": 0.2702, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.026277971669061793, | |
| "grad_norm": 0.5819835662841797, | |
| "learning_rate": 9.921689684362989e-05, | |
| "loss": 0.2699, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.027099158283719976, | |
| "grad_norm": 0.6171815395355225, | |
| "learning_rate": 9.914429602677162e-05, | |
| "loss": 0.3477, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.027920344898378156, | |
| "grad_norm": 0.6020647883415222, | |
| "learning_rate": 9.906850630697068e-05, | |
| "loss": 0.2901, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.028741531513036336, | |
| "grad_norm": 0.7458943724632263, | |
| "learning_rate": 9.898953260211338e-05, | |
| "loss": 0.2498, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02956271812769452, | |
| "grad_norm": 0.6588975787162781, | |
| "learning_rate": 9.890738003669029e-05, | |
| "loss": 0.2599, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0303839047423527, | |
| "grad_norm": 0.6839740872383118, | |
| "learning_rate": 9.882205394146361e-05, | |
| "loss": 0.337, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.03120509135701088, | |
| "grad_norm": 0.6753020882606506, | |
| "learning_rate": 9.87335598531214e-05, | |
| "loss": 0.3069, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.032026277971669063, | |
| "grad_norm": 0.8709951043128967, | |
| "learning_rate": 9.864190351391822e-05, | |
| "loss": 0.3396, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.032847464586327244, | |
| "grad_norm": 0.6819374561309814, | |
| "learning_rate": 9.85470908713026e-05, | |
| "loss": 0.2963, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.033668651200985424, | |
| "grad_norm": 0.856820821762085, | |
| "learning_rate": 9.844912807753104e-05, | |
| "loss": 0.289, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.034489837815643604, | |
| "grad_norm": 0.7196516990661621, | |
| "learning_rate": 9.834802148926882e-05, | |
| "loss": 0.2858, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.035311024430301784, | |
| "grad_norm": 0.7757695913314819, | |
| "learning_rate": 9.824377766717759e-05, | |
| "loss": 0.2882, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.036132211044959964, | |
| "grad_norm": 0.7751405835151672, | |
| "learning_rate": 9.813640337548954e-05, | |
| "loss": 0.3174, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.03695339765961815, | |
| "grad_norm": 0.8659068942070007, | |
| "learning_rate": 9.802590558156862e-05, | |
| "loss": 0.2818, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03777458427427633, | |
| "grad_norm": 1.336848258972168, | |
| "learning_rate": 9.791229145545831e-05, | |
| "loss": 0.3209, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.03859577088893451, | |
| "grad_norm": 0.9144354462623596, | |
| "learning_rate": 9.779556836941645e-05, | |
| "loss": 0.28, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.03941695750359269, | |
| "grad_norm": 0.8315229415893555, | |
| "learning_rate": 9.767574389743682e-05, | |
| "loss": 0.276, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04023814411825087, | |
| "grad_norm": 0.967755913734436, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.3298, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.04105933073290905, | |
| "grad_norm": 1.0207139253616333, | |
| "learning_rate": 9.742682209735727e-05, | |
| "loss": 0.3058, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.04105933073290905, | |
| "eval_loss": 0.44632911682128906, | |
| "eval_runtime": 291.2748, | |
| "eval_samples_per_second": 7.041, | |
| "eval_steps_per_second": 1.761, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.722470612133478e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |