| { | |
| "best_metric": 1.5858772993087769, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-500", | |
| "epoch": 0.01620929440941436, | |
| "eval_steps": 50, | |
| "global_step": 500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.241858881882872e-05, | |
| "eval_loss": 2.906552791595459, | |
| "eval_runtime": 397.3517, | |
| "eval_samples_per_second": 32.686, | |
| "eval_steps_per_second": 8.172, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003241858881882872, | |
| "grad_norm": 6.263719081878662, | |
| "learning_rate": 4.1400000000000003e-05, | |
| "loss": 2.7332, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006483717763765744, | |
| "grad_norm": 5.530974388122559, | |
| "learning_rate": 8.280000000000001e-05, | |
| "loss": 1.9108, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0009725576645648615, | |
| "grad_norm": 3.9441070556640625, | |
| "learning_rate": 0.00012419999999999998, | |
| "loss": 1.8745, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0012967435527531487, | |
| "grad_norm": 4.260671138763428, | |
| "learning_rate": 0.00016560000000000001, | |
| "loss": 1.7333, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0016209294409414358, | |
| "grad_norm": 4.642955303192139, | |
| "learning_rate": 0.000207, | |
| "loss": 1.6797, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0016209294409414358, | |
| "eval_loss": 1.8519707918167114, | |
| "eval_runtime": 398.2732, | |
| "eval_samples_per_second": 32.611, | |
| "eval_steps_per_second": 8.153, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.001945115329129723, | |
| "grad_norm": 4.400924205780029, | |
| "learning_rate": 0.00020674787920189178, | |
| "loss": 1.868, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.00226930121731801, | |
| "grad_norm": 5.454312324523926, | |
| "learning_rate": 0.00020599274511475253, | |
| "loss": 2.0069, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.0025934871055062975, | |
| "grad_norm": 4.467811107635498, | |
| "learning_rate": 0.00020473827667594888, | |
| "loss": 1.7519, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0029176729936945846, | |
| "grad_norm": 4.802621841430664, | |
| "learning_rate": 0.00020299058552961598, | |
| "loss": 1.6975, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0032418588818828717, | |
| "grad_norm": 4.396114826202393, | |
| "learning_rate": 0.00020075818625134152, | |
| "loss": 1.6838, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0032418588818828717, | |
| "eval_loss": 1.8345727920532227, | |
| "eval_runtime": 398.358, | |
| "eval_samples_per_second": 32.604, | |
| "eval_steps_per_second": 8.151, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0035660447700711587, | |
| "grad_norm": 3.908578872680664, | |
| "learning_rate": 0.00019805195486600916, | |
| "loss": 2.0062, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.003890230658259446, | |
| "grad_norm": 3.713029623031616, | |
| "learning_rate": 0.00019488507586089894, | |
| "loss": 1.7925, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.004214416546447733, | |
| "grad_norm": 4.107682704925537, | |
| "learning_rate": 0.00019127297795219008, | |
| "loss": 1.8635, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.00453860243463602, | |
| "grad_norm": 5.115502834320068, | |
| "learning_rate": 0.00018723325891780706, | |
| "loss": 1.8397, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.004862788322824307, | |
| "grad_norm": 4.171757221221924, | |
| "learning_rate": 0.0001827855998628142, | |
| "loss": 1.8328, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.004862788322824307, | |
| "eval_loss": 1.7966933250427246, | |
| "eval_runtime": 397.1601, | |
| "eval_samples_per_second": 32.702, | |
| "eval_steps_per_second": 8.176, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.005186974211012595, | |
| "grad_norm": 3.389646053314209, | |
| "learning_rate": 0.0001779516693350504, | |
| "loss": 1.8123, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.005511160099200882, | |
| "grad_norm": 4.33231258392334, | |
| "learning_rate": 0.00017275501775814182, | |
| "loss": 1.8088, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.005835345987389169, | |
| "grad_norm": 4.176562309265137, | |
| "learning_rate": 0.00016722096269620562, | |
| "loss": 1.7369, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.006159531875577456, | |
| "grad_norm": 3.4682700634002686, | |
| "learning_rate": 0.00016137646550922228, | |
| "loss": 1.6268, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.006483717763765743, | |
| "grad_norm": 4.2149200439453125, | |
| "learning_rate": 0.00015525, | |
| "loss": 1.6822, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.006483717763765743, | |
| "eval_loss": 1.7772059440612793, | |
| "eval_runtime": 397.9979, | |
| "eval_samples_per_second": 32.633, | |
| "eval_steps_per_second": 8.158, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.00680790365195403, | |
| "grad_norm": 2.8696839809417725, | |
| "learning_rate": 0.0001488714136926695, | |
| "loss": 1.8906, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.0071320895401423175, | |
| "grad_norm": 3.76540207862854, | |
| "learning_rate": 0.0001422717824185469, | |
| "loss": 1.7974, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.0074562754283306045, | |
| "grad_norm": 4.557528972625732, | |
| "learning_rate": 0.00013548325891780705, | |
| "loss": 1.8021, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.007780461316518892, | |
| "grad_norm": 4.325812339782715, | |
| "learning_rate": 0.0001285389161945656, | |
| "loss": 1.7236, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.00810464720470718, | |
| "grad_norm": 3.879993200302124, | |
| "learning_rate": 0.0001214725863885273, | |
| "loss": 1.7255, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.00810464720470718, | |
| "eval_loss": 1.7434029579162598, | |
| "eval_runtime": 397.2014, | |
| "eval_samples_per_second": 32.699, | |
| "eval_steps_per_second": 8.175, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.008428833092895466, | |
| "grad_norm": 3.901002883911133, | |
| "learning_rate": 0.00011431869594820213, | |
| "loss": 1.7344, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.008753018981083754, | |
| "grad_norm": 4.044349670410156, | |
| "learning_rate": 0.00010711209790870886, | |
| "loss": 1.576, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.00907720486927204, | |
| "grad_norm": 3.8595011234283447, | |
| "learning_rate": 9.988790209129117e-05, | |
| "loss": 1.802, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.009401390757460328, | |
| "grad_norm": 3.7126569747924805, | |
| "learning_rate": 9.268130405179787e-05, | |
| "loss": 1.6513, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.009725576645648614, | |
| "grad_norm": 4.118965148925781, | |
| "learning_rate": 8.55274136114727e-05, | |
| "loss": 1.5466, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.009725576645648614, | |
| "eval_loss": 1.6769126653671265, | |
| "eval_runtime": 399.0787, | |
| "eval_samples_per_second": 32.545, | |
| "eval_steps_per_second": 8.136, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.010049762533836902, | |
| "grad_norm": 3.541172981262207, | |
| "learning_rate": 7.84610838054344e-05, | |
| "loss": 1.8639, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.01037394842202519, | |
| "grad_norm": 4.0853753089904785, | |
| "learning_rate": 7.151674108219295e-05, | |
| "loss": 1.6957, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.010698134310213476, | |
| "grad_norm": 3.440962076187134, | |
| "learning_rate": 6.472821758145309e-05, | |
| "loss": 1.6691, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.011022320198401764, | |
| "grad_norm": 3.6532485485076904, | |
| "learning_rate": 5.8128586307330475e-05, | |
| "loss": 1.5867, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.01134650608659005, | |
| "grad_norm": 3.979214906692505, | |
| "learning_rate": 5.175000000000002e-05, | |
| "loss": 1.5499, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.01134650608659005, | |
| "eval_loss": 1.6310955286026, | |
| "eval_runtime": 398.0556, | |
| "eval_samples_per_second": 32.629, | |
| "eval_steps_per_second": 8.157, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.011670691974778338, | |
| "grad_norm": 3.600574254989624, | |
| "learning_rate": 4.5623534490777714e-05, | |
| "loss": 1.8409, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.011994877862966625, | |
| "grad_norm": 3.5220589637756348, | |
| "learning_rate": 3.9779037303794365e-05, | |
| "loss": 1.5889, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.012319063751154912, | |
| "grad_norm": 3.7355663776397705, | |
| "learning_rate": 3.42449822418582e-05, | |
| "loss": 1.5124, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.012643249639343199, | |
| "grad_norm": 3.8457112312316895, | |
| "learning_rate": 2.9048330664949622e-05, | |
| "loss": 1.5491, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.012967435527531487, | |
| "grad_norm": 3.4412333965301514, | |
| "learning_rate": 2.4214400137185785e-05, | |
| "loss": 1.549, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.012967435527531487, | |
| "eval_loss": 1.606103539466858, | |
| "eval_runtime": 396.0436, | |
| "eval_samples_per_second": 32.794, | |
| "eval_steps_per_second": 8.199, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.013291621415719775, | |
| "grad_norm": 3.6701438426971436, | |
| "learning_rate": 1.976674108219295e-05, | |
| "loss": 1.6744, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.01361580730390806, | |
| "grad_norm": 4.545055389404297, | |
| "learning_rate": 1.572702204780991e-05, | |
| "loss": 1.6089, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.013939993192096349, | |
| "grad_norm": 3.4341204166412354, | |
| "learning_rate": 1.2114924139101056e-05, | |
| "loss": 1.5792, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.014264179080284635, | |
| "grad_norm": 3.332812547683716, | |
| "learning_rate": 8.948045133990798e-06, | |
| "loss": 1.5303, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.014588364968472923, | |
| "grad_norm": 3.597540855407715, | |
| "learning_rate": 6.241813748658489e-06, | |
| "loss": 1.5332, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.014588364968472923, | |
| "eval_loss": 1.5877035856246948, | |
| "eval_runtime": 397.7506, | |
| "eval_samples_per_second": 32.654, | |
| "eval_steps_per_second": 8.163, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.014912550856661209, | |
| "grad_norm": 3.2884576320648193, | |
| "learning_rate": 4.009414470383994e-06, | |
| "loss": 1.8572, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.015236736744849497, | |
| "grad_norm": 3.6394126415252686, | |
| "learning_rate": 2.261723324051111e-06, | |
| "loss": 1.7304, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.015560922633037783, | |
| "grad_norm": 2.9843626022338867, | |
| "learning_rate": 1.0072548852474675e-06, | |
| "loss": 1.631, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.01588510852122607, | |
| "grad_norm": 3.780142068862915, | |
| "learning_rate": 2.5212079810819554e-07, | |
| "loss": 1.2314, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.01620929440941436, | |
| "grad_norm": 3.420269012451172, | |
| "learning_rate": 0.0, | |
| "loss": 1.4883, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.01620929440941436, | |
| "eval_loss": 1.5858772993087769, | |
| "eval_runtime": 398.3709, | |
| "eval_samples_per_second": 32.603, | |
| "eval_steps_per_second": 8.151, | |
| "step": 500 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 500, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "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": 2.789971686378701e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |