| { | |
| "best_global_step": 1000, | |
| "best_metric": 0.8179630041122437, | |
| "best_model_checkpoint": "./biomistral-lora-finetuned/checkpoint-1000", | |
| "epoch": 1.0823290453622207, | |
| "eval_steps": 500, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.010832769126607989, | |
| "grad_norm": 0.7727395296096802, | |
| "learning_rate": 1.8e-05, | |
| "loss": 0.889, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.021665538253215978, | |
| "grad_norm": 0.8008129596710205, | |
| "learning_rate": 3.8e-05, | |
| "loss": 0.8378, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03249830737982397, | |
| "grad_norm": 0.9147247076034546, | |
| "learning_rate": 5.8e-05, | |
| "loss": 0.8108, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.043331076506431955, | |
| "grad_norm": 0.8121607303619385, | |
| "learning_rate": 7.800000000000001e-05, | |
| "loss": 0.8597, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05416384563303995, | |
| "grad_norm": 1.0018593072891235, | |
| "learning_rate": 9.8e-05, | |
| "loss": 0.7486, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06499661475964794, | |
| "grad_norm": 1.2048218250274658, | |
| "learning_rate": 0.000118, | |
| "loss": 0.6825, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07582938388625593, | |
| "grad_norm": 0.9863468408584595, | |
| "learning_rate": 0.000138, | |
| "loss": 0.6539, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08666215301286391, | |
| "grad_norm": 1.2911494970321655, | |
| "learning_rate": 0.00015800000000000002, | |
| "loss": 0.6198, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.0974949221394719, | |
| "grad_norm": 1.159672737121582, | |
| "learning_rate": 0.00017800000000000002, | |
| "loss": 0.6222, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1083276912660799, | |
| "grad_norm": 1.0924432277679443, | |
| "learning_rate": 0.00019800000000000002, | |
| "loss": 0.5923, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11916046039268788, | |
| "grad_norm": 1.3423463106155396, | |
| "learning_rate": 0.00019932634730538925, | |
| "loss": 0.5548, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.12999322951929587, | |
| "grad_norm": 1.4929102659225464, | |
| "learning_rate": 0.00019857784431137723, | |
| "loss": 0.6701, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.14082599864590387, | |
| "grad_norm": 0.9462954998016357, | |
| "learning_rate": 0.00019782934131736527, | |
| "loss": 0.8675, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.15165876777251186, | |
| "grad_norm": 0.9912289977073669, | |
| "learning_rate": 0.0001970808383233533, | |
| "loss": 0.9074, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.16249153689911983, | |
| "grad_norm": 1.1070538759231567, | |
| "learning_rate": 0.00019633233532934132, | |
| "loss": 0.8755, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17332430602572782, | |
| "grad_norm": 0.9465340375900269, | |
| "learning_rate": 0.00019558383233532936, | |
| "loss": 0.882, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.18415707515233581, | |
| "grad_norm": 0.8657329678535461, | |
| "learning_rate": 0.00019483532934131737, | |
| "loss": 0.8737, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.1949898442789438, | |
| "grad_norm": 0.7293577790260315, | |
| "learning_rate": 0.0001940868263473054, | |
| "loss": 0.8473, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.2058226134055518, | |
| "grad_norm": 0.849353551864624, | |
| "learning_rate": 0.00019333832335329343, | |
| "loss": 0.9414, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2166553825321598, | |
| "grad_norm": 0.7525314688682556, | |
| "learning_rate": 0.00019258982035928144, | |
| "loss": 0.8852, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.22748815165876776, | |
| "grad_norm": 1.0732208490371704, | |
| "learning_rate": 0.00019184131736526948, | |
| "loss": 0.8074, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.23832092078537576, | |
| "grad_norm": 0.8420374393463135, | |
| "learning_rate": 0.0001910928143712575, | |
| "loss": 0.9508, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.24915368991198375, | |
| "grad_norm": 0.8308244347572327, | |
| "learning_rate": 0.0001903443113772455, | |
| "loss": 0.8734, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.25998645903859174, | |
| "grad_norm": 0.9915153384208679, | |
| "learning_rate": 0.00018959580838323354, | |
| "loss": 0.8816, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.2708192281651997, | |
| "grad_norm": 4.8621978759765625, | |
| "learning_rate": 0.00018884730538922158, | |
| "loss": 0.8848, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28165199729180773, | |
| "grad_norm": 0.7945590019226074, | |
| "learning_rate": 0.0001880988023952096, | |
| "loss": 0.8503, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.2924847664184157, | |
| "grad_norm": 0.7896672487258911, | |
| "learning_rate": 0.00018735029940119763, | |
| "loss": 0.8798, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.3033175355450237, | |
| "grad_norm": 0.8870701789855957, | |
| "learning_rate": 0.00018660179640718564, | |
| "loss": 0.9112, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.3141503046716317, | |
| "grad_norm": 0.9003740549087524, | |
| "learning_rate": 0.00018585329341317365, | |
| "loss": 0.846, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.32498307379823965, | |
| "grad_norm": 0.7067676186561584, | |
| "learning_rate": 0.0001851047904191617, | |
| "loss": 0.8588, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.3358158429248477, | |
| "grad_norm": 0.9696246385574341, | |
| "learning_rate": 0.0001843562874251497, | |
| "loss": 0.8244, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.34664861205145564, | |
| "grad_norm": 0.9892609715461731, | |
| "learning_rate": 0.00018360778443113774, | |
| "loss": 0.8214, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.35748138117806366, | |
| "grad_norm": 0.822260856628418, | |
| "learning_rate": 0.00018285928143712575, | |
| "loss": 0.7977, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.36831415030467163, | |
| "grad_norm": 0.7743964791297913, | |
| "learning_rate": 0.00018211077844311376, | |
| "loss": 0.8002, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3791469194312796, | |
| "grad_norm": 0.7090775370597839, | |
| "learning_rate": 0.0001813622754491018, | |
| "loss": 0.8192, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3899796885578876, | |
| "grad_norm": 1.0970802307128906, | |
| "learning_rate": 0.00018061377245508984, | |
| "loss": 0.8516, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.4008124576844956, | |
| "grad_norm": 0.9633163213729858, | |
| "learning_rate": 0.00017986526946107785, | |
| "loss": 0.8414, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.4116452268111036, | |
| "grad_norm": 0.6846926808357239, | |
| "learning_rate": 0.00017911676646706587, | |
| "loss": 0.8187, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.42247799593771157, | |
| "grad_norm": 0.7262110710144043, | |
| "learning_rate": 0.0001783682634730539, | |
| "loss": 0.8572, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.4333107650643196, | |
| "grad_norm": 0.8537372350692749, | |
| "learning_rate": 0.00017761976047904192, | |
| "loss": 0.8286, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.44414353419092756, | |
| "grad_norm": 0.8860271573066711, | |
| "learning_rate": 0.00017687125748502996, | |
| "loss": 0.8416, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.4549763033175355, | |
| "grad_norm": 0.7984218597412109, | |
| "learning_rate": 0.000176122754491018, | |
| "loss": 0.8373, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.46580907244414355, | |
| "grad_norm": 0.8060943484306335, | |
| "learning_rate": 0.000175374251497006, | |
| "loss": 0.9165, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.4766418415707515, | |
| "grad_norm": 0.7871391177177429, | |
| "learning_rate": 0.00017462574850299402, | |
| "loss": 0.8276, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.48747461069735953, | |
| "grad_norm": 0.7732688784599304, | |
| "learning_rate": 0.00017387724550898203, | |
| "loss": 0.8346, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4983073798239675, | |
| "grad_norm": 0.9314000606536865, | |
| "learning_rate": 0.00017312874251497007, | |
| "loss": 0.8291, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.5091401489505755, | |
| "grad_norm": 0.6721988916397095, | |
| "learning_rate": 0.0001723802395209581, | |
| "loss": 0.7091, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.5199729180771835, | |
| "grad_norm": 0.825965940952301, | |
| "learning_rate": 0.00017163173652694612, | |
| "loss": 0.8934, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.5308056872037915, | |
| "grad_norm": 0.8427668213844299, | |
| "learning_rate": 0.00017088323353293413, | |
| "loss": 0.7603, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.5416384563303994, | |
| "grad_norm": 1.0061259269714355, | |
| "learning_rate": 0.00017013473053892217, | |
| "loss": 0.8277, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5416384563303994, | |
| "eval_loss": 0.8331602811813354, | |
| "eval_runtime": 355.9061, | |
| "eval_samples_per_second": 4.614, | |
| "eval_steps_per_second": 2.307, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5524712254570074, | |
| "grad_norm": 0.8820628523826599, | |
| "learning_rate": 0.00016938622754491018, | |
| "loss": 0.8348, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.5633039945836155, | |
| "grad_norm": 0.8095284700393677, | |
| "learning_rate": 0.00016863772455089822, | |
| "loss": 0.9172, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5741367637102234, | |
| "grad_norm": 0.6959540843963623, | |
| "learning_rate": 0.00016788922155688623, | |
| "loss": 0.838, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5849695328368314, | |
| "grad_norm": 0.835831880569458, | |
| "learning_rate": 0.00016714071856287424, | |
| "loss": 0.8887, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5958023019634394, | |
| "grad_norm": 0.9289611577987671, | |
| "learning_rate": 0.00016639221556886228, | |
| "loss": 0.8514, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.6066350710900474, | |
| "grad_norm": 0.6904628872871399, | |
| "learning_rate": 0.00016564371257485032, | |
| "loss": 0.8645, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.6174678402166554, | |
| "grad_norm": 0.8879178762435913, | |
| "learning_rate": 0.00016489520958083833, | |
| "loss": 0.8201, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.6283006093432634, | |
| "grad_norm": 0.8411425948143005, | |
| "learning_rate": 0.00016414670658682637, | |
| "loss": 0.836, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.6391333784698714, | |
| "grad_norm": 0.8564555644989014, | |
| "learning_rate": 0.00016339820359281436, | |
| "loss": 0.7724, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.6499661475964793, | |
| "grad_norm": 0.8382830619812012, | |
| "learning_rate": 0.0001626497005988024, | |
| "loss": 0.7839, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.6607989167230873, | |
| "grad_norm": 0.7657437920570374, | |
| "learning_rate": 0.00016190119760479043, | |
| "loss": 0.7973, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.6716316858496953, | |
| "grad_norm": 0.7758445143699646, | |
| "learning_rate": 0.00016115269461077845, | |
| "loss": 0.8111, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6824644549763034, | |
| "grad_norm": 1.0041533708572388, | |
| "learning_rate": 0.00016040419161676649, | |
| "loss": 0.8359, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6932972241029113, | |
| "grad_norm": 0.9679577946662903, | |
| "learning_rate": 0.0001596556886227545, | |
| "loss": 0.8822, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.7041299932295193, | |
| "grad_norm": 0.8141391277313232, | |
| "learning_rate": 0.0001589071856287425, | |
| "loss": 0.8714, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.7149627623561273, | |
| "grad_norm": 0.7982810139656067, | |
| "learning_rate": 0.00015815868263473055, | |
| "loss": 0.856, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.7257955314827352, | |
| "grad_norm": 0.7932000160217285, | |
| "learning_rate": 0.00015741017964071859, | |
| "loss": 0.8405, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.7366283006093433, | |
| "grad_norm": 0.7269508242607117, | |
| "learning_rate": 0.0001566616766467066, | |
| "loss": 0.8371, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.7474610697359513, | |
| "grad_norm": 0.9001722931861877, | |
| "learning_rate": 0.0001559131736526946, | |
| "loss": 0.8305, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.7582938388625592, | |
| "grad_norm": 0.6795508861541748, | |
| "learning_rate": 0.00015516467065868262, | |
| "loss": 0.8324, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7691266079891672, | |
| "grad_norm": 0.8868729472160339, | |
| "learning_rate": 0.00015441616766467066, | |
| "loss": 0.8521, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.7799593771157752, | |
| "grad_norm": 0.9720478653907776, | |
| "learning_rate": 0.0001536676646706587, | |
| "loss": 0.7759, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.7907921462423833, | |
| "grad_norm": 0.8006075620651245, | |
| "learning_rate": 0.0001529191616766467, | |
| "loss": 0.7981, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.8016249153689912, | |
| "grad_norm": 0.9107721447944641, | |
| "learning_rate": 0.00015217065868263475, | |
| "loss": 0.7868, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.8124576844955992, | |
| "grad_norm": 0.7584466338157654, | |
| "learning_rate": 0.00015142215568862276, | |
| "loss": 0.7401, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.8232904536222072, | |
| "grad_norm": 1.0075221061706543, | |
| "learning_rate": 0.00015067365269461077, | |
| "loss": 0.8024, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.8341232227488151, | |
| "grad_norm": 0.8769344091415405, | |
| "learning_rate": 0.0001499251497005988, | |
| "loss": 0.7779, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.8449559918754231, | |
| "grad_norm": 0.84312903881073, | |
| "learning_rate": 0.00014917664670658685, | |
| "loss": 0.8314, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.8557887610020312, | |
| "grad_norm": 0.8116353750228882, | |
| "learning_rate": 0.00014842814371257486, | |
| "loss": 0.8146, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.8666215301286392, | |
| "grad_norm": 0.8301011919975281, | |
| "learning_rate": 0.00014767964071856287, | |
| "loss": 0.7422, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8774542992552471, | |
| "grad_norm": 0.8579692244529724, | |
| "learning_rate": 0.00014693113772455091, | |
| "loss": 0.7442, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.8882870683818551, | |
| "grad_norm": 0.7513943910598755, | |
| "learning_rate": 0.00014618263473053893, | |
| "loss": 0.7671, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.8991198375084631, | |
| "grad_norm": 0.9639107584953308, | |
| "learning_rate": 0.00014543413173652696, | |
| "loss": 0.7896, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.909952606635071, | |
| "grad_norm": 0.8897636532783508, | |
| "learning_rate": 0.00014468562874251498, | |
| "loss": 0.7613, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.9207853757616791, | |
| "grad_norm": 0.7998213171958923, | |
| "learning_rate": 0.000143937125748503, | |
| "loss": 0.7647, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.9316181448882871, | |
| "grad_norm": 0.6916050910949707, | |
| "learning_rate": 0.00014318862275449103, | |
| "loss": 0.7697, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.942450914014895, | |
| "grad_norm": 1.0154324769973755, | |
| "learning_rate": 0.00014244011976047904, | |
| "loss": 0.7314, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.953283683141503, | |
| "grad_norm": 0.9787517786026001, | |
| "learning_rate": 0.00014169161676646708, | |
| "loss": 0.8047, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.964116452268111, | |
| "grad_norm": 0.6035457253456116, | |
| "learning_rate": 0.00014094311377245512, | |
| "loss": 0.783, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.9749492213947191, | |
| "grad_norm": 0.940951943397522, | |
| "learning_rate": 0.0001401946107784431, | |
| "loss": 0.7741, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.985781990521327, | |
| "grad_norm": 0.7785654067993164, | |
| "learning_rate": 0.00013944610778443114, | |
| "loss": 0.7855, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.996614759647935, | |
| "grad_norm": 0.8356137275695801, | |
| "learning_rate": 0.00013869760479041918, | |
| "loss": 0.8292, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 1.0064996614759647, | |
| "grad_norm": 0.6590499877929688, | |
| "learning_rate": 0.0001379491017964072, | |
| "loss": 0.6858, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 1.0173324306025728, | |
| "grad_norm": 1.0389671325683594, | |
| "learning_rate": 0.00013720059880239523, | |
| "loss": 0.6097, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 1.0281651997291807, | |
| "grad_norm": 0.9596243500709534, | |
| "learning_rate": 0.00013645209580838324, | |
| "loss": 0.5676, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 1.0389979688557887, | |
| "grad_norm": 1.0831798315048218, | |
| "learning_rate": 0.00013570359281437125, | |
| "loss": 0.6106, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 1.0498307379823968, | |
| "grad_norm": 0.92978835105896, | |
| "learning_rate": 0.0001349550898203593, | |
| "loss": 0.5924, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 1.0606635071090047, | |
| "grad_norm": 0.9672062993049622, | |
| "learning_rate": 0.0001342065868263473, | |
| "loss": 0.5496, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 1.0714962762356128, | |
| "grad_norm": 1.1402652263641357, | |
| "learning_rate": 0.00013345808383233534, | |
| "loss": 0.5871, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 1.0823290453622207, | |
| "grad_norm": 1.1109035015106201, | |
| "learning_rate": 0.00013270958083832335, | |
| "loss": 0.5424, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0823290453622207, | |
| "eval_loss": 0.8179630041122437, | |
| "eval_runtime": 357.2769, | |
| "eval_samples_per_second": 4.596, | |
| "eval_steps_per_second": 2.298, | |
| "step": 1000 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 2772, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.523118244330209e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |