| { | |
| "best_metric": 0.5748393021120294, | |
| "best_model_checkpoint": "convnextv2-base-22k-224-finetuned-tekno24/checkpoint-615", | |
| "epoch": 11.941463414634146, | |
| "eval_steps": 500, | |
| "global_step": 1224, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 12.655921936035156, | |
| "learning_rate": 4.0650406504065046e-06, | |
| "loss": 1.4164, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1951219512195122, | |
| "grad_norm": 17.018129348754883, | |
| "learning_rate": 8.130081300813009e-06, | |
| "loss": 1.4339, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2926829268292683, | |
| "grad_norm": 16.979167938232422, | |
| "learning_rate": 1.1788617886178862e-05, | |
| "loss": 1.4233, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.3902439024390244, | |
| "grad_norm": 18.95262908935547, | |
| "learning_rate": 1.5447154471544717e-05, | |
| "loss": 1.3995, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4878048780487805, | |
| "grad_norm": 10.330867767333984, | |
| "learning_rate": 1.9512195121951222e-05, | |
| "loss": 1.3879, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5853658536585366, | |
| "grad_norm": 7.81517219543457, | |
| "learning_rate": 2.3577235772357724e-05, | |
| "loss": 1.3701, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6829268292682927, | |
| "grad_norm": 13.965815544128418, | |
| "learning_rate": 2.764227642276423e-05, | |
| "loss": 1.3374, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7804878048780488, | |
| "grad_norm": 13.348392486572266, | |
| "learning_rate": 3.170731707317073e-05, | |
| "loss": 1.3221, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8780487804878049, | |
| "grad_norm": 13.079450607299805, | |
| "learning_rate": 3.577235772357724e-05, | |
| "loss": 1.3228, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.975609756097561, | |
| "grad_norm": 9.20757007598877, | |
| "learning_rate": 3.983739837398374e-05, | |
| "loss": 1.2643, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9951219512195122, | |
| "eval_accuracy": 0.5206611570247934, | |
| "eval_f1": 0.47635822656042665, | |
| "eval_loss": 1.1486896276474, | |
| "eval_precision": 0.4782877718762662, | |
| "eval_recall": 0.5206611570247934, | |
| "eval_runtime": 10.5321, | |
| "eval_samples_per_second": 103.399, | |
| "eval_steps_per_second": 6.551, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 1.0731707317073171, | |
| "grad_norm": 11.261804580688477, | |
| "learning_rate": 4.390243902439025e-05, | |
| "loss": 1.2688, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.170731707317073, | |
| "grad_norm": 20.570632934570312, | |
| "learning_rate": 4.796747967479675e-05, | |
| "loss": 1.2293, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.2682926829268293, | |
| "grad_norm": 8.604395866394043, | |
| "learning_rate": 4.9772933696639425e-05, | |
| "loss": 1.2657, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.3658536585365852, | |
| "grad_norm": 23.755281448364258, | |
| "learning_rate": 4.931880108991826e-05, | |
| "loss": 1.2812, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.4634146341463414, | |
| "grad_norm": 17.45159912109375, | |
| "learning_rate": 4.886466848319709e-05, | |
| "loss": 1.2578, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.5609756097560976, | |
| "grad_norm": 6.092088222503662, | |
| "learning_rate": 4.841053587647593e-05, | |
| "loss": 1.2356, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.6585365853658538, | |
| "grad_norm": 7.634965419769287, | |
| "learning_rate": 4.795640326975477e-05, | |
| "loss": 1.2367, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.7560975609756098, | |
| "grad_norm": 12.493597984313965, | |
| "learning_rate": 4.750227066303361e-05, | |
| "loss": 1.2391, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.8536585365853657, | |
| "grad_norm": 7.179015159606934, | |
| "learning_rate": 4.704813805631245e-05, | |
| "loss": 1.2718, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.951219512195122, | |
| "grad_norm": 11.228482246398926, | |
| "learning_rate": 4.659400544959128e-05, | |
| "loss": 1.1889, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.5087235996326905, | |
| "eval_f1": 0.5190802114624434, | |
| "eval_loss": 1.1037839651107788, | |
| "eval_precision": 0.5564617175099487, | |
| "eval_recall": 0.5087235996326905, | |
| "eval_runtime": 10.5165, | |
| "eval_samples_per_second": 103.551, | |
| "eval_steps_per_second": 6.561, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 2.048780487804878, | |
| "grad_norm": 8.938887596130371, | |
| "learning_rate": 4.613987284287012e-05, | |
| "loss": 1.1869, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 2.1463414634146343, | |
| "grad_norm": 8.932198524475098, | |
| "learning_rate": 4.5685740236148955e-05, | |
| "loss": 1.208, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.2439024390243905, | |
| "grad_norm": 5.741872787475586, | |
| "learning_rate": 4.52316076294278e-05, | |
| "loss": 1.2029, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.341463414634146, | |
| "grad_norm": 8.091480255126953, | |
| "learning_rate": 4.477747502270663e-05, | |
| "loss": 1.19, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.4390243902439024, | |
| "grad_norm": 7.227927207946777, | |
| "learning_rate": 4.432334241598547e-05, | |
| "loss": 1.2083, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.5365853658536586, | |
| "grad_norm": 5.250303745269775, | |
| "learning_rate": 4.3869209809264305e-05, | |
| "loss": 1.1941, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.6341463414634148, | |
| "grad_norm": 8.268411636352539, | |
| "learning_rate": 4.341507720254315e-05, | |
| "loss": 1.1783, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.7317073170731705, | |
| "grad_norm": 6.347944259643555, | |
| "learning_rate": 4.296094459582199e-05, | |
| "loss": 1.1653, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.8292682926829267, | |
| "grad_norm": 8.626900672912598, | |
| "learning_rate": 4.250681198910082e-05, | |
| "loss": 1.1733, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.926829268292683, | |
| "grad_norm": 7.539112567901611, | |
| "learning_rate": 4.2052679382379655e-05, | |
| "loss": 1.215, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 2.995121951219512, | |
| "eval_accuracy": 0.4830119375573921, | |
| "eval_f1": 0.4794682324453807, | |
| "eval_loss": 1.0810357332229614, | |
| "eval_precision": 0.5588554246566038, | |
| "eval_recall": 0.4830119375573921, | |
| "eval_runtime": 10.5448, | |
| "eval_samples_per_second": 103.274, | |
| "eval_steps_per_second": 6.544, | |
| "step": 307 | |
| }, | |
| { | |
| "epoch": 3.024390243902439, | |
| "grad_norm": 7.887587547302246, | |
| "learning_rate": 4.159854677565849e-05, | |
| "loss": 1.1419, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 3.1219512195121952, | |
| "grad_norm": 8.143919944763184, | |
| "learning_rate": 4.114441416893734e-05, | |
| "loss": 1.1339, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 3.2195121951219514, | |
| "grad_norm": 8.059014320373535, | |
| "learning_rate": 4.069028156221617e-05, | |
| "loss": 1.0966, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 3.317073170731707, | |
| "grad_norm": 7.19610595703125, | |
| "learning_rate": 4.0236148955495005e-05, | |
| "loss": 1.1837, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 3.4146341463414633, | |
| "grad_norm": 6.76222038269043, | |
| "learning_rate": 3.978201634877384e-05, | |
| "loss": 1.1768, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 3.5121951219512195, | |
| "grad_norm": 6.472099781036377, | |
| "learning_rate": 3.932788374205268e-05, | |
| "loss": 1.1588, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 3.6097560975609757, | |
| "grad_norm": 7.446631908416748, | |
| "learning_rate": 3.887375113533152e-05, | |
| "loss": 1.1531, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 3.7073170731707314, | |
| "grad_norm": 7.529073238372803, | |
| "learning_rate": 3.8419618528610355e-05, | |
| "loss": 1.1203, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 3.8048780487804876, | |
| "grad_norm": 8.24229907989502, | |
| "learning_rate": 3.796548592188919e-05, | |
| "loss": 1.1788, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 3.902439024390244, | |
| "grad_norm": 5.0005412101745605, | |
| "learning_rate": 3.751135331516803e-05, | |
| "loss": 1.1577, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 11.378023147583008, | |
| "learning_rate": 3.705722070844687e-05, | |
| "loss": 1.1062, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_accuracy": 0.5619834710743802, | |
| "eval_f1": 0.5281037322147313, | |
| "eval_loss": 1.0103230476379395, | |
| "eval_precision": 0.5357616363900534, | |
| "eval_recall": 0.5619834710743802, | |
| "eval_runtime": 10.5649, | |
| "eval_samples_per_second": 103.077, | |
| "eval_steps_per_second": 6.531, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 4.097560975609756, | |
| "grad_norm": 7.739734172821045, | |
| "learning_rate": 3.6603088101725705e-05, | |
| "loss": 1.076, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 4.195121951219512, | |
| "grad_norm": 6.631500244140625, | |
| "learning_rate": 3.614895549500454e-05, | |
| "loss": 1.1469, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 4.2926829268292686, | |
| "grad_norm": 9.386627197265625, | |
| "learning_rate": 3.569482288828338e-05, | |
| "loss": 1.0905, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 4.390243902439025, | |
| "grad_norm": 11.621010780334473, | |
| "learning_rate": 3.524069028156222e-05, | |
| "loss": 1.1032, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 4.487804878048781, | |
| "grad_norm": 8.444263458251953, | |
| "learning_rate": 3.4786557674841055e-05, | |
| "loss": 1.1181, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 4.585365853658536, | |
| "grad_norm": 8.17673110961914, | |
| "learning_rate": 3.433242506811989e-05, | |
| "loss": 1.116, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 4.682926829268292, | |
| "grad_norm": 6.36055326461792, | |
| "learning_rate": 3.387829246139873e-05, | |
| "loss": 1.0976, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 4.780487804878049, | |
| "grad_norm": 6.861799240112305, | |
| "learning_rate": 3.342415985467757e-05, | |
| "loss": 1.0847, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 4.878048780487805, | |
| "grad_norm": 8.115589141845703, | |
| "learning_rate": 3.2970027247956405e-05, | |
| "loss": 1.1018, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 4.975609756097561, | |
| "grad_norm": 10.135653495788574, | |
| "learning_rate": 3.251589464123524e-05, | |
| "loss": 1.089, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 4.995121951219512, | |
| "eval_accuracy": 0.5344352617079889, | |
| "eval_f1": 0.5440491210548923, | |
| "eval_loss": 1.0458588600158691, | |
| "eval_precision": 0.5719778943634586, | |
| "eval_recall": 0.5344352617079889, | |
| "eval_runtime": 10.4912, | |
| "eval_samples_per_second": 103.801, | |
| "eval_steps_per_second": 6.577, | |
| "step": 512 | |
| }, | |
| { | |
| "epoch": 5.073170731707317, | |
| "grad_norm": 6.753456115722656, | |
| "learning_rate": 3.206176203451408e-05, | |
| "loss": 1.0425, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 5.170731707317073, | |
| "grad_norm": 8.520686149597168, | |
| "learning_rate": 3.160762942779292e-05, | |
| "loss": 1.0978, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 5.2682926829268295, | |
| "grad_norm": 9.387904167175293, | |
| "learning_rate": 3.1153496821071755e-05, | |
| "loss": 1.0495, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 5.365853658536586, | |
| "grad_norm": 9.20468807220459, | |
| "learning_rate": 3.069936421435059e-05, | |
| "loss": 1.117, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 5.463414634146342, | |
| "grad_norm": 11.512433052062988, | |
| "learning_rate": 3.0245231607629433e-05, | |
| "loss": 1.0678, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 5.560975609756097, | |
| "grad_norm": 8.392121315002441, | |
| "learning_rate": 2.9791099000908267e-05, | |
| "loss": 1.0267, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 5.658536585365853, | |
| "grad_norm": 10.961865425109863, | |
| "learning_rate": 2.9336966394187105e-05, | |
| "loss": 1.0381, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 5.7560975609756095, | |
| "grad_norm": 6.7657599449157715, | |
| "learning_rate": 2.888283378746594e-05, | |
| "loss": 1.0351, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 5.853658536585366, | |
| "grad_norm": 10.026562690734863, | |
| "learning_rate": 2.8428701180744776e-05, | |
| "loss": 1.0566, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 5.951219512195122, | |
| "grad_norm": 10.82862663269043, | |
| "learning_rate": 2.7974568574023617e-05, | |
| "loss": 1.0335, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_accuracy": 0.5748393021120294, | |
| "eval_f1": 0.5696724052779626, | |
| "eval_loss": 0.9780603051185608, | |
| "eval_precision": 0.5821729436076757, | |
| "eval_recall": 0.5748393021120294, | |
| "eval_runtime": 10.5116, | |
| "eval_samples_per_second": 103.6, | |
| "eval_steps_per_second": 6.564, | |
| "step": 615 | |
| }, | |
| { | |
| "epoch": 6.048780487804878, | |
| "grad_norm": 10.993868827819824, | |
| "learning_rate": 2.7520435967302455e-05, | |
| "loss": 0.9885, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 6.146341463414634, | |
| "grad_norm": 7.851088523864746, | |
| "learning_rate": 2.7066303360581292e-05, | |
| "loss": 1.0104, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 6.2439024390243905, | |
| "grad_norm": 8.290712356567383, | |
| "learning_rate": 2.6612170753860126e-05, | |
| "loss": 0.992, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 6.341463414634147, | |
| "grad_norm": 8.147354125976562, | |
| "learning_rate": 2.6158038147138964e-05, | |
| "loss": 1.0323, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 6.439024390243903, | |
| "grad_norm": 8.147374153137207, | |
| "learning_rate": 2.5703905540417805e-05, | |
| "loss": 1.0089, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 6.536585365853659, | |
| "grad_norm": 13.995866775512695, | |
| "learning_rate": 2.5249772933696642e-05, | |
| "loss": 1.0377, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 6.634146341463414, | |
| "grad_norm": 10.2506685256958, | |
| "learning_rate": 2.4795640326975476e-05, | |
| "loss": 0.979, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 6.7317073170731705, | |
| "grad_norm": 11.913418769836426, | |
| "learning_rate": 2.4341507720254317e-05, | |
| "loss": 0.9912, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 6.829268292682927, | |
| "grad_norm": 8.07094669342041, | |
| "learning_rate": 2.388737511353315e-05, | |
| "loss": 1.0496, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 6.926829268292683, | |
| "grad_norm": 11.005784034729004, | |
| "learning_rate": 2.343324250681199e-05, | |
| "loss": 1.0139, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 6.995121951219512, | |
| "eval_accuracy": 0.559228650137741, | |
| "eval_f1": 0.5604831098024555, | |
| "eval_loss": 0.990472674369812, | |
| "eval_precision": 0.5624792636698613, | |
| "eval_recall": 0.559228650137741, | |
| "eval_runtime": 10.478, | |
| "eval_samples_per_second": 103.932, | |
| "eval_steps_per_second": 6.585, | |
| "step": 717 | |
| }, | |
| { | |
| "epoch": 7.024390243902439, | |
| "grad_norm": 7.640585899353027, | |
| "learning_rate": 2.297910990009083e-05, | |
| "loss": 1.0333, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 7.121951219512195, | |
| "grad_norm": 10.462299346923828, | |
| "learning_rate": 2.2524977293369664e-05, | |
| "loss": 0.9744, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 7.219512195121951, | |
| "grad_norm": 9.705671310424805, | |
| "learning_rate": 2.2070844686648505e-05, | |
| "loss": 0.9582, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 7.317073170731708, | |
| "grad_norm": 7.699019908905029, | |
| "learning_rate": 2.161671207992734e-05, | |
| "loss": 0.979, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 7.414634146341464, | |
| "grad_norm": 12.271793365478516, | |
| "learning_rate": 2.1162579473206176e-05, | |
| "loss": 0.9407, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 7.512195121951219, | |
| "grad_norm": 8.415149688720703, | |
| "learning_rate": 2.0708446866485014e-05, | |
| "loss": 0.9282, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 7.609756097560975, | |
| "grad_norm": 10.61991024017334, | |
| "learning_rate": 2.025431425976385e-05, | |
| "loss": 0.9563, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 7.7073170731707314, | |
| "grad_norm": 7.090912818908691, | |
| "learning_rate": 1.980018165304269e-05, | |
| "loss": 0.9637, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 7.804878048780488, | |
| "grad_norm": 11.96972370147705, | |
| "learning_rate": 1.9346049046321526e-05, | |
| "loss": 0.998, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 7.902439024390244, | |
| "grad_norm": 8.186046600341797, | |
| "learning_rate": 1.8891916439600364e-05, | |
| "loss": 0.9622, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 15.831442832946777, | |
| "learning_rate": 1.84377838328792e-05, | |
| "loss": 0.9047, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "eval_accuracy": 0.5629017447199265, | |
| "eval_f1": 0.5524851150741983, | |
| "eval_loss": 0.9877268075942993, | |
| "eval_precision": 0.5482104981099638, | |
| "eval_recall": 0.5629017447199265, | |
| "eval_runtime": 10.4831, | |
| "eval_samples_per_second": 103.882, | |
| "eval_steps_per_second": 6.582, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 8.097560975609756, | |
| "grad_norm": 8.30269718170166, | |
| "learning_rate": 1.798365122615804e-05, | |
| "loss": 0.9005, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 8.195121951219512, | |
| "grad_norm": 10.962409973144531, | |
| "learning_rate": 1.7529518619436876e-05, | |
| "loss": 0.9167, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 8.292682926829269, | |
| "grad_norm": 8.846582412719727, | |
| "learning_rate": 1.7075386012715714e-05, | |
| "loss": 0.9393, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 8.390243902439025, | |
| "grad_norm": 10.282524108886719, | |
| "learning_rate": 1.662125340599455e-05, | |
| "loss": 0.9473, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 8.487804878048781, | |
| "grad_norm": 11.323814392089844, | |
| "learning_rate": 1.616712079927339e-05, | |
| "loss": 0.8695, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 8.585365853658537, | |
| "grad_norm": 10.95213794708252, | |
| "learning_rate": 1.5712988192552226e-05, | |
| "loss": 0.9257, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 8.682926829268293, | |
| "grad_norm": 11.248684883117676, | |
| "learning_rate": 1.5258855585831064e-05, | |
| "loss": 0.8916, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 8.78048780487805, | |
| "grad_norm": 10.221022605895996, | |
| "learning_rate": 1.48047229791099e-05, | |
| "loss": 0.8961, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 8.878048780487806, | |
| "grad_norm": 8.226391792297363, | |
| "learning_rate": 1.4350590372388739e-05, | |
| "loss": 0.8783, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 8.975609756097562, | |
| "grad_norm": 9.135197639465332, | |
| "learning_rate": 1.3896457765667576e-05, | |
| "loss": 0.8856, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 8.995121951219513, | |
| "eval_accuracy": 0.5564738292011019, | |
| "eval_f1": 0.556882933826955, | |
| "eval_loss": 1.0059682130813599, | |
| "eval_precision": 0.5592586252036796, | |
| "eval_recall": 0.5564738292011019, | |
| "eval_runtime": 10.5466, | |
| "eval_samples_per_second": 103.256, | |
| "eval_steps_per_second": 6.542, | |
| "step": 922 | |
| }, | |
| { | |
| "epoch": 9.073170731707316, | |
| "grad_norm": 11.500414848327637, | |
| "learning_rate": 1.3442325158946412e-05, | |
| "loss": 0.8476, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 9.170731707317072, | |
| "grad_norm": 11.68885612487793, | |
| "learning_rate": 1.2988192552225251e-05, | |
| "loss": 0.869, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 9.268292682926829, | |
| "grad_norm": 9.877538681030273, | |
| "learning_rate": 1.2534059945504087e-05, | |
| "loss": 0.8572, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 9.365853658536585, | |
| "grad_norm": 11.605177879333496, | |
| "learning_rate": 1.2079927338782924e-05, | |
| "loss": 0.8434, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 9.463414634146341, | |
| "grad_norm": 10.330570220947266, | |
| "learning_rate": 1.1625794732061762e-05, | |
| "loss": 0.894, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 9.560975609756097, | |
| "grad_norm": 9.849478721618652, | |
| "learning_rate": 1.11716621253406e-05, | |
| "loss": 0.894, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 9.658536585365853, | |
| "grad_norm": 9.98214340209961, | |
| "learning_rate": 1.0717529518619437e-05, | |
| "loss": 0.8652, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 9.75609756097561, | |
| "grad_norm": 9.999092102050781, | |
| "learning_rate": 1.0263396911898274e-05, | |
| "loss": 0.8855, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 9.853658536585366, | |
| "grad_norm": 10.021332740783691, | |
| "learning_rate": 9.809264305177112e-06, | |
| "loss": 0.8754, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 9.951219512195122, | |
| "grad_norm": 10.624610900878906, | |
| "learning_rate": 9.35513169845595e-06, | |
| "loss": 0.8306, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "eval_accuracy": 0.566574839302112, | |
| "eval_f1": 0.5574087205222212, | |
| "eval_loss": 0.9907031655311584, | |
| "eval_precision": 0.5531200477134914, | |
| "eval_recall": 0.566574839302112, | |
| "eval_runtime": 10.5011, | |
| "eval_samples_per_second": 103.703, | |
| "eval_steps_per_second": 6.571, | |
| "step": 1025 | |
| }, | |
| { | |
| "epoch": 10.048780487804878, | |
| "grad_norm": 9.162467956542969, | |
| "learning_rate": 8.900999091734787e-06, | |
| "loss": 0.8177, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 10.146341463414634, | |
| "grad_norm": 9.493200302124023, | |
| "learning_rate": 8.446866485013624e-06, | |
| "loss": 0.7632, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 10.24390243902439, | |
| "grad_norm": 9.642596244812012, | |
| "learning_rate": 7.992733878292462e-06, | |
| "loss": 0.7732, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 10.341463414634147, | |
| "grad_norm": 11.928635597229004, | |
| "learning_rate": 7.538601271571299e-06, | |
| "loss": 0.7979, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 10.439024390243903, | |
| "grad_norm": 9.884861946105957, | |
| "learning_rate": 7.084468664850137e-06, | |
| "loss": 0.834, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 10.536585365853659, | |
| "grad_norm": 10.674219131469727, | |
| "learning_rate": 6.6303360581289735e-06, | |
| "loss": 0.83, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 10.634146341463415, | |
| "grad_norm": 11.04780387878418, | |
| "learning_rate": 6.176203451407812e-06, | |
| "loss": 0.8157, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 10.731707317073171, | |
| "grad_norm": 11.664216995239258, | |
| "learning_rate": 5.7220708446866485e-06, | |
| "loss": 0.8041, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 10.829268292682928, | |
| "grad_norm": 11.164298057556152, | |
| "learning_rate": 5.267938237965486e-06, | |
| "loss": 0.7685, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 10.926829268292684, | |
| "grad_norm": 11.851963996887207, | |
| "learning_rate": 4.813805631244324e-06, | |
| "loss": 0.8458, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 10.995121951219513, | |
| "eval_accuracy": 0.5500459136822773, | |
| "eval_f1": 0.5489227474870219, | |
| "eval_loss": 1.0134857892990112, | |
| "eval_precision": 0.5505838083040273, | |
| "eval_recall": 0.5500459136822773, | |
| "eval_runtime": 10.4709, | |
| "eval_samples_per_second": 104.003, | |
| "eval_steps_per_second": 6.59, | |
| "step": 1127 | |
| }, | |
| { | |
| "epoch": 11.024390243902438, | |
| "grad_norm": 9.90632438659668, | |
| "learning_rate": 4.359673024523161e-06, | |
| "loss": 0.7881, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 11.121951219512194, | |
| "grad_norm": 11.564204216003418, | |
| "learning_rate": 3.9055404178019984e-06, | |
| "loss": 0.7449, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 11.21951219512195, | |
| "grad_norm": 10.323161125183105, | |
| "learning_rate": 3.451407811080836e-06, | |
| "loss": 0.7865, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 11.317073170731707, | |
| "grad_norm": 11.201330184936523, | |
| "learning_rate": 2.997275204359673e-06, | |
| "loss": 0.781, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 11.414634146341463, | |
| "grad_norm": 9.596723556518555, | |
| "learning_rate": 2.5431425976385105e-06, | |
| "loss": 0.7847, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 11.512195121951219, | |
| "grad_norm": 10.385799407958984, | |
| "learning_rate": 2.089009990917348e-06, | |
| "loss": 0.8139, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 11.609756097560975, | |
| "grad_norm": 12.413230895996094, | |
| "learning_rate": 1.6348773841961852e-06, | |
| "loss": 0.7824, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 11.707317073170731, | |
| "grad_norm": 10.438215255737305, | |
| "learning_rate": 1.1807447774750227e-06, | |
| "loss": 0.7464, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 11.804878048780488, | |
| "grad_norm": 10.087923049926758, | |
| "learning_rate": 7.266121707538601e-07, | |
| "loss": 0.8032, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 11.902439024390244, | |
| "grad_norm": 10.667466163635254, | |
| "learning_rate": 2.7247956403269756e-07, | |
| "loss": 0.815, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 11.941463414634146, | |
| "eval_accuracy": 0.549127640036731, | |
| "eval_f1": 0.5520258447427934, | |
| "eval_loss": 1.0185083150863647, | |
| "eval_precision": 0.5558049078671707, | |
| "eval_recall": 0.549127640036731, | |
| "eval_runtime": 10.5534, | |
| "eval_samples_per_second": 103.19, | |
| "eval_steps_per_second": 6.538, | |
| "step": 1224 | |
| }, | |
| { | |
| "epoch": 11.941463414634146, | |
| "step": 1224, | |
| "total_flos": 6.197635483154842e+18, | |
| "train_loss": 1.0363535090209612, | |
| "train_runtime": 3088.0708, | |
| "train_samples_per_second": 25.461, | |
| "train_steps_per_second": 0.396 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1224, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6.197635483154842e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |