| { | |
| "best_metric": 0.24565543234348297, | |
| "best_model_checkpoint": "/scratch/skscla001/speech/results/mms-1b-bemgen-combined-model/checkpoint-3900", | |
| "epoch": 2.1660649819494586, | |
| "eval_steps": 100, | |
| "global_step": 4200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05157297576070139, | |
| "grad_norm": 2.867751359939575, | |
| "learning_rate": 0.000285, | |
| "loss": 6.8762, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.05157297576070139, | |
| "eval_loss": 0.9800576567649841, | |
| "eval_runtime": 61.3726, | |
| "eval_samples_per_second": 15.903, | |
| "eval_steps_per_second": 3.976, | |
| "eval_wer": 0.9386155855463648, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10314595152140278, | |
| "grad_norm": 4.205641269683838, | |
| "learning_rate": 0.0002995092130187704, | |
| "loss": 0.5788, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.10314595152140278, | |
| "eval_loss": 0.34664157032966614, | |
| "eval_runtime": 60.8325, | |
| "eval_samples_per_second": 16.044, | |
| "eval_steps_per_second": 4.011, | |
| "eval_wer": 0.5014148889856335, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.15471892728210418, | |
| "grad_norm": 16.612009048461914, | |
| "learning_rate": 0.00029899259514379193, | |
| "loss": 0.4891, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.15471892728210418, | |
| "eval_loss": 0.3219561278820038, | |
| "eval_runtime": 60.7824, | |
| "eval_samples_per_second": 16.057, | |
| "eval_steps_per_second": 4.014, | |
| "eval_wer": 0.48204179364388333, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.20629190304280556, | |
| "grad_norm": 15.71129035949707, | |
| "learning_rate": 0.0002984759772688135, | |
| "loss": 0.4386, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.20629190304280556, | |
| "eval_loss": 0.30709779262542725, | |
| "eval_runtime": 60.8186, | |
| "eval_samples_per_second": 16.048, | |
| "eval_steps_per_second": 4.012, | |
| "eval_wer": 0.4801915542011319, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25786487880350695, | |
| "grad_norm": 2.6226158142089844, | |
| "learning_rate": 0.000297959359393835, | |
| "loss": 0.4272, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.25786487880350695, | |
| "eval_loss": 0.30557531118392944, | |
| "eval_runtime": 61.7053, | |
| "eval_samples_per_second": 15.817, | |
| "eval_steps_per_second": 3.954, | |
| "eval_wer": 0.49880278624292557, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.30943785456420836, | |
| "grad_norm": 2.265719413757324, | |
| "learning_rate": 0.00029744274151885655, | |
| "loss": 0.3982, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.30943785456420836, | |
| "eval_loss": 0.2980726957321167, | |
| "eval_runtime": 61.2582, | |
| "eval_samples_per_second": 15.933, | |
| "eval_steps_per_second": 3.983, | |
| "eval_wer": 0.4625598606878537, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.36101083032490977, | |
| "grad_norm": 1.4846241474151611, | |
| "learning_rate": 0.00029692612364387805, | |
| "loss": 0.425, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.36101083032490977, | |
| "eval_loss": 0.2976619601249695, | |
| "eval_runtime": 61.0566, | |
| "eval_samples_per_second": 15.985, | |
| "eval_steps_per_second": 3.996, | |
| "eval_wer": 0.4631040487592512, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4125838060856111, | |
| "grad_norm": 1.5233323574066162, | |
| "learning_rate": 0.0002964095057688996, | |
| "loss": 0.4036, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.4125838060856111, | |
| "eval_loss": 0.2897385358810425, | |
| "eval_runtime": 60.9529, | |
| "eval_samples_per_second": 16.012, | |
| "eval_steps_per_second": 4.003, | |
| "eval_wer": 0.44383979103178056, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.46415678184631254, | |
| "grad_norm": 1.4918992519378662, | |
| "learning_rate": 0.0002958928878939211, | |
| "loss": 0.3903, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.46415678184631254, | |
| "eval_loss": 0.28775253891944885, | |
| "eval_runtime": 61.5398, | |
| "eval_samples_per_second": 15.86, | |
| "eval_steps_per_second": 3.965, | |
| "eval_wer": 0.4626686983021332, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.5157297576070139, | |
| "grad_norm": 35.91661071777344, | |
| "learning_rate": 0.0002953762700189426, | |
| "loss": 0.3758, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5157297576070139, | |
| "eval_loss": 0.29262155294418335, | |
| "eval_runtime": 61.6256, | |
| "eval_samples_per_second": 15.838, | |
| "eval_steps_per_second": 3.959, | |
| "eval_wer": 0.4523291249455812, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5673027333677153, | |
| "grad_norm": 2.335728645324707, | |
| "learning_rate": 0.0002948596521439642, | |
| "loss": 0.3861, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.5673027333677153, | |
| "eval_loss": 0.28073564171791077, | |
| "eval_runtime": 60.9884, | |
| "eval_samples_per_second": 16.003, | |
| "eval_steps_per_second": 4.001, | |
| "eval_wer": 0.44101001306051374, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.6188757091284167, | |
| "grad_norm": 1.2785513401031494, | |
| "learning_rate": 0.0002943430342689857, | |
| "loss": 0.3763, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6188757091284167, | |
| "eval_loss": 0.2789745032787323, | |
| "eval_runtime": 61.0183, | |
| "eval_samples_per_second": 15.995, | |
| "eval_steps_per_second": 3.999, | |
| "eval_wer": 0.4330648672181106, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.6704486848891181, | |
| "grad_norm": 4.705647945404053, | |
| "learning_rate": 0.0002938264163940072, | |
| "loss": 0.3984, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.6704486848891181, | |
| "eval_loss": 0.2803143262863159, | |
| "eval_runtime": 61.7547, | |
| "eval_samples_per_second": 15.804, | |
| "eval_steps_per_second": 3.951, | |
| "eval_wer": 0.4312146277753592, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.7220216606498195, | |
| "grad_norm": 1.780588984489441, | |
| "learning_rate": 0.00029330979851902874, | |
| "loss": 0.373, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.7220216606498195, | |
| "eval_loss": 0.2802477478981018, | |
| "eval_runtime": 61.6178, | |
| "eval_samples_per_second": 15.84, | |
| "eval_steps_per_second": 3.96, | |
| "eval_wer": 0.42457553330430997, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.7735946364105208, | |
| "grad_norm": 2.3556313514709473, | |
| "learning_rate": 0.0002927931806440503, | |
| "loss": 0.3848, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.7735946364105208, | |
| "eval_loss": 0.2759012281894684, | |
| "eval_runtime": 61.2513, | |
| "eval_samples_per_second": 15.934, | |
| "eval_steps_per_second": 3.984, | |
| "eval_wer": 0.47518502394427514, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8251676121712223, | |
| "grad_norm": 4.117414951324463, | |
| "learning_rate": 0.0002922765627690718, | |
| "loss": 0.4235, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.8251676121712223, | |
| "eval_loss": 0.2738034725189209, | |
| "eval_runtime": 60.9855, | |
| "eval_samples_per_second": 16.004, | |
| "eval_steps_per_second": 4.001, | |
| "eval_wer": 0.42675228558989986, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.8767405879319237, | |
| "grad_norm": 7.5644683837890625, | |
| "learning_rate": 0.0002917651110728431, | |
| "loss": 0.3704, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.8767405879319237, | |
| "eval_loss": 0.26875266432762146, | |
| "eval_runtime": 61.6159, | |
| "eval_samples_per_second": 15.84, | |
| "eval_steps_per_second": 3.96, | |
| "eval_wer": 0.4218545929473226, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.9283135636926251, | |
| "grad_norm": 2.0241034030914307, | |
| "learning_rate": 0.00029124849319786463, | |
| "loss": 0.3911, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.9283135636926251, | |
| "eval_loss": 0.2653037905693054, | |
| "eval_runtime": 61.6914, | |
| "eval_samples_per_second": 15.821, | |
| "eval_steps_per_second": 3.955, | |
| "eval_wer": 0.42011319111885065, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.9798865394533265, | |
| "grad_norm": 1.9250996112823486, | |
| "learning_rate": 0.00029073187532288613, | |
| "loss": 0.3954, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.9798865394533265, | |
| "eval_loss": 0.26971080899238586, | |
| "eval_runtime": 61.0364, | |
| "eval_samples_per_second": 15.99, | |
| "eval_steps_per_second": 3.998, | |
| "eval_wer": 0.4481932956029604, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.0314595152140278, | |
| "grad_norm": 2.152578353881836, | |
| "learning_rate": 0.0002902152574479077, | |
| "loss": 0.352, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0314595152140278, | |
| "eval_loss": 0.26541659235954285, | |
| "eval_runtime": 61.1446, | |
| "eval_samples_per_second": 15.962, | |
| "eval_steps_per_second": 3.991, | |
| "eval_wer": 0.4154331737048324, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.0830324909747293, | |
| "grad_norm": 1.2193535566329956, | |
| "learning_rate": 0.0002896986395729292, | |
| "loss": 0.3808, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.0830324909747293, | |
| "eval_loss": 0.2631310522556305, | |
| "eval_runtime": 61.7949, | |
| "eval_samples_per_second": 15.794, | |
| "eval_steps_per_second": 3.949, | |
| "eval_wer": 0.40509360034828035, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.1346054667354306, | |
| "grad_norm": 0.9607815742492676, | |
| "learning_rate": 0.0002891820216979507, | |
| "loss": 0.3681, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.1346054667354306, | |
| "eval_loss": 0.26097217202186584, | |
| "eval_runtime": 61.6359, | |
| "eval_samples_per_second": 15.835, | |
| "eval_steps_per_second": 3.959, | |
| "eval_wer": 0.4218545929473226, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.1861784424961321, | |
| "grad_norm": 1.6105040311813354, | |
| "learning_rate": 0.00028866540382297226, | |
| "loss": 0.3355, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.1861784424961321, | |
| "eval_loss": 0.26081275939941406, | |
| "eval_runtime": 61.1026, | |
| "eval_samples_per_second": 15.973, | |
| "eval_steps_per_second": 3.993, | |
| "eval_wer": 0.40977361776229865, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.2377514182568334, | |
| "grad_norm": 2.3081679344177246, | |
| "learning_rate": 0.0002881487859479938, | |
| "loss": 0.342, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.2377514182568334, | |
| "eval_loss": 0.2601791322231293, | |
| "eval_runtime": 61.0993, | |
| "eval_samples_per_second": 15.974, | |
| "eval_steps_per_second": 3.993, | |
| "eval_wer": 0.40824989116238575, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.2893243940175347, | |
| "grad_norm": 0.6918842792510986, | |
| "learning_rate": 0.0002876321680730153, | |
| "loss": 0.347, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.2893243940175347, | |
| "eval_loss": 0.26280567049980164, | |
| "eval_runtime": 61.7023, | |
| "eval_samples_per_second": 15.818, | |
| "eval_steps_per_second": 3.954, | |
| "eval_wer": 0.40552895080539836, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.3408973697782363, | |
| "grad_norm": 0.920050323009491, | |
| "learning_rate": 0.0002871155501980368, | |
| "loss": 0.3409, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.3408973697782363, | |
| "eval_loss": 0.25879552960395813, | |
| "eval_runtime": 61.69, | |
| "eval_samples_per_second": 15.821, | |
| "eval_steps_per_second": 3.955, | |
| "eval_wer": 0.412929908576404, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.3924703455389376, | |
| "grad_norm": 0.7028564810752869, | |
| "learning_rate": 0.0002865989323230584, | |
| "loss": 0.3423, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.3924703455389376, | |
| "eval_loss": 0.2616526484489441, | |
| "eval_runtime": 61.13, | |
| "eval_samples_per_second": 15.966, | |
| "eval_steps_per_second": 3.991, | |
| "eval_wer": 0.41924249020461474, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.444043321299639, | |
| "grad_norm": 3.5141775608062744, | |
| "learning_rate": 0.0002860823144480799, | |
| "loss": 0.3341, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.444043321299639, | |
| "eval_loss": 0.25779473781585693, | |
| "eval_runtime": 61.3161, | |
| "eval_samples_per_second": 15.918, | |
| "eval_steps_per_second": 3.979, | |
| "eval_wer": 0.40552895080539836, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.4956162970603404, | |
| "grad_norm": 1.0055650472640991, | |
| "learning_rate": 0.0002855656965731014, | |
| "loss": 0.3425, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.4956162970603404, | |
| "eval_loss": 0.2579568922519684, | |
| "eval_runtime": 61.9639, | |
| "eval_samples_per_second": 15.751, | |
| "eval_steps_per_second": 3.938, | |
| "eval_wer": 0.39878101872006966, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.5471892728210417, | |
| "grad_norm": 1.4293900728225708, | |
| "learning_rate": 0.00028504907869812294, | |
| "loss": 0.337, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.5471892728210417, | |
| "eval_loss": 0.25681352615356445, | |
| "eval_runtime": 61.6019, | |
| "eval_samples_per_second": 15.844, | |
| "eval_steps_per_second": 3.961, | |
| "eval_wer": 0.40705267740531126, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.5987622485817432, | |
| "grad_norm": 0.6135945916175842, | |
| "learning_rate": 0.00028453246082314445, | |
| "loss": 0.3412, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.5987622485817432, | |
| "eval_loss": 0.25524020195007324, | |
| "eval_runtime": 61.308, | |
| "eval_samples_per_second": 15.92, | |
| "eval_steps_per_second": 3.98, | |
| "eval_wer": 0.39932520679146716, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.6503352243424445, | |
| "grad_norm": 4.757889270782471, | |
| "learning_rate": 0.00028401584294816595, | |
| "loss": 0.3837, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.6503352243424445, | |
| "eval_loss": 0.26221156120300293, | |
| "eval_runtime": 61.5959, | |
| "eval_samples_per_second": 15.845, | |
| "eval_steps_per_second": 3.961, | |
| "eval_wer": 0.40835872877666524, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.701908200103146, | |
| "grad_norm": 1.1227970123291016, | |
| "learning_rate": 0.0002834992250731875, | |
| "loss": 0.3372, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.701908200103146, | |
| "eval_loss": 0.2548165023326874, | |
| "eval_runtime": 61.9858, | |
| "eval_samples_per_second": 15.746, | |
| "eval_steps_per_second": 3.936, | |
| "eval_wer": 0.3991075315629081, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.7534811758638473, | |
| "grad_norm": 0.8613722324371338, | |
| "learning_rate": 0.00028298260719820907, | |
| "loss": 0.3394, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.7534811758638473, | |
| "eval_loss": 0.2535094916820526, | |
| "eval_runtime": 61.5961, | |
| "eval_samples_per_second": 15.845, | |
| "eval_steps_per_second": 3.961, | |
| "eval_wer": 0.4060731388767958, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.8050541516245486, | |
| "grad_norm": 0.5101200938224792, | |
| "learning_rate": 0.00028246598932323057, | |
| "loss": 0.3542, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.8050541516245486, | |
| "eval_loss": 0.25123441219329834, | |
| "eval_runtime": 61.2846, | |
| "eval_samples_per_second": 15.926, | |
| "eval_steps_per_second": 3.981, | |
| "eval_wer": 0.39268611232041795, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.8566271273852502, | |
| "grad_norm": 1.271552324295044, | |
| "learning_rate": 0.0002819493714482521, | |
| "loss": 0.3368, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.8566271273852502, | |
| "eval_loss": 0.258027583360672, | |
| "eval_runtime": 61.4346, | |
| "eval_samples_per_second": 15.887, | |
| "eval_steps_per_second": 3.972, | |
| "eval_wer": 0.4004135829342621, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 1.9082001031459517, | |
| "grad_norm": 1.8105818033218384, | |
| "learning_rate": 0.00028143275357327363, | |
| "loss": 0.3807, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.9082001031459517, | |
| "eval_loss": 0.24900555610656738, | |
| "eval_runtime": 61.7426, | |
| "eval_samples_per_second": 15.808, | |
| "eval_steps_per_second": 3.952, | |
| "eval_wer": 0.39747496734871574, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.959773078906653, | |
| "grad_norm": 1.8133718967437744, | |
| "learning_rate": 0.00028091613569829514, | |
| "loss": 0.3454, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.959773078906653, | |
| "eval_loss": 0.2513742446899414, | |
| "eval_runtime": 61.6449, | |
| "eval_samples_per_second": 15.833, | |
| "eval_steps_per_second": 3.958, | |
| "eval_wer": 0.40019590770570307, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.0113460546673543, | |
| "grad_norm": 0.7546507120132446, | |
| "learning_rate": 0.00028039951782331664, | |
| "loss": 0.3456, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.0113460546673543, | |
| "eval_loss": 0.24565543234348297, | |
| "eval_runtime": 61.2207, | |
| "eval_samples_per_second": 15.942, | |
| "eval_steps_per_second": 3.986, | |
| "eval_wer": 0.3931214627775359, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.0629190304280556, | |
| "grad_norm": 0.9227738976478577, | |
| "learning_rate": 0.0002798828999483382, | |
| "loss": 0.3202, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.0629190304280556, | |
| "eval_loss": 0.24660241603851318, | |
| "eval_runtime": 61.4456, | |
| "eval_samples_per_second": 15.884, | |
| "eval_steps_per_second": 3.971, | |
| "eval_wer": 0.391597736177623, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.114492006188757, | |
| "grad_norm": 1.0991692543029785, | |
| "learning_rate": 0.00027937144825210947, | |
| "loss": 0.3233, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.114492006188757, | |
| "eval_loss": 0.2494671791791916, | |
| "eval_runtime": 61.9678, | |
| "eval_samples_per_second": 15.75, | |
| "eval_steps_per_second": 3.938, | |
| "eval_wer": 0.39747496734871574, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.1660649819494586, | |
| "grad_norm": 0.6972938776016235, | |
| "learning_rate": 0.000278854830377131, | |
| "loss": 0.3052, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.1660649819494586, | |
| "eval_loss": 0.247751384973526, | |
| "eval_runtime": 61.6785, | |
| "eval_samples_per_second": 15.824, | |
| "eval_steps_per_second": 3.956, | |
| "eval_wer": 0.38985633434915107, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.1660649819494586, | |
| "step": 4200, | |
| "total_flos": 1.0016492328632693e+19, | |
| "train_loss": 0.5294508952186221, | |
| "train_runtime": 6287.6058, | |
| "train_samples_per_second": 37.006, | |
| "train_steps_per_second": 9.252 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 58170, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 30, | |
| "save_steps": 400, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 3, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 1 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0016492328632693e+19, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |