| { |
| "best_global_step": 3800, |
| "best_metric": 0.5745245466607696, |
| "best_model_checkpoint": "./wav2vec2-ser/checkpoint-3800", |
| "epoch": 1.4938077452329468, |
| "eval_steps": 200, |
| "global_step": 3800, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.01965795164143896, |
| "grad_norm": 2.8652937412261963, |
| "learning_rate": 1.9600000000000003e-06, |
| "loss": 3.21733642578125, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.03931590328287792, |
| "grad_norm": 1.6962387561798096, |
| "learning_rate": 3.96e-06, |
| "loss": 3.21944091796875, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.058973854924316886, |
| "grad_norm": 2.3543405532836914, |
| "learning_rate": 5.9600000000000005e-06, |
| "loss": 3.2060595703125, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.07863180656575584, |
| "grad_norm": 1.2512654066085815, |
| "learning_rate": 7.960000000000002e-06, |
| "loss": 3.17433837890625, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.07863180656575584, |
| "eval_accuracy": 0.2961079168509509, |
| "eval_loss": 1.5817829370498657, |
| "eval_runtime": 335.3131, |
| "eval_samples_per_second": 13.486, |
| "eval_steps_per_second": 1.688, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.09828975820719481, |
| "grad_norm": 2.069725751876831, |
| "learning_rate": 9.960000000000001e-06, |
| "loss": 3.1632666015625, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.11794770984863377, |
| "grad_norm": 1.6658483743667603, |
| "learning_rate": 1.196e-05, |
| "loss": 3.1508447265625, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.13760566149007272, |
| "grad_norm": 2.283766031265259, |
| "learning_rate": 1.396e-05, |
| "loss": 3.1141455078125, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.1572636131315117, |
| "grad_norm": 3.5048413276672363, |
| "learning_rate": 1.5960000000000003e-05, |
| "loss": 3.06096435546875, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.1572636131315117, |
| "eval_accuracy": 0.3206545776205219, |
| "eval_loss": 1.512808084487915, |
| "eval_runtime": 325.7105, |
| "eval_samples_per_second": 13.883, |
| "eval_steps_per_second": 1.738, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.17692156477295065, |
| "grad_norm": 2.638303518295288, |
| "learning_rate": 1.796e-05, |
| "loss": 2.99643310546875, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.19657951641438962, |
| "grad_norm": 2.99685001373291, |
| "learning_rate": 1.9960000000000002e-05, |
| "loss": 2.95502197265625, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.21623746805582858, |
| "grad_norm": 2.6780219078063965, |
| "learning_rate": 1.9994371737450327e-05, |
| "loss": 2.9004931640625, |
| "step": 550 |
| }, |
| { |
| "epoch": 0.23589541969726754, |
| "grad_norm": 3.321932792663574, |
| "learning_rate": 1.99770317978944e-05, |
| "loss": 2.890068359375, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.23589541969726754, |
| "eval_accuracy": 0.40955329500221144, |
| "eval_loss": 1.392472505569458, |
| "eval_runtime": 325.9726, |
| "eval_samples_per_second": 13.872, |
| "eval_steps_per_second": 1.736, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.2555533713387065, |
| "grad_norm": 4.617715358734131, |
| "learning_rate": 1.994799816046053e-05, |
| "loss": 2.804796142578125, |
| "step": 650 |
| }, |
| { |
| "epoch": 0.27521132298014545, |
| "grad_norm": 4.8346333503723145, |
| "learning_rate": 1.9907304854366155e-05, |
| "loss": 2.678243408203125, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.2948692746215844, |
| "grad_norm": 5.104816436767578, |
| "learning_rate": 1.9854999574680995e-05, |
| "loss": 2.60962158203125, |
| "step": 750 |
| }, |
| { |
| "epoch": 0.3145272262630234, |
| "grad_norm": 4.435685157775879, |
| "learning_rate": 1.9791143626425464e-05, |
| "loss": 2.5450653076171874, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.3145272262630234, |
| "eval_accuracy": 0.48009730207872625, |
| "eval_loss": 1.2766602039337158, |
| "eval_runtime": 327.96, |
| "eval_samples_per_second": 13.788, |
| "eval_steps_per_second": 1.726, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.33418517790446234, |
| "grad_norm": 4.054291248321533, |
| "learning_rate": 1.9715811852717404e-05, |
| "loss": 2.560736083984375, |
| "step": 850 |
| }, |
| { |
| "epoch": 0.3538431295459013, |
| "grad_norm": 3.9081740379333496, |
| "learning_rate": 1.9629092547051333e-05, |
| "loss": 2.4451812744140624, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.37350108118734027, |
| "grad_norm": 4.999874114990234, |
| "learning_rate": 1.9531087349813018e-05, |
| "loss": 2.55667236328125, |
| "step": 950 |
| }, |
| { |
| "epoch": 0.39315903282877923, |
| "grad_norm": 5.165968894958496, |
| "learning_rate": 1.9421911129150625e-05, |
| "loss": 2.45402587890625, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.39315903282877923, |
| "eval_accuracy": 0.5112781954887218, |
| "eval_loss": 1.1984201669692993, |
| "eval_runtime": 328.0873, |
| "eval_samples_per_second": 13.783, |
| "eval_steps_per_second": 1.725, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4128169844702182, |
| "grad_norm": 4.574248790740967, |
| "learning_rate": 1.93016918463422e-05, |
| "loss": 2.4238107299804685, |
| "step": 1050 |
| }, |
| { |
| "epoch": 0.43247493611165716, |
| "grad_norm": 5.340658187866211, |
| "learning_rate": 1.9170570405817114e-05, |
| "loss": 2.430352783203125, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.4521328877530961, |
| "grad_norm": 4.740163326263428, |
| "learning_rate": 1.9028700490007357e-05, |
| "loss": 2.342404479980469, |
| "step": 1150 |
| }, |
| { |
| "epoch": 0.4717908393945351, |
| "grad_norm": 5.874159336090088, |
| "learning_rate": 1.8876248379222253e-05, |
| "loss": 2.316078796386719, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.4717908393945351, |
| "eval_accuracy": 0.5249889429455993, |
| "eval_loss": 1.1859393119812012, |
| "eval_runtime": 328.2885, |
| "eval_samples_per_second": 13.774, |
| "eval_steps_per_second": 1.724, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.49144879103597405, |
| "grad_norm": 4.75585412979126, |
| "learning_rate": 1.8713392756757644e-05, |
| "loss": 2.343719482421875, |
| "step": 1250 |
| }, |
| { |
| "epoch": 0.511106742677413, |
| "grad_norm": 4.5981011390686035, |
| "learning_rate": 1.854032449946803e-05, |
| "loss": 2.3870013427734373, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.530764694318852, |
| "grad_norm": 5.217740535736084, |
| "learning_rate": 1.83572464540471e-05, |
| "loss": 2.384723815917969, |
| "step": 1350 |
| }, |
| { |
| "epoch": 0.5504226459602909, |
| "grad_norm": 4.053684711456299, |
| "learning_rate": 1.8164373199278858e-05, |
| "loss": 2.26161865234375, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.5504226459602909, |
| "eval_accuracy": 0.5247678018575851, |
| "eval_loss": 1.1737440824508667, |
| "eval_runtime": 328.4706, |
| "eval_samples_per_second": 13.767, |
| "eval_steps_per_second": 1.723, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.5700805976017299, |
| "grad_norm": 4.007900714874268, |
| "learning_rate": 1.796193079453805e-05, |
| "loss": 2.2281451416015625, |
| "step": 1450 |
| }, |
| { |
| "epoch": 0.5897385492431688, |
| "grad_norm": 6.056822299957275, |
| "learning_rate": 1.775015651483459e-05, |
| "loss": 2.258458251953125, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6093965008846078, |
| "grad_norm": 5.119473934173584, |
| "learning_rate": 1.7529298572712575e-05, |
| "loss": 2.3008908081054686, |
| "step": 1550 |
| }, |
| { |
| "epoch": 0.6290544525260467, |
| "grad_norm": 4.8242340087890625, |
| "learning_rate": 1.7299615827329867e-05, |
| "loss": 2.220987548828125, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.6290544525260467, |
| "eval_accuracy": 0.5325077399380805, |
| "eval_loss": 1.1489901542663574, |
| "eval_runtime": 329.0833, |
| "eval_samples_per_second": 13.741, |
| "eval_steps_per_second": 1.72, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.6487124041674858, |
| "grad_norm": 5.568704605102539, |
| "learning_rate": 1.706137748105914e-05, |
| "loss": 2.341977233886719, |
| "step": 1650 |
| }, |
| { |
| "epoch": 0.6683703558089247, |
| "grad_norm": 6.586209297180176, |
| "learning_rate": 1.6814862763966083e-05, |
| "loss": 2.229486389160156, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.6880283074503637, |
| "grad_norm": 6.6926774978637695, |
| "learning_rate": 1.6560360606534478e-05, |
| "loss": 2.328319091796875, |
| "step": 1750 |
| }, |
| { |
| "epoch": 0.7076862590918026, |
| "grad_norm": 6.120084285736084, |
| "learning_rate": 1.6298169301021843e-05, |
| "loss": 2.280043029785156, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.7076862590918026, |
| "eval_accuracy": 0.5550641309155241, |
| "eval_loss": 1.1256910562515259, |
| "eval_runtime": 328.6794, |
| "eval_samples_per_second": 13.758, |
| "eval_steps_per_second": 1.722, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.7273442107332416, |
| "grad_norm": 5.448923110961914, |
| "learning_rate": 1.6028596151842457e-05, |
| "loss": 2.28103271484375, |
| "step": 1850 |
| }, |
| { |
| "epoch": 0.7470021623746805, |
| "grad_norm": 4.197726249694824, |
| "learning_rate": 1.5751957115387595e-05, |
| "loss": 2.1898208618164063, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.7666601140161196, |
| "grad_norm": 4.532899856567383, |
| "learning_rate": 1.5468576429705114e-05, |
| "loss": 2.231734313964844, |
| "step": 1950 |
| }, |
| { |
| "epoch": 0.7863180656575585, |
| "grad_norm": 4.065794467926025, |
| "learning_rate": 1.5178786234472416e-05, |
| "loss": 2.248075408935547, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.7863180656575585, |
| "eval_accuracy": 0.542016806722689, |
| "eval_loss": 1.1329021453857422, |
| "eval_runtime": 328.231, |
| "eval_samples_per_second": 13.777, |
| "eval_steps_per_second": 1.724, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.8059760172989975, |
| "grad_norm": 4.701900482177734, |
| "learning_rate": 1.488292618170823e-05, |
| "loss": 2.2806770324707033, |
| "step": 2050 |
| }, |
| { |
| "epoch": 0.8256339689404364, |
| "grad_norm": 5.148760795593262, |
| "learning_rate": 1.4581343037679442e-05, |
| "loss": 2.295329132080078, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.8452919205818754, |
| "grad_norm": 6.680943965911865, |
| "learning_rate": 1.427439027646961e-05, |
| "loss": 2.195320281982422, |
| "step": 2150 |
| }, |
| { |
| "epoch": 0.8649498722233143, |
| "grad_norm": 5.498937606811523, |
| "learning_rate": 1.3962427665685476e-05, |
| "loss": 2.2433233642578125, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.8649498722233143, |
| "eval_accuracy": 0.5555064130915525, |
| "eval_loss": 1.1091567277908325, |
| "eval_runtime": 329.1188, |
| "eval_samples_per_second": 13.74, |
| "eval_steps_per_second": 1.72, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.8846078238647533, |
| "grad_norm": 5.7843756675720215, |
| "learning_rate": 1.364582084478712e-05, |
| "loss": 2.169947509765625, |
| "step": 2250 |
| }, |
| { |
| "epoch": 0.9042657755061922, |
| "grad_norm": 5.912988662719727, |
| "learning_rate": 1.3324940896535887e-05, |
| "loss": 2.233917541503906, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.9239237271476313, |
| "grad_norm": 5.806344032287598, |
| "learning_rate": 1.3000163912062496e-05, |
| "loss": 2.2279705810546875, |
| "step": 2350 |
| }, |
| { |
| "epoch": 0.9435816787890702, |
| "grad_norm": 4.6818156242370605, |
| "learning_rate": 1.267187055006494e-05, |
| "loss": 2.1614779663085937, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.9435816787890702, |
| "eval_accuracy": 0.5444493586908448, |
| "eval_loss": 1.1343119144439697, |
| "eval_runtime": 329.1184, |
| "eval_samples_per_second": 13.74, |
| "eval_steps_per_second": 1.72, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.9632396304305091, |
| "grad_norm": 4.4695539474487305, |
| "learning_rate": 1.2340445590653009e-05, |
| "loss": 2.2052578735351562, |
| "step": 2450 |
| }, |
| { |
| "epoch": 0.9828975820719481, |
| "grad_norm": 4.087518692016602, |
| "learning_rate": 1.20062774843622e-05, |
| "loss": 2.2076112365722658, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.0023589541969726, |
| "grad_norm": 4.782010078430176, |
| "learning_rate": 1.166975789686569e-05, |
| "loss": 2.170450439453125, |
| "step": 2550 |
| }, |
| { |
| "epoch": 1.0220169058384116, |
| "grad_norm": 4.854877948760986, |
| "learning_rate": 1.1331281249917954e-05, |
| "loss": 2.043843078613281, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.0220169058384116, |
| "eval_accuracy": 0.5603715170278638, |
| "eval_loss": 1.1000322103500366, |
| "eval_runtime": 328.0984, |
| "eval_samples_per_second": 13.782, |
| "eval_steps_per_second": 1.725, |
| "step": 2600 |
| }, |
| { |
| "epoch": 1.0416748574798507, |
| "grad_norm": 3.8572657108306885, |
| "learning_rate": 1.0991244259068096e-05, |
| "loss": 2.138960113525391, |
| "step": 2650 |
| }, |
| { |
| "epoch": 1.0613328091212895, |
| "grad_norm": 4.365851402282715, |
| "learning_rate": 1.0650045468684712e-05, |
| "loss": 2.197817840576172, |
| "step": 2700 |
| }, |
| { |
| "epoch": 1.0809907607627285, |
| "grad_norm": 7.220186710357666, |
| "learning_rate": 1.030808478483725e-05, |
| "loss": 2.146515350341797, |
| "step": 2750 |
| }, |
| { |
| "epoch": 1.1006487124041675, |
| "grad_norm": 6.4457221031188965, |
| "learning_rate": 9.965763006581379e-06, |
| "loss": 2.1561953735351564, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1.1006487124041675, |
| "eval_accuracy": 0.5614772224679345, |
| "eval_loss": 1.0972065925598145, |
| "eval_runtime": 328.3752, |
| "eval_samples_per_second": 13.771, |
| "eval_steps_per_second": 1.724, |
| "step": 2800 |
| }, |
| { |
| "epoch": 1.1203066640456065, |
| "grad_norm": 4.797411918640137, |
| "learning_rate": 9.623481356197753e-06, |
| "loss": 2.1051173400878906, |
| "step": 2850 |
| }, |
| { |
| "epoch": 1.1399646156870453, |
| "grad_norm": 6.007393836975098, |
| "learning_rate": 9.281641008934649e-06, |
| "loss": 2.175015106201172, |
| "step": 2900 |
| }, |
| { |
| "epoch": 1.1596225673284843, |
| "grad_norm": 6.098006725311279, |
| "learning_rate": 8.94064262280584e-06, |
| "loss": 2.146817169189453, |
| "step": 2950 |
| }, |
| { |
| "epoch": 1.1792805189699234, |
| "grad_norm": 4.9183430671691895, |
| "learning_rate": 8.600885868994604e-06, |
| "loss": 2.096255035400391, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.1792805189699234, |
| "eval_accuracy": 0.5647943387881469, |
| "eval_loss": 1.0831283330917358, |
| "eval_runtime": 328.7436, |
| "eval_samples_per_second": 13.755, |
| "eval_steps_per_second": 1.722, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.1989384706113624, |
| "grad_norm": 4.816256523132324, |
| "learning_rate": 8.262768963414394e-06, |
| "loss": 2.1057098388671873, |
| "step": 3050 |
| }, |
| { |
| "epoch": 1.2185964222528012, |
| "grad_norm": 5.202821731567383, |
| "learning_rate": 7.92668819997521e-06, |
| "loss": 2.0772235107421877, |
| "step": 3100 |
| }, |
| { |
| "epoch": 1.2382543738942402, |
| "grad_norm": 4.992208957672119, |
| "learning_rate": 7.593037486102606e-06, |
| "loss": 2.0673654174804685, |
| "step": 3150 |
| }, |
| { |
| "epoch": 1.2579123255356792, |
| "grad_norm": 3.8897881507873535, |
| "learning_rate": 7.262207881053871e-06, |
| "loss": 2.0743988037109373, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1.2579123255356792, |
| "eval_accuracy": 0.572313135780628, |
| "eval_loss": 1.0740091800689697, |
| "eval_runtime": 328.8232, |
| "eval_samples_per_second": 13.752, |
| "eval_steps_per_second": 1.721, |
| "step": 3200 |
| }, |
| { |
| "epoch": 1.277570277177118, |
| "grad_norm": 5.777435779571533, |
| "learning_rate": 6.934587137572396e-06, |
| "loss": 2.0646961975097655, |
| "step": 3250 |
| }, |
| { |
| "epoch": 1.297228228818557, |
| "grad_norm": 6.062273979187012, |
| "learning_rate": 6.610559247417488e-06, |
| "loss": 2.1331820678710938, |
| "step": 3300 |
| }, |
| { |
| "epoch": 1.316886180459996, |
| "grad_norm": 4.261849880218506, |
| "learning_rate": 6.290503991302324e-06, |
| "loss": 1.9793887329101563, |
| "step": 3350 |
| }, |
| { |
| "epoch": 1.336544132101435, |
| "grad_norm": 6.28417444229126, |
| "learning_rate": 5.974796493767451e-06, |
| "loss": 2.111780090332031, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.336544132101435, |
| "eval_accuracy": 0.5670057496682883, |
| "eval_loss": 1.0762923955917358, |
| "eval_runtime": 330.4419, |
| "eval_samples_per_second": 13.685, |
| "eval_steps_per_second": 1.713, |
| "step": 3400 |
| }, |
| { |
| "epoch": 1.356202083742874, |
| "grad_norm": 6.641109466552734, |
| "learning_rate": 5.6638067835116575e-06, |
| "loss": 2.1948291015625, |
| "step": 3450 |
| }, |
| { |
| "epoch": 1.375860035384313, |
| "grad_norm": 6.004929065704346, |
| "learning_rate": 5.357899359695476e-06, |
| "loss": 2.132998809814453, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.395517987025752, |
| "grad_norm": 4.525647163391113, |
| "learning_rate": 5.057432764725621e-06, |
| "loss": 2.013247222900391, |
| "step": 3550 |
| }, |
| { |
| "epoch": 1.415175938667191, |
| "grad_norm": 5.710597991943359, |
| "learning_rate": 4.762759164021145e-06, |
| "loss": 2.0336631774902343, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1.415175938667191, |
| "eval_accuracy": 0.5731977001326847, |
| "eval_loss": 1.0696245431900024, |
| "eval_runtime": 328.9046, |
| "eval_samples_per_second": 13.749, |
| "eval_steps_per_second": 1.721, |
| "step": 3600 |
| }, |
| { |
| "epoch": 1.4348338903086297, |
| "grad_norm": 4.879547119140625, |
| "learning_rate": 4.474223933253797e-06, |
| "loss": 1.960496826171875, |
| "step": 3650 |
| }, |
| { |
| "epoch": 1.4544918419500688, |
| "grad_norm": 5.0256195068359375, |
| "learning_rate": 4.1921652535463866e-06, |
| "loss": 1.9839112854003906, |
| "step": 3700 |
| }, |
| { |
| "epoch": 1.4741497935915078, |
| "grad_norm": 4.576383113861084, |
| "learning_rate": 3.91691371510361e-06, |
| "loss": 2.098377227783203, |
| "step": 3750 |
| }, |
| { |
| "epoch": 1.4938077452329468, |
| "grad_norm": 7.432518005371094, |
| "learning_rate": 3.6487919297399065e-06, |
| "loss": 2.1130029296875, |
| "step": 3800 |
| }, |
| { |
| "epoch": 1.4938077452329468, |
| "eval_accuracy": 0.5745245466607696, |
| "eval_loss": 1.0636652708053589, |
| "eval_runtime": 329.6619, |
| "eval_samples_per_second": 13.717, |
| "eval_steps_per_second": 1.717, |
| "step": 3800 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 5088, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.228277915637816e+19, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
