| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.6348773841961854, | |
| "eval_steps": 200, | |
| "global_step": 6000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.013623978201634877, | |
| "grad_norm": 3.040151834487915, | |
| "learning_rate": 4.9786557674841054e-05, | |
| "loss": 1.5564, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.027247956403269755, | |
| "grad_norm": 4.2518086433410645, | |
| "learning_rate": 4.9559491371480476e-05, | |
| "loss": 1.2807, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.04087193460490463, | |
| "grad_norm": 24.88307762145996, | |
| "learning_rate": 4.933242506811989e-05, | |
| "loss": 1.0105, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05449591280653951, | |
| "grad_norm": 5.034740447998047, | |
| "learning_rate": 4.910535876475931e-05, | |
| "loss": 0.8276, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.05449591280653951, | |
| "eval_accuracy": 0.7211171662125341, | |
| "eval_f1": 0.6750582112410249, | |
| "eval_loss": 0.6712220311164856, | |
| "eval_precision": 0.7004051229737172, | |
| "eval_recall": 0.7211171662125341, | |
| "eval_runtime": 38.3333, | |
| "eval_samples_per_second": 191.478, | |
| "eval_steps_per_second": 11.974, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0681198910081744, | |
| "grad_norm": 16.025089263916016, | |
| "learning_rate": 4.887829246139873e-05, | |
| "loss": 0.722, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.08174386920980926, | |
| "grad_norm": 5.8490891456604, | |
| "learning_rate": 4.865122615803815e-05, | |
| "loss": 0.8055, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.09536784741144415, | |
| "grad_norm": 6.563209056854248, | |
| "learning_rate": 4.842415985467757e-05, | |
| "loss": 0.6658, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.10899182561307902, | |
| "grad_norm": 5.135402679443359, | |
| "learning_rate": 4.819709355131699e-05, | |
| "loss": 0.6751, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.10899182561307902, | |
| "eval_accuracy": 0.7158038147138964, | |
| "eval_f1": 0.7029378642258501, | |
| "eval_loss": 0.6223507523536682, | |
| "eval_precision": 0.7307304008889945, | |
| "eval_recall": 0.7158038147138964, | |
| "eval_runtime": 38.9436, | |
| "eval_samples_per_second": 188.478, | |
| "eval_steps_per_second": 11.786, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1226158038147139, | |
| "grad_norm": 4.828739643096924, | |
| "learning_rate": 4.7970027247956404e-05, | |
| "loss": 0.6159, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.1362397820163488, | |
| "grad_norm": 7.577467441558838, | |
| "learning_rate": 4.7742960944595826e-05, | |
| "loss": 0.71, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.14986376021798364, | |
| "grad_norm": 12.106951713562012, | |
| "learning_rate": 4.751589464123524e-05, | |
| "loss": 0.6515, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.16348773841961853, | |
| "grad_norm": 4.246662616729736, | |
| "learning_rate": 4.728882833787466e-05, | |
| "loss": 0.6159, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.16348773841961853, | |
| "eval_accuracy": 0.7670299727520435, | |
| "eval_f1": 0.7441405099406139, | |
| "eval_loss": 0.5788103342056274, | |
| "eval_precision": 0.7589364817682434, | |
| "eval_recall": 0.7670299727520435, | |
| "eval_runtime": 40.7278, | |
| "eval_samples_per_second": 180.221, | |
| "eval_steps_per_second": 11.27, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.1771117166212534, | |
| "grad_norm": 3.4937551021575928, | |
| "learning_rate": 4.706176203451408e-05, | |
| "loss": 0.5875, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.1907356948228883, | |
| "grad_norm": 7.366335868835449, | |
| "learning_rate": 4.68346957311535e-05, | |
| "loss": 0.5755, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.20435967302452315, | |
| "grad_norm": 5.80669641494751, | |
| "learning_rate": 4.660762942779292e-05, | |
| "loss": 0.6529, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.21798365122615804, | |
| "grad_norm": 5.406530857086182, | |
| "learning_rate": 4.638056312443234e-05, | |
| "loss": 0.5457, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.21798365122615804, | |
| "eval_accuracy": 0.8043596730245232, | |
| "eval_f1": 0.7884436299849555, | |
| "eval_loss": 0.5009222626686096, | |
| "eval_precision": 0.7887104187578498, | |
| "eval_recall": 0.8043596730245232, | |
| "eval_runtime": 39.3034, | |
| "eval_samples_per_second": 186.752, | |
| "eval_steps_per_second": 11.678, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.23160762942779292, | |
| "grad_norm": 5.1995062828063965, | |
| "learning_rate": 4.6153496821071754e-05, | |
| "loss": 0.5113, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.2452316076294278, | |
| "grad_norm": 7.262979030609131, | |
| "learning_rate": 4.592643051771117e-05, | |
| "loss": 0.5886, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.25885558583106266, | |
| "grad_norm": 4.326200485229492, | |
| "learning_rate": 4.569936421435059e-05, | |
| "loss": 0.5004, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.2724795640326976, | |
| "grad_norm": 4.408982753753662, | |
| "learning_rate": 4.547229791099001e-05, | |
| "loss": 0.5958, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.2724795640326976, | |
| "eval_accuracy": 0.8019073569482289, | |
| "eval_f1": 0.7884210613649448, | |
| "eval_loss": 0.5075427889823914, | |
| "eval_precision": 0.7978971957067001, | |
| "eval_recall": 0.8019073569482289, | |
| "eval_runtime": 39.1465, | |
| "eval_samples_per_second": 187.501, | |
| "eval_steps_per_second": 11.725, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.28610354223433243, | |
| "grad_norm": 4.403244972229004, | |
| "learning_rate": 4.524523160762943e-05, | |
| "loss": 0.5382, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.2997275204359673, | |
| "grad_norm": 3.9688315391540527, | |
| "learning_rate": 4.501816530426885e-05, | |
| "loss": 0.626, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.3133514986376022, | |
| "grad_norm": 5.429931163787842, | |
| "learning_rate": 4.4791099000908266e-05, | |
| "loss": 0.5669, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.32697547683923706, | |
| "grad_norm": 2.1590607166290283, | |
| "learning_rate": 4.456403269754769e-05, | |
| "loss": 0.5207, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.32697547683923706, | |
| "eval_accuracy": 0.8042234332425068, | |
| "eval_f1": 0.7882201527973293, | |
| "eval_loss": 0.4852093756198883, | |
| "eval_precision": 0.7987108830073256, | |
| "eval_recall": 0.8042234332425068, | |
| "eval_runtime": 39.4766, | |
| "eval_samples_per_second": 185.933, | |
| "eval_steps_per_second": 11.627, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.3405994550408719, | |
| "grad_norm": 2.970989942550659, | |
| "learning_rate": 4.433696639418711e-05, | |
| "loss": 0.5158, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.3542234332425068, | |
| "grad_norm": 4.843904972076416, | |
| "learning_rate": 4.4109900090826526e-05, | |
| "loss": 0.4638, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.3678474114441417, | |
| "grad_norm": 2.107961654663086, | |
| "learning_rate": 4.388283378746594e-05, | |
| "loss": 0.5054, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.3814713896457766, | |
| "grad_norm": 2.267613410949707, | |
| "learning_rate": 4.3655767484105356e-05, | |
| "loss": 0.5511, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.3814713896457766, | |
| "eval_accuracy": 0.8220708446866485, | |
| "eval_f1": 0.8151771754853724, | |
| "eval_loss": 0.44333121180534363, | |
| "eval_precision": 0.8163392565792945, | |
| "eval_recall": 0.8220708446866485, | |
| "eval_runtime": 39.2848, | |
| "eval_samples_per_second": 186.841, | |
| "eval_steps_per_second": 11.684, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.39509536784741145, | |
| "grad_norm": 5.881214618682861, | |
| "learning_rate": 4.342870118074478e-05, | |
| "loss": 0.5019, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.4087193460490463, | |
| "grad_norm": 6.367845058441162, | |
| "learning_rate": 4.32016348773842e-05, | |
| "loss": 0.4986, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.4223433242506812, | |
| "grad_norm": 3.946660041809082, | |
| "learning_rate": 4.2974568574023616e-05, | |
| "loss": 0.5056, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.4359673024523161, | |
| "grad_norm": 3.114546060562134, | |
| "learning_rate": 4.274750227066304e-05, | |
| "loss": 0.5094, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.4359673024523161, | |
| "eval_accuracy": 0.8198910081743869, | |
| "eval_f1": 0.8085671594623058, | |
| "eval_loss": 0.44843149185180664, | |
| "eval_precision": 0.8199358535824399, | |
| "eval_recall": 0.8198910081743869, | |
| "eval_runtime": 39.3837, | |
| "eval_samples_per_second": 186.371, | |
| "eval_steps_per_second": 11.655, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.44959128065395093, | |
| "grad_norm": 5.56833553314209, | |
| "learning_rate": 4.2520435967302454e-05, | |
| "loss": 0.49, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.46321525885558584, | |
| "grad_norm": 1.3245644569396973, | |
| "learning_rate": 4.2293369663941876e-05, | |
| "loss": 0.4293, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.4768392370572207, | |
| "grad_norm": 1.4964958429336548, | |
| "learning_rate": 4.206630336058129e-05, | |
| "loss": 0.4674, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.4904632152588556, | |
| "grad_norm": 6.4207868576049805, | |
| "learning_rate": 4.1839237057220706e-05, | |
| "loss": 0.486, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.4904632152588556, | |
| "eval_accuracy": 0.7931880108991826, | |
| "eval_f1": 0.7892022337920381, | |
| "eval_loss": 0.5324758291244507, | |
| "eval_precision": 0.8152839001650488, | |
| "eval_recall": 0.7931880108991826, | |
| "eval_runtime": 39.0794, | |
| "eval_samples_per_second": 187.823, | |
| "eval_steps_per_second": 11.745, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.5040871934604905, | |
| "grad_norm": 3.860630512237549, | |
| "learning_rate": 4.161217075386013e-05, | |
| "loss": 0.5087, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.5177111716621253, | |
| "grad_norm": 4.180031776428223, | |
| "learning_rate": 4.1385104450499544e-05, | |
| "loss": 0.4508, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.5313351498637602, | |
| "grad_norm": 3.8397634029388428, | |
| "learning_rate": 4.1158038147138966e-05, | |
| "loss": 0.475, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.5449591280653951, | |
| "grad_norm": 5.710933208465576, | |
| "learning_rate": 4.093097184377839e-05, | |
| "loss": 0.4404, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.5449591280653951, | |
| "eval_accuracy": 0.821117166212534, | |
| "eval_f1": 0.814914871858581, | |
| "eval_loss": 0.45968085527420044, | |
| "eval_precision": 0.8191778311906968, | |
| "eval_recall": 0.821117166212534, | |
| "eval_runtime": 39.2262, | |
| "eval_samples_per_second": 187.12, | |
| "eval_steps_per_second": 11.701, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.55858310626703, | |
| "grad_norm": 3.4445128440856934, | |
| "learning_rate": 4.0703905540417803e-05, | |
| "loss": 0.485, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.5722070844686649, | |
| "grad_norm": 2.0595271587371826, | |
| "learning_rate": 4.0476839237057226e-05, | |
| "loss": 0.4662, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.5858310626702997, | |
| "grad_norm": 1.4724421501159668, | |
| "learning_rate": 4.024977293369664e-05, | |
| "loss": 0.4597, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.5994550408719346, | |
| "grad_norm": 3.4617927074432373, | |
| "learning_rate": 4.002270663033606e-05, | |
| "loss": 0.5117, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.5994550408719346, | |
| "eval_accuracy": 0.8012261580381471, | |
| "eval_f1": 0.7838518874639891, | |
| "eval_loss": 0.5174744725227356, | |
| "eval_precision": 0.8073537320499754, | |
| "eval_recall": 0.8012261580381471, | |
| "eval_runtime": 39.2852, | |
| "eval_samples_per_second": 186.839, | |
| "eval_steps_per_second": 11.684, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.6130790190735694, | |
| "grad_norm": 5.364044189453125, | |
| "learning_rate": 3.979564032697548e-05, | |
| "loss": 0.5748, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.6267029972752044, | |
| "grad_norm": 6.066217422485352, | |
| "learning_rate": 3.9568574023614894e-05, | |
| "loss": 0.5297, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.6403269754768393, | |
| "grad_norm": 0.9179258346557617, | |
| "learning_rate": 3.9341507720254316e-05, | |
| "loss": 0.4056, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.6539509536784741, | |
| "grad_norm": 5.265466213226318, | |
| "learning_rate": 3.911444141689373e-05, | |
| "loss": 0.5134, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.6539509536784741, | |
| "eval_accuracy": 0.8224795640326975, | |
| "eval_f1": 0.8176549340592166, | |
| "eval_loss": 0.43617671728134155, | |
| "eval_precision": 0.8297416199964833, | |
| "eval_recall": 0.8224795640326975, | |
| "eval_runtime": 39.4454, | |
| "eval_samples_per_second": 186.08, | |
| "eval_steps_per_second": 11.636, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.667574931880109, | |
| "grad_norm": 3.929473400115967, | |
| "learning_rate": 3.8887375113533153e-05, | |
| "loss": 0.4943, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.6811989100817438, | |
| "grad_norm": 5.633317947387695, | |
| "learning_rate": 3.8660308810172576e-05, | |
| "loss": 0.4633, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.6948228882833788, | |
| "grad_norm": 5.290429592132568, | |
| "learning_rate": 3.843324250681199e-05, | |
| "loss": 0.443, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.7084468664850136, | |
| "grad_norm": 7.304491996765137, | |
| "learning_rate": 3.820617620345141e-05, | |
| "loss": 0.5273, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.7084468664850136, | |
| "eval_accuracy": 0.8346049046321525, | |
| "eval_f1": 0.8301732046667709, | |
| "eval_loss": 0.42213955521583557, | |
| "eval_precision": 0.836033830915573, | |
| "eval_recall": 0.8346049046321525, | |
| "eval_runtime": 39.2458, | |
| "eval_samples_per_second": 187.026, | |
| "eval_steps_per_second": 11.696, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.7220708446866485, | |
| "grad_norm": 4.835093975067139, | |
| "learning_rate": 3.797910990009083e-05, | |
| "loss": 0.4684, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.7356948228882834, | |
| "grad_norm": 2.2180492877960205, | |
| "learning_rate": 3.7752043596730244e-05, | |
| "loss": 0.4262, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.7493188010899182, | |
| "grad_norm": 2.7012526988983154, | |
| "learning_rate": 3.7524977293369666e-05, | |
| "loss": 0.4145, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.7629427792915532, | |
| "grad_norm": 6.204261779785156, | |
| "learning_rate": 3.729791099000908e-05, | |
| "loss": 0.4236, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.7629427792915532, | |
| "eval_accuracy": 0.8416893732970028, | |
| "eval_f1": 0.8376095906779634, | |
| "eval_loss": 0.4056047201156616, | |
| "eval_precision": 0.8385532518248264, | |
| "eval_recall": 0.8416893732970028, | |
| "eval_runtime": 39.2548, | |
| "eval_samples_per_second": 186.984, | |
| "eval_steps_per_second": 11.693, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.776566757493188, | |
| "grad_norm": 5.149259090423584, | |
| "learning_rate": 3.7070844686648503e-05, | |
| "loss": 0.463, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.7901907356948229, | |
| "grad_norm": 3.473318576812744, | |
| "learning_rate": 3.684377838328792e-05, | |
| "loss": 0.3832, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.8038147138964578, | |
| "grad_norm": 4.627190589904785, | |
| "learning_rate": 3.661671207992734e-05, | |
| "loss": 0.349, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.8174386920980926, | |
| "grad_norm": 6.506262302398682, | |
| "learning_rate": 3.638964577656676e-05, | |
| "loss": 0.4429, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8174386920980926, | |
| "eval_accuracy": 0.8209809264305177, | |
| "eval_f1": 0.8212439998778114, | |
| "eval_loss": 0.48423996567726135, | |
| "eval_precision": 0.8278178165511351, | |
| "eval_recall": 0.8209809264305177, | |
| "eval_runtime": 39.376, | |
| "eval_samples_per_second": 186.408, | |
| "eval_steps_per_second": 11.657, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.8310626702997275, | |
| "grad_norm": 4.5560383796691895, | |
| "learning_rate": 3.616257947320618e-05, | |
| "loss": 0.4988, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.8446866485013624, | |
| "grad_norm": 4.5877156257629395, | |
| "learning_rate": 3.59355131698456e-05, | |
| "loss": 0.3699, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.8583106267029973, | |
| "grad_norm": 5.670323371887207, | |
| "learning_rate": 3.5708446866485016e-05, | |
| "loss": 0.4385, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.8719346049046321, | |
| "grad_norm": 2.6689882278442383, | |
| "learning_rate": 3.548138056312443e-05, | |
| "loss": 0.4039, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.8719346049046321, | |
| "eval_accuracy": 0.8485013623978201, | |
| "eval_f1": 0.843592674785316, | |
| "eval_loss": 0.39310726523399353, | |
| "eval_precision": 0.847405927098554, | |
| "eval_recall": 0.8485013623978201, | |
| "eval_runtime": 39.4436, | |
| "eval_samples_per_second": 186.089, | |
| "eval_steps_per_second": 11.637, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.885558583106267, | |
| "grad_norm": 1.9075839519500732, | |
| "learning_rate": 3.525431425976385e-05, | |
| "loss": 0.411, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.8991825613079019, | |
| "grad_norm": 4.115935802459717, | |
| "learning_rate": 3.502724795640327e-05, | |
| "loss": 0.4112, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.9128065395095368, | |
| "grad_norm": 2.8845183849334717, | |
| "learning_rate": 3.480018165304269e-05, | |
| "loss": 0.3931, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.9264305177111717, | |
| "grad_norm": 5.959798336029053, | |
| "learning_rate": 3.457311534968211e-05, | |
| "loss": 0.4499, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.9264305177111717, | |
| "eval_accuracy": 0.8366485013623978, | |
| "eval_f1": 0.8371173604861236, | |
| "eval_loss": 0.43168991804122925, | |
| "eval_precision": 0.8493978099646374, | |
| "eval_recall": 0.8366485013623978, | |
| "eval_runtime": 40.9976, | |
| "eval_samples_per_second": 179.035, | |
| "eval_steps_per_second": 11.196, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.9400544959128065, | |
| "grad_norm": 7.796460151672363, | |
| "learning_rate": 3.434604904632153e-05, | |
| "loss": 0.487, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.9536784741144414, | |
| "grad_norm": 5.747544288635254, | |
| "learning_rate": 3.411898274296095e-05, | |
| "loss": 0.4197, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.9673024523160763, | |
| "grad_norm": 2.902282953262329, | |
| "learning_rate": 3.3891916439600366e-05, | |
| "loss": 0.4066, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.9809264305177112, | |
| "grad_norm": 7.779834747314453, | |
| "learning_rate": 3.366485013623978e-05, | |
| "loss": 0.3876, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.9809264305177112, | |
| "eval_accuracy": 0.8555858310626703, | |
| "eval_f1": 0.8510007395096015, | |
| "eval_loss": 0.3871959149837494, | |
| "eval_precision": 0.8520110874749584, | |
| "eval_recall": 0.8555858310626703, | |
| "eval_runtime": 39.3945, | |
| "eval_samples_per_second": 186.32, | |
| "eval_steps_per_second": 11.651, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.9945504087193461, | |
| "grad_norm": 6.112946033477783, | |
| "learning_rate": 3.34377838328792e-05, | |
| "loss": 0.394, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 1.008174386920981, | |
| "grad_norm": 2.9620373249053955, | |
| "learning_rate": 3.321071752951862e-05, | |
| "loss": 0.3563, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 1.021798365122616, | |
| "grad_norm": 4.225318908691406, | |
| "learning_rate": 3.298365122615804e-05, | |
| "loss": 0.3394, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 1.0354223433242506, | |
| "grad_norm": 4.271127223968506, | |
| "learning_rate": 3.2756584922797456e-05, | |
| "loss": 0.3265, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.0354223433242506, | |
| "eval_accuracy": 0.8442779291553133, | |
| "eval_f1": 0.8423344722305859, | |
| "eval_loss": 0.4092128872871399, | |
| "eval_precision": 0.844819730861473, | |
| "eval_recall": 0.8442779291553133, | |
| "eval_runtime": 39.2791, | |
| "eval_samples_per_second": 186.868, | |
| "eval_steps_per_second": 11.686, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 1.0490463215258856, | |
| "grad_norm": 5.944393634796143, | |
| "learning_rate": 3.252951861943688e-05, | |
| "loss": 0.3015, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 1.0626702997275204, | |
| "grad_norm": 4.36716890335083, | |
| "learning_rate": 3.23024523160763e-05, | |
| "loss": 0.3369, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 1.0762942779291553, | |
| "grad_norm": 6.840479850769043, | |
| "learning_rate": 3.207992733878293e-05, | |
| "loss": 0.3459, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 1.0899182561307903, | |
| "grad_norm": 2.2635903358459473, | |
| "learning_rate": 3.185286103542234e-05, | |
| "loss": 0.369, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.0899182561307903, | |
| "eval_accuracy": 0.8351498637602179, | |
| "eval_f1": 0.8345444526814599, | |
| "eval_loss": 0.44853049516677856, | |
| "eval_precision": 0.8451624069805984, | |
| "eval_recall": 0.8351498637602179, | |
| "eval_runtime": 39.2298, | |
| "eval_samples_per_second": 187.103, | |
| "eval_steps_per_second": 11.7, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 1.103542234332425, | |
| "grad_norm": 10.20390510559082, | |
| "learning_rate": 3.1625794732061765e-05, | |
| "loss": 0.3449, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 1.11716621253406, | |
| "grad_norm": 0.1351608783006668, | |
| "learning_rate": 3.139872842870118e-05, | |
| "loss": 0.3357, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 1.1307901907356948, | |
| "grad_norm": 2.0290515422821045, | |
| "learning_rate": 3.11716621253406e-05, | |
| "loss": 0.3782, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 1.1444141689373297, | |
| "grad_norm": 2.227574586868286, | |
| "learning_rate": 3.094459582198002e-05, | |
| "loss": 0.3383, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.1444141689373297, | |
| "eval_accuracy": 0.8622615803814714, | |
| "eval_f1": 0.8598094201224885, | |
| "eval_loss": 0.3893040716648102, | |
| "eval_precision": 0.8592251940540689, | |
| "eval_recall": 0.8622615803814714, | |
| "eval_runtime": 39.4522, | |
| "eval_samples_per_second": 186.048, | |
| "eval_steps_per_second": 11.634, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 1.1580381471389645, | |
| "grad_norm": 2.8619637489318848, | |
| "learning_rate": 3.0717529518619433e-05, | |
| "loss": 0.4244, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 1.1716621253405994, | |
| "grad_norm": 2.4978890419006348, | |
| "learning_rate": 3.049046321525886e-05, | |
| "loss": 0.3951, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 1.1852861035422344, | |
| "grad_norm": 2.387751579284668, | |
| "learning_rate": 3.0263396911898274e-05, | |
| "loss": 0.3153, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 1.1989100817438691, | |
| "grad_norm": 7.264976978302002, | |
| "learning_rate": 3.0036330608537693e-05, | |
| "loss": 0.3985, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.1989100817438691, | |
| "eval_accuracy": 0.8493188010899183, | |
| "eval_f1": 0.850019326075464, | |
| "eval_loss": 0.44555896520614624, | |
| "eval_precision": 0.8541605321280626, | |
| "eval_recall": 0.8493188010899183, | |
| "eval_runtime": 39.3959, | |
| "eval_samples_per_second": 186.314, | |
| "eval_steps_per_second": 11.651, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 1.2125340599455041, | |
| "grad_norm": 2.748687505722046, | |
| "learning_rate": 2.9809264305177115e-05, | |
| "loss": 0.3217, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 1.226158038147139, | |
| "grad_norm": 7.619766712188721, | |
| "learning_rate": 2.958219800181653e-05, | |
| "loss": 0.4105, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 1.2397820163487738, | |
| "grad_norm": 5.104996204376221, | |
| "learning_rate": 2.935513169845595e-05, | |
| "loss": 0.3711, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 1.2534059945504088, | |
| "grad_norm": 4.894058704376221, | |
| "learning_rate": 2.912806539509537e-05, | |
| "loss": 0.3878, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.2534059945504088, | |
| "eval_accuracy": 0.8566757493188011, | |
| "eval_f1": 0.8522483893823563, | |
| "eval_loss": 0.3841998875141144, | |
| "eval_precision": 0.8541643709440505, | |
| "eval_recall": 0.8566757493188011, | |
| "eval_runtime": 39.394, | |
| "eval_samples_per_second": 186.323, | |
| "eval_steps_per_second": 11.652, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 1.2670299727520435, | |
| "grad_norm": 2.4597229957580566, | |
| "learning_rate": 2.8900999091734787e-05, | |
| "loss": 0.406, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 1.2806539509536785, | |
| "grad_norm": 5.7981343269348145, | |
| "learning_rate": 2.867393278837421e-05, | |
| "loss": 0.3517, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 1.2942779291553133, | |
| "grad_norm": 4.284982681274414, | |
| "learning_rate": 2.8446866485013624e-05, | |
| "loss": 0.3071, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 1.3079019073569482, | |
| "grad_norm": 8.857301712036133, | |
| "learning_rate": 2.8219800181653043e-05, | |
| "loss": 0.3578, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.3079019073569482, | |
| "eval_accuracy": 0.8568119891008175, | |
| "eval_f1": 0.8532818648850209, | |
| "eval_loss": 0.40182751417160034, | |
| "eval_precision": 0.8533652780848004, | |
| "eval_recall": 0.8568119891008175, | |
| "eval_runtime": 39.2999, | |
| "eval_samples_per_second": 186.769, | |
| "eval_steps_per_second": 11.679, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 1.3215258855585832, | |
| "grad_norm": 3.8386123180389404, | |
| "learning_rate": 2.7992733878292465e-05, | |
| "loss": 0.295, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 1.335149863760218, | |
| "grad_norm": 6.5531463623046875, | |
| "learning_rate": 2.776566757493188e-05, | |
| "loss": 0.3963, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 1.348773841961853, | |
| "grad_norm": 7.941685199737549, | |
| "learning_rate": 2.7538601271571303e-05, | |
| "loss": 0.3396, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 1.3623978201634879, | |
| "grad_norm": 5.075099468231201, | |
| "learning_rate": 2.7311534968210718e-05, | |
| "loss": 0.3962, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.3623978201634879, | |
| "eval_accuracy": 0.8622615803814714, | |
| "eval_f1": 0.8595333600713432, | |
| "eval_loss": 0.37939050793647766, | |
| "eval_precision": 0.8596955747598374, | |
| "eval_recall": 0.8622615803814714, | |
| "eval_runtime": 39.294, | |
| "eval_samples_per_second": 186.797, | |
| "eval_steps_per_second": 11.681, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 1.3760217983651226, | |
| "grad_norm": 2.8509788513183594, | |
| "learning_rate": 2.7084468664850137e-05, | |
| "loss": 0.3855, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 1.3896457765667574, | |
| "grad_norm": 5.918415546417236, | |
| "learning_rate": 2.685740236148956e-05, | |
| "loss": 0.3238, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 1.4032697547683923, | |
| "grad_norm": 4.571900844573975, | |
| "learning_rate": 2.6630336058128974e-05, | |
| "loss": 0.3277, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 1.4168937329700273, | |
| "grad_norm": 5.005604267120361, | |
| "learning_rate": 2.6403269754768396e-05, | |
| "loss": 0.3979, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.4168937329700273, | |
| "eval_accuracy": 0.8600817438692098, | |
| "eval_f1": 0.8570639571936529, | |
| "eval_loss": 0.3867308795452118, | |
| "eval_precision": 0.858591149569358, | |
| "eval_recall": 0.8600817438692098, | |
| "eval_runtime": 39.3968, | |
| "eval_samples_per_second": 186.31, | |
| "eval_steps_per_second": 11.651, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 1.430517711171662, | |
| "grad_norm": 3.3436524868011475, | |
| "learning_rate": 2.6176203451407812e-05, | |
| "loss": 0.3755, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 1.444141689373297, | |
| "grad_norm": 2.1698825359344482, | |
| "learning_rate": 2.594913714804723e-05, | |
| "loss": 0.2778, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 1.457765667574932, | |
| "grad_norm": 4.432777404785156, | |
| "learning_rate": 2.5722070844686653e-05, | |
| "loss": 0.3833, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 1.4713896457765667, | |
| "grad_norm": 4.060556411743164, | |
| "learning_rate": 2.5495004541326068e-05, | |
| "loss": 0.393, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.4713896457765667, | |
| "eval_accuracy": 0.8645776566757494, | |
| "eval_f1": 0.859894933118512, | |
| "eval_loss": 0.3773682415485382, | |
| "eval_precision": 0.8635251166375231, | |
| "eval_recall": 0.8645776566757494, | |
| "eval_runtime": 39.4823, | |
| "eval_samples_per_second": 185.906, | |
| "eval_steps_per_second": 11.625, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 1.4850136239782017, | |
| "grad_norm": 2.296135425567627, | |
| "learning_rate": 2.5267938237965487e-05, | |
| "loss": 0.2596, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 1.4986376021798364, | |
| "grad_norm": 3.110579013824463, | |
| "learning_rate": 2.5040871934604902e-05, | |
| "loss": 0.3188, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 1.5122615803814714, | |
| "grad_norm": 0.38325050473213196, | |
| "learning_rate": 2.4813805631244324e-05, | |
| "loss": 0.3707, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 1.5258855585831061, | |
| "grad_norm": 1.0077499151229858, | |
| "learning_rate": 2.4586739327883743e-05, | |
| "loss": 0.2461, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.5258855585831061, | |
| "eval_accuracy": 0.8677111716621253, | |
| "eval_f1": 0.8647432485320001, | |
| "eval_loss": 0.40655508637428284, | |
| "eval_precision": 0.866115043606446, | |
| "eval_recall": 0.8677111716621253, | |
| "eval_runtime": 39.421, | |
| "eval_samples_per_second": 186.195, | |
| "eval_steps_per_second": 11.644, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 1.5395095367847411, | |
| "grad_norm": 4.395697116851807, | |
| "learning_rate": 2.4359673024523162e-05, | |
| "loss": 0.3078, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 1.553133514986376, | |
| "grad_norm": 4.02500581741333, | |
| "learning_rate": 2.413260672116258e-05, | |
| "loss": 0.4794, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 1.5667574931880108, | |
| "grad_norm": 3.775764226913452, | |
| "learning_rate": 2.3905540417802e-05, | |
| "loss": 0.2948, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 1.5803814713896458, | |
| "grad_norm": 1.1017502546310425, | |
| "learning_rate": 2.3678474114441418e-05, | |
| "loss": 0.322, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.5803814713896458, | |
| "eval_accuracy": 0.8683923705722071, | |
| "eval_f1": 0.8666679607870518, | |
| "eval_loss": 0.3748830556869507, | |
| "eval_precision": 0.8666797382883451, | |
| "eval_recall": 0.8683923705722071, | |
| "eval_runtime": 39.4374, | |
| "eval_samples_per_second": 186.118, | |
| "eval_steps_per_second": 11.639, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 1.5940054495912808, | |
| "grad_norm": 24.16415786743164, | |
| "learning_rate": 2.3451407811080837e-05, | |
| "loss": 0.3231, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 1.6076294277929155, | |
| "grad_norm": 5.224663734436035, | |
| "learning_rate": 2.3224341507720255e-05, | |
| "loss": 0.3528, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 1.6212534059945503, | |
| "grad_norm": 4.033137321472168, | |
| "learning_rate": 2.2997275204359674e-05, | |
| "loss": 0.362, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 1.6348773841961854, | |
| "grad_norm": 3.7657642364501953, | |
| "learning_rate": 2.2770208900999093e-05, | |
| "loss": 0.3104, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 1.6348773841961854, | |
| "eval_accuracy": 0.8681198910081744, | |
| "eval_f1": 0.8658248505222946, | |
| "eval_loss": 0.35615479946136475, | |
| "eval_precision": 0.8666734700848255, | |
| "eval_recall": 0.8681198910081744, | |
| "eval_runtime": 39.4899, | |
| "eval_samples_per_second": 185.87, | |
| "eval_steps_per_second": 11.623, | |
| "step": 6000 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 11010, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "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": 2.5379531411779584e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |