| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 40.0, | |
| "eval_steps": 60, | |
| "global_step": 9920, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.24193548387096775, | |
| "eval_f1": 0.5851960435915661, | |
| "eval_loss": 0.8871086835861206, | |
| "eval_runtime": 0.2564, | |
| "eval_samples_per_second": 585.087, | |
| "eval_steps_per_second": 11.702, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.4838709677419355, | |
| "eval_f1": 0.6617468749727405, | |
| "eval_loss": 0.7329094409942627, | |
| "eval_runtime": 0.2545, | |
| "eval_samples_per_second": 589.47, | |
| "eval_steps_per_second": 11.789, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7258064516129032, | |
| "eval_f1": 0.8160652328346837, | |
| "eval_loss": 0.46765777468681335, | |
| "eval_runtime": 0.2541, | |
| "eval_samples_per_second": 590.294, | |
| "eval_steps_per_second": 11.806, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.967741935483871, | |
| "eval_f1": 0.8587881420000322, | |
| "eval_loss": 0.44318950176239014, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.306, | |
| "eval_steps_per_second": 11.746, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 1.2096774193548387, | |
| "eval_f1": 0.809411799328179, | |
| "eval_loss": 0.5408520102500916, | |
| "eval_runtime": 0.2546, | |
| "eval_samples_per_second": 589.168, | |
| "eval_steps_per_second": 11.783, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.4516129032258065, | |
| "eval_f1": 0.8382158435345435, | |
| "eval_loss": 0.5099673271179199, | |
| "eval_runtime": 0.2543, | |
| "eval_samples_per_second": 589.946, | |
| "eval_steps_per_second": 11.799, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 1.6935483870967742, | |
| "eval_f1": 0.850649606409975, | |
| "eval_loss": 0.3776738941669464, | |
| "eval_runtime": 0.2587, | |
| "eval_samples_per_second": 579.748, | |
| "eval_steps_per_second": 11.595, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 1.935483870967742, | |
| "eval_f1": 0.9060457516339869, | |
| "eval_loss": 0.3096984922885895, | |
| "eval_runtime": 0.2544, | |
| "eval_samples_per_second": 589.649, | |
| "eval_steps_per_second": 11.793, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 2.0161290322580645, | |
| "grad_norm": 6.729659080505371, | |
| "learning_rate": 4.647087149462068e-05, | |
| "loss": 0.3881, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.1774193548387095, | |
| "eval_f1": 0.9331478793742946, | |
| "eval_loss": 0.19595660269260406, | |
| "eval_runtime": 0.2551, | |
| "eval_samples_per_second": 587.93, | |
| "eval_steps_per_second": 11.759, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 2.4193548387096775, | |
| "eval_f1": 0.9535178217421209, | |
| "eval_loss": 0.15902738273143768, | |
| "eval_runtime": 0.2546, | |
| "eval_samples_per_second": 589.066, | |
| "eval_steps_per_second": 11.781, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.661290322580645, | |
| "eval_f1": 0.9534276314241835, | |
| "eval_loss": 0.1501321643590927, | |
| "eval_runtime": 0.2547, | |
| "eval_samples_per_second": 589.023, | |
| "eval_steps_per_second": 11.78, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 2.903225806451613, | |
| "eval_f1": 0.9800105522453767, | |
| "eval_loss": 0.07951977103948593, | |
| "eval_runtime": 0.2544, | |
| "eval_samples_per_second": 589.701, | |
| "eval_steps_per_second": 11.794, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 3.1451612903225805, | |
| "eval_f1": 0.9931623931623932, | |
| "eval_loss": 0.009822274558246136, | |
| "eval_runtime": 0.2546, | |
| "eval_samples_per_second": 589.081, | |
| "eval_steps_per_second": 11.782, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 3.3870967741935485, | |
| "eval_f1": 0.9931623931623932, | |
| "eval_loss": 0.028039630502462387, | |
| "eval_runtime": 0.2548, | |
| "eval_samples_per_second": 588.756, | |
| "eval_steps_per_second": 11.775, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 3.629032258064516, | |
| "eval_f1": 0.9805444220089162, | |
| "eval_loss": 0.048611294478178024, | |
| "eval_runtime": 0.2559, | |
| "eval_samples_per_second": 586.116, | |
| "eval_steps_per_second": 11.722, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 3.870967741935484, | |
| "eval_f1": 0.9804415639480298, | |
| "eval_loss": 0.08277872949838638, | |
| "eval_runtime": 0.256, | |
| "eval_samples_per_second": 585.987, | |
| "eval_steps_per_second": 11.72, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 4.032258064516129, | |
| "grad_norm": 0.015000954270362854, | |
| "learning_rate": 4.560063227687659e-05, | |
| "loss": 0.083, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 4.112903225806452, | |
| "eval_f1": 0.9804415639480298, | |
| "eval_loss": 0.05285938084125519, | |
| "eval_runtime": 0.2542, | |
| "eval_samples_per_second": 590.087, | |
| "eval_steps_per_second": 11.802, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 4.354838709677419, | |
| "eval_f1": 0.9931394168504323, | |
| "eval_loss": 0.042371999472379684, | |
| "eval_runtime": 0.2565, | |
| "eval_samples_per_second": 584.745, | |
| "eval_steps_per_second": 11.695, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 4.596774193548387, | |
| "eval_f1": 0.9931394168504323, | |
| "eval_loss": 0.020373299717903137, | |
| "eval_runtime": 0.2568, | |
| "eval_samples_per_second": 584.182, | |
| "eval_steps_per_second": 11.684, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 4.838709677419355, | |
| "eval_f1": 0.9873004354136429, | |
| "eval_loss": 0.01691700704395771, | |
| "eval_runtime": 0.2564, | |
| "eval_samples_per_second": 584.952, | |
| "eval_steps_per_second": 11.699, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 5.080645161290323, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0007654120563529432, | |
| "eval_runtime": 0.2582, | |
| "eval_samples_per_second": 581.0, | |
| "eval_steps_per_second": 11.62, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 5.32258064516129, | |
| "eval_f1": 0.9863433667781494, | |
| "eval_loss": 0.026578061282634735, | |
| "eval_runtime": 0.2557, | |
| "eval_samples_per_second": 586.566, | |
| "eval_steps_per_second": 11.731, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 5.564516129032258, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.002019105711951852, | |
| "eval_runtime": 0.2547, | |
| "eval_samples_per_second": 588.941, | |
| "eval_steps_per_second": 11.779, | |
| "step": 1380 | |
| }, | |
| { | |
| "epoch": 5.806451612903226, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00011336191528243944, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.273, | |
| "eval_steps_per_second": 11.745, | |
| "step": 1440 | |
| }, | |
| { | |
| "epoch": 6.048387096774194, | |
| "grad_norm": 0.0038932343013584614, | |
| "learning_rate": 4.4174447775380035e-05, | |
| "loss": 0.0341, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.048387096774194, | |
| "eval_f1": 0.9931394168504323, | |
| "eval_loss": 0.005218833684921265, | |
| "eval_runtime": 0.2547, | |
| "eval_samples_per_second": 588.864, | |
| "eval_steps_per_second": 11.777, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 6.290322580645161, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.001448934432119131, | |
| "eval_runtime": 0.2549, | |
| "eval_samples_per_second": 588.397, | |
| "eval_steps_per_second": 11.768, | |
| "step": 1560 | |
| }, | |
| { | |
| "epoch": 6.532258064516129, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0035662834998220205, | |
| "eval_runtime": 0.2544, | |
| "eval_samples_per_second": 589.724, | |
| "eval_steps_per_second": 11.794, | |
| "step": 1620 | |
| }, | |
| { | |
| "epoch": 6.774193548387097, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.003718534717336297, | |
| "eval_runtime": 0.2544, | |
| "eval_samples_per_second": 589.734, | |
| "eval_steps_per_second": 11.795, | |
| "step": 1680 | |
| }, | |
| { | |
| "epoch": 7.016129032258065, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00021605176152661443, | |
| "eval_runtime": 0.2549, | |
| "eval_samples_per_second": 588.428, | |
| "eval_steps_per_second": 11.769, | |
| "step": 1740 | |
| }, | |
| { | |
| "epoch": 7.258064516129032, | |
| "eval_f1": 0.9931623931623932, | |
| "eval_loss": 0.013021533377468586, | |
| "eval_runtime": 0.254, | |
| "eval_samples_per_second": 590.458, | |
| "eval_steps_per_second": 11.809, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 7.5, | |
| "eval_f1": 1.0, | |
| "eval_loss": 8.37745756143704e-05, | |
| "eval_runtime": 0.2567, | |
| "eval_samples_per_second": 584.393, | |
| "eval_steps_per_second": 11.688, | |
| "step": 1860 | |
| }, | |
| { | |
| "epoch": 7.741935483870968, | |
| "eval_f1": 1.0, | |
| "eval_loss": 7.913756417110562e-05, | |
| "eval_runtime": 0.2556, | |
| "eval_samples_per_second": 586.853, | |
| "eval_steps_per_second": 11.737, | |
| "step": 1920 | |
| }, | |
| { | |
| "epoch": 7.983870967741936, | |
| "eval_f1": 1.0, | |
| "eval_loss": 6.221562944119796e-05, | |
| "eval_runtime": 0.2559, | |
| "eval_samples_per_second": 586.146, | |
| "eval_steps_per_second": 11.723, | |
| "step": 1980 | |
| }, | |
| { | |
| "epoch": 8.064516129032258, | |
| "grad_norm": 0.0007441982161253691, | |
| "learning_rate": 4.222800289057154e-05, | |
| "loss": 0.017, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 8.225806451612904, | |
| "eval_f1": 1.0, | |
| "eval_loss": 7.838715828256682e-05, | |
| "eval_runtime": 0.2539, | |
| "eval_samples_per_second": 590.717, | |
| "eval_steps_per_second": 11.814, | |
| "step": 2040 | |
| }, | |
| { | |
| "epoch": 8.46774193548387, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0009664014796726406, | |
| "eval_runtime": 0.2556, | |
| "eval_samples_per_second": 586.876, | |
| "eval_steps_per_second": 11.738, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 8.709677419354838, | |
| "eval_f1": 0.9936507936507937, | |
| "eval_loss": 0.00964354071766138, | |
| "eval_runtime": 0.2545, | |
| "eval_samples_per_second": 589.449, | |
| "eval_steps_per_second": 11.789, | |
| "step": 2160 | |
| }, | |
| { | |
| "epoch": 8.951612903225806, | |
| "eval_f1": 0.9661393494972598, | |
| "eval_loss": 0.08236207813024521, | |
| "eval_runtime": 0.2545, | |
| "eval_samples_per_second": 589.3, | |
| "eval_steps_per_second": 11.786, | |
| "step": 2220 | |
| }, | |
| { | |
| "epoch": 9.193548387096774, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00091545470058918, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.389, | |
| "eval_steps_per_second": 11.748, | |
| "step": 2280 | |
| }, | |
| { | |
| "epoch": 9.435483870967742, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0017120252596214414, | |
| "eval_runtime": 0.2536, | |
| "eval_samples_per_second": 591.372, | |
| "eval_steps_per_second": 11.827, | |
| "step": 2340 | |
| }, | |
| { | |
| "epoch": 9.67741935483871, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0004082757805008441, | |
| "eval_runtime": 0.2565, | |
| "eval_samples_per_second": 584.858, | |
| "eval_steps_per_second": 11.697, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 9.919354838709678, | |
| "eval_f1": 0.9867521367521368, | |
| "eval_loss": 0.0258210189640522, | |
| "eval_runtime": 0.2589, | |
| "eval_samples_per_second": 579.307, | |
| "eval_steps_per_second": 11.586, | |
| "step": 2460 | |
| }, | |
| { | |
| "epoch": 10.080645161290322, | |
| "grad_norm": 0.001595139503479004, | |
| "learning_rate": 3.981000008125249e-05, | |
| "loss": 0.0278, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 10.161290322580646, | |
| "eval_f1": 0.9930800784733368, | |
| "eval_loss": 0.02786369062960148, | |
| "eval_runtime": 0.2601, | |
| "eval_samples_per_second": 576.62, | |
| "eval_steps_per_second": 11.532, | |
| "step": 2520 | |
| }, | |
| { | |
| "epoch": 10.403225806451612, | |
| "eval_f1": 0.9931007503823038, | |
| "eval_loss": 0.05510010942816734, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.317, | |
| "eval_steps_per_second": 11.746, | |
| "step": 2580 | |
| }, | |
| { | |
| "epoch": 10.64516129032258, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.751836943090893e-05, | |
| "eval_runtime": 0.2573, | |
| "eval_samples_per_second": 583.023, | |
| "eval_steps_per_second": 11.66, | |
| "step": 2640 | |
| }, | |
| { | |
| "epoch": 10.887096774193548, | |
| "eval_f1": 0.9936484892477996, | |
| "eval_loss": 0.031413882970809937, | |
| "eval_runtime": 0.2541, | |
| "eval_samples_per_second": 590.408, | |
| "eval_steps_per_second": 11.808, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 11.129032258064516, | |
| "eval_f1": 0.9930800784733368, | |
| "eval_loss": 0.034935660660266876, | |
| "eval_runtime": 0.2557, | |
| "eval_samples_per_second": 586.588, | |
| "eval_steps_per_second": 11.732, | |
| "step": 2760 | |
| }, | |
| { | |
| "epoch": 11.370967741935484, | |
| "eval_f1": 0.9930800784733368, | |
| "eval_loss": 0.005744210444390774, | |
| "eval_runtime": 0.2558, | |
| "eval_samples_per_second": 586.315, | |
| "eval_steps_per_second": 11.726, | |
| "step": 2820 | |
| }, | |
| { | |
| "epoch": 11.612903225806452, | |
| "eval_f1": 0.9930800784733368, | |
| "eval_loss": 0.044621676206588745, | |
| "eval_runtime": 0.255, | |
| "eval_samples_per_second": 588.201, | |
| "eval_steps_per_second": 11.764, | |
| "step": 2880 | |
| }, | |
| { | |
| "epoch": 11.85483870967742, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.108299956191331e-05, | |
| "eval_runtime": 0.2538, | |
| "eval_samples_per_second": 591.101, | |
| "eval_steps_per_second": 11.822, | |
| "step": 2940 | |
| }, | |
| { | |
| "epoch": 12.096774193548388, | |
| "grad_norm": 1.4287638664245605, | |
| "learning_rate": 3.698094076882026e-05, | |
| "loss": 0.0099, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12.096774193548388, | |
| "eval_f1": 0.9867291604401759, | |
| "eval_loss": 0.09647814929485321, | |
| "eval_runtime": 0.2561, | |
| "eval_samples_per_second": 585.684, | |
| "eval_steps_per_second": 11.714, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 12.338709677419354, | |
| "eval_f1": 0.9936507936507937, | |
| "eval_loss": 0.0637097880244255, | |
| "eval_runtime": 0.256, | |
| "eval_samples_per_second": 586.002, | |
| "eval_steps_per_second": 11.72, | |
| "step": 3060 | |
| }, | |
| { | |
| "epoch": 12.580645161290322, | |
| "eval_f1": 0.9867291604401759, | |
| "eval_loss": 0.08844030648469925, | |
| "eval_runtime": 0.2555, | |
| "eval_samples_per_second": 587.048, | |
| "eval_steps_per_second": 11.741, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 12.82258064516129, | |
| "eval_f1": 0.9930800784733368, | |
| "eval_loss": 0.07371941953897476, | |
| "eval_runtime": 0.2568, | |
| "eval_samples_per_second": 584.175, | |
| "eval_steps_per_second": 11.684, | |
| "step": 3180 | |
| }, | |
| { | |
| "epoch": 13.064516129032258, | |
| "eval_f1": 0.9930800784733368, | |
| "eval_loss": 0.07483946532011032, | |
| "eval_runtime": 0.2538, | |
| "eval_samples_per_second": 590.92, | |
| "eval_steps_per_second": 11.818, | |
| "step": 3240 | |
| }, | |
| { | |
| "epoch": 13.306451612903226, | |
| "eval_f1": 0.9930800784733368, | |
| "eval_loss": 0.07480111718177795, | |
| "eval_runtime": 0.2557, | |
| "eval_samples_per_second": 586.667, | |
| "eval_steps_per_second": 11.733, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 13.548387096774194, | |
| "eval_f1": 1.0, | |
| "eval_loss": 2.3137790776672773e-05, | |
| "eval_runtime": 0.2547, | |
| "eval_samples_per_second": 589.018, | |
| "eval_steps_per_second": 11.78, | |
| "step": 3360 | |
| }, | |
| { | |
| "epoch": 13.790322580645162, | |
| "eval_f1": 1.0, | |
| "eval_loss": 2.158356255677063e-05, | |
| "eval_runtime": 0.2541, | |
| "eval_samples_per_second": 590.234, | |
| "eval_steps_per_second": 11.805, | |
| "step": 3420 | |
| }, | |
| { | |
| "epoch": 14.03225806451613, | |
| "eval_f1": 0.9659544901858607, | |
| "eval_loss": 0.15978649258613586, | |
| "eval_runtime": 0.2579, | |
| "eval_samples_per_second": 581.665, | |
| "eval_steps_per_second": 11.633, | |
| "step": 3480 | |
| }, | |
| { | |
| "epoch": 14.112903225806452, | |
| "grad_norm": 0.0005940676783211529, | |
| "learning_rate": 3.381161151686362e-05, | |
| "loss": 0.0169, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 14.274193548387096, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0006047336501069367, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.341, | |
| "eval_steps_per_second": 11.747, | |
| "step": 3540 | |
| }, | |
| { | |
| "epoch": 14.516129032258064, | |
| "eval_f1": 1.0, | |
| "eval_loss": 7.13071713107638e-05, | |
| "eval_runtime": 0.2552, | |
| "eval_samples_per_second": 587.767, | |
| "eval_steps_per_second": 11.755, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 14.758064516129032, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00021068091155029833, | |
| "eval_runtime": 0.2571, | |
| "eval_samples_per_second": 583.488, | |
| "eval_steps_per_second": 11.67, | |
| "step": 3660 | |
| }, | |
| { | |
| "epoch": 15.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0005000072997063398, | |
| "eval_runtime": 0.2551, | |
| "eval_samples_per_second": 587.982, | |
| "eval_steps_per_second": 11.76, | |
| "step": 3720 | |
| }, | |
| { | |
| "epoch": 15.241935483870968, | |
| "eval_f1": 1.0, | |
| "eval_loss": 3.806134554906748e-05, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.376, | |
| "eval_steps_per_second": 11.748, | |
| "step": 3780 | |
| }, | |
| { | |
| "epoch": 15.483870967741936, | |
| "eval_f1": 1.0, | |
| "eval_loss": 2.8680979085038416e-05, | |
| "eval_runtime": 0.2548, | |
| "eval_samples_per_second": 588.673, | |
| "eval_steps_per_second": 11.773, | |
| "step": 3840 | |
| }, | |
| { | |
| "epoch": 15.725806451612904, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0001551912137074396, | |
| "eval_runtime": 0.255, | |
| "eval_samples_per_second": 588.229, | |
| "eval_steps_per_second": 11.765, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 15.967741935483872, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0014714256394654512, | |
| "eval_runtime": 0.2542, | |
| "eval_samples_per_second": 590.047, | |
| "eval_steps_per_second": 11.801, | |
| "step": 3960 | |
| }, | |
| { | |
| "epoch": 16.129032258064516, | |
| "grad_norm": 0.0009025487233884633, | |
| "learning_rate": 3.038131286377757e-05, | |
| "loss": 0.0155, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 16.20967741935484, | |
| "eval_f1": 1.0, | |
| "eval_loss": 2.558559936005622e-05, | |
| "eval_runtime": 0.2538, | |
| "eval_samples_per_second": 590.96, | |
| "eval_steps_per_second": 11.819, | |
| "step": 4020 | |
| }, | |
| { | |
| "epoch": 16.451612903225808, | |
| "eval_f1": 1.0, | |
| "eval_loss": 3.426855255383998e-05, | |
| "eval_runtime": 0.2563, | |
| "eval_samples_per_second": 585.204, | |
| "eval_steps_per_second": 11.704, | |
| "step": 4080 | |
| }, | |
| { | |
| "epoch": 16.693548387096776, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0018926361808553338, | |
| "eval_runtime": 0.2547, | |
| "eval_samples_per_second": 588.923, | |
| "eval_steps_per_second": 11.778, | |
| "step": 4140 | |
| }, | |
| { | |
| "epoch": 16.93548387096774, | |
| "eval_f1": 0.9931394168504323, | |
| "eval_loss": 0.05736490711569786, | |
| "eval_runtime": 0.256, | |
| "eval_samples_per_second": 586.046, | |
| "eval_steps_per_second": 11.721, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 17.177419354838708, | |
| "eval_f1": 0.9931394168504323, | |
| "eval_loss": 0.05700461566448212, | |
| "eval_runtime": 0.2546, | |
| "eval_samples_per_second": 589.274, | |
| "eval_steps_per_second": 11.785, | |
| "step": 4260 | |
| }, | |
| { | |
| "epoch": 17.419354838709676, | |
| "eval_f1": 0.9931394168504323, | |
| "eval_loss": 0.05664278194308281, | |
| "eval_runtime": 0.254, | |
| "eval_samples_per_second": 590.639, | |
| "eval_steps_per_second": 11.813, | |
| "step": 4320 | |
| }, | |
| { | |
| "epoch": 17.661290322580644, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00015866669127717614, | |
| "eval_runtime": 0.2545, | |
| "eval_samples_per_second": 589.42, | |
| "eval_steps_per_second": 11.788, | |
| "step": 4380 | |
| }, | |
| { | |
| "epoch": 17.903225806451612, | |
| "eval_f1": 1.0, | |
| "eval_loss": 8.310633711516857e-05, | |
| "eval_runtime": 0.3017, | |
| "eval_samples_per_second": 497.145, | |
| "eval_steps_per_second": 9.943, | |
| "step": 4440 | |
| }, | |
| { | |
| "epoch": 18.14516129032258, | |
| "grad_norm": 0.0018858049297705293, | |
| "learning_rate": 2.6775875125196684e-05, | |
| "loss": 0.0214, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 18.14516129032258, | |
| "eval_f1": 1.0, | |
| "eval_loss": 6.328391464194283e-05, | |
| "eval_runtime": 0.255, | |
| "eval_samples_per_second": 588.208, | |
| "eval_steps_per_second": 11.764, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 18.387096774193548, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00011058977543143556, | |
| "eval_runtime": 0.2575, | |
| "eval_samples_per_second": 582.543, | |
| "eval_steps_per_second": 11.651, | |
| "step": 4560 | |
| }, | |
| { | |
| "epoch": 18.629032258064516, | |
| "eval_f1": 0.9936507936507937, | |
| "eval_loss": 0.0063561322167515755, | |
| "eval_runtime": 0.2546, | |
| "eval_samples_per_second": 589.057, | |
| "eval_steps_per_second": 11.781, | |
| "step": 4620 | |
| }, | |
| { | |
| "epoch": 18.870967741935484, | |
| "eval_f1": 0.9936484892477996, | |
| "eval_loss": 0.07243207842111588, | |
| "eval_runtime": 0.2542, | |
| "eval_samples_per_second": 590.195, | |
| "eval_steps_per_second": 11.804, | |
| "step": 4680 | |
| }, | |
| { | |
| "epoch": 19.112903225806452, | |
| "eval_f1": 1.0, | |
| "eval_loss": 3.163903966196813e-05, | |
| "eval_runtime": 0.2549, | |
| "eval_samples_per_second": 588.475, | |
| "eval_steps_per_second": 11.769, | |
| "step": 4740 | |
| }, | |
| { | |
| "epoch": 19.35483870967742, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00013194132770877331, | |
| "eval_runtime": 0.2542, | |
| "eval_samples_per_second": 590.164, | |
| "eval_steps_per_second": 11.803, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 19.596774193548388, | |
| "eval_f1": 1.0, | |
| "eval_loss": 8.35082828416489e-05, | |
| "eval_runtime": 0.2555, | |
| "eval_samples_per_second": 587.138, | |
| "eval_steps_per_second": 11.743, | |
| "step": 4860 | |
| }, | |
| { | |
| "epoch": 19.838709677419356, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00017465968267060816, | |
| "eval_runtime": 0.2551, | |
| "eval_samples_per_second": 588.086, | |
| "eval_steps_per_second": 11.762, | |
| "step": 4920 | |
| }, | |
| { | |
| "epoch": 20.080645161290324, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.00028180619119666517, | |
| "eval_runtime": 0.2551, | |
| "eval_samples_per_second": 588.014, | |
| "eval_steps_per_second": 11.76, | |
| "step": 4980 | |
| }, | |
| { | |
| "epoch": 20.161290322580644, | |
| "grad_norm": 0.0009010693174786866, | |
| "learning_rate": 2.308551081332452e-05, | |
| "loss": 0.0161, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 20.322580645161292, | |
| "eval_f1": 1.0, | |
| "eval_loss": 0.0002893185301218182, | |
| "eval_runtime": 0.2539, | |
| "eval_samples_per_second": 590.81, | |
| "eval_steps_per_second": 11.816, | |
| "step": 5040 | |
| }, | |
| { | |
| "epoch": 20.56451612903226, | |
| "eval_f1": 1.0, | |
| "eval_loss": 3.712088437168859e-05, | |
| "eval_runtime": 0.2569, | |
| "eval_samples_per_second": 583.889, | |
| "eval_steps_per_second": 11.678, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 20.806451612903224, | |
| "eval_f1": 1.0, | |
| "eval_loss": 3.2648320484440774e-05, | |
| "eval_runtime": 0.2548, | |
| "eval_samples_per_second": 588.741, | |
| "eval_steps_per_second": 11.775, | |
| "step": 5160 | |
| }, | |
| { | |
| "epoch": 21.048387096774192, | |
| "eval_f1": 1.0, | |
| "eval_loss": 2.866457543859724e-05, | |
| "eval_runtime": 0.2559, | |
| "eval_samples_per_second": 586.183, | |
| "eval_steps_per_second": 11.724, | |
| "step": 5220 | |
| }, | |
| { | |
| "epoch": 21.29032258064516, | |
| "eval_f1": 1.0, | |
| "eval_loss": 2.9972579795867205e-05, | |
| "eval_runtime": 0.2547, | |
| "eval_samples_per_second": 588.897, | |
| "eval_steps_per_second": 11.778, | |
| "step": 5280 | |
| }, | |
| { | |
| "epoch": 21.532258064516128, | |
| "eval_f1": 1.0, | |
| "eval_loss": 2.6008663553511724e-05, | |
| "eval_runtime": 0.2568, | |
| "eval_samples_per_second": 584.06, | |
| "eval_steps_per_second": 11.681, | |
| "step": 5340 | |
| }, | |
| { | |
| "epoch": 21.774193548387096, | |
| "eval_f1": 1.0, | |
| "eval_loss": 2.6406421966385096e-05, | |
| "eval_runtime": 0.2542, | |
| "eval_samples_per_second": 590.17, | |
| "eval_steps_per_second": 11.803, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 22.016129032258064, | |
| "eval_f1": 1.0, | |
| "eval_loss": 2.0519637473626062e-05, | |
| "eval_runtime": 0.2555, | |
| "eval_samples_per_second": 587.081, | |
| "eval_steps_per_second": 11.742, | |
| "step": 5460 | |
| }, | |
| { | |
| "epoch": 22.177419354838708, | |
| "grad_norm": 0.0008068878669291735, | |
| "learning_rate": 1.940255740828388e-05, | |
| "loss": 0.004, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 22.258064516129032, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.894849083328154e-05, | |
| "eval_runtime": 0.2549, | |
| "eval_samples_per_second": 588.573, | |
| "eval_steps_per_second": 11.771, | |
| "step": 5520 | |
| }, | |
| { | |
| "epoch": 22.5, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.6999869330902584e-05, | |
| "eval_runtime": 0.2551, | |
| "eval_samples_per_second": 587.891, | |
| "eval_steps_per_second": 11.758, | |
| "step": 5580 | |
| }, | |
| { | |
| "epoch": 22.741935483870968, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.7026062778313644e-05, | |
| "eval_runtime": 0.2555, | |
| "eval_samples_per_second": 587.094, | |
| "eval_steps_per_second": 11.742, | |
| "step": 5640 | |
| }, | |
| { | |
| "epoch": 22.983870967741936, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.6268664694507606e-05, | |
| "eval_runtime": 0.2555, | |
| "eval_samples_per_second": 587.126, | |
| "eval_steps_per_second": 11.743, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 23.225806451612904, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.5551027900073677e-05, | |
| "eval_runtime": 0.2557, | |
| "eval_samples_per_second": 586.707, | |
| "eval_steps_per_second": 11.734, | |
| "step": 5760 | |
| }, | |
| { | |
| "epoch": 23.467741935483872, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.4529051441058982e-05, | |
| "eval_runtime": 0.255, | |
| "eval_samples_per_second": 588.162, | |
| "eval_steps_per_second": 11.763, | |
| "step": 5820 | |
| }, | |
| { | |
| "epoch": 23.70967741935484, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.2737024917441886e-05, | |
| "eval_runtime": 0.2548, | |
| "eval_samples_per_second": 588.642, | |
| "eval_steps_per_second": 11.773, | |
| "step": 5880 | |
| }, | |
| { | |
| "epoch": 23.951612903225808, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.2093305485905148e-05, | |
| "eval_runtime": 0.2559, | |
| "eval_samples_per_second": 586.075, | |
| "eval_steps_per_second": 11.722, | |
| "step": 5940 | |
| }, | |
| { | |
| "epoch": 24.193548387096776, | |
| "grad_norm": 0.0002727832761593163, | |
| "learning_rate": 1.5819166960141247e-05, | |
| "loss": 0.0026, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 24.193548387096776, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.1829461072920822e-05, | |
| "eval_runtime": 0.255, | |
| "eval_samples_per_second": 588.148, | |
| "eval_steps_per_second": 11.763, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 24.43548387096774, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.2995285942452028e-05, | |
| "eval_runtime": 0.2539, | |
| "eval_samples_per_second": 590.855, | |
| "eval_steps_per_second": 11.817, | |
| "step": 6060 | |
| }, | |
| { | |
| "epoch": 24.677419354838708, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.1007723514921963e-05, | |
| "eval_runtime": 0.255, | |
| "eval_samples_per_second": 588.252, | |
| "eval_steps_per_second": 11.765, | |
| "step": 6120 | |
| }, | |
| { | |
| "epoch": 24.919354838709676, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.0587315045995638e-05, | |
| "eval_runtime": 0.255, | |
| "eval_samples_per_second": 588.297, | |
| "eval_steps_per_second": 11.766, | |
| "step": 6180 | |
| }, | |
| { | |
| "epoch": 25.161290322580644, | |
| "eval_f1": 1.0, | |
| "eval_loss": 1.0195521099376492e-05, | |
| "eval_runtime": 0.2548, | |
| "eval_samples_per_second": 588.807, | |
| "eval_steps_per_second": 11.776, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 25.403225806451612, | |
| "eval_f1": 1.0, | |
| "eval_loss": 9.860146747087128e-06, | |
| "eval_runtime": 0.2557, | |
| "eval_samples_per_second": 586.556, | |
| "eval_steps_per_second": 11.731, | |
| "step": 6300 | |
| }, | |
| { | |
| "epoch": 25.64516129032258, | |
| "eval_f1": 1.0, | |
| "eval_loss": 9.539876373310108e-06, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.288, | |
| "eval_steps_per_second": 11.746, | |
| "step": 6360 | |
| }, | |
| { | |
| "epoch": 25.887096774193548, | |
| "eval_f1": 1.0, | |
| "eval_loss": 9.233906894223765e-06, | |
| "eval_runtime": 0.2561, | |
| "eval_samples_per_second": 585.792, | |
| "eval_steps_per_second": 11.716, | |
| "step": 6420 | |
| }, | |
| { | |
| "epoch": 26.129032258064516, | |
| "eval_f1": 1.0, | |
| "eval_loss": 8.902509762265254e-06, | |
| "eval_runtime": 0.2539, | |
| "eval_samples_per_second": 590.758, | |
| "eval_steps_per_second": 11.815, | |
| "step": 6480 | |
| }, | |
| { | |
| "epoch": 26.20967741935484, | |
| "grad_norm": 0.0002617554273456335, | |
| "learning_rate": 1.242500033062053e-05, | |
| "loss": 0.0009, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 26.370967741935484, | |
| "eval_f1": 1.0, | |
| "eval_loss": 8.575877473049331e-06, | |
| "eval_runtime": 0.2549, | |
| "eval_samples_per_second": 588.489, | |
| "eval_steps_per_second": 11.77, | |
| "step": 6540 | |
| }, | |
| { | |
| "epoch": 26.612903225806452, | |
| "eval_f1": 1.0, | |
| "eval_loss": 8.099837941699661e-06, | |
| "eval_runtime": 0.2547, | |
| "eval_samples_per_second": 588.925, | |
| "eval_steps_per_second": 11.778, | |
| "step": 6600 | |
| }, | |
| { | |
| "epoch": 26.85483870967742, | |
| "eval_f1": 1.0, | |
| "eval_loss": 7.677047506149393e-06, | |
| "eval_runtime": 0.2549, | |
| "eval_samples_per_second": 588.508, | |
| "eval_steps_per_second": 11.77, | |
| "step": 6660 | |
| }, | |
| { | |
| "epoch": 27.096774193548388, | |
| "eval_f1": 1.0, | |
| "eval_loss": 7.495055797335226e-06, | |
| "eval_runtime": 0.2547, | |
| "eval_samples_per_second": 588.85, | |
| "eval_steps_per_second": 11.777, | |
| "step": 6720 | |
| }, | |
| { | |
| "epoch": 27.338709677419356, | |
| "eval_f1": 1.0, | |
| "eval_loss": 7.2447178354195785e-06, | |
| "eval_runtime": 0.255, | |
| "eval_samples_per_second": 588.316, | |
| "eval_steps_per_second": 11.766, | |
| "step": 6780 | |
| }, | |
| { | |
| "epoch": 27.580645161290324, | |
| "eval_f1": 1.0, | |
| "eval_loss": 7.079415809130296e-06, | |
| "eval_runtime": 0.2558, | |
| "eval_samples_per_second": 586.414, | |
| "eval_steps_per_second": 11.728, | |
| "step": 6840 | |
| }, | |
| { | |
| "epoch": 27.822580645161292, | |
| "eval_f1": 1.0, | |
| "eval_loss": 7.096105036907829e-06, | |
| "eval_runtime": 0.2567, | |
| "eval_samples_per_second": 584.45, | |
| "eval_steps_per_second": 11.689, | |
| "step": 6900 | |
| }, | |
| { | |
| "epoch": 28.06451612903226, | |
| "eval_f1": 1.0, | |
| "eval_loss": 6.859276709292317e-06, | |
| "eval_runtime": 0.2543, | |
| "eval_samples_per_second": 589.912, | |
| "eval_steps_per_second": 11.798, | |
| "step": 6960 | |
| }, | |
| { | |
| "epoch": 28.225806451612904, | |
| "grad_norm": 0.00016708578914403915, | |
| "learning_rate": 9.304983767430839e-06, | |
| "loss": 0.0007, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 28.306451612903224, | |
| "eval_f1": 1.0, | |
| "eval_loss": 6.732917427143548e-06, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.412, | |
| "eval_steps_per_second": 11.748, | |
| "step": 7020 | |
| }, | |
| { | |
| "epoch": 28.548387096774192, | |
| "eval_f1": 1.0, | |
| "eval_loss": 6.600993401661981e-06, | |
| "eval_runtime": 0.2602, | |
| "eval_samples_per_second": 576.473, | |
| "eval_steps_per_second": 11.529, | |
| "step": 7080 | |
| }, | |
| { | |
| "epoch": 28.79032258064516, | |
| "eval_f1": 1.0, | |
| "eval_loss": 6.482578555733198e-06, | |
| "eval_runtime": 0.2561, | |
| "eval_samples_per_second": 585.802, | |
| "eval_steps_per_second": 11.716, | |
| "step": 7140 | |
| }, | |
| { | |
| "epoch": 29.032258064516128, | |
| "eval_f1": 1.0, | |
| "eval_loss": 6.322838999039959e-06, | |
| "eval_runtime": 0.2545, | |
| "eval_samples_per_second": 589.379, | |
| "eval_steps_per_second": 11.788, | |
| "step": 7200 | |
| }, | |
| { | |
| "epoch": 29.274193548387096, | |
| "eval_f1": 1.0, | |
| "eval_loss": 6.2060144045972265e-06, | |
| "eval_runtime": 0.255, | |
| "eval_samples_per_second": 588.181, | |
| "eval_steps_per_second": 11.764, | |
| "step": 7260 | |
| }, | |
| { | |
| "epoch": 29.516129032258064, | |
| "eval_f1": 1.0, | |
| "eval_loss": 6.097932327975286e-06, | |
| "eval_runtime": 0.2575, | |
| "eval_samples_per_second": 582.488, | |
| "eval_steps_per_second": 11.65, | |
| "step": 7320 | |
| }, | |
| { | |
| "epoch": 29.758064516129032, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.999386758048786e-06, | |
| "eval_runtime": 0.2549, | |
| "eval_samples_per_second": 588.48, | |
| "eval_steps_per_second": 11.77, | |
| "step": 7380 | |
| }, | |
| { | |
| "epoch": 30.0, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.888920895813499e-06, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.296, | |
| "eval_steps_per_second": 11.746, | |
| "step": 7440 | |
| }, | |
| { | |
| "epoch": 30.241935483870968, | |
| "grad_norm": 0.00016466749366372824, | |
| "learning_rate": 6.537183944493647e-06, | |
| "loss": 0.0009, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 30.241935483870968, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.9008411881222855e-06, | |
| "eval_runtime": 0.2545, | |
| "eval_samples_per_second": 589.276, | |
| "eval_steps_per_second": 11.786, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 30.483870967741936, | |
| "eval_f1": 1.0, | |
| "eval_loss": 6.41104315945995e-06, | |
| "eval_runtime": 0.254, | |
| "eval_samples_per_second": 590.649, | |
| "eval_steps_per_second": 11.813, | |
| "step": 7560 | |
| }, | |
| { | |
| "epoch": 30.725806451612904, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.6163312365242746e-06, | |
| "eval_runtime": 0.254, | |
| "eval_samples_per_second": 590.583, | |
| "eval_steps_per_second": 11.812, | |
| "step": 7620 | |
| }, | |
| { | |
| "epoch": 30.967741935483872, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.524143034563167e-06, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.338, | |
| "eval_steps_per_second": 11.747, | |
| "step": 7680 | |
| }, | |
| { | |
| "epoch": 31.20967741935484, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.447849162010243e-06, | |
| "eval_runtime": 0.2559, | |
| "eval_samples_per_second": 586.279, | |
| "eval_steps_per_second": 11.726, | |
| "step": 7740 | |
| }, | |
| { | |
| "epoch": 31.451612903225808, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.366786808735924e-06, | |
| "eval_runtime": 0.2551, | |
| "eval_samples_per_second": 587.967, | |
| "eval_steps_per_second": 11.759, | |
| "step": 7800 | |
| }, | |
| { | |
| "epoch": 31.693548387096776, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.3008247959951404e-06, | |
| "eval_runtime": 0.2549, | |
| "eval_samples_per_second": 588.378, | |
| "eval_steps_per_second": 11.768, | |
| "step": 7860 | |
| }, | |
| { | |
| "epoch": 31.93548387096774, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.241220605967101e-06, | |
| "eval_runtime": 0.254, | |
| "eval_samples_per_second": 590.438, | |
| "eval_steps_per_second": 11.809, | |
| "step": 7920 | |
| }, | |
| { | |
| "epoch": 32.17741935483871, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.184000656299759e-06, | |
| "eval_runtime": 0.2548, | |
| "eval_samples_per_second": 588.705, | |
| "eval_steps_per_second": 11.774, | |
| "step": 7980 | |
| }, | |
| { | |
| "epoch": 32.25806451612903, | |
| "grad_norm": 0.0001813564304029569, | |
| "learning_rate": 4.190854637191562e-06, | |
| "loss": 0.0, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 32.41935483870968, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.115653948450927e-06, | |
| "eval_runtime": 0.2548, | |
| "eval_samples_per_second": 588.735, | |
| "eval_steps_per_second": 11.775, | |
| "step": 8040 | |
| }, | |
| { | |
| "epoch": 32.66129032258065, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.066380708740326e-06, | |
| "eval_runtime": 0.255, | |
| "eval_samples_per_second": 588.337, | |
| "eval_steps_per_second": 11.767, | |
| "step": 8100 | |
| }, | |
| { | |
| "epoch": 32.903225806451616, | |
| "eval_f1": 1.0, | |
| "eval_loss": 5.009161668567685e-06, | |
| "eval_runtime": 0.2543, | |
| "eval_samples_per_second": 589.863, | |
| "eval_steps_per_second": 11.797, | |
| "step": 8160 | |
| }, | |
| { | |
| "epoch": 33.145161290322584, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.943993189954199e-06, | |
| "eval_runtime": 0.2543, | |
| "eval_samples_per_second": 589.901, | |
| "eval_steps_per_second": 11.798, | |
| "step": 8220 | |
| }, | |
| { | |
| "epoch": 33.38709677419355, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.893926870863652e-06, | |
| "eval_runtime": 0.2545, | |
| "eval_samples_per_second": 589.333, | |
| "eval_steps_per_second": 11.787, | |
| "step": 8280 | |
| }, | |
| { | |
| "epoch": 33.62903225806452, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.85418968310114e-06, | |
| "eval_runtime": 0.2543, | |
| "eval_samples_per_second": 589.802, | |
| "eval_steps_per_second": 11.796, | |
| "step": 8340 | |
| }, | |
| { | |
| "epoch": 33.87096774193548, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.81445340483333e-06, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.21, | |
| "eval_steps_per_second": 11.744, | |
| "step": 8400 | |
| }, | |
| { | |
| "epoch": 34.11290322580645, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.774717581312871e-06, | |
| "eval_runtime": 0.2556, | |
| "eval_samples_per_second": 586.894, | |
| "eval_steps_per_second": 11.738, | |
| "step": 8460 | |
| }, | |
| { | |
| "epoch": 34.274193548387096, | |
| "grad_norm": 0.00011297773016849533, | |
| "learning_rate": 2.3247039072402065e-06, | |
| "loss": 0.0, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 34.354838709677416, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.748492301587248e-06, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.245, | |
| "eval_steps_per_second": 11.745, | |
| "step": 8520 | |
| }, | |
| { | |
| "epoch": 34.596774193548384, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.70478153147269e-06, | |
| "eval_runtime": 0.2545, | |
| "eval_samples_per_second": 589.454, | |
| "eval_steps_per_second": 11.789, | |
| "step": 8580 | |
| }, | |
| { | |
| "epoch": 34.83870967741935, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.678555796999717e-06, | |
| "eval_runtime": 0.2551, | |
| "eval_samples_per_second": 588.068, | |
| "eval_steps_per_second": 11.761, | |
| "step": 8640 | |
| }, | |
| { | |
| "epoch": 35.08064516129032, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.659482328861486e-06, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.313, | |
| "eval_steps_per_second": 11.746, | |
| "step": 8700 | |
| }, | |
| { | |
| "epoch": 35.32258064516129, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.6300779104058165e-06, | |
| "eval_runtime": 0.2558, | |
| "eval_samples_per_second": 586.379, | |
| "eval_steps_per_second": 11.728, | |
| "step": 8760 | |
| }, | |
| { | |
| "epoch": 35.564516129032256, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.600673037202796e-06, | |
| "eval_runtime": 0.255, | |
| "eval_samples_per_second": 588.143, | |
| "eval_steps_per_second": 11.763, | |
| "step": 8820 | |
| }, | |
| { | |
| "epoch": 35.806451612903224, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.583984264172614e-06, | |
| "eval_runtime": 0.2548, | |
| "eval_samples_per_second": 588.693, | |
| "eval_steps_per_second": 11.774, | |
| "step": 8880 | |
| }, | |
| { | |
| "epoch": 36.04838709677419, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.560936304187635e-06, | |
| "eval_runtime": 0.2541, | |
| "eval_samples_per_second": 590.228, | |
| "eval_steps_per_second": 11.805, | |
| "step": 8940 | |
| }, | |
| { | |
| "epoch": 36.29032258064516, | |
| "grad_norm": 0.00010865663352888077, | |
| "learning_rate": 9.854251543613312e-07, | |
| "loss": 0.0, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 36.29032258064516, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.545041974779451e-06, | |
| "eval_runtime": 0.2628, | |
| "eval_samples_per_second": 570.734, | |
| "eval_steps_per_second": 11.415, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 36.53225806451613, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.527558303379919e-06, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.354, | |
| "eval_steps_per_second": 11.747, | |
| "step": 9060 | |
| }, | |
| { | |
| "epoch": 36.774193548387096, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.5124579628463835e-06, | |
| "eval_runtime": 0.2575, | |
| "eval_samples_per_second": 582.554, | |
| "eval_steps_per_second": 11.651, | |
| "step": 9120 | |
| }, | |
| { | |
| "epoch": 37.016129032258064, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.502126103034243e-06, | |
| "eval_runtime": 0.2542, | |
| "eval_samples_per_second": 590.074, | |
| "eval_steps_per_second": 11.801, | |
| "step": 9180 | |
| }, | |
| { | |
| "epoch": 37.25806451612903, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.493384949455503e-06, | |
| "eval_runtime": 0.2554, | |
| "eval_samples_per_second": 587.314, | |
| "eval_steps_per_second": 11.746, | |
| "step": 9240 | |
| }, | |
| { | |
| "epoch": 37.5, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.461595381144434e-06, | |
| "eval_runtime": 0.2547, | |
| "eval_samples_per_second": 588.917, | |
| "eval_steps_per_second": 11.778, | |
| "step": 9300 | |
| }, | |
| { | |
| "epoch": 37.74193548387097, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.452854227565695e-06, | |
| "eval_runtime": 0.2549, | |
| "eval_samples_per_second": 588.51, | |
| "eval_steps_per_second": 11.77, | |
| "step": 9360 | |
| }, | |
| { | |
| "epoch": 37.983870967741936, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.44729084847495e-06, | |
| "eval_runtime": 0.2567, | |
| "eval_samples_per_second": 584.253, | |
| "eval_steps_per_second": 11.685, | |
| "step": 9420 | |
| }, | |
| { | |
| "epoch": 38.225806451612904, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.4433177208702546e-06, | |
| "eval_runtime": 0.2562, | |
| "eval_samples_per_second": 585.502, | |
| "eval_steps_per_second": 11.71, | |
| "step": 9480 | |
| }, | |
| { | |
| "epoch": 38.306451612903224, | |
| "grad_norm": 0.00010896463209064677, | |
| "learning_rate": 2.0652878966122916e-07, | |
| "loss": 0.0, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 38.46774193548387, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.434575657796813e-06, | |
| "eval_runtime": 0.2594, | |
| "eval_samples_per_second": 578.204, | |
| "eval_steps_per_second": 11.564, | |
| "step": 9540 | |
| }, | |
| { | |
| "epoch": 38.70967741935484, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.4282178350840695e-06, | |
| "eval_runtime": 0.2571, | |
| "eval_samples_per_second": 583.366, | |
| "eval_steps_per_second": 11.667, | |
| "step": 9600 | |
| }, | |
| { | |
| "epoch": 38.95161290322581, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.4266280383453704e-06, | |
| "eval_runtime": 0.261, | |
| "eval_samples_per_second": 574.674, | |
| "eval_steps_per_second": 11.493, | |
| "step": 9660 | |
| }, | |
| { | |
| "epoch": 39.193548387096776, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.425038696354022e-06, | |
| "eval_runtime": 0.2615, | |
| "eval_samples_per_second": 573.707, | |
| "eval_steps_per_second": 11.474, | |
| "step": 9720 | |
| }, | |
| { | |
| "epoch": 39.435483870967744, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.423449354362674e-06, | |
| "eval_runtime": 0.2582, | |
| "eval_samples_per_second": 580.933, | |
| "eval_steps_per_second": 11.619, | |
| "step": 9780 | |
| }, | |
| { | |
| "epoch": 39.67741935483871, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.4226544559933245e-06, | |
| "eval_runtime": 0.258, | |
| "eval_samples_per_second": 581.476, | |
| "eval_steps_per_second": 11.63, | |
| "step": 9840 | |
| }, | |
| { | |
| "epoch": 39.91935483870968, | |
| "eval_f1": 1.0, | |
| "eval_loss": 4.4226544559933245e-06, | |
| "eval_runtime": 0.257, | |
| "eval_samples_per_second": 583.764, | |
| "eval_steps_per_second": 11.675, | |
| "step": 9900 | |
| }, | |
| { | |
| "epoch": 40.0, | |
| "step": 9920, | |
| "total_flos": 1.041666020785152e+16, | |
| "train_loss": 0.03220151995762623, | |
| "train_runtime": 939.6593, | |
| "train_samples_per_second": 168.529, | |
| "train_steps_per_second": 10.557 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 9920, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 40, | |
| "save_steps": 1200, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.041666020785152e+16, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |