Instructions to use RGarrido03/modernbert-conll2003-ner-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RGarrido03/modernbert-conll2003-ner-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="RGarrido03/modernbert-conll2003-ner-base")# Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("RGarrido03/modernbert-conll2003-ner-base") model = AutoModelForTokenClassification.from_pretrained("RGarrido03/modernbert-conll2003-ner-base") - Notebooks
- Google Colab
- Kaggle
| { | |
| "best_global_step": 5268, | |
| "best_metric": 0.9415502968475625, | |
| "best_model_checkpoint": "outputs/modernbert-conll2003-ner/checkpoint-5268", | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 5268, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02847380410022779, | |
| "grad_norm": 7.455692768096924, | |
| "learning_rate": 4.648956356736243e-06, | |
| "loss": 1.6615650939941407, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.05694760820045558, | |
| "grad_norm": 4.326021194458008, | |
| "learning_rate": 9.392789373814043e-06, | |
| "loss": 0.7773161315917969, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08542141230068337, | |
| "grad_norm": 8.716073036193848, | |
| "learning_rate": 1.413662239089184e-05, | |
| "loss": 0.5420105361938476, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.11389521640091116, | |
| "grad_norm": 9.381856918334961, | |
| "learning_rate": 1.888045540796964e-05, | |
| "loss": 0.42453876495361326, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14236902050113895, | |
| "grad_norm": 12.2055082321167, | |
| "learning_rate": 2.362428842504744e-05, | |
| "loss": 0.3617136001586914, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.17084282460136674, | |
| "grad_norm": 10.941551208496094, | |
| "learning_rate": 2.836812144212524e-05, | |
| "loss": 0.31678779602050783, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.19931662870159453, | |
| "grad_norm": 5.196351528167725, | |
| "learning_rate": 3.311195445920304e-05, | |
| "loss": 0.3272995376586914, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.22779043280182232, | |
| "grad_norm": 4.492961406707764, | |
| "learning_rate": 3.7855787476280835e-05, | |
| "loss": 0.24839899063110352, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.25626423690205014, | |
| "grad_norm": 5.2656145095825195, | |
| "learning_rate": 4.2599620493358636e-05, | |
| "loss": 0.24544755935668947, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.2847380410022779, | |
| "grad_norm": 4.304174900054932, | |
| "learning_rate": 4.7343453510436436e-05, | |
| "loss": 0.2118685722351074, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.3132118451025057, | |
| "grad_norm": 2.092153310775757, | |
| "learning_rate": 4.976798143851508e-05, | |
| "loss": 0.20026132583618164, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.3416856492027335, | |
| "grad_norm": 3.674985647201538, | |
| "learning_rate": 4.924066652604936e-05, | |
| "loss": 0.17270835876464843, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3701594533029613, | |
| "grad_norm": 2.756453514099121, | |
| "learning_rate": 4.871335161358363e-05, | |
| "loss": 0.11772419929504395, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.39863325740318906, | |
| "grad_norm": 1.9030200242996216, | |
| "learning_rate": 4.818603670111791e-05, | |
| "loss": 0.15580097198486328, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.4271070615034169, | |
| "grad_norm": 3.236600399017334, | |
| "learning_rate": 4.7658721788652186e-05, | |
| "loss": 0.1331379795074463, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.45558086560364464, | |
| "grad_norm": 1.866998553276062, | |
| "learning_rate": 4.713140687618646e-05, | |
| "loss": 0.13968156814575194, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.48405466970387245, | |
| "grad_norm": 2.0798587799072266, | |
| "learning_rate": 4.660409196372073e-05, | |
| "loss": 0.11728707313537598, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.5125284738041003, | |
| "grad_norm": 2.82535982131958, | |
| "learning_rate": 4.607677705125501e-05, | |
| "loss": 0.12277777671813965, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.541002277904328, | |
| "grad_norm": 2.927178382873535, | |
| "learning_rate": 4.554946213878929e-05, | |
| "loss": 0.12073131561279297, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.5694760820045558, | |
| "grad_norm": 0.4732373356819153, | |
| "learning_rate": 4.5022147226323564e-05, | |
| "loss": 0.1002076244354248, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.5979498861047836, | |
| "grad_norm": 4.891218185424805, | |
| "learning_rate": 4.449483231385784e-05, | |
| "loss": 0.09534002304077148, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.6264236902050114, | |
| "grad_norm": 2.673395872116089, | |
| "learning_rate": 4.396751740139211e-05, | |
| "loss": 0.0849313735961914, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.6548974943052391, | |
| "grad_norm": 0.45503002405166626, | |
| "learning_rate": 4.344020248892639e-05, | |
| "loss": 0.10159985542297363, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.683371298405467, | |
| "grad_norm": 4.175873279571533, | |
| "learning_rate": 4.2912887576460664e-05, | |
| "loss": 0.10804034233093261, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.7118451025056948, | |
| "grad_norm": 7.960940361022949, | |
| "learning_rate": 4.238557266399494e-05, | |
| "loss": 0.08453042030334473, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.7403189066059226, | |
| "grad_norm": 6.540600299835205, | |
| "learning_rate": 4.185825775152922e-05, | |
| "loss": 0.09416821479797363, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.7687927107061503, | |
| "grad_norm": 0.6882961392402649, | |
| "learning_rate": 4.133094283906349e-05, | |
| "loss": 0.07157005310058594, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.7972665148063781, | |
| "grad_norm": 0.6619611382484436, | |
| "learning_rate": 4.0803627926597765e-05, | |
| "loss": 0.066082763671875, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.8257403189066059, | |
| "grad_norm": 7.522312164306641, | |
| "learning_rate": 4.027631301413204e-05, | |
| "loss": 0.07188422203063966, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.8542141230068337, | |
| "grad_norm": 2.3896121978759766, | |
| "learning_rate": 3.974899810166632e-05, | |
| "loss": 0.09095027923583984, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8826879271070615, | |
| "grad_norm": 2.823428153991699, | |
| "learning_rate": 3.9221683189200595e-05, | |
| "loss": 0.07988889217376709, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.9111617312072893, | |
| "grad_norm": 2.9240481853485107, | |
| "learning_rate": 3.8694368276734865e-05, | |
| "loss": 0.08108667373657226, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.9396355353075171, | |
| "grad_norm": 1.862162470817566, | |
| "learning_rate": 3.816705336426914e-05, | |
| "loss": 0.08407090187072754, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.9681093394077449, | |
| "grad_norm": 0.9724222421646118, | |
| "learning_rate": 3.763973845180342e-05, | |
| "loss": 0.07995471477508545, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.9965831435079726, | |
| "grad_norm": 4.660816192626953, | |
| "learning_rate": 3.7112423539337696e-05, | |
| "loss": 0.06137389659881592, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_accuracy": 0.9792204696253327, | |
| "eval_f1": 0.8985579313774242, | |
| "eval_loss": 0.0853828489780426, | |
| "eval_precision": 0.8852057478772044, | |
| "eval_recall": 0.912319084483339, | |
| "eval_runtime": 16.3062, | |
| "eval_samples_per_second": 199.311, | |
| "eval_steps_per_second": 24.96, | |
| "step": 1756 | |
| }, | |
| { | |
| "epoch": 1.0250569476082005, | |
| "grad_norm": 4.244996070861816, | |
| "learning_rate": 3.658510862687197e-05, | |
| "loss": 0.08307218551635742, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.0535307517084282, | |
| "grad_norm": 0.8549637794494629, | |
| "learning_rate": 3.605779371440625e-05, | |
| "loss": 0.04152585983276367, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.082004555808656, | |
| "grad_norm": 0.12734612822532654, | |
| "learning_rate": 3.553047880194052e-05, | |
| "loss": 0.06275240421295165, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.1104783599088839, | |
| "grad_norm": 0.20831361413002014, | |
| "learning_rate": 3.5003163889474796e-05, | |
| "loss": 0.049036874771118164, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.1389521640091116, | |
| "grad_norm": 5.43148136138916, | |
| "learning_rate": 3.447584897700907e-05, | |
| "loss": 0.03665179252624512, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.1674259681093395, | |
| "grad_norm": 8.092423439025879, | |
| "learning_rate": 3.394853406454335e-05, | |
| "loss": 0.060383148193359375, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 1.1958997722095672, | |
| "grad_norm": 0.1143074557185173, | |
| "learning_rate": 3.342121915207762e-05, | |
| "loss": 0.04986677646636963, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.224373576309795, | |
| "grad_norm": 1.1334632635116577, | |
| "learning_rate": 3.2893904239611903e-05, | |
| "loss": 0.04261885643005371, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 1.2528473804100229, | |
| "grad_norm": 2.409695863723755, | |
| "learning_rate": 3.2366589327146174e-05, | |
| "loss": 0.02984976053237915, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.2813211845102506, | |
| "grad_norm": 0.023305846378207207, | |
| "learning_rate": 3.183927441468045e-05, | |
| "loss": 0.02986645221710205, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 1.3097949886104785, | |
| "grad_norm": 1.741888165473938, | |
| "learning_rate": 3.131195950221472e-05, | |
| "loss": 0.060981402397155764, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.3382687927107062, | |
| "grad_norm": 0.6020044684410095, | |
| "learning_rate": 3.0784644589749004e-05, | |
| "loss": 0.03794198751449585, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 1.366742596810934, | |
| "grad_norm": 0.08001784235239029, | |
| "learning_rate": 3.0257329677283274e-05, | |
| "loss": 0.03673994779586792, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.3952164009111616, | |
| "grad_norm": 0.02995702251791954, | |
| "learning_rate": 2.9730014764817547e-05, | |
| "loss": 0.044854021072387694, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 1.4236902050113895, | |
| "grad_norm": 0.1147884801030159, | |
| "learning_rate": 2.9202699852351828e-05, | |
| "loss": 0.047550201416015625, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.4521640091116172, | |
| "grad_norm": 0.69696444272995, | |
| "learning_rate": 2.86753849398861e-05, | |
| "loss": 0.049544329643249514, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 1.4806378132118452, | |
| "grad_norm": 0.4860750436782837, | |
| "learning_rate": 2.8148070027420375e-05, | |
| "loss": 0.03159741163253784, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.5091116173120729, | |
| "grad_norm": 0.16090558469295502, | |
| "learning_rate": 2.7620755114954648e-05, | |
| "loss": 0.0480596923828125, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 1.5375854214123006, | |
| "grad_norm": 0.7413948774337769, | |
| "learning_rate": 2.7093440202488928e-05, | |
| "loss": 0.050900745391845706, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.5660592255125285, | |
| "grad_norm": 0.39893922209739685, | |
| "learning_rate": 2.65661252900232e-05, | |
| "loss": 0.04174707412719727, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 1.5945330296127562, | |
| "grad_norm": 0.12018123269081116, | |
| "learning_rate": 2.6038810377557475e-05, | |
| "loss": 0.041312184333801266, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.6230068337129842, | |
| "grad_norm": 0.47460970282554626, | |
| "learning_rate": 2.5511495465091755e-05, | |
| "loss": 0.04030419826507568, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 1.6514806378132119, | |
| "grad_norm": 1.4622207880020142, | |
| "learning_rate": 2.498418055262603e-05, | |
| "loss": 0.038981842994689944, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.6799544419134396, | |
| "grad_norm": 0.041533201932907104, | |
| "learning_rate": 2.4456865640160302e-05, | |
| "loss": 0.040003185272216794, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 1.7084282460136673, | |
| "grad_norm": 0.4670565724372864, | |
| "learning_rate": 2.392955072769458e-05, | |
| "loss": 0.02680367946624756, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.7369020501138952, | |
| "grad_norm": 0.12279506027698517, | |
| "learning_rate": 2.3402235815228856e-05, | |
| "loss": 0.017171299457550047, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 1.7653758542141231, | |
| "grad_norm": 1.5912784337997437, | |
| "learning_rate": 2.287492090276313e-05, | |
| "loss": 0.040563864707946776, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.7938496583143508, | |
| "grad_norm": 0.5954166650772095, | |
| "learning_rate": 2.2347605990297406e-05, | |
| "loss": 0.03170608520507812, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 1.8223234624145785, | |
| "grad_norm": 0.18454942107200623, | |
| "learning_rate": 2.182029107783168e-05, | |
| "loss": 0.04065796375274658, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.8507972665148062, | |
| "grad_norm": 1.792156457901001, | |
| "learning_rate": 2.1292976165365956e-05, | |
| "loss": 0.043567652702331545, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 1.8792710706150342, | |
| "grad_norm": 3.5496325492858887, | |
| "learning_rate": 2.0765661252900233e-05, | |
| "loss": 0.04890557765960693, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.907744874715262, | |
| "grad_norm": 2.243587017059326, | |
| "learning_rate": 2.0238346340434507e-05, | |
| "loss": 0.02435559272766113, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 1.9362186788154898, | |
| "grad_norm": 0.041429150849580765, | |
| "learning_rate": 1.9711031427968783e-05, | |
| "loss": 0.022826697826385498, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.9646924829157175, | |
| "grad_norm": 0.40412697196006775, | |
| "learning_rate": 1.918371651550306e-05, | |
| "loss": 0.028880558013916015, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 1.9931662870159452, | |
| "grad_norm": 1.1296610832214355, | |
| "learning_rate": 1.8656401603037334e-05, | |
| "loss": 0.020482330322265624, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_accuracy": 0.985113962943833, | |
| "eval_f1": 0.9321198964682308, | |
| "eval_loss": 0.06826692074537277, | |
| "eval_precision": 0.9249378624689313, | |
| "eval_recall": 0.9394143386065298, | |
| "eval_runtime": 13.3568, | |
| "eval_samples_per_second": 243.322, | |
| "eval_steps_per_second": 30.471, | |
| "step": 3512 | |
| }, | |
| { | |
| "epoch": 2.021640091116173, | |
| "grad_norm": 0.9621429443359375, | |
| "learning_rate": 1.812908669057161e-05, | |
| "loss": 0.019875452518463135, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 2.050113895216401, | |
| "grad_norm": 0.0837482139468193, | |
| "learning_rate": 1.7601771778105884e-05, | |
| "loss": 0.008889197707176208, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.078587699316629, | |
| "grad_norm": 0.19263038039207458, | |
| "learning_rate": 1.707445686564016e-05, | |
| "loss": 0.014765473604202271, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 2.1070615034168565, | |
| "grad_norm": 0.0060101840645074844, | |
| "learning_rate": 1.6547141953174438e-05, | |
| "loss": 0.007849201560020447, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.135535307517084, | |
| "grad_norm": 0.1244562640786171, | |
| "learning_rate": 1.601982704070871e-05, | |
| "loss": 0.01726690411567688, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 2.164009111617312, | |
| "grad_norm": 0.109648697078228, | |
| "learning_rate": 1.5492512128242988e-05, | |
| "loss": 0.012216633558273316, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.19248291571754, | |
| "grad_norm": 0.1934421807527542, | |
| "learning_rate": 1.4965197215777263e-05, | |
| "loss": 0.010779581069946288, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 2.2209567198177678, | |
| "grad_norm": 0.425420880317688, | |
| "learning_rate": 1.443788230331154e-05, | |
| "loss": 0.011902832984924316, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.2494305239179955, | |
| "grad_norm": 0.25650277733802795, | |
| "learning_rate": 1.3910567390845813e-05, | |
| "loss": 0.01777989387512207, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 2.277904328018223, | |
| "grad_norm": 7.346250534057617, | |
| "learning_rate": 1.338325247838009e-05, | |
| "loss": 0.015151877403259278, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.306378132118451, | |
| "grad_norm": 0.4072627127170563, | |
| "learning_rate": 1.2855937565914363e-05, | |
| "loss": 0.013375531435012817, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 2.334851936218679, | |
| "grad_norm": 0.08192279189825058, | |
| "learning_rate": 1.232862265344864e-05, | |
| "loss": 0.01477469563484192, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.3633257403189067, | |
| "grad_norm": 0.08017744868993759, | |
| "learning_rate": 1.1801307740982915e-05, | |
| "loss": 0.015454013347625733, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 2.3917995444191344, | |
| "grad_norm": 0.013294419273734093, | |
| "learning_rate": 1.127399282851719e-05, | |
| "loss": 0.011264841556549072, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.420273348519362, | |
| "grad_norm": 8.798260688781738, | |
| "learning_rate": 1.0746677916051466e-05, | |
| "loss": 0.009926987290382385, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 2.44874715261959, | |
| "grad_norm": 0.02044219709932804, | |
| "learning_rate": 1.021936300358574e-05, | |
| "loss": 0.007129186391830444, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.477220956719818, | |
| "grad_norm": 0.004201766103506088, | |
| "learning_rate": 9.692048091120018e-06, | |
| "loss": 0.003962487280368805, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 2.5056947608200457, | |
| "grad_norm": 0.002541273133829236, | |
| "learning_rate": 9.164733178654293e-06, | |
| "loss": 0.019802603721618652, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.5341685649202734, | |
| "grad_norm": 0.09866471588611603, | |
| "learning_rate": 8.637418266188568e-06, | |
| "loss": 0.008758165240287781, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 2.562642369020501, | |
| "grad_norm": 0.025510091334581375, | |
| "learning_rate": 8.110103353722843e-06, | |
| "loss": 0.013702048063278198, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.591116173120729, | |
| "grad_norm": 0.06137232854962349, | |
| "learning_rate": 7.582788441257119e-06, | |
| "loss": 0.020511729717254637, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 2.619589977220957, | |
| "grad_norm": 0.03561195358633995, | |
| "learning_rate": 7.055473528791394e-06, | |
| "loss": 0.006835119724273682, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.6480637813211843, | |
| "grad_norm": 0.12753430008888245, | |
| "learning_rate": 6.528158616325671e-06, | |
| "loss": 0.016694604158401488, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 2.6765375854214124, | |
| "grad_norm": 0.11613287031650543, | |
| "learning_rate": 6.000843703859946e-06, | |
| "loss": 0.008856379985809326, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.70501138952164, | |
| "grad_norm": 0.024386335164308548, | |
| "learning_rate": 5.473528791394221e-06, | |
| "loss": 0.019774538278579713, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 2.733485193621868, | |
| "grad_norm": 0.0066336095333099365, | |
| "learning_rate": 4.946213878928496e-06, | |
| "loss": 0.007424172759056091, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.7619589977220955, | |
| "grad_norm": 0.346383661031723, | |
| "learning_rate": 4.418898966462772e-06, | |
| "loss": 0.011786254644393921, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 2.7904328018223232, | |
| "grad_norm": 4.314459323883057, | |
| "learning_rate": 3.891584053997047e-06, | |
| "loss": 0.02354264497756958, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.8189066059225514, | |
| "grad_norm": 0.010090876370668411, | |
| "learning_rate": 3.3642691415313225e-06, | |
| "loss": 0.01016837239265442, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 2.847380410022779, | |
| "grad_norm": 0.03358423337340355, | |
| "learning_rate": 2.836954229065598e-06, | |
| "loss": 0.02623087167739868, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.875854214123007, | |
| "grad_norm": 1.0688987970352173, | |
| "learning_rate": 2.3096393165998736e-06, | |
| "loss": 0.01581504225730896, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 2.9043280182232345, | |
| "grad_norm": 0.038196414709091187, | |
| "learning_rate": 1.782324404134149e-06, | |
| "loss": 0.007836873531341553, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.932801822323462, | |
| "grad_norm": 1.5274938344955444, | |
| "learning_rate": 1.2550094916684245e-06, | |
| "loss": 0.008381766080856324, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 2.9612756264236904, | |
| "grad_norm": 7.337849140167236, | |
| "learning_rate": 7.276945792026999e-07, | |
| "loss": 0.012459511756896973, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.989749430523918, | |
| "grad_norm": 0.03858187794685364, | |
| "learning_rate": 2.0037966673697531e-07, | |
| "loss": 0.018138412237167358, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_accuracy": 0.9870740461149298, | |
| "eval_f1": 0.9415502968475625, | |
| "eval_loss": 0.06246870011091232, | |
| "eval_precision": 0.9356822336712648, | |
| "eval_recall": 0.9474924267923258, | |
| "eval_runtime": 13.2725, | |
| "eval_samples_per_second": 244.868, | |
| "eval_steps_per_second": 30.665, | |
| "step": 5268 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 5268, | |
| "total_flos": 1376902220737806.0, | |
| "train_loss": 0.09179677247107255, | |
| "train_runtime": 679.9594, | |
| "train_samples_per_second": 61.949, | |
| "train_steps_per_second": 7.748 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "step": 5268, | |
| "test_accuracy": 0.9711330077729939, | |
| "test_f1": 0.885148687538153, | |
| "test_loss": 0.18729883432388306, | |
| "test_precision": 0.8721429798934525, | |
| "test_recall": 0.8985481586402266, | |
| "test_runtime": 15.1489, | |
| "test_samples_per_second": 227.938, | |
| "test_steps_per_second": 28.517 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 5268, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1376902220737806.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |