| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1357658039881205, | |
| "eval_steps": 100, | |
| "global_step": 400, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00033941450997030124, | |
| "eval_loss": 1.0783847570419312, | |
| "eval_runtime": 44.9561, | |
| "eval_samples_per_second": 27.605, | |
| "eval_steps_per_second": 13.813, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0016970725498515061, | |
| "grad_norm": 0.1010773554444313, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.0131, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0033941450997030122, | |
| "grad_norm": 0.16712668538093567, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.0535, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005091217649554518, | |
| "grad_norm": 0.18495769798755646, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0728, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0067882901994060245, | |
| "grad_norm": 0.1742364764213562, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.0827, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00848536274925753, | |
| "grad_norm": 0.11210238933563232, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.0162, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.010182435299109036, | |
| "grad_norm": 0.11551474034786224, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0265, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011879507848960543, | |
| "grad_norm": 0.12017826735973358, | |
| "learning_rate": 9.995494831023409e-05, | |
| "loss": 0.9762, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.013576580398812049, | |
| "grad_norm": 0.11704757809638977, | |
| "learning_rate": 9.981987442712633e-05, | |
| "loss": 0.9976, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.015273652948663556, | |
| "grad_norm": 0.13527105748653412, | |
| "learning_rate": 9.959502176294383e-05, | |
| "loss": 0.9852, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.01697072549851506, | |
| "grad_norm": 0.14121846854686737, | |
| "learning_rate": 9.928079551738543e-05, | |
| "loss": 0.9254, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.018667798048366567, | |
| "grad_norm": 0.10977321863174438, | |
| "learning_rate": 9.887776194738432e-05, | |
| "loss": 0.9057, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.020364870598218072, | |
| "grad_norm": 0.10828328132629395, | |
| "learning_rate": 9.838664734667495e-05, | |
| "loss": 0.9088, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.02206194314806958, | |
| "grad_norm": 0.11655944585800171, | |
| "learning_rate": 9.780833673696254e-05, | |
| "loss": 0.9398, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.023759015697921087, | |
| "grad_norm": 0.12264937162399292, | |
| "learning_rate": 9.714387227305422e-05, | |
| "loss": 0.9248, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.025456088247772592, | |
| "grad_norm": 0.11704964190721512, | |
| "learning_rate": 9.639445136482548e-05, | |
| "loss": 0.959, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.027153160797624098, | |
| "grad_norm": 0.11848966777324677, | |
| "learning_rate": 9.55614245194068e-05, | |
| "loss": 0.9352, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.028850233347475603, | |
| "grad_norm": 0.12205510586500168, | |
| "learning_rate": 9.464629290747842e-05, | |
| "loss": 0.9375, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.030547305897327112, | |
| "grad_norm": 0.12488099932670593, | |
| "learning_rate": 9.365070565805941e-05, | |
| "loss": 0.9028, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.03224437844717862, | |
| "grad_norm": 0.13809776306152344, | |
| "learning_rate": 9.257645688666556e-05, | |
| "loss": 0.8989, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.03394145099703012, | |
| "grad_norm": 0.15688276290893555, | |
| "learning_rate": 9.142548246219212e-05, | |
| "loss": 0.9198, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03394145099703012, | |
| "eval_loss": 0.9021005034446716, | |
| "eval_runtime": 44.9924, | |
| "eval_samples_per_second": 27.582, | |
| "eval_steps_per_second": 13.802, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.03563852354688163, | |
| "grad_norm": 0.11339419335126877, | |
| "learning_rate": 9.019985651834703e-05, | |
| "loss": 0.8167, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.037335596096733134, | |
| "grad_norm": 0.12288001924753189, | |
| "learning_rate": 8.890178771592199e-05, | |
| "loss": 0.8914, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.03903266864658464, | |
| "grad_norm": 0.11485109478235245, | |
| "learning_rate": 8.753361526263621e-05, | |
| "loss": 0.8693, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.040729741196436145, | |
| "grad_norm": 0.1271563172340393, | |
| "learning_rate": 8.609780469772623e-05, | |
| "loss": 0.9041, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.04242681374628765, | |
| "grad_norm": 0.1423531323671341, | |
| "learning_rate": 8.459694344887732e-05, | |
| "loss": 0.9286, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.04412388629613916, | |
| "grad_norm": 0.13821588456630707, | |
| "learning_rate": 8.303373616950408e-05, | |
| "loss": 0.9031, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.04582095884599067, | |
| "grad_norm": 0.13980436325073242, | |
| "learning_rate": 8.141099986478212e-05, | |
| "loss": 0.9131, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.047518031395842174, | |
| "grad_norm": 0.1347670555114746, | |
| "learning_rate": 7.973165881521434e-05, | |
| "loss": 0.8773, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.04921510394569368, | |
| "grad_norm": 0.14950723946094513, | |
| "learning_rate": 7.799873930687978e-05, | |
| "loss": 0.8948, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.050912176495545185, | |
| "grad_norm": 0.18788067996501923, | |
| "learning_rate": 7.621536417786159e-05, | |
| "loss": 0.8823, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.05260924904539669, | |
| "grad_norm": 0.1297345906496048, | |
| "learning_rate": 7.438474719068173e-05, | |
| "loss": 0.8322, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.054306321595248196, | |
| "grad_norm": 0.13188786804676056, | |
| "learning_rate": 7.251018724088367e-05, | |
| "loss": 0.8435, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0560033941450997, | |
| "grad_norm": 0.1300618201494217, | |
| "learning_rate": 7.059506241219965e-05, | |
| "loss": 0.8863, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.05770046669495121, | |
| "grad_norm": 0.13592050969600677, | |
| "learning_rate": 6.864282388901544e-05, | |
| "loss": 0.9136, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.05939753924480271, | |
| "grad_norm": 0.13553154468536377, | |
| "learning_rate": 6.665698973710288e-05, | |
| "loss": 0.8958, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.061094611794654224, | |
| "grad_norm": 0.13615025579929352, | |
| "learning_rate": 6.464113856382752e-05, | |
| "loss": 0.8792, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.06279168434450573, | |
| "grad_norm": 0.15309178829193115, | |
| "learning_rate": 6.259890306925627e-05, | |
| "loss": 0.895, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.06448875689435724, | |
| "grad_norm": 0.15061669051647186, | |
| "learning_rate": 6.0533963499786314e-05, | |
| "loss": 0.9012, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.06618582944420874, | |
| "grad_norm": 0.1602875143289566, | |
| "learning_rate": 5.8450041016092464e-05, | |
| "loss": 0.8835, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.06788290199406025, | |
| "grad_norm": 0.1957070380449295, | |
| "learning_rate": 5.6350890987343944e-05, | |
| "loss": 0.9218, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06788290199406025, | |
| "eval_loss": 0.8846060037612915, | |
| "eval_runtime": 45.0393, | |
| "eval_samples_per_second": 27.554, | |
| "eval_steps_per_second": 13.788, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.06957997454391175, | |
| "grad_norm": 0.1319158971309662, | |
| "learning_rate": 5.4240296223775465e-05, | |
| "loss": 0.8126, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.07127704709376326, | |
| "grad_norm": 0.13598619401454926, | |
| "learning_rate": 5.212206015980742e-05, | |
| "loss": 0.8657, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.07297411964361476, | |
| "grad_norm": 0.14428776502609253, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8644, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.07467119219346627, | |
| "grad_norm": 0.1368338167667389, | |
| "learning_rate": 4.78779398401926e-05, | |
| "loss": 0.8273, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.07636826474331777, | |
| "grad_norm": 0.14459089934825897, | |
| "learning_rate": 4.575970377622456e-05, | |
| "loss": 0.8976, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.07806533729316928, | |
| "grad_norm": 0.16228264570236206, | |
| "learning_rate": 4.364910901265606e-05, | |
| "loss": 0.8903, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.07976240984302078, | |
| "grad_norm": 0.16205894947052002, | |
| "learning_rate": 4.1549958983907555e-05, | |
| "loss": 0.8889, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 0.08145948239287229, | |
| "grad_norm": 0.17543725669384003, | |
| "learning_rate": 3.94660365002137e-05, | |
| "loss": 0.8785, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.0831565549427238, | |
| "grad_norm": 0.17680653929710388, | |
| "learning_rate": 3.740109693074375e-05, | |
| "loss": 0.8956, | |
| "step": 245 | |
| }, | |
| { | |
| "epoch": 0.0848536274925753, | |
| "grad_norm": 0.20075836777687073, | |
| "learning_rate": 3.5358861436172485e-05, | |
| "loss": 0.8945, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.08655070004242682, | |
| "grad_norm": 0.13078618049621582, | |
| "learning_rate": 3.334301026289712e-05, | |
| "loss": 0.8476, | |
| "step": 255 | |
| }, | |
| { | |
| "epoch": 0.08824777259227833, | |
| "grad_norm": 0.137261301279068, | |
| "learning_rate": 3.135717611098458e-05, | |
| "loss": 0.8548, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.08994484514212983, | |
| "grad_norm": 0.1424454301595688, | |
| "learning_rate": 2.9404937587800375e-05, | |
| "loss": 0.8593, | |
| "step": 265 | |
| }, | |
| { | |
| "epoch": 0.09164191769198134, | |
| "grad_norm": 0.14868776500225067, | |
| "learning_rate": 2.748981275911633e-05, | |
| "loss": 0.8754, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.09333899024183284, | |
| "grad_norm": 0.15813228487968445, | |
| "learning_rate": 2.5615252809318284e-05, | |
| "loss": 0.9024, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 0.09503606279168435, | |
| "grad_norm": 0.154763862490654, | |
| "learning_rate": 2.3784635822138424e-05, | |
| "loss": 0.8658, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.09673313534153585, | |
| "grad_norm": 0.15902037918567657, | |
| "learning_rate": 2.2001260693120233e-05, | |
| "loss": 0.8618, | |
| "step": 285 | |
| }, | |
| { | |
| "epoch": 0.09843020789138736, | |
| "grad_norm": 0.16416916251182556, | |
| "learning_rate": 2.026834118478567e-05, | |
| "loss": 0.8884, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.10012728044123886, | |
| "grad_norm": 0.17667396366596222, | |
| "learning_rate": 1.858900013521788e-05, | |
| "loss": 0.886, | |
| "step": 295 | |
| }, | |
| { | |
| "epoch": 0.10182435299109037, | |
| "grad_norm": 0.2230517417192459, | |
| "learning_rate": 1.6966263830495936e-05, | |
| "loss": 0.8466, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10182435299109037, | |
| "eval_loss": 0.8769205808639526, | |
| "eval_runtime": 44.971, | |
| "eval_samples_per_second": 27.596, | |
| "eval_steps_per_second": 13.809, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.10352142554094187, | |
| "grad_norm": 0.13488075137138367, | |
| "learning_rate": 1.5403056551122697e-05, | |
| "loss": 0.828, | |
| "step": 305 | |
| }, | |
| { | |
| "epoch": 0.10521849809079338, | |
| "grad_norm": 0.13659627735614777, | |
| "learning_rate": 1.3902195302273779e-05, | |
| "loss": 0.8685, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.10691557064064489, | |
| "grad_norm": 0.1448042243719101, | |
| "learning_rate": 1.246638473736378e-05, | |
| "loss": 0.8928, | |
| "step": 315 | |
| }, | |
| { | |
| "epoch": 0.10861264319049639, | |
| "grad_norm": 0.16210302710533142, | |
| "learning_rate": 1.1098212284078036e-05, | |
| "loss": 0.8782, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.1103097157403479, | |
| "grad_norm": 0.16703711450099945, | |
| "learning_rate": 9.800143481652979e-06, | |
| "loss": 0.8806, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 0.1120067882901994, | |
| "grad_norm": 0.1568247526884079, | |
| "learning_rate": 8.574517537807897e-06, | |
| "loss": 0.8889, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.11370386084005091, | |
| "grad_norm": 0.15522243082523346, | |
| "learning_rate": 7.423543113334436e-06, | |
| "loss": 0.8875, | |
| "step": 335 | |
| }, | |
| { | |
| "epoch": 0.11540093338990241, | |
| "grad_norm": 0.15694765746593475, | |
| "learning_rate": 6.349294341940593e-06, | |
| "loss": 0.8936, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.11709800593975392, | |
| "grad_norm": 0.16879591345787048, | |
| "learning_rate": 5.353707092521582e-06, | |
| "loss": 0.8803, | |
| "step": 345 | |
| }, | |
| { | |
| "epoch": 0.11879507848960542, | |
| "grad_norm": 0.21898403763771057, | |
| "learning_rate": 4.43857548059321e-06, | |
| "loss": 0.8808, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.12049215103945694, | |
| "grad_norm": 0.14227333664894104, | |
| "learning_rate": 3.605548635174533e-06, | |
| "loss": 0.8426, | |
| "step": 355 | |
| }, | |
| { | |
| "epoch": 0.12218922358930845, | |
| "grad_norm": 0.13415607810020447, | |
| "learning_rate": 2.85612772694579e-06, | |
| "loss": 0.8488, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.12388629613915995, | |
| "grad_norm": 0.1472204476594925, | |
| "learning_rate": 2.191663263037458e-06, | |
| "loss": 0.8659, | |
| "step": 365 | |
| }, | |
| { | |
| "epoch": 0.12558336868901146, | |
| "grad_norm": 0.14583653211593628, | |
| "learning_rate": 1.6133526533250565e-06, | |
| "loss": 0.8837, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.12728044123886295, | |
| "grad_norm": 0.1621737778186798, | |
| "learning_rate": 1.1222380526156928e-06, | |
| "loss": 0.9043, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 0.12897751378871447, | |
| "grad_norm": 0.16353023052215576, | |
| "learning_rate": 7.192044826145771e-07, | |
| "loss": 0.8725, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.13067458633856596, | |
| "grad_norm": 0.16524522006511688, | |
| "learning_rate": 4.049782370561583e-07, | |
| "loss": 0.8853, | |
| "step": 385 | |
| }, | |
| { | |
| "epoch": 0.13237165888841748, | |
| "grad_norm": 0.1743895709514618, | |
| "learning_rate": 1.8012557287367392e-07, | |
| "loss": 0.8803, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.13406873143826897, | |
| "grad_norm": 0.1702079176902771, | |
| "learning_rate": 4.5051689765929214e-08, | |
| "loss": 0.883, | |
| "step": 395 | |
| }, | |
| { | |
| "epoch": 0.1357658039881205, | |
| "grad_norm": 0.2783662676811218, | |
| "learning_rate": 0.0, | |
| "loss": 0.8893, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.1357658039881205, | |
| "eval_loss": 0.875480592250824, | |
| "eval_runtime": 45.0476, | |
| "eval_samples_per_second": 27.549, | |
| "eval_steps_per_second": 13.785, | |
| "step": 400 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 400, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 3.325887333059789e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |