| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9991537376586743, | |
| "eval_steps": 500, | |
| "global_step": 1329, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.022566995768688293, | |
| "grad_norm": 1.1096520316172054, | |
| "learning_rate": 5e-06, | |
| "loss": 0.744, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.045133991537376586, | |
| "grad_norm": 0.9122978446333387, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6807, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06770098730606489, | |
| "grad_norm": 0.6346075490211303, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6632, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09026798307475317, | |
| "grad_norm": 0.644158557259213, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6406, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11283497884344147, | |
| "grad_norm": 0.7926751486847664, | |
| "learning_rate": 5e-06, | |
| "loss": 0.634, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.13540197461212977, | |
| "grad_norm": 0.6355148794198717, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6334, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.15796897038081806, | |
| "grad_norm": 0.7184290150899074, | |
| "learning_rate": 5e-06, | |
| "loss": 0.629, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.18053596614950634, | |
| "grad_norm": 0.8485255099309241, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6308, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.20310296191819463, | |
| "grad_norm": 0.907415069912097, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6284, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.22566995768688294, | |
| "grad_norm": 0.6791580454456693, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6275, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.24823695345557123, | |
| "grad_norm": 0.5868952135190455, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6181, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.27080394922425954, | |
| "grad_norm": 0.7185283136864035, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6174, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2933709449929478, | |
| "grad_norm": 0.6793470563217162, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6187, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.3159379407616361, | |
| "grad_norm": 0.6866370437838811, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6136, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3385049365303244, | |
| "grad_norm": 0.7624542009212121, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6139, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.3610719322990127, | |
| "grad_norm": 0.5670049736454741, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6158, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.383638928067701, | |
| "grad_norm": 0.674515645964626, | |
| "learning_rate": 5e-06, | |
| "loss": 0.612, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.40620592383638926, | |
| "grad_norm": 0.6395111816709952, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6087, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.4287729196050776, | |
| "grad_norm": 0.7228729780890316, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6034, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.4513399153737659, | |
| "grad_norm": 0.6359367979025581, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6099, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.47390691114245415, | |
| "grad_norm": 0.5529928726958753, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6063, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.49647390691114246, | |
| "grad_norm": 0.7203121657077105, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5981, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.5190409026798307, | |
| "grad_norm": 0.5884566138797194, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6069, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.5416078984485191, | |
| "grad_norm": 0.5680258676280858, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6057, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.5641748942172073, | |
| "grad_norm": 0.5976334720348693, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5999, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.5867418899858956, | |
| "grad_norm": 0.7322668494196893, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6026, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.609308885754584, | |
| "grad_norm": 0.5581559480474937, | |
| "learning_rate": 5e-06, | |
| "loss": 0.598, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.6318758815232722, | |
| "grad_norm": 0.5458883179876004, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6045, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.6544428772919605, | |
| "grad_norm": 0.6056045571233394, | |
| "learning_rate": 5e-06, | |
| "loss": 0.598, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.6770098730606487, | |
| "grad_norm": 0.6222844032859247, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6041, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.6995768688293371, | |
| "grad_norm": 0.5534363061428031, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5973, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.7221438645980254, | |
| "grad_norm": 0.6988575619337959, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6006, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.7447108603667136, | |
| "grad_norm": 0.5794083927351209, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5963, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.767277856135402, | |
| "grad_norm": 0.6122372451743079, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5957, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.7898448519040903, | |
| "grad_norm": 0.7493879285669082, | |
| "learning_rate": 5e-06, | |
| "loss": 0.597, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.8124118476727785, | |
| "grad_norm": 0.5603389574893285, | |
| "learning_rate": 5e-06, | |
| "loss": 0.596, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.8349788434414669, | |
| "grad_norm": 0.5972337008615317, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6031, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.8575458392101551, | |
| "grad_norm": 0.6488471089146787, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5999, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.8801128349788434, | |
| "grad_norm": 0.5813626386687312, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5938, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.9026798307475318, | |
| "grad_norm": 0.5316271715903418, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5961, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.92524682651622, | |
| "grad_norm": 0.6048061064813547, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5941, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.9478138222849083, | |
| "grad_norm": 0.5936532217112329, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5947, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.9703808180535967, | |
| "grad_norm": 0.574531708859424, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5888, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.9929478138222849, | |
| "grad_norm": 0.6711323560467252, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5936, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.9997179125528914, | |
| "eval_loss": 0.5913681387901306, | |
| "eval_runtime": 697.6116, | |
| "eval_samples_per_second": 17.117, | |
| "eval_steps_per_second": 0.536, | |
| "step": 443 | |
| }, | |
| { | |
| "epoch": 1.0155148095909732, | |
| "grad_norm": 0.7268447078847582, | |
| "learning_rate": 5e-06, | |
| "loss": 0.6006, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 1.0380818053596614, | |
| "grad_norm": 0.5732383250485011, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5274, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 1.0606488011283497, | |
| "grad_norm": 0.6051041162305182, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5421, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 1.0832157968970382, | |
| "grad_norm": 0.5731582423193028, | |
| "learning_rate": 5e-06, | |
| "loss": 0.53, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 1.1057827926657264, | |
| "grad_norm": 0.6128630592519895, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5401, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 1.1283497884344147, | |
| "grad_norm": 0.5904141940083983, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5387, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 1.150916784203103, | |
| "grad_norm": 0.7022917090539815, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5399, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 1.1734837799717912, | |
| "grad_norm": 0.5731738347454584, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5324, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 1.1960507757404795, | |
| "grad_norm": 0.7246031496920289, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5387, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 1.2186177715091677, | |
| "grad_norm": 0.5696614848674469, | |
| "learning_rate": 5e-06, | |
| "loss": 0.536, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.2411847672778562, | |
| "grad_norm": 0.6542521164361487, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5408, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 1.2637517630465445, | |
| "grad_norm": 0.6706655302808069, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5427, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 1.2863187588152327, | |
| "grad_norm": 0.5713802367676806, | |
| "learning_rate": 5e-06, | |
| "loss": 0.54, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 1.308885754583921, | |
| "grad_norm": 0.5720250086292773, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5398, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 1.3314527503526092, | |
| "grad_norm": 0.5519092322076451, | |
| "learning_rate": 5e-06, | |
| "loss": 0.54, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 1.3540197461212977, | |
| "grad_norm": 0.6061004913438247, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5453, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 1.376586741889986, | |
| "grad_norm": 0.54008499279403, | |
| "learning_rate": 5e-06, | |
| "loss": 0.538, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 1.3991537376586742, | |
| "grad_norm": 0.5739979207854969, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5422, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 1.4217207334273625, | |
| "grad_norm": 0.5474321427386326, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5404, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 1.4442877291960508, | |
| "grad_norm": 0.6486717244236897, | |
| "learning_rate": 5e-06, | |
| "loss": 0.54, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 1.466854724964739, | |
| "grad_norm": 0.5674328769717695, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5409, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 1.4894217207334273, | |
| "grad_norm": 0.6437778353374325, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5447, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 1.5119887165021155, | |
| "grad_norm": 0.5740743217989274, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5393, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 1.5345557122708038, | |
| "grad_norm": 0.5530367304846456, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5336, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 1.5571227080394923, | |
| "grad_norm": 0.5896556944460669, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5357, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 1.5796897038081805, | |
| "grad_norm": 0.5702119466199734, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5399, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 1.6022566995768688, | |
| "grad_norm": 0.5457633328629294, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5427, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 1.6248236953455573, | |
| "grad_norm": 0.5813985653049328, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5507, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 1.6473906911142455, | |
| "grad_norm": 0.5773592052172303, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5339, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 1.6699576868829338, | |
| "grad_norm": 0.7024422394795109, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5498, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 1.692524682651622, | |
| "grad_norm": 0.6198371019281352, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5412, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 1.7150916784203103, | |
| "grad_norm": 0.6206766376942175, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5402, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 1.7376586741889986, | |
| "grad_norm": 0.8876798469818571, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5414, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 1.7602256699576868, | |
| "grad_norm": 0.6454735529692549, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5367, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 1.782792665726375, | |
| "grad_norm": 0.5640065520091834, | |
| "learning_rate": 5e-06, | |
| "loss": 0.54, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 1.8053596614950633, | |
| "grad_norm": 0.6437842162195886, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5351, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 1.8279266572637518, | |
| "grad_norm": 0.5364569494187976, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5458, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 1.85049365303244, | |
| "grad_norm": 0.6372467429532644, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5332, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 1.8730606488011283, | |
| "grad_norm": 0.5667642300890294, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5453, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 1.8956276445698168, | |
| "grad_norm": 0.6292324542663285, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5454, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 1.918194640338505, | |
| "grad_norm": 0.5359738824194854, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5334, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 1.9407616361071933, | |
| "grad_norm": 0.6110789865963517, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5384, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 1.9633286318758816, | |
| "grad_norm": 0.6818169983817923, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5449, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 1.9858956276445698, | |
| "grad_norm": 0.607679292904791, | |
| "learning_rate": 5e-06, | |
| "loss": 0.5431, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 1.9994358251057829, | |
| "eval_loss": 0.587314784526825, | |
| "eval_runtime": 695.4072, | |
| "eval_samples_per_second": 17.171, | |
| "eval_steps_per_second": 0.538, | |
| "step": 886 | |
| }, | |
| { | |
| "epoch": 2.008462623413258, | |
| "grad_norm": 1.0551195477645454, | |
| "learning_rate": 5e-06, | |
| "loss": 0.567, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 2.0310296191819464, | |
| "grad_norm": 0.6627990985792488, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4782, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 2.0535966149506346, | |
| "grad_norm": 0.6383666257677532, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4798, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 2.076163610719323, | |
| "grad_norm": 0.6389368523448007, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4721, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 2.098730606488011, | |
| "grad_norm": 0.5722750118689505, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4792, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 2.1212976022566994, | |
| "grad_norm": 0.6088961879653472, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4833, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 2.143864598025388, | |
| "grad_norm": 0.6394884138596829, | |
| "learning_rate": 5e-06, | |
| "loss": 0.485, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 2.1664315937940763, | |
| "grad_norm": 0.6101358628155096, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4811, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 2.1889985895627646, | |
| "grad_norm": 0.7097822402886351, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4792, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 2.211565585331453, | |
| "grad_norm": 0.6513094055573179, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4741, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 2.234132581100141, | |
| "grad_norm": 0.6185979196999992, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4741, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 2.2566995768688294, | |
| "grad_norm": 0.5898104504895565, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4829, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 2.2792665726375176, | |
| "grad_norm": 0.6044370773906275, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4892, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 2.301833568406206, | |
| "grad_norm": 0.7060015814845905, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4835, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 2.324400564174894, | |
| "grad_norm": 0.6277702807897904, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4877, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 2.3469675599435824, | |
| "grad_norm": 0.7014468153576923, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4857, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 2.3695345557122707, | |
| "grad_norm": 0.5979537329375223, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4836, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 2.392101551480959, | |
| "grad_norm": 0.5724278822524301, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4827, | |
| "step": 1060 | |
| }, | |
| { | |
| "epoch": 2.414668547249647, | |
| "grad_norm": 0.6094804305902596, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4839, | |
| "step": 1070 | |
| }, | |
| { | |
| "epoch": 2.4372355430183354, | |
| "grad_norm": 0.6584799733332577, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4872, | |
| "step": 1080 | |
| }, | |
| { | |
| "epoch": 2.459802538787024, | |
| "grad_norm": 0.577947147177415, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4853, | |
| "step": 1090 | |
| }, | |
| { | |
| "epoch": 2.4823695345557124, | |
| "grad_norm": 0.5998433634691931, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4884, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 2.5049365303244007, | |
| "grad_norm": 0.5965762031241623, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4918, | |
| "step": 1110 | |
| }, | |
| { | |
| "epoch": 2.527503526093089, | |
| "grad_norm": 0.6554403444343672, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4825, | |
| "step": 1120 | |
| }, | |
| { | |
| "epoch": 2.550070521861777, | |
| "grad_norm": 0.574534309523368, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4875, | |
| "step": 1130 | |
| }, | |
| { | |
| "epoch": 2.5726375176304654, | |
| "grad_norm": 0.5681388329823351, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4857, | |
| "step": 1140 | |
| }, | |
| { | |
| "epoch": 2.5952045133991537, | |
| "grad_norm": 0.7384496157662809, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4866, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 2.617771509167842, | |
| "grad_norm": 0.6076094430353052, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4902, | |
| "step": 1160 | |
| }, | |
| { | |
| "epoch": 2.64033850493653, | |
| "grad_norm": 0.576931484268167, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4792, | |
| "step": 1170 | |
| }, | |
| { | |
| "epoch": 2.6629055007052185, | |
| "grad_norm": 0.6130340243205236, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4902, | |
| "step": 1180 | |
| }, | |
| { | |
| "epoch": 2.685472496473907, | |
| "grad_norm": 0.5574302117676829, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4908, | |
| "step": 1190 | |
| }, | |
| { | |
| "epoch": 2.7080394922425954, | |
| "grad_norm": 0.6775339732075475, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4894, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 2.7306064880112837, | |
| "grad_norm": 0.5758452111087213, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4907, | |
| "step": 1210 | |
| }, | |
| { | |
| "epoch": 2.753173483779972, | |
| "grad_norm": 0.5991383407736889, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4874, | |
| "step": 1220 | |
| }, | |
| { | |
| "epoch": 2.77574047954866, | |
| "grad_norm": 0.6337617318240264, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4939, | |
| "step": 1230 | |
| }, | |
| { | |
| "epoch": 2.7983074753173485, | |
| "grad_norm": 0.6226058340602839, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4921, | |
| "step": 1240 | |
| }, | |
| { | |
| "epoch": 2.8208744710860367, | |
| "grad_norm": 0.5635539209906445, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4923, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 2.843441466854725, | |
| "grad_norm": 0.5836376386084916, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4942, | |
| "step": 1260 | |
| }, | |
| { | |
| "epoch": 2.8660084626234132, | |
| "grad_norm": 0.5834760483019259, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4912, | |
| "step": 1270 | |
| }, | |
| { | |
| "epoch": 2.8885754583921015, | |
| "grad_norm": 0.5453775847159935, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4891, | |
| "step": 1280 | |
| }, | |
| { | |
| "epoch": 2.9111424541607898, | |
| "grad_norm": 0.5928177413547667, | |
| "learning_rate": 5e-06, | |
| "loss": 0.493, | |
| "step": 1290 | |
| }, | |
| { | |
| "epoch": 2.933709449929478, | |
| "grad_norm": 0.579440975363755, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4886, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 2.9562764456981663, | |
| "grad_norm": 0.6369568326270619, | |
| "learning_rate": 5e-06, | |
| "loss": 0.4925, | |
| "step": 1310 | |
| }, | |
| { | |
| "epoch": 2.9788434414668545, | |
| "grad_norm": 0.635755019164249, | |
| "learning_rate": 5e-06, | |
| "loss": 0.489, | |
| "step": 1320 | |
| }, | |
| { | |
| "epoch": 2.9991537376586743, | |
| "eval_loss": 0.6002675294876099, | |
| "eval_runtime": 696.4593, | |
| "eval_samples_per_second": 17.145, | |
| "eval_steps_per_second": 0.537, | |
| "step": 1329 | |
| }, | |
| { | |
| "epoch": 2.9991537376586743, | |
| "step": 1329, | |
| "total_flos": 5064195066298368.0, | |
| "train_loss": 0.5472425596439542, | |
| "train_runtime": 121923.5756, | |
| "train_samples_per_second": 5.582, | |
| "train_steps_per_second": 0.011 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1329, | |
| "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": 5064195066298368.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |