| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.6557377049180327, |
| "eval_steps": 1000, |
| "global_step": 12000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.00546448087431694, |
| "grad_norm": 0.33557644486427307, |
| "learning_rate": 0.00014918852459016392, |
| "loss": 3.2997506713867186, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.01092896174863388, |
| "grad_norm": 0.3691432774066925, |
| "learning_rate": 0.00014836885245901637, |
| "loss": 3.297074279785156, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.01639344262295082, |
| "grad_norm": 0.33957722783088684, |
| "learning_rate": 0.00014754918032786884, |
| "loss": 3.284024353027344, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.02185792349726776, |
| "grad_norm": 0.324457049369812, |
| "learning_rate": 0.0001467295081967213, |
| "loss": 3.2819815063476563, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.0273224043715847, |
| "grad_norm": 0.3473037779331207, |
| "learning_rate": 0.00014590983606557376, |
| "loss": 3.273143005371094, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.03278688524590164, |
| "grad_norm": 0.33360302448272705, |
| "learning_rate": 0.0001450901639344262, |
| "loss": 3.2673272705078125, |
| "step": 600 |
| }, |
| { |
| "epoch": 0.03825136612021858, |
| "grad_norm": 0.35968998074531555, |
| "learning_rate": 0.00014427049180327868, |
| "loss": 3.2718386840820313, |
| "step": 700 |
| }, |
| { |
| "epoch": 0.04371584699453552, |
| "grad_norm": 0.34233754873275757, |
| "learning_rate": 0.00014345081967213113, |
| "loss": 3.2761669921875, |
| "step": 800 |
| }, |
| { |
| "epoch": 0.04918032786885246, |
| "grad_norm": 0.34049418568611145, |
| "learning_rate": 0.00014263114754098358, |
| "loss": 3.2359161376953125, |
| "step": 900 |
| }, |
| { |
| "epoch": 0.0546448087431694, |
| "grad_norm": 0.3437342047691345, |
| "learning_rate": 0.00014181147540983605, |
| "loss": 3.2309716796875, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.0546448087431694, |
| "eval_loss": 3.141683578491211, |
| "eval_runtime": 167.5376, |
| "eval_samples_per_second": 51.851, |
| "eval_steps_per_second": 1.624, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.060109289617486336, |
| "grad_norm": 0.3368486166000366, |
| "learning_rate": 0.00014099180327868853, |
| "loss": 3.2491357421875, |
| "step": 1100 |
| }, |
| { |
| "epoch": 0.06557377049180328, |
| "grad_norm": 0.3406209945678711, |
| "learning_rate": 0.00014017213114754097, |
| "loss": 3.241882629394531, |
| "step": 1200 |
| }, |
| { |
| "epoch": 0.07103825136612021, |
| "grad_norm": 0.36890581250190735, |
| "learning_rate": 0.00013935245901639345, |
| "loss": 3.21847412109375, |
| "step": 1300 |
| }, |
| { |
| "epoch": 0.07650273224043716, |
| "grad_norm": 0.32925161719322205, |
| "learning_rate": 0.0001385327868852459, |
| "loss": 3.247527770996094, |
| "step": 1400 |
| }, |
| { |
| "epoch": 0.08196721311475409, |
| "grad_norm": 0.3606502115726471, |
| "learning_rate": 0.00013771311475409834, |
| "loss": 3.2279705810546875, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.08743169398907104, |
| "grad_norm": 0.35976818203926086, |
| "learning_rate": 0.00013689344262295082, |
| "loss": 3.2205975341796873, |
| "step": 1600 |
| }, |
| { |
| "epoch": 0.09289617486338798, |
| "grad_norm": 0.35467588901519775, |
| "learning_rate": 0.00013607377049180326, |
| "loss": 3.23948486328125, |
| "step": 1700 |
| }, |
| { |
| "epoch": 0.09836065573770492, |
| "grad_norm": 0.33707618713378906, |
| "learning_rate": 0.00013525409836065574, |
| "loss": 3.22716796875, |
| "step": 1800 |
| }, |
| { |
| "epoch": 0.10382513661202186, |
| "grad_norm": 0.34896889328956604, |
| "learning_rate": 0.00013443442622950818, |
| "loss": 3.254466247558594, |
| "step": 1900 |
| }, |
| { |
| "epoch": 0.1092896174863388, |
| "grad_norm": 0.33358848094940186, |
| "learning_rate": 0.00013361475409836063, |
| "loss": 3.235157470703125, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.1092896174863388, |
| "eval_loss": 3.129152297973633, |
| "eval_runtime": 166.3667, |
| "eval_samples_per_second": 52.216, |
| "eval_steps_per_second": 1.635, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.11475409836065574, |
| "grad_norm": 0.36108165979385376, |
| "learning_rate": 0.0001327950819672131, |
| "loss": 3.2411184692382813, |
| "step": 2100 |
| }, |
| { |
| "epoch": 0.12021857923497267, |
| "grad_norm": 0.33732327818870544, |
| "learning_rate": 0.00013197540983606555, |
| "loss": 3.2485076904296877, |
| "step": 2200 |
| }, |
| { |
| "epoch": 0.12568306010928962, |
| "grad_norm": 0.35349759459495544, |
| "learning_rate": 0.00013115573770491803, |
| "loss": 3.2446453857421873, |
| "step": 2300 |
| }, |
| { |
| "epoch": 0.13114754098360656, |
| "grad_norm": 0.33498039841651917, |
| "learning_rate": 0.00013033606557377047, |
| "loss": 3.2644442749023437, |
| "step": 2400 |
| }, |
| { |
| "epoch": 0.1366120218579235, |
| "grad_norm": 0.3694196939468384, |
| "learning_rate": 0.00012951639344262292, |
| "loss": 3.235172119140625, |
| "step": 2500 |
| }, |
| { |
| "epoch": 0.14207650273224043, |
| "grad_norm": 0.34429556131362915, |
| "learning_rate": 0.0001286967213114754, |
| "loss": 3.2346224975585938, |
| "step": 2600 |
| }, |
| { |
| "epoch": 0.14754098360655737, |
| "grad_norm": 0.3450092673301697, |
| "learning_rate": 0.00012787704918032784, |
| "loss": 3.2645361328125, |
| "step": 2700 |
| }, |
| { |
| "epoch": 0.15300546448087432, |
| "grad_norm": 0.3353455662727356, |
| "learning_rate": 0.00012705737704918032, |
| "loss": 3.259942626953125, |
| "step": 2800 |
| }, |
| { |
| "epoch": 0.15846994535519127, |
| "grad_norm": 0.3381529450416565, |
| "learning_rate": 0.0001262377049180328, |
| "loss": 3.219759826660156, |
| "step": 2900 |
| }, |
| { |
| "epoch": 0.16393442622950818, |
| "grad_norm": 0.3392621576786041, |
| "learning_rate": 0.00012541803278688524, |
| "loss": 3.2325253295898437, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.16393442622950818, |
| "eval_loss": 3.116848945617676, |
| "eval_runtime": 167.4485, |
| "eval_samples_per_second": 51.879, |
| "eval_steps_per_second": 1.624, |
| "step": 3000 |
| }, |
| { |
| "epoch": 0.16939890710382513, |
| "grad_norm": 0.3316171169281006, |
| "learning_rate": 0.0001245983606557377, |
| "loss": 3.2304959106445312, |
| "step": 3100 |
| }, |
| { |
| "epoch": 0.17486338797814208, |
| "grad_norm": 0.3558633625507355, |
| "learning_rate": 0.00012377868852459016, |
| "loss": 3.233113098144531, |
| "step": 3200 |
| }, |
| { |
| "epoch": 0.18032786885245902, |
| "grad_norm": 0.3265064060688019, |
| "learning_rate": 0.0001229590163934426, |
| "loss": 3.2334609985351563, |
| "step": 3300 |
| }, |
| { |
| "epoch": 0.18579234972677597, |
| "grad_norm": 0.3422014117240906, |
| "learning_rate": 0.00012213934426229508, |
| "loss": 3.2320993041992185, |
| "step": 3400 |
| }, |
| { |
| "epoch": 0.1912568306010929, |
| "grad_norm": 0.3564997911453247, |
| "learning_rate": 0.00012131967213114753, |
| "loss": 3.24385009765625, |
| "step": 3500 |
| }, |
| { |
| "epoch": 0.19672131147540983, |
| "grad_norm": 0.350437730550766, |
| "learning_rate": 0.00012049999999999999, |
| "loss": 3.2268707275390627, |
| "step": 3600 |
| }, |
| { |
| "epoch": 0.20218579234972678, |
| "grad_norm": 0.3819025158882141, |
| "learning_rate": 0.00011968032786885245, |
| "loss": 3.2548171997070314, |
| "step": 3700 |
| }, |
| { |
| "epoch": 0.20765027322404372, |
| "grad_norm": 0.3577027916908264, |
| "learning_rate": 0.00011886065573770491, |
| "loss": 3.242948303222656, |
| "step": 3800 |
| }, |
| { |
| "epoch": 0.21311475409836064, |
| "grad_norm": 0.34992942214012146, |
| "learning_rate": 0.00011804098360655737, |
| "loss": 3.247112121582031, |
| "step": 3900 |
| }, |
| { |
| "epoch": 0.2185792349726776, |
| "grad_norm": 0.33957329392433167, |
| "learning_rate": 0.00011722131147540982, |
| "loss": 3.2855084228515623, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.2185792349726776, |
| "eval_loss": 3.1081910133361816, |
| "eval_runtime": 166.2296, |
| "eval_samples_per_second": 52.259, |
| "eval_steps_per_second": 1.636, |
| "step": 4000 |
| }, |
| { |
| "epoch": 0.22404371584699453, |
| "grad_norm": 0.39298462867736816, |
| "learning_rate": 0.00011640163934426228, |
| "loss": 3.2725079345703123, |
| "step": 4100 |
| }, |
| { |
| "epoch": 0.22950819672131148, |
| "grad_norm": 0.3378917872905731, |
| "learning_rate": 0.00011558196721311474, |
| "loss": 3.2375408935546877, |
| "step": 4200 |
| }, |
| { |
| "epoch": 0.23497267759562843, |
| "grad_norm": 0.34373924136161804, |
| "learning_rate": 0.0001147622950819672, |
| "loss": 3.264992980957031, |
| "step": 4300 |
| }, |
| { |
| "epoch": 0.24043715846994534, |
| "grad_norm": 0.3387899398803711, |
| "learning_rate": 0.00011394262295081966, |
| "loss": 3.25844482421875, |
| "step": 4400 |
| }, |
| { |
| "epoch": 0.2459016393442623, |
| "grad_norm": 0.35700681805610657, |
| "learning_rate": 0.00011312295081967212, |
| "loss": 3.262210693359375, |
| "step": 4500 |
| }, |
| { |
| "epoch": 0.25136612021857924, |
| "grad_norm": 0.3377688229084015, |
| "learning_rate": 0.00011230327868852457, |
| "loss": 3.2448056030273436, |
| "step": 4600 |
| }, |
| { |
| "epoch": 0.2568306010928962, |
| "grad_norm": 0.3596217930316925, |
| "learning_rate": 0.00011148360655737704, |
| "loss": 3.2498098754882814, |
| "step": 4700 |
| }, |
| { |
| "epoch": 0.26229508196721313, |
| "grad_norm": 0.33321240544319153, |
| "learning_rate": 0.0001106639344262295, |
| "loss": 3.23698486328125, |
| "step": 4800 |
| }, |
| { |
| "epoch": 0.2677595628415301, |
| "grad_norm": 0.3356533944606781, |
| "learning_rate": 0.00010984426229508196, |
| "loss": 3.2359185791015626, |
| "step": 4900 |
| }, |
| { |
| "epoch": 0.273224043715847, |
| "grad_norm": 0.3382013142108917, |
| "learning_rate": 0.00010902459016393442, |
| "loss": 3.17927978515625, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.273224043715847, |
| "eval_loss": 3.099688768386841, |
| "eval_runtime": 167.6483, |
| "eval_samples_per_second": 51.817, |
| "eval_steps_per_second": 1.622, |
| "step": 5000 |
| }, |
| { |
| "epoch": 0.2786885245901639, |
| "grad_norm": 0.3593096435070038, |
| "learning_rate": 0.00010820491803278688, |
| "loss": 3.2057940673828127, |
| "step": 5100 |
| }, |
| { |
| "epoch": 0.28415300546448086, |
| "grad_norm": 0.3411197364330292, |
| "learning_rate": 0.00010738524590163934, |
| "loss": 3.1890634155273436, |
| "step": 5200 |
| }, |
| { |
| "epoch": 0.2896174863387978, |
| "grad_norm": 0.3614797592163086, |
| "learning_rate": 0.00010656557377049179, |
| "loss": 3.1959136962890624, |
| "step": 5300 |
| }, |
| { |
| "epoch": 0.29508196721311475, |
| "grad_norm": 0.3614165782928467, |
| "learning_rate": 0.00010574590163934425, |
| "loss": 3.190245361328125, |
| "step": 5400 |
| }, |
| { |
| "epoch": 0.3005464480874317, |
| "grad_norm": 0.34652748703956604, |
| "learning_rate": 0.00010492622950819671, |
| "loss": 3.170889892578125, |
| "step": 5500 |
| }, |
| { |
| "epoch": 0.30601092896174864, |
| "grad_norm": 0.3489515781402588, |
| "learning_rate": 0.00010410655737704917, |
| "loss": 3.202828063964844, |
| "step": 5600 |
| }, |
| { |
| "epoch": 0.3114754098360656, |
| "grad_norm": 0.33419397473335266, |
| "learning_rate": 0.00010328688524590163, |
| "loss": 3.1874429321289064, |
| "step": 5700 |
| }, |
| { |
| "epoch": 0.31693989071038253, |
| "grad_norm": 0.33504703640937805, |
| "learning_rate": 0.00010246721311475408, |
| "loss": 3.180716857910156, |
| "step": 5800 |
| }, |
| { |
| "epoch": 0.3224043715846995, |
| "grad_norm": 0.3674669861793518, |
| "learning_rate": 0.00010164754098360654, |
| "loss": 3.1808792114257813, |
| "step": 5900 |
| }, |
| { |
| "epoch": 0.32786885245901637, |
| "grad_norm": 0.3543224036693573, |
| "learning_rate": 0.000100827868852459, |
| "loss": 3.2052008056640626, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.32786885245901637, |
| "eval_loss": 3.0916807651519775, |
| "eval_runtime": 167.0778, |
| "eval_samples_per_second": 51.994, |
| "eval_steps_per_second": 1.628, |
| "step": 6000 |
| }, |
| { |
| "epoch": 0.3333333333333333, |
| "grad_norm": 0.34399476647377014, |
| "learning_rate": 0.00010000819672131146, |
| "loss": 3.2100375366210936, |
| "step": 6100 |
| }, |
| { |
| "epoch": 0.33879781420765026, |
| "grad_norm": 0.33845406770706177, |
| "learning_rate": 9.918852459016392e-05, |
| "loss": 3.2021624755859377, |
| "step": 6200 |
| }, |
| { |
| "epoch": 0.3442622950819672, |
| "grad_norm": 0.35047417879104614, |
| "learning_rate": 9.836885245901638e-05, |
| "loss": 3.1676751708984376, |
| "step": 6300 |
| }, |
| { |
| "epoch": 0.34972677595628415, |
| "grad_norm": 0.3295944929122925, |
| "learning_rate": 9.754918032786883e-05, |
| "loss": 3.191239929199219, |
| "step": 6400 |
| }, |
| { |
| "epoch": 0.3551912568306011, |
| "grad_norm": 0.35513830184936523, |
| "learning_rate": 9.672950819672129e-05, |
| "loss": 3.2161325073242186, |
| "step": 6500 |
| }, |
| { |
| "epoch": 0.36065573770491804, |
| "grad_norm": 0.34763020277023315, |
| "learning_rate": 9.590983606557377e-05, |
| "loss": 3.1975909423828126, |
| "step": 6600 |
| }, |
| { |
| "epoch": 0.366120218579235, |
| "grad_norm": 0.35204017162323, |
| "learning_rate": 9.509016393442623e-05, |
| "loss": 3.2129571533203123, |
| "step": 6700 |
| }, |
| { |
| "epoch": 0.37158469945355194, |
| "grad_norm": 0.3598620295524597, |
| "learning_rate": 9.427049180327869e-05, |
| "loss": 3.233637390136719, |
| "step": 6800 |
| }, |
| { |
| "epoch": 0.3770491803278688, |
| "grad_norm": 0.3516027331352234, |
| "learning_rate": 9.345081967213115e-05, |
| "loss": 3.236307373046875, |
| "step": 6900 |
| }, |
| { |
| "epoch": 0.3825136612021858, |
| "grad_norm": 0.3794242739677429, |
| "learning_rate": 9.26311475409836e-05, |
| "loss": 3.2149234008789063, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.3825136612021858, |
| "eval_loss": 3.0852153301239014, |
| "eval_runtime": 166.2243, |
| "eval_samples_per_second": 52.261, |
| "eval_steps_per_second": 1.636, |
| "step": 7000 |
| }, |
| { |
| "epoch": 0.3879781420765027, |
| "grad_norm": 0.355341374874115, |
| "learning_rate": 9.181147540983606e-05, |
| "loss": 3.2003558349609373, |
| "step": 7100 |
| }, |
| { |
| "epoch": 0.39344262295081966, |
| "grad_norm": 0.3544386029243469, |
| "learning_rate": 9.099180327868852e-05, |
| "loss": 3.183940734863281, |
| "step": 7200 |
| }, |
| { |
| "epoch": 0.3989071038251366, |
| "grad_norm": 0.35201796889305115, |
| "learning_rate": 9.017213114754098e-05, |
| "loss": 3.2111468505859375, |
| "step": 7300 |
| }, |
| { |
| "epoch": 0.40437158469945356, |
| "grad_norm": 0.3590731918811798, |
| "learning_rate": 8.935245901639344e-05, |
| "loss": 3.2194284057617186, |
| "step": 7400 |
| }, |
| { |
| "epoch": 0.4098360655737705, |
| "grad_norm": 0.34875085949897766, |
| "learning_rate": 8.85327868852459e-05, |
| "loss": 3.2164602661132813, |
| "step": 7500 |
| }, |
| { |
| "epoch": 0.41530054644808745, |
| "grad_norm": 0.36371952295303345, |
| "learning_rate": 8.771311475409835e-05, |
| "loss": 3.1858474731445314, |
| "step": 7600 |
| }, |
| { |
| "epoch": 0.4207650273224044, |
| "grad_norm": 0.3518809974193573, |
| "learning_rate": 8.68934426229508e-05, |
| "loss": 3.15969970703125, |
| "step": 7700 |
| }, |
| { |
| "epoch": 0.4262295081967213, |
| "grad_norm": 0.3700133264064789, |
| "learning_rate": 8.607377049180327e-05, |
| "loss": 3.1636505126953125, |
| "step": 7800 |
| }, |
| { |
| "epoch": 0.43169398907103823, |
| "grad_norm": 0.34737807512283325, |
| "learning_rate": 8.525409836065573e-05, |
| "loss": 3.15463623046875, |
| "step": 7900 |
| }, |
| { |
| "epoch": 0.4371584699453552, |
| "grad_norm": 0.36737293004989624, |
| "learning_rate": 8.443442622950819e-05, |
| "loss": 3.138258056640625, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.4371584699453552, |
| "eval_loss": 3.0774519443511963, |
| "eval_runtime": 166.4678, |
| "eval_samples_per_second": 52.184, |
| "eval_steps_per_second": 1.634, |
| "step": 8000 |
| }, |
| { |
| "epoch": 0.4426229508196721, |
| "grad_norm": 0.34968650341033936, |
| "learning_rate": 8.361475409836064e-05, |
| "loss": 3.1346026611328126, |
| "step": 8100 |
| }, |
| { |
| "epoch": 0.44808743169398907, |
| "grad_norm": 0.347873330116272, |
| "learning_rate": 8.27950819672131e-05, |
| "loss": 3.1654531860351565, |
| "step": 8200 |
| }, |
| { |
| "epoch": 0.453551912568306, |
| "grad_norm": 0.3486824929714203, |
| "learning_rate": 8.197540983606556e-05, |
| "loss": 3.158487548828125, |
| "step": 8300 |
| }, |
| { |
| "epoch": 0.45901639344262296, |
| "grad_norm": 0.34259742498397827, |
| "learning_rate": 8.115573770491803e-05, |
| "loss": 3.1289462280273437, |
| "step": 8400 |
| }, |
| { |
| "epoch": 0.4644808743169399, |
| "grad_norm": 0.34342944622039795, |
| "learning_rate": 8.033606557377049e-05, |
| "loss": 3.1434490966796873, |
| "step": 8500 |
| }, |
| { |
| "epoch": 0.46994535519125685, |
| "grad_norm": 0.35807445645332336, |
| "learning_rate": 7.951639344262295e-05, |
| "loss": 3.1603570556640626, |
| "step": 8600 |
| }, |
| { |
| "epoch": 0.47540983606557374, |
| "grad_norm": 0.3534564971923828, |
| "learning_rate": 7.869672131147541e-05, |
| "loss": 3.176658020019531, |
| "step": 8700 |
| }, |
| { |
| "epoch": 0.4808743169398907, |
| "grad_norm": 0.36163410544395447, |
| "learning_rate": 7.787704918032786e-05, |
| "loss": 3.1730413818359375, |
| "step": 8800 |
| }, |
| { |
| "epoch": 0.48633879781420764, |
| "grad_norm": 0.3280462920665741, |
| "learning_rate": 7.705737704918032e-05, |
| "loss": 3.1541357421875, |
| "step": 8900 |
| }, |
| { |
| "epoch": 0.4918032786885246, |
| "grad_norm": 0.34871619939804077, |
| "learning_rate": 7.623770491803278e-05, |
| "loss": 3.1691409301757814, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.4918032786885246, |
| "eval_loss": 3.0718374252319336, |
| "eval_runtime": 165.8669, |
| "eval_samples_per_second": 52.373, |
| "eval_steps_per_second": 1.64, |
| "step": 9000 |
| }, |
| { |
| "epoch": 0.4972677595628415, |
| "grad_norm": 0.37653326988220215, |
| "learning_rate": 7.541803278688524e-05, |
| "loss": 3.173928527832031, |
| "step": 9100 |
| }, |
| { |
| "epoch": 0.5027322404371585, |
| "grad_norm": 0.3302043676376343, |
| "learning_rate": 7.45983606557377e-05, |
| "loss": 3.185494689941406, |
| "step": 9200 |
| }, |
| { |
| "epoch": 0.5081967213114754, |
| "grad_norm": 0.35126709938049316, |
| "learning_rate": 7.377868852459016e-05, |
| "loss": 3.16490234375, |
| "step": 9300 |
| }, |
| { |
| "epoch": 0.5136612021857924, |
| "grad_norm": 0.38984546065330505, |
| "learning_rate": 7.295901639344261e-05, |
| "loss": 3.20061279296875, |
| "step": 9400 |
| }, |
| { |
| "epoch": 0.5191256830601093, |
| "grad_norm": 0.3627556264400482, |
| "learning_rate": 7.213934426229507e-05, |
| "loss": 3.2119021606445313, |
| "step": 9500 |
| }, |
| { |
| "epoch": 0.5245901639344263, |
| "grad_norm": 0.34836238622665405, |
| "learning_rate": 7.131967213114753e-05, |
| "loss": 3.192005920410156, |
| "step": 9600 |
| }, |
| { |
| "epoch": 0.5300546448087432, |
| "grad_norm": 0.362745463848114, |
| "learning_rate": 7.049999999999999e-05, |
| "loss": 3.2035980224609375, |
| "step": 9700 |
| }, |
| { |
| "epoch": 0.5355191256830601, |
| "grad_norm": 0.35114485025405884, |
| "learning_rate": 6.968032786885245e-05, |
| "loss": 3.200631103515625, |
| "step": 9800 |
| }, |
| { |
| "epoch": 0.5409836065573771, |
| "grad_norm": 0.45677778124809265, |
| "learning_rate": 6.886065573770491e-05, |
| "loss": 3.2338800048828125, |
| "step": 9900 |
| }, |
| { |
| "epoch": 0.546448087431694, |
| "grad_norm": 0.38240864872932434, |
| "learning_rate": 6.804098360655737e-05, |
| "loss": 3.2340545654296875, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.546448087431694, |
| "eval_loss": 3.064678907394409, |
| "eval_runtime": 166.0237, |
| "eval_samples_per_second": 52.324, |
| "eval_steps_per_second": 1.638, |
| "step": 10000 |
| }, |
| { |
| "epoch": 0.5519125683060109, |
| "grad_norm": 0.36993658542633057, |
| "learning_rate": 6.722131147540984e-05, |
| "loss": 3.217573547363281, |
| "step": 10100 |
| }, |
| { |
| "epoch": 0.5573770491803278, |
| "grad_norm": 0.34514835476875305, |
| "learning_rate": 6.64016393442623e-05, |
| "loss": 3.228822937011719, |
| "step": 10200 |
| }, |
| { |
| "epoch": 0.5628415300546448, |
| "grad_norm": 0.3509940803050995, |
| "learning_rate": 6.558196721311474e-05, |
| "loss": 3.224437561035156, |
| "step": 10300 |
| }, |
| { |
| "epoch": 0.5683060109289617, |
| "grad_norm": 0.34477314352989197, |
| "learning_rate": 6.47622950819672e-05, |
| "loss": 3.226252136230469, |
| "step": 10400 |
| }, |
| { |
| "epoch": 0.5737704918032787, |
| "grad_norm": 0.3412553071975708, |
| "learning_rate": 6.394262295081966e-05, |
| "loss": 3.2269625854492188, |
| "step": 10500 |
| }, |
| { |
| "epoch": 0.5792349726775956, |
| "grad_norm": 0.3485320508480072, |
| "learning_rate": 6.312295081967212e-05, |
| "loss": 3.2041766357421877, |
| "step": 10600 |
| }, |
| { |
| "epoch": 0.5846994535519126, |
| "grad_norm": 0.33190447092056274, |
| "learning_rate": 6.230327868852459e-05, |
| "loss": 3.1985888671875, |
| "step": 10700 |
| }, |
| { |
| "epoch": 0.5901639344262295, |
| "grad_norm": 0.36425039172172546, |
| "learning_rate": 6.148360655737705e-05, |
| "loss": 3.208878479003906, |
| "step": 10800 |
| }, |
| { |
| "epoch": 0.5956284153005464, |
| "grad_norm": 0.3473658859729767, |
| "learning_rate": 6.066393442622951e-05, |
| "loss": 3.2074591064453126, |
| "step": 10900 |
| }, |
| { |
| "epoch": 0.6010928961748634, |
| "grad_norm": 0.43133220076560974, |
| "learning_rate": 5.984426229508196e-05, |
| "loss": 3.2229376220703125, |
| "step": 11000 |
| }, |
| { |
| "epoch": 0.6010928961748634, |
| "eval_loss": 3.0597853660583496, |
| "eval_runtime": 165.5808, |
| "eval_samples_per_second": 52.464, |
| "eval_steps_per_second": 1.643, |
| "step": 11000 |
| }, |
| { |
| "epoch": 0.6065573770491803, |
| "grad_norm": 0.37588736414909363, |
| "learning_rate": 5.902459016393442e-05, |
| "loss": 3.1838412475585938, |
| "step": 11100 |
| }, |
| { |
| "epoch": 0.6120218579234973, |
| "grad_norm": 0.34238529205322266, |
| "learning_rate": 5.820491803278688e-05, |
| "loss": 3.1839044189453123, |
| "step": 11200 |
| }, |
| { |
| "epoch": 0.6174863387978142, |
| "grad_norm": 0.3399714231491089, |
| "learning_rate": 5.7385245901639336e-05, |
| "loss": 3.2120074462890624, |
| "step": 11300 |
| }, |
| { |
| "epoch": 0.6229508196721312, |
| "grad_norm": 0.3523642420768738, |
| "learning_rate": 5.6565573770491796e-05, |
| "loss": 3.1816641235351564, |
| "step": 11400 |
| }, |
| { |
| "epoch": 0.6284153005464481, |
| "grad_norm": 0.3372739255428314, |
| "learning_rate": 5.574590163934426e-05, |
| "loss": 3.194277038574219, |
| "step": 11500 |
| }, |
| { |
| "epoch": 0.6338797814207651, |
| "grad_norm": 0.36970576643943787, |
| "learning_rate": 5.492622950819672e-05, |
| "loss": 3.183469543457031, |
| "step": 11600 |
| }, |
| { |
| "epoch": 0.639344262295082, |
| "grad_norm": 0.3468629717826843, |
| "learning_rate": 5.410655737704918e-05, |
| "loss": 3.1655535888671875, |
| "step": 11700 |
| }, |
| { |
| "epoch": 0.644808743169399, |
| "grad_norm": 0.3488897979259491, |
| "learning_rate": 5.328688524590164e-05, |
| "loss": 3.1525448608398436, |
| "step": 11800 |
| }, |
| { |
| "epoch": 0.6502732240437158, |
| "grad_norm": 0.3539671301841736, |
| "learning_rate": 5.246721311475409e-05, |
| "loss": 3.1822393798828124, |
| "step": 11900 |
| }, |
| { |
| "epoch": 0.6557377049180327, |
| "grad_norm": 0.3764471709728241, |
| "learning_rate": 5.164754098360655e-05, |
| "loss": 3.1826312255859377, |
| "step": 12000 |
| }, |
| { |
| "epoch": 0.6557377049180327, |
| "eval_loss": 3.053892135620117, |
| "eval_runtime": 169.2137, |
| "eval_samples_per_second": 51.337, |
| "eval_steps_per_second": 1.607, |
| "step": 12000 |
| } |
| ], |
| "logging_steps": 100, |
| "max_steps": 18300, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 9223372036854775807, |
| "save_steps": 1000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 2.00672280576e+17, |
| "train_batch_size": 32, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
