| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 6135, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008149959250203748, | |
| "grad_norm": 0.18579324653121165, | |
| "learning_rate": 0.0007999910290180627, | |
| "loss": 0.6628, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.016299918500407497, | |
| "grad_norm": 0.17807681860788138, | |
| "learning_rate": 0.0007997893323384012, | |
| "loss": 0.5165, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02444987775061125, | |
| "grad_norm": 0.19350751669754768, | |
| "learning_rate": 0.0007993223754535443, | |
| "loss": 0.4975, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.032599837000814993, | |
| "grad_norm": 0.1628741338405071, | |
| "learning_rate": 0.0007985904681893655, | |
| "loss": 0.4859, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.040749796251018745, | |
| "grad_norm": 0.1692654309709468, | |
| "learning_rate": 0.0007975940961663036, | |
| "loss": 0.4698, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.0488997555012225, | |
| "grad_norm": 0.16755101172401649, | |
| "learning_rate": 0.0007963339204771541, | |
| "loss": 0.4584, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.05704971475142624, | |
| "grad_norm": 0.16981406073926134, | |
| "learning_rate": 0.0007948107772484337, | |
| "loss": 0.4497, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.06519967400162999, | |
| "grad_norm": 0.13393142327752477, | |
| "learning_rate": 0.0007930256770856106, | |
| "loss": 0.435, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.07334963325183375, | |
| "grad_norm": 0.14862318790293866, | |
| "learning_rate": 0.000790979804402568, | |
| "loss": 0.4379, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.08149959250203749, | |
| "grad_norm": 0.14157872785652958, | |
| "learning_rate": 0.0007886745166357449, | |
| "loss": 0.4389, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.08964955175224124, | |
| "grad_norm": 0.14597403141832885, | |
| "learning_rate": 0.0007861113433434774, | |
| "loss": 0.4248, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.097799511002445, | |
| "grad_norm": 0.14439776167516288, | |
| "learning_rate": 0.0007832919851911376, | |
| "loss": 0.4316, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.10594947025264874, | |
| "grad_norm": 0.2043224587005451, | |
| "learning_rate": 0.0007802183128227408, | |
| "loss": 0.4168, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.11409942950285248, | |
| "grad_norm": 0.13509782410904447, | |
| "learning_rate": 0.0007768923656197741, | |
| "loss": 0.4198, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.12224938875305623, | |
| "grad_norm": 0.21692882701447652, | |
| "learning_rate": 0.0007734641630410531, | |
| "loss": 0.4286, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.13039934800325997, | |
| "grad_norm": 0.18392281414572664, | |
| "learning_rate": 0.000769650312579427, | |
| "loss": 0.4466, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.13854930725346373, | |
| "grad_norm": 0.17037687429265078, | |
| "learning_rate": 0.000765591199150948, | |
| "loss": 0.4376, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.1466992665036675, | |
| "grad_norm": 0.17552399857385595, | |
| "learning_rate": 0.0007612895159772056, | |
| "loss": 0.4264, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.15484922575387122, | |
| "grad_norm": 0.1438151353983127, | |
| "learning_rate": 0.0007567481172248043, | |
| "loss": 0.41, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.16299918500407498, | |
| "grad_norm": 0.1447417216259079, | |
| "learning_rate": 0.0007519700161116256, | |
| "loss": 0.4119, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.17114914425427874, | |
| "grad_norm": 0.15199420470790867, | |
| "learning_rate": 0.000746958382907557, | |
| "loss": 0.412, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 0.17929910350448247, | |
| "grad_norm": 0.14727418743789575, | |
| "learning_rate": 0.0007417165428310189, | |
| "loss": 0.3946, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.18744906275468623, | |
| "grad_norm": 0.34678998038165904, | |
| "learning_rate": 0.000736471024768781, | |
| "loss": 0.393, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 0.19559902200489, | |
| "grad_norm": 0.1482936724234658, | |
| "learning_rate": 0.0007307882077545133, | |
| "loss": 0.3992, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.20374898125509372, | |
| "grad_norm": 0.14346039255661802, | |
| "learning_rate": 0.00072488591277831, | |
| "loss": 0.39, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 0.21189894050529748, | |
| "grad_norm": 0.14534505858629046, | |
| "learning_rate": 0.0007187680560126396, | |
| "loss": 0.3878, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.2200488997555012, | |
| "grad_norm": 0.1388631218472249, | |
| "learning_rate": 0.0007124386966552088, | |
| "loss": 0.3746, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 0.22819885900570497, | |
| "grad_norm": 0.15086917327804153, | |
| "learning_rate": 0.0007059020342356855, | |
| "loss": 0.3859, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.23634881825590873, | |
| "grad_norm": 0.15384912931521313, | |
| "learning_rate": 0.0006991624058293096, | |
| "loss": 0.3731, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 0.24449877750611246, | |
| "grad_norm": 0.15914151929826, | |
| "learning_rate": 0.000692224283179246, | |
| "loss": 0.3754, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.2526487367563162, | |
| "grad_norm": 0.11506887001881892, | |
| "learning_rate": 0.0006850922697295807, | |
| "loss": 0.3666, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 0.26079869600651995, | |
| "grad_norm": 0.13052208168058513, | |
| "learning_rate": 0.0006777710975709381, | |
| "loss": 0.3766, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.26894865525672373, | |
| "grad_norm": 0.11941691123999496, | |
| "learning_rate": 0.0006702656243007372, | |
| "loss": 0.3602, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 0.27709861450692747, | |
| "grad_norm": 0.11925894836007636, | |
| "learning_rate": 0.0006625808298001773, | |
| "loss": 0.3612, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.2852485737571312, | |
| "grad_norm": 0.14308144825812302, | |
| "learning_rate": 0.0006547218129300866, | |
| "loss": 0.3609, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 0.293398533007335, | |
| "grad_norm": 0.14967189995049074, | |
| "learning_rate": 0.0006466937881478278, | |
| "loss": 0.3561, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 0.3015484922575387, | |
| "grad_norm": 0.13228828753052413, | |
| "learning_rate": 0.0006385020820475062, | |
| "loss": 0.348, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 0.30969845150774244, | |
| "grad_norm": 0.13322170574643283, | |
| "learning_rate": 0.000630152129825775, | |
| "loss": 0.3697, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 0.31784841075794623, | |
| "grad_norm": 0.12720122919651028, | |
| "learning_rate": 0.0006216494716755822, | |
| "loss": 0.3448, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 0.32599837000814996, | |
| "grad_norm": 0.13582416923221627, | |
| "learning_rate": 0.0006129997491102531, | |
| "loss": 0.3567, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.3341483292583537, | |
| "grad_norm": 0.14925459708686192, | |
| "learning_rate": 0.000604208701220346, | |
| "loss": 0.3484, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 0.3422982885085575, | |
| "grad_norm": 0.1243721342991605, | |
| "learning_rate": 0.000595282160865766, | |
| "loss": 0.3484, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 0.3504482477587612, | |
| "grad_norm": 0.11953241203626794, | |
| "learning_rate": 0.0005862260508056631, | |
| "loss": 0.3458, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 0.35859820700896494, | |
| "grad_norm": 0.11268782331878287, | |
| "learning_rate": 0.0005770463797686815, | |
| "loss": 0.339, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 0.36674816625916873, | |
| "grad_norm": 0.11687380056427817, | |
| "learning_rate": 0.0005677492384661679, | |
| "loss": 0.3337, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 0.37489812550937246, | |
| "grad_norm": 0.12673741702704472, | |
| "learning_rate": 0.0005583407955509861, | |
| "loss": 0.3346, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 0.3830480847595762, | |
| "grad_norm": 0.11915610120268014, | |
| "learning_rate": 0.0005488272935246143, | |
| "loss": 0.333, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 0.39119804400978, | |
| "grad_norm": 0.13402357429565842, | |
| "learning_rate": 0.0005392150445952471, | |
| "loss": 0.3305, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 0.3993480032599837, | |
| "grad_norm": 0.1160573866470615, | |
| "learning_rate": 0.0005295104264896449, | |
| "loss": 0.34, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 0.40749796251018744, | |
| "grad_norm": 0.11766125729550878, | |
| "learning_rate": 0.0005197198782215126, | |
| "loss": 0.3282, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.4156479217603912, | |
| "grad_norm": 0.10590606446287697, | |
| "learning_rate": 0.0005098498958192145, | |
| "loss": 0.3299, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 0.42379788101059496, | |
| "grad_norm": 0.11241439393785868, | |
| "learning_rate": 0.0004999070280156597, | |
| "loss": 0.3298, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 0.4319478402607987, | |
| "grad_norm": 0.11125810401522715, | |
| "learning_rate": 0.0004898978719032175, | |
| "loss": 0.3215, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 0.4400977995110024, | |
| "grad_norm": 0.11191318960071489, | |
| "learning_rate": 0.0004798290685565476, | |
| "loss": 0.3249, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 0.4482477587612062, | |
| "grad_norm": 0.1287365840788498, | |
| "learning_rate": 0.0004697072986262474, | |
| "loss": 0.3161, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 0.45639771801140994, | |
| "grad_norm": 0.11552326003349313, | |
| "learning_rate": 0.00045953927790623976, | |
| "loss": 0.3124, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 0.46454767726161367, | |
| "grad_norm": 0.11748617144150195, | |
| "learning_rate": 0.0004493317528778449, | |
| "loss": 0.3218, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 0.47269763651181745, | |
| "grad_norm": 0.10367103487291035, | |
| "learning_rate": 0.00043909149623349, | |
| "loss": 0.3038, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 0.4808475957620212, | |
| "grad_norm": 0.13997935598004313, | |
| "learning_rate": 0.00042882530238302793, | |
| "loss": 0.3079, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 0.4889975550122249, | |
| "grad_norm": 0.11405505781771122, | |
| "learning_rate": 0.000418539982945647, | |
| "loss": 0.3161, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.4971475142624287, | |
| "grad_norm": 0.10244350957803788, | |
| "learning_rate": 0.000408242362230361, | |
| "loss": 0.3121, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 0.5052974735126324, | |
| "grad_norm": 0.11487103054153286, | |
| "learning_rate": 0.0003979392727080819, | |
| "loss": 0.3048, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 0.5134474327628362, | |
| "grad_norm": 0.1105131381250625, | |
| "learning_rate": 0.0003876375504782742, | |
| "loss": 0.2951, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 0.5215973920130399, | |
| "grad_norm": 0.1114339713919424, | |
| "learning_rate": 0.00037734403073320455, | |
| "loss": 0.2978, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 0.5297473512632437, | |
| "grad_norm": 0.12439423946252776, | |
| "learning_rate": 0.0003670655432227906, | |
| "loss": 0.2977, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 0.5378973105134475, | |
| "grad_norm": 0.10946864392870362, | |
| "learning_rate": 0.0003568089077230634, | |
| "loss": 0.2966, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 0.5460472697636511, | |
| "grad_norm": 0.09312964606321276, | |
| "learning_rate": 0.00034658092951124573, | |
| "loss": 0.2877, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 0.5541972290138549, | |
| "grad_norm": 0.1251440088268339, | |
| "learning_rate": 0.00033638839485045124, | |
| "loss": 0.2953, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 0.5623471882640587, | |
| "grad_norm": 0.11260490319865255, | |
| "learning_rate": 0.00032623806648699865, | |
| "loss": 0.2836, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 0.5704971475142624, | |
| "grad_norm": 0.10260196893419725, | |
| "learning_rate": 0.00031613667916333013, | |
| "loss": 0.2883, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.5786471067644662, | |
| "grad_norm": 0.11067247135798225, | |
| "learning_rate": 0.0003060909351495104, | |
| "loss": 0.2919, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 0.58679706601467, | |
| "grad_norm": 0.13049869044328746, | |
| "learning_rate": 0.00029610749979627, | |
| "loss": 0.2801, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 0.5949470252648736, | |
| "grad_norm": 0.0994668923515135, | |
| "learning_rate": 0.0002861929971125462, | |
| "loss": 0.2764, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 0.6030969845150774, | |
| "grad_norm": 0.12787979565602525, | |
| "learning_rate": 0.0002763540053704528, | |
| "loss": 0.2828, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 0.6112469437652812, | |
| "grad_norm": 0.11702233580318924, | |
| "learning_rate": 0.0002665970527405966, | |
| "loss": 0.275, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 0.6193969030154849, | |
| "grad_norm": 0.12216378448453033, | |
| "learning_rate": 0.0002569286129606376, | |
| "loss": 0.2781, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 0.6275468622656887, | |
| "grad_norm": 0.11991224657683039, | |
| "learning_rate": 0.00024735510103996296, | |
| "loss": 0.2779, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 0.6356968215158925, | |
| "grad_norm": 0.11355699073704052, | |
| "learning_rate": 0.00023788286900332977, | |
| "loss": 0.278, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 0.6438467807660961, | |
| "grad_norm": 0.10548043571718951, | |
| "learning_rate": 0.00022851820167629582, | |
| "loss": 0.2737, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 0.6519967400162999, | |
| "grad_norm": 0.10359945452094396, | |
| "learning_rate": 0.0002192673125152389, | |
| "loss": 0.2724, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.6601466992665037, | |
| "grad_norm": 0.11760044543664713, | |
| "learning_rate": 0.0002101363394847284, | |
| "loss": 0.2629, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 0.6682966585167074, | |
| "grad_norm": 0.1061394336514801, | |
| "learning_rate": 0.00020113134098498586, | |
| "loss": 0.2686, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 0.6764466177669112, | |
| "grad_norm": 0.12584575464846712, | |
| "learning_rate": 0.00019225829183213756, | |
| "loss": 0.2699, | |
| "step": 4150 | |
| }, | |
| { | |
| "epoch": 0.684596577017115, | |
| "grad_norm": 0.11274050205692296, | |
| "learning_rate": 0.00018352307929392337, | |
| "loss": 0.26, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 0.6927465362673186, | |
| "grad_norm": 0.10624178207114862, | |
| "learning_rate": 0.0001749314991834945, | |
| "loss": 0.2676, | |
| "step": 4250 | |
| }, | |
| { | |
| "epoch": 0.7008964955175224, | |
| "grad_norm": 0.10585200267430328, | |
| "learning_rate": 0.00016648925201389348, | |
| "loss": 0.2699, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 0.7090464547677262, | |
| "grad_norm": 0.1036684915414757, | |
| "learning_rate": 0.00015820193921576214, | |
| "loss": 0.266, | |
| "step": 4350 | |
| }, | |
| { | |
| "epoch": 0.7171964140179299, | |
| "grad_norm": 0.11470877255663611, | |
| "learning_rate": 0.00015007505942079362, | |
| "loss": 0.2574, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 0.7253463732681337, | |
| "grad_norm": 0.11442215173910815, | |
| "learning_rate": 0.00014211400481339013, | |
| "loss": 0.2536, | |
| "step": 4450 | |
| }, | |
| { | |
| "epoch": 0.7334963325183375, | |
| "grad_norm": 0.10579448760201741, | |
| "learning_rate": 0.00013432405755294893, | |
| "loss": 0.2518, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.7416462917685411, | |
| "grad_norm": 0.11019413291456029, | |
| "learning_rate": 0.0001267103862691497, | |
| "loss": 0.2528, | |
| "step": 4550 | |
| }, | |
| { | |
| "epoch": 0.7497962510187449, | |
| "grad_norm": 0.1237941013535732, | |
| "learning_rate": 0.00011927804263256903, | |
| "loss": 0.2506, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 0.7579462102689487, | |
| "grad_norm": 0.11747893253572085, | |
| "learning_rate": 0.0001120319580028975, | |
| "loss": 0.2432, | |
| "step": 4650 | |
| }, | |
| { | |
| "epoch": 0.7660961695191524, | |
| "grad_norm": 0.13243835140024088, | |
| "learning_rate": 0.00010497694015698214, | |
| "loss": 0.2502, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 0.7742461287693562, | |
| "grad_norm": 0.12096359907685643, | |
| "learning_rate": 9.811767009886681e-05, | |
| "loss": 0.2515, | |
| "step": 4750 | |
| }, | |
| { | |
| "epoch": 0.78239608801956, | |
| "grad_norm": 0.1010867422514499, | |
| "learning_rate": 9.145869895394685e-05, | |
| "loss": 0.2471, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 0.7905460472697636, | |
| "grad_norm": 0.12108612955883465, | |
| "learning_rate": 8.500444494929692e-05, | |
| "loss": 0.2508, | |
| "step": 4850 | |
| }, | |
| { | |
| "epoch": 0.7986960065199674, | |
| "grad_norm": 0.11827129819048823, | |
| "learning_rate": 7.875919048217753e-05, | |
| "loss": 0.2421, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 0.8068459657701712, | |
| "grad_norm": 0.10889141696060357, | |
| "learning_rate": 7.272707927866531e-05, | |
| "loss": 0.2444, | |
| "step": 4950 | |
| }, | |
| { | |
| "epoch": 0.8149959250203749, | |
| "grad_norm": 0.11478478031330713, | |
| "learning_rate": 6.691211364428989e-05, | |
| "loss": 0.239, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.8231458842705787, | |
| "grad_norm": 0.12806490540385113, | |
| "learning_rate": 6.131815180850508e-05, | |
| "loss": 0.2429, | |
| "step": 5050 | |
| }, | |
| { | |
| "epoch": 0.8312958435207825, | |
| "grad_norm": 0.10357727349126965, | |
| "learning_rate": 5.5948905364753945e-05, | |
| "loss": 0.2467, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 0.8394458027709861, | |
| "grad_norm": 0.1101292515864723, | |
| "learning_rate": 5.080793680782607e-05, | |
| "loss": 0.2405, | |
| "step": 5150 | |
| }, | |
| { | |
| "epoch": 0.8475957620211899, | |
| "grad_norm": 0.10144980764898691, | |
| "learning_rate": 4.5898657170142746e-05, | |
| "loss": 0.235, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 0.8557457212713936, | |
| "grad_norm": 0.11277819168557472, | |
| "learning_rate": 4.1224323758537155e-05, | |
| "loss": 0.2341, | |
| "step": 5250 | |
| }, | |
| { | |
| "epoch": 0.8638956805215974, | |
| "grad_norm": 0.10800888686256803, | |
| "learning_rate": 3.678803799303134e-05, | |
| "loss": 0.24, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 0.8720456397718012, | |
| "grad_norm": 0.11901575566402685, | |
| "learning_rate": 3.2592743349044186e-05, | |
| "loss": 0.2341, | |
| "step": 5350 | |
| }, | |
| { | |
| "epoch": 0.8801955990220048, | |
| "grad_norm": 0.12444346139158177, | |
| "learning_rate": 2.8641223404395524e-05, | |
| "loss": 0.2291, | |
| "step": 5400 | |
| }, | |
| { | |
| "epoch": 0.8883455582722086, | |
| "grad_norm": 0.10818161109308624, | |
| "learning_rate": 2.4936099992402606e-05, | |
| "loss": 0.2357, | |
| "step": 5450 | |
| }, | |
| { | |
| "epoch": 0.8964955175224124, | |
| "grad_norm": 0.12545021889499927, | |
| "learning_rate": 2.1479831462293265e-05, | |
| "loss": 0.2349, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.9046454767726161, | |
| "grad_norm": 0.14021615830916254, | |
| "learning_rate": 1.8274711048092084e-05, | |
| "loss": 0.2306, | |
| "step": 5550 | |
| }, | |
| { | |
| "epoch": 0.9127954360228199, | |
| "grad_norm": 0.10349748867815296, | |
| "learning_rate": 1.5322865347059044e-05, | |
| "loss": 0.2243, | |
| "step": 5600 | |
| }, | |
| { | |
| "epoch": 0.9209453952730237, | |
| "grad_norm": 0.11963300064608776, | |
| "learning_rate": 1.2626252908692638e-05, | |
| "loss": 0.2333, | |
| "step": 5650 | |
| }, | |
| { | |
| "epoch": 0.9290953545232273, | |
| "grad_norm": 0.10953396833548994, | |
| "learning_rate": 1.0186662935232384e-05, | |
| "loss": 0.2339, | |
| "step": 5700 | |
| }, | |
| { | |
| "epoch": 0.9372453137734311, | |
| "grad_norm": 0.1224263724970897, | |
| "learning_rate": 8.00571409452302e-06, | |
| "loss": 0.2313, | |
| "step": 5750 | |
| }, | |
| { | |
| "epoch": 0.9453952730236349, | |
| "grad_norm": 0.12352858513849092, | |
| "learning_rate": 6.084853446028671e-06, | |
| "loss": 0.2296, | |
| "step": 5800 | |
| }, | |
| { | |
| "epoch": 0.9535452322738386, | |
| "grad_norm": 0.12633679586576274, | |
| "learning_rate": 4.425355480708859e-06, | |
| "loss": 0.2354, | |
| "step": 5850 | |
| }, | |
| { | |
| "epoch": 0.9616951915240424, | |
| "grad_norm": 0.10627066652464928, | |
| "learning_rate": 3.028321275393786e-06, | |
| "loss": 0.2332, | |
| "step": 5900 | |
| }, | |
| { | |
| "epoch": 0.9698451507742462, | |
| "grad_norm": 0.12495472546410136, | |
| "learning_rate": 1.8946777622199652e-06, | |
| "loss": 0.2297, | |
| "step": 5950 | |
| }, | |
| { | |
| "epoch": 0.9779951100244498, | |
| "grad_norm": 0.11479937267870474, | |
| "learning_rate": 1.0251771136106314e-06, | |
| "loss": 0.2372, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.9861450692746536, | |
| "grad_norm": 0.1274989460799885, | |
| "learning_rate": 4.203962432096642e-07, | |
| "loss": 0.2316, | |
| "step": 6050 | |
| }, | |
| { | |
| "epoch": 0.9942950285248574, | |
| "grad_norm": 0.10997701182931913, | |
| "learning_rate": 8.073642309907036e-08, | |
| "loss": 0.2289, | |
| "step": 6100 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 6135, | |
| "total_flos": 307270109495296.0, | |
| "train_loss": 0.320441021565606, | |
| "train_runtime": 141453.5974, | |
| "train_samples_per_second": 6.245, | |
| "train_steps_per_second": 0.043 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 6135, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 307270109495296.0, | |
| "train_batch_size": 18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |