| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.3929971796106486, | |
| "global_step": 40500, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0019942675013184747, | |
| "loss": 0.2155, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0019885350026369497, | |
| "loss": 0.2135, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.001982802503955424, | |
| "loss": 0.2123, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.001977070005273899, | |
| "loss": 0.2196, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0019713375065923736, | |
| "loss": 0.2223, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0019656050079108482, | |
| "loss": 0.2209, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.001959872509229323, | |
| "loss": 0.2181, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0019541400105477975, | |
| "loss": 0.2142, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0019484075118662723, | |
| "loss": 0.2145, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.001942675013184747, | |
| "loss": 0.2261, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.0019369425145032218, | |
| "loss": 0.2171, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0019312100158216962, | |
| "loss": 0.2158, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.001925477517140171, | |
| "loss": 0.2179, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.001919745018458646, | |
| "loss": 0.2137, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.0019140125197771205, | |
| "loss": 0.2148, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.0019082800210955954, | |
| "loss": 0.2114, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.29, | |
| "learning_rate": 0.0019025475224140698, | |
| "loss": 0.2138, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.0018968150237325446, | |
| "loss": 0.2159, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0018910825250510192, | |
| "loss": 0.2185, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.34, | |
| "learning_rate": 0.001885350026369494, | |
| "loss": 0.2123, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0018796175276879685, | |
| "loss": 0.2172, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.38, | |
| "learning_rate": 0.0018738850290064433, | |
| "loss": 0.2162, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.001868152530324918, | |
| "loss": 0.2103, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.0018624200316433928, | |
| "loss": 0.221, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 0.0018566875329618674, | |
| "loss": 0.2108, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.001850955034280342, | |
| "loss": 0.2217, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.001845222535598817, | |
| "loss": 0.2157, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.0018394900369172915, | |
| "loss": 0.2076, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.0018337575382357664, | |
| "loss": 0.2162, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.52, | |
| "learning_rate": 0.001828025039554241, | |
| "loss": 0.207, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0018222925408727156, | |
| "loss": 0.2131, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.0018165600421911903, | |
| "loss": 0.2119, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.001810827543509665, | |
| "loss": 0.2205, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.0018050950448281397, | |
| "loss": 0.2134, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0017993625461466144, | |
| "loss": 0.216, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.001793630047465089, | |
| "loss": 0.2132, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.0017878975487835638, | |
| "loss": 0.2125, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 0.65, | |
| "learning_rate": 0.0017821650501020385, | |
| "loss": 0.2138, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 0.0017764325514205133, | |
| "loss": 0.2111, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 0.69, | |
| "learning_rate": 0.001770700052738988, | |
| "loss": 0.209, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 0.71, | |
| "learning_rate": 0.0017649675540574626, | |
| "loss": 0.2086, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 0.72, | |
| "learning_rate": 0.0017592350553759374, | |
| "loss": 0.211, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 0.74, | |
| "learning_rate": 0.001753502556694412, | |
| "loss": 0.206, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 0.76, | |
| "learning_rate": 0.0017477700580128869, | |
| "loss": 0.2149, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 0.0017420375593313613, | |
| "loss": 0.2093, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 0.79, | |
| "learning_rate": 0.0017363050606498361, | |
| "loss": 0.2089, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 0.81, | |
| "learning_rate": 0.0017305725619683107, | |
| "loss": 0.2093, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 0.0017248400632867856, | |
| "loss": 0.2009, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 0.84, | |
| "learning_rate": 0.00171910756460526, | |
| "loss": 0.2058, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 0.86, | |
| "learning_rate": 0.0017133750659237348, | |
| "loss": 0.2143, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 0.88, | |
| "learning_rate": 0.0017076425672422095, | |
| "loss": 0.2071, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 0.89, | |
| "learning_rate": 0.0017019100685606843, | |
| "loss": 0.2098, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 0.91, | |
| "learning_rate": 0.0016961775698791592, | |
| "loss": 0.2064, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 0.0016904450711976336, | |
| "loss": 0.207, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 0.95, | |
| "learning_rate": 0.0016847125725161084, | |
| "loss": 0.2063, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 0.001678980073834583, | |
| "loss": 0.2109, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 0.98, | |
| "learning_rate": 0.0016732475751530579, | |
| "loss": 0.2038, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 0.0016675150764715325, | |
| "loss": 0.2082, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 0.1924375593662262, | |
| "eval_runtime": 1182.2501, | |
| "eval_samples_per_second": 147.549, | |
| "eval_steps_per_second": 6.148, | |
| "step": 29074 | |
| }, | |
| { | |
| "epoch": 1.01, | |
| "learning_rate": 0.0016617825777900071, | |
| "loss": 0.2098, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 0.0016560500791084818, | |
| "loss": 0.2011, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 1.05, | |
| "learning_rate": 0.0016503175804269566, | |
| "loss": 0.2008, | |
| "step": 30500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 0.0016445850817454312, | |
| "loss": 0.1995, | |
| "step": 31000 | |
| }, | |
| { | |
| "epoch": 1.08, | |
| "learning_rate": 0.0016388525830639059, | |
| "loss": 0.2022, | |
| "step": 31500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 0.0016331200843823805, | |
| "loss": 0.2006, | |
| "step": 32000 | |
| }, | |
| { | |
| "epoch": 1.12, | |
| "learning_rate": 0.0016273875857008553, | |
| "loss": 0.2007, | |
| "step": 32500 | |
| }, | |
| { | |
| "epoch": 1.14, | |
| "learning_rate": 0.0016216550870193302, | |
| "loss": 0.2041, | |
| "step": 33000 | |
| }, | |
| { | |
| "epoch": 1.15, | |
| "learning_rate": 0.0016159225883378048, | |
| "loss": 0.2069, | |
| "step": 33500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 0.0016101900896562794, | |
| "loss": 0.2029, | |
| "step": 34000 | |
| }, | |
| { | |
| "epoch": 1.19, | |
| "learning_rate": 0.001604457590974754, | |
| "loss": 0.2002, | |
| "step": 34500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 0.0015987250922932289, | |
| "loss": 0.2026, | |
| "step": 35000 | |
| }, | |
| { | |
| "epoch": 1.22, | |
| "learning_rate": 0.0015929925936117035, | |
| "loss": 0.1978, | |
| "step": 35500 | |
| }, | |
| { | |
| "epoch": 1.24, | |
| "learning_rate": 0.0015872600949301781, | |
| "loss": 0.2063, | |
| "step": 36000 | |
| }, | |
| { | |
| "epoch": 1.26, | |
| "learning_rate": 0.0015815275962486528, | |
| "loss": 0.1958, | |
| "step": 36500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 0.0015757950975671276, | |
| "loss": 0.2023, | |
| "step": 37000 | |
| }, | |
| { | |
| "epoch": 1.29, | |
| "learning_rate": 0.0015700625988856022, | |
| "loss": 0.2014, | |
| "step": 37500 | |
| }, | |
| { | |
| "epoch": 1.31, | |
| "learning_rate": 0.001564330100204077, | |
| "loss": 0.2116, | |
| "step": 38000 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "learning_rate": 0.0015585976015225515, | |
| "loss": 0.2047, | |
| "step": 38500 | |
| }, | |
| { | |
| "epoch": 1.34, | |
| "learning_rate": 0.0015528651028410263, | |
| "loss": 0.2048, | |
| "step": 39000 | |
| }, | |
| { | |
| "epoch": 1.36, | |
| "learning_rate": 0.0015471326041595012, | |
| "loss": 0.2003, | |
| "step": 39500 | |
| }, | |
| { | |
| "epoch": 1.38, | |
| "learning_rate": 0.0015414001054779758, | |
| "loss": 0.2046, | |
| "step": 40000 | |
| }, | |
| { | |
| "epoch": 1.39, | |
| "learning_rate": 0.0015356676067964507, | |
| "loss": 0.2001, | |
| "step": 40500 | |
| } | |
| ], | |
| "max_steps": 174444, | |
| "num_train_epochs": 6, | |
| "total_flos": 1.3154952419475456e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |