| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.9196940726577436, | |
| "eval_steps": 500, | |
| "global_step": 4100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04780114722753346, | |
| "grad_norm": 0.0546465665102005, | |
| "learning_rate": 4.941443594646272e-05, | |
| "loss": 2.2922, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.09560229445506692, | |
| "grad_norm": 0.08099879324436188, | |
| "learning_rate": 4.881692160611855e-05, | |
| "loss": 2.2658, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.14340344168260039, | |
| "grad_norm": 0.08135072886943817, | |
| "learning_rate": 4.821940726577438e-05, | |
| "loss": 2.1959, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.19120458891013384, | |
| "grad_norm": 0.08765063434839249, | |
| "learning_rate": 4.7621892925430214e-05, | |
| "loss": 2.1285, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2390057361376673, | |
| "grad_norm": 0.10307478904724121, | |
| "learning_rate": 4.7024378585086046e-05, | |
| "loss": 2.0899, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.28680688336520077, | |
| "grad_norm": 0.10948552936315536, | |
| "learning_rate": 4.642686424474187e-05, | |
| "loss": 2.0663, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.33460803059273425, | |
| "grad_norm": 0.1135614812374115, | |
| "learning_rate": 4.5829349904397704e-05, | |
| "loss": 2.0508, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.3824091778202677, | |
| "grad_norm": 0.12696176767349243, | |
| "learning_rate": 4.5231835564053536e-05, | |
| "loss": 1.9819, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.43021032504780116, | |
| "grad_norm": 0.13437969982624054, | |
| "learning_rate": 4.463432122370937e-05, | |
| "loss": 2.0004, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.4780114722753346, | |
| "grad_norm": 0.1275995969772339, | |
| "learning_rate": 4.40368068833652e-05, | |
| "loss": 1.9961, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.5258126195028681, | |
| "grad_norm": 0.14496305584907532, | |
| "learning_rate": 4.343929254302104e-05, | |
| "loss": 1.9855, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5736137667304015, | |
| "grad_norm": 0.13401177525520325, | |
| "learning_rate": 4.284177820267687e-05, | |
| "loss": 1.976, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.621414913957935, | |
| "grad_norm": 0.15063685178756714, | |
| "learning_rate": 4.2244263862332704e-05, | |
| "loss": 1.9428, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6692160611854685, | |
| "grad_norm": 0.1525646150112152, | |
| "learning_rate": 4.164674952198853e-05, | |
| "loss": 1.9565, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.7170172084130019, | |
| "grad_norm": 0.1553465574979782, | |
| "learning_rate": 4.104923518164436e-05, | |
| "loss": 1.9499, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7648183556405354, | |
| "grad_norm": 0.178068146109581, | |
| "learning_rate": 4.0451720841300193e-05, | |
| "loss": 1.9342, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.8126195028680688, | |
| "grad_norm": 0.16074113547801971, | |
| "learning_rate": 3.9854206500956026e-05, | |
| "loss": 1.9304, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8604206500956023, | |
| "grad_norm": 0.17012304067611694, | |
| "learning_rate": 3.925669216061186e-05, | |
| "loss": 1.9358, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.9082217973231358, | |
| "grad_norm": 0.1635637879371643, | |
| "learning_rate": 3.865917782026769e-05, | |
| "loss": 1.9145, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.9560229445506692, | |
| "grad_norm": 0.18287719786167145, | |
| "learning_rate": 3.806166347992352e-05, | |
| "loss": 1.9186, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0038240917782026, | |
| "grad_norm": 0.18034423887729645, | |
| "learning_rate": 3.7464149139579354e-05, | |
| "loss": 1.8995, | |
| "step": 1050 | |
| }, | |
| { | |
| "epoch": 1.0516252390057361, | |
| "grad_norm": 0.16354230046272278, | |
| "learning_rate": 3.6866634799235186e-05, | |
| "loss": 1.9068, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 1.0994263862332696, | |
| "grad_norm": 0.236989825963974, | |
| "learning_rate": 3.626912045889101e-05, | |
| "loss": 1.9141, | |
| "step": 1150 | |
| }, | |
| { | |
| "epoch": 1.147227533460803, | |
| "grad_norm": 0.2356785088777542, | |
| "learning_rate": 3.5671606118546844e-05, | |
| "loss": 1.9088, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 1.1950286806883366, | |
| "grad_norm": 0.1805247962474823, | |
| "learning_rate": 3.5074091778202676e-05, | |
| "loss": 1.8923, | |
| "step": 1250 | |
| }, | |
| { | |
| "epoch": 1.24282982791587, | |
| "grad_norm": 0.21303710341453552, | |
| "learning_rate": 3.447657743785851e-05, | |
| "loss": 1.898, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 1.2906309751434035, | |
| "grad_norm": 0.18716047704219818, | |
| "learning_rate": 3.387906309751434e-05, | |
| "loss": 1.8986, | |
| "step": 1350 | |
| }, | |
| { | |
| "epoch": 1.338432122370937, | |
| "grad_norm": 0.16454172134399414, | |
| "learning_rate": 3.328154875717017e-05, | |
| "loss": 1.9149, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 1.3862332695984705, | |
| "grad_norm": 0.18206411600112915, | |
| "learning_rate": 3.2684034416826005e-05, | |
| "loss": 1.8662, | |
| "step": 1450 | |
| }, | |
| { | |
| "epoch": 1.4340344168260037, | |
| "grad_norm": 0.19803249835968018, | |
| "learning_rate": 3.208652007648184e-05, | |
| "loss": 1.9015, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.4818355640535372, | |
| "grad_norm": 0.19260399043560028, | |
| "learning_rate": 3.148900573613767e-05, | |
| "loss": 1.905, | |
| "step": 1550 | |
| }, | |
| { | |
| "epoch": 1.5296367112810707, | |
| "grad_norm": 0.20765070617198944, | |
| "learning_rate": 3.08914913957935e-05, | |
| "loss": 1.8981, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 1.5774378585086042, | |
| "grad_norm": 0.1981675922870636, | |
| "learning_rate": 3.029397705544933e-05, | |
| "loss": 1.8957, | |
| "step": 1650 | |
| }, | |
| { | |
| "epoch": 1.6252390057361377, | |
| "grad_norm": 0.19996145367622375, | |
| "learning_rate": 2.9696462715105166e-05, | |
| "loss": 1.8797, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 1.6730401529636711, | |
| "grad_norm": 0.21547172963619232, | |
| "learning_rate": 2.9098948374760998e-05, | |
| "loss": 1.8919, | |
| "step": 1750 | |
| }, | |
| { | |
| "epoch": 1.7208413001912046, | |
| "grad_norm": 0.21214577555656433, | |
| "learning_rate": 2.850143403441683e-05, | |
| "loss": 1.8942, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.7686424474187379, | |
| "grad_norm": 0.19430747628211975, | |
| "learning_rate": 2.7903919694072662e-05, | |
| "loss": 1.8744, | |
| "step": 1850 | |
| }, | |
| { | |
| "epoch": 1.8164435946462714, | |
| "grad_norm": 0.20672687888145447, | |
| "learning_rate": 2.730640535372849e-05, | |
| "loss": 1.8784, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.8642447418738048, | |
| "grad_norm": 0.204985573887825, | |
| "learning_rate": 2.6708891013384323e-05, | |
| "loss": 1.8902, | |
| "step": 1950 | |
| }, | |
| { | |
| "epoch": 1.9120458891013383, | |
| "grad_norm": 0.20450404286384583, | |
| "learning_rate": 2.6111376673040155e-05, | |
| "loss": 1.8649, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.9598470363288718, | |
| "grad_norm": 0.20468485355377197, | |
| "learning_rate": 2.5513862332695987e-05, | |
| "loss": 1.8899, | |
| "step": 2050 | |
| }, | |
| { | |
| "epoch": 2.0076481835564053, | |
| "grad_norm": 0.206816628575325, | |
| "learning_rate": 2.491634799235182e-05, | |
| "loss": 1.8607, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 2.0554493307839388, | |
| "grad_norm": 0.2078491896390915, | |
| "learning_rate": 2.431883365200765e-05, | |
| "loss": 1.8737, | |
| "step": 2150 | |
| }, | |
| { | |
| "epoch": 2.1032504780114722, | |
| "grad_norm": 0.19321344792842865, | |
| "learning_rate": 2.372131931166348e-05, | |
| "loss": 1.8597, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 2.1510516252390057, | |
| "grad_norm": 0.22135953605175018, | |
| "learning_rate": 2.3123804971319313e-05, | |
| "loss": 1.88, | |
| "step": 2250 | |
| }, | |
| { | |
| "epoch": 2.198852772466539, | |
| "grad_norm": 0.20404009521007538, | |
| "learning_rate": 2.2526290630975145e-05, | |
| "loss": 1.8908, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 2.2466539196940727, | |
| "grad_norm": 0.21296437084674835, | |
| "learning_rate": 2.1928776290630977e-05, | |
| "loss": 1.8632, | |
| "step": 2350 | |
| }, | |
| { | |
| "epoch": 2.294455066921606, | |
| "grad_norm": 0.2082318514585495, | |
| "learning_rate": 2.1331261950286806e-05, | |
| "loss": 1.8819, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 2.3422562141491396, | |
| "grad_norm": 0.2119467705488205, | |
| "learning_rate": 2.0733747609942638e-05, | |
| "loss": 1.8679, | |
| "step": 2450 | |
| }, | |
| { | |
| "epoch": 2.390057361376673, | |
| "grad_norm": 0.2162160575389862, | |
| "learning_rate": 2.013623326959847e-05, | |
| "loss": 1.8698, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.4378585086042066, | |
| "grad_norm": 0.19639310240745544, | |
| "learning_rate": 1.9538718929254306e-05, | |
| "loss": 1.8808, | |
| "step": 2550 | |
| }, | |
| { | |
| "epoch": 2.48565965583174, | |
| "grad_norm": 0.2149832397699356, | |
| "learning_rate": 1.8941204588910135e-05, | |
| "loss": 1.8743, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 2.5334608030592736, | |
| "grad_norm": 0.20657892525196075, | |
| "learning_rate": 1.8343690248565967e-05, | |
| "loss": 1.8611, | |
| "step": 2650 | |
| }, | |
| { | |
| "epoch": 2.581261950286807, | |
| "grad_norm": 0.22579824924468994, | |
| "learning_rate": 1.77461759082218e-05, | |
| "loss": 1.8834, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 2.62906309751434, | |
| "grad_norm": 0.214285746216774, | |
| "learning_rate": 1.714866156787763e-05, | |
| "loss": 1.8712, | |
| "step": 2750 | |
| }, | |
| { | |
| "epoch": 2.676864244741874, | |
| "grad_norm": 0.2056400179862976, | |
| "learning_rate": 1.6551147227533463e-05, | |
| "loss": 1.8515, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 2.724665391969407, | |
| "grad_norm": 0.21018265187740326, | |
| "learning_rate": 1.5953632887189292e-05, | |
| "loss": 1.8537, | |
| "step": 2850 | |
| }, | |
| { | |
| "epoch": 2.772466539196941, | |
| "grad_norm": 0.1982487589120865, | |
| "learning_rate": 1.5356118546845124e-05, | |
| "loss": 1.8637, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 2.820267686424474, | |
| "grad_norm": 0.22870182991027832, | |
| "learning_rate": 1.4758604206500956e-05, | |
| "loss": 1.857, | |
| "step": 2950 | |
| }, | |
| { | |
| "epoch": 2.8680688336520075, | |
| "grad_norm": 0.2098233997821808, | |
| "learning_rate": 1.4161089866156787e-05, | |
| "loss": 1.8433, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 2.915869980879541, | |
| "grad_norm": 0.23259004950523376, | |
| "learning_rate": 1.3563575525812619e-05, | |
| "loss": 1.8934, | |
| "step": 3050 | |
| }, | |
| { | |
| "epoch": 2.9636711281070744, | |
| "grad_norm": 0.2191799432039261, | |
| "learning_rate": 1.2966061185468451e-05, | |
| "loss": 1.8603, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 3.011472275334608, | |
| "grad_norm": 0.21849119663238525, | |
| "learning_rate": 1.2368546845124283e-05, | |
| "loss": 1.8603, | |
| "step": 3150 | |
| }, | |
| { | |
| "epoch": 3.0592734225621414, | |
| "grad_norm": 0.22140590846538544, | |
| "learning_rate": 1.1771032504780115e-05, | |
| "loss": 1.8696, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 3.107074569789675, | |
| "grad_norm": 0.2533087432384491, | |
| "learning_rate": 1.1173518164435948e-05, | |
| "loss": 1.8491, | |
| "step": 3250 | |
| }, | |
| { | |
| "epoch": 3.1548757170172084, | |
| "grad_norm": 0.22291821241378784, | |
| "learning_rate": 1.057600382409178e-05, | |
| "loss": 1.8664, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 3.202676864244742, | |
| "grad_norm": 0.23389829695224762, | |
| "learning_rate": 9.97848948374761e-06, | |
| "loss": 1.8633, | |
| "step": 3350 | |
| }, | |
| { | |
| "epoch": 3.2504780114722753, | |
| "grad_norm": 0.2284611165523529, | |
| "learning_rate": 9.380975143403442e-06, | |
| "loss": 1.8739, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 3.298279158699809, | |
| "grad_norm": 0.2357141673564911, | |
| "learning_rate": 8.783460803059273e-06, | |
| "loss": 1.8837, | |
| "step": 3450 | |
| }, | |
| { | |
| "epoch": 3.3460803059273423, | |
| "grad_norm": 0.23133474588394165, | |
| "learning_rate": 8.185946462715105e-06, | |
| "loss": 1.8284, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.3938814531548758, | |
| "grad_norm": 0.24003466963768005, | |
| "learning_rate": 7.588432122370938e-06, | |
| "loss": 1.8557, | |
| "step": 3550 | |
| }, | |
| { | |
| "epoch": 3.4416826003824093, | |
| "grad_norm": 0.22754019498825073, | |
| "learning_rate": 6.990917782026769e-06, | |
| "loss": 1.8726, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 3.4894837476099427, | |
| "grad_norm": 0.24840685725212097, | |
| "learning_rate": 6.393403441682601e-06, | |
| "loss": 1.8683, | |
| "step": 3650 | |
| }, | |
| { | |
| "epoch": 3.537284894837476, | |
| "grad_norm": 0.23282456398010254, | |
| "learning_rate": 5.795889101338432e-06, | |
| "loss": 1.8624, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 3.5850860420650097, | |
| "grad_norm": 0.22449611127376556, | |
| "learning_rate": 5.198374760994264e-06, | |
| "loss": 1.8355, | |
| "step": 3750 | |
| }, | |
| { | |
| "epoch": 3.632887189292543, | |
| "grad_norm": 0.22073350846767426, | |
| "learning_rate": 4.6008604206500955e-06, | |
| "loss": 1.8706, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 3.6806883365200767, | |
| "grad_norm": 0.2504482567310333, | |
| "learning_rate": 4.003346080305928e-06, | |
| "loss": 1.8607, | |
| "step": 3850 | |
| }, | |
| { | |
| "epoch": 3.7284894837476097, | |
| "grad_norm": 0.23835700750350952, | |
| "learning_rate": 3.4058317399617594e-06, | |
| "loss": 1.8495, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 3.7762906309751436, | |
| "grad_norm": 0.2028919905424118, | |
| "learning_rate": 2.808317399617591e-06, | |
| "loss": 1.8423, | |
| "step": 3950 | |
| }, | |
| { | |
| "epoch": 3.8240917782026767, | |
| "grad_norm": 0.23366276919841766, | |
| "learning_rate": 2.210803059273423e-06, | |
| "loss": 1.8431, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 3.8718929254302106, | |
| "grad_norm": 0.261652410030365, | |
| "learning_rate": 1.6132887189292542e-06, | |
| "loss": 1.8639, | |
| "step": 4050 | |
| }, | |
| { | |
| "epoch": 3.9196940726577436, | |
| "grad_norm": 0.2397291362285614, | |
| "learning_rate": 1.015774378585086e-06, | |
| "loss": 1.8626, | |
| "step": 4100 | |
| } | |
| ], | |
| "logging_steps": 50, | |
| "max_steps": 4184, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.491537700349542e+16, | |
| "train_batch_size": 10, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |