| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0, | |
| "eval_steps": 500, | |
| "global_step": 5478, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.054764512595837894, | |
| "grad_norm": 3.8052456378936768, | |
| "learning_rate": 1.8248175182481753e-05, | |
| "loss": 2.2411, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10952902519167579, | |
| "grad_norm": 2.646080255508423, | |
| "learning_rate": 3.649635036496351e-05, | |
| "loss": 1.8231, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.16429353778751368, | |
| "grad_norm": 2.700340986251831, | |
| "learning_rate": 5.474452554744526e-05, | |
| "loss": 1.7334, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21905805038335158, | |
| "grad_norm": 3.046970844268799, | |
| "learning_rate": 7.299270072992701e-05, | |
| "loss": 1.6861, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.2738225629791895, | |
| "grad_norm": 2.5365347862243652, | |
| "learning_rate": 9.124087591240877e-05, | |
| "loss": 1.6711, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.32858707557502737, | |
| "grad_norm": 2.219165802001953, | |
| "learning_rate": 9.997255186358079e-05, | |
| "loss": 1.6651, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.3833515881708653, | |
| "grad_norm": 2.6104276180267334, | |
| "learning_rate": 9.976563458663239e-05, | |
| "loss": 1.5924, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.43811610076670315, | |
| "grad_norm": 2.4602837562561035, | |
| "learning_rate": 9.93567000457336e-05, | |
| "loss": 1.5787, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.4928806133625411, | |
| "grad_norm": 2.33683705329895, | |
| "learning_rate": 9.874740825864108e-05, | |
| "loss": 1.5269, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.547645125958379, | |
| "grad_norm": 3.0263447761535645, | |
| "learning_rate": 9.794023256786919e-05, | |
| "loss": 1.5251, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.6024096385542169, | |
| "grad_norm": 2.4210712909698486, | |
| "learning_rate": 9.693844960047051e-05, | |
| "loss": 1.4886, | |
| "step": 1100 | |
| }, | |
| { | |
| "epoch": 0.6571741511500547, | |
| "grad_norm": 2.1745235919952393, | |
| "learning_rate": 9.574612596698522e-05, | |
| "loss": 1.4715, | |
| "step": 1200 | |
| }, | |
| { | |
| "epoch": 0.7119386637458927, | |
| "grad_norm": 2.216663360595703, | |
| "learning_rate": 9.436810175355263e-05, | |
| "loss": 1.4191, | |
| "step": 1300 | |
| }, | |
| { | |
| "epoch": 0.7667031763417306, | |
| "grad_norm": 2.010982036590576, | |
| "learning_rate": 9.280997087419733e-05, | |
| "loss": 1.4411, | |
| "step": 1400 | |
| }, | |
| { | |
| "epoch": 0.8214676889375685, | |
| "grad_norm": 2.0168168544769287, | |
| "learning_rate": 9.107805836304658e-05, | |
| "loss": 1.4264, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.8762322015334063, | |
| "grad_norm": 2.2413294315338135, | |
| "learning_rate": 8.91793946986587e-05, | |
| "loss": 1.4056, | |
| "step": 1600 | |
| }, | |
| { | |
| "epoch": 0.9309967141292442, | |
| "grad_norm": 2.189241409301758, | |
| "learning_rate": 8.712168726468965e-05, | |
| "loss": 1.368, | |
| "step": 1700 | |
| }, | |
| { | |
| "epoch": 0.9857612267250822, | |
| "grad_norm": 2.0814454555511475, | |
| "learning_rate": 8.491328906274937e-05, | |
| "loss": 1.3536, | |
| "step": 1800 | |
| }, | |
| { | |
| "epoch": 1.04052573932092, | |
| "grad_norm": 2.4284451007843018, | |
| "learning_rate": 8.256316480445412e-05, | |
| "loss": 1.1463, | |
| "step": 1900 | |
| }, | |
| { | |
| "epoch": 1.095290251916758, | |
| "grad_norm": 2.5235214233398438, | |
| "learning_rate": 8.008085452031985e-05, | |
| "loss": 1.0484, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 1.1500547645125958, | |
| "grad_norm": 2.3191304206848145, | |
| "learning_rate": 7.747643483322187e-05, | |
| "loss": 1.0878, | |
| "step": 2100 | |
| }, | |
| { | |
| "epoch": 1.2048192771084336, | |
| "grad_norm": 2.206143856048584, | |
| "learning_rate": 7.476047805362569e-05, | |
| "loss": 1.0593, | |
| "step": 2200 | |
| }, | |
| { | |
| "epoch": 1.2595837897042717, | |
| "grad_norm": 2.5182549953460693, | |
| "learning_rate": 7.194400926263763e-05, | |
| "loss": 1.0407, | |
| "step": 2300 | |
| }, | |
| { | |
| "epoch": 1.3143483023001095, | |
| "grad_norm": 2.556648015975952, | |
| "learning_rate": 6.903846155709005e-05, | |
| "loss": 1.0629, | |
| "step": 2400 | |
| }, | |
| { | |
| "epoch": 1.3691128148959475, | |
| "grad_norm": 2.1211650371551514, | |
| "learning_rate": 6.605562963833925e-05, | |
| "loss": 1.0505, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 1.4238773274917853, | |
| "grad_norm": 2.1135342121124268, | |
| "learning_rate": 6.300762193317518e-05, | |
| "loss": 0.9912, | |
| "step": 2600 | |
| }, | |
| { | |
| "epoch": 1.4786418400876231, | |
| "grad_norm": 2.554298162460327, | |
| "learning_rate": 5.9906811441203135e-05, | |
| "loss": 1.0007, | |
| "step": 2700 | |
| }, | |
| { | |
| "epoch": 1.5334063526834611, | |
| "grad_norm": 1.823740839958191, | |
| "learning_rate": 5.67657855082255e-05, | |
| "loss": 0.9865, | |
| "step": 2800 | |
| }, | |
| { | |
| "epoch": 1.588170865279299, | |
| "grad_norm": 1.8818488121032715, | |
| "learning_rate": 5.359729472951246e-05, | |
| "loss": 0.9782, | |
| "step": 2900 | |
| }, | |
| { | |
| "epoch": 1.642935377875137, | |
| "grad_norm": 2.093569040298462, | |
| "learning_rate": 5.041420119038218e-05, | |
| "loss": 0.9874, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 1.6976998904709748, | |
| "grad_norm": 2.0732619762420654, | |
| "learning_rate": 4.72294262542015e-05, | |
| "loss": 0.984, | |
| "step": 3100 | |
| }, | |
| { | |
| "epoch": 1.7524644030668126, | |
| "grad_norm": 1.9700407981872559, | |
| "learning_rate": 4.405589810975468e-05, | |
| "loss": 0.9442, | |
| "step": 3200 | |
| }, | |
| { | |
| "epoch": 1.8072289156626506, | |
| "grad_norm": 1.8880764245986938, | |
| "learning_rate": 4.090649929090541e-05, | |
| "loss": 0.9511, | |
| "step": 3300 | |
| }, | |
| { | |
| "epoch": 1.8619934282584885, | |
| "grad_norm": 1.8169358968734741, | |
| "learning_rate": 3.7794014381589125e-05, | |
| "loss": 0.9123, | |
| "step": 3400 | |
| }, | |
| { | |
| "epoch": 1.9167579408543265, | |
| "grad_norm": 2.062743663787842, | |
| "learning_rate": 3.473107811842055e-05, | |
| "loss": 0.9308, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 1.9715224534501643, | |
| "grad_norm": 1.9522345066070557, | |
| "learning_rate": 3.173012410158744e-05, | |
| "loss": 0.9195, | |
| "step": 3600 | |
| }, | |
| { | |
| "epoch": 2.026286966046002, | |
| "grad_norm": 1.4607131481170654, | |
| "learning_rate": 2.8803334322232017e-05, | |
| "loss": 0.7255, | |
| "step": 3700 | |
| }, | |
| { | |
| "epoch": 2.08105147864184, | |
| "grad_norm": 2.2295525074005127, | |
| "learning_rate": 2.596258971120737e-05, | |
| "loss": 0.5014, | |
| "step": 3800 | |
| }, | |
| { | |
| "epoch": 2.135815991237678, | |
| "grad_norm": 1.6707744598388672, | |
| "learning_rate": 2.3219421909949735e-05, | |
| "loss": 0.5206, | |
| "step": 3900 | |
| }, | |
| { | |
| "epoch": 2.190580503833516, | |
| "grad_norm": 1.4230283498764038, | |
| "learning_rate": 2.0584966459246906e-05, | |
| "loss": 0.4994, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 2.245345016429354, | |
| "grad_norm": 1.987844467163086, | |
| "learning_rate": 1.8069917595926504e-05, | |
| "loss": 0.4941, | |
| "step": 4100 | |
| }, | |
| { | |
| "epoch": 2.3001095290251916, | |
| "grad_norm": 1.8899997472763062, | |
| "learning_rate": 1.568448484096205e-05, | |
| "loss": 0.4926, | |
| "step": 4200 | |
| }, | |
| { | |
| "epoch": 2.3548740416210294, | |
| "grad_norm": 2.2514610290527344, | |
| "learning_rate": 1.3438351555220874e-05, | |
| "loss": 0.4809, | |
| "step": 4300 | |
| }, | |
| { | |
| "epoch": 2.4096385542168672, | |
| "grad_norm": 1.9894077777862549, | |
| "learning_rate": 1.1340635631092428e-05, | |
| "loss": 0.4834, | |
| "step": 4400 | |
| }, | |
| { | |
| "epoch": 2.4644030668127055, | |
| "grad_norm": 2.134925603866577, | |
| "learning_rate": 9.399852479563775e-06, | |
| "loss": 0.494, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 2.5191675794085433, | |
| "grad_norm": 1.5433528423309326, | |
| "learning_rate": 7.623880462991801e-06, | |
| "loss": 0.475, | |
| "step": 4600 | |
| }, | |
| { | |
| "epoch": 2.573932092004381, | |
| "grad_norm": 1.8533953428268433, | |
| "learning_rate": 6.019928913893208e-06, | |
| "loss": 0.4692, | |
| "step": 4700 | |
| }, | |
| { | |
| "epoch": 2.628696604600219, | |
| "grad_norm": 1.9672038555145264, | |
| "learning_rate": 4.594508869576164e-06, | |
| "loss": 0.4806, | |
| "step": 4800 | |
| }, | |
| { | |
| "epoch": 2.6834611171960567, | |
| "grad_norm": 1.722920536994934, | |
| "learning_rate": 3.35340664141246e-06, | |
| "loss": 0.4629, | |
| "step": 4900 | |
| }, | |
| { | |
| "epoch": 2.738225629791895, | |
| "grad_norm": 2.070141315460205, | |
| "learning_rate": 2.301660326042443e-06, | |
| "loss": 0.4596, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 2.792990142387733, | |
| "grad_norm": 1.5731868743896484, | |
| "learning_rate": 1.4435393538625497e-06, | |
| "loss": 0.4652, | |
| "step": 5100 | |
| }, | |
| { | |
| "epoch": 2.8477546549835706, | |
| "grad_norm": 1.4046640396118164, | |
| "learning_rate": 7.825271578155602e-07, | |
| "loss": 0.4419, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 2.9025191675794084, | |
| "grad_norm": 2.1482276916503906, | |
| "learning_rate": 3.2130703283768106e-07, | |
| "loss": 0.4663, | |
| "step": 5300 | |
| }, | |
| { | |
| "epoch": 2.9572836801752462, | |
| "grad_norm": 1.5635905265808105, | |
| "learning_rate": 6.175124336402217e-08, | |
| "loss": 0.4757, | |
| "step": 5400 | |
| } | |
| ], | |
| "logging_steps": 100, | |
| "max_steps": 5478, | |
| "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": 2.633057747449823e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |