| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 1773, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.08460236886632826, |
| "grad_norm": 4.897884368896484, |
| "learning_rate": 1.9447264523406657e-05, |
| "loss": 2.026262054443359, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1692047377326565, |
| "grad_norm": 9.024230003356934, |
| "learning_rate": 1.888324873096447e-05, |
| "loss": 1.0631247711181642, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.25380710659898476, |
| "grad_norm": 8.573076248168945, |
| "learning_rate": 1.831923293852228e-05, |
| "loss": 0.8047801971435546, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.338409475465313, |
| "grad_norm": 9.223526954650879, |
| "learning_rate": 1.7755217146080094e-05, |
| "loss": 0.6834676361083984, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.4230118443316413, |
| "grad_norm": 6.011892795562744, |
| "learning_rate": 1.7191201353637904e-05, |
| "loss": 0.5958165359497071, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.5076142131979695, |
| "grad_norm": 7.655128002166748, |
| "learning_rate": 1.6627185561195714e-05, |
| "loss": 0.6095886993408203, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.5922165820642978, |
| "grad_norm": 6.9969353675842285, |
| "learning_rate": 1.6063169768753528e-05, |
| "loss": 0.5533372116088867, |
| "step": 350 |
| }, |
| { |
| "epoch": 0.676818950930626, |
| "grad_norm": 9.313193321228027, |
| "learning_rate": 1.5499153976311338e-05, |
| "loss": 0.5110644149780273, |
| "step": 400 |
| }, |
| { |
| "epoch": 0.7614213197969543, |
| "grad_norm": 12.71023941040039, |
| "learning_rate": 1.493513818386915e-05, |
| "loss": 0.5459028244018554, |
| "step": 450 |
| }, |
| { |
| "epoch": 0.8460236886632826, |
| "grad_norm": 8.374627113342285, |
| "learning_rate": 1.4371122391426961e-05, |
| "loss": 0.46964054107666015, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.9306260575296108, |
| "grad_norm": 9.238364219665527, |
| "learning_rate": 1.3807106598984771e-05, |
| "loss": 0.5043766021728515, |
| "step": 550 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_f1": 0.7749147704749069, |
| "eval_loss": 0.43065306544303894, |
| "eval_precision": 0.791417004048583, |
| "eval_recall": 0.7590866728797764, |
| "eval_runtime": 107.5887, |
| "eval_samples_per_second": 2.444, |
| "eval_steps_per_second": 0.613, |
| "step": 591 |
| }, |
| { |
| "epoch": 1.015228426395939, |
| "grad_norm": 5.481167793273926, |
| "learning_rate": 1.3243090806542585e-05, |
| "loss": 0.4575632858276367, |
| "step": 600 |
| }, |
| { |
| "epoch": 1.0998307952622675, |
| "grad_norm": 6.10057258605957, |
| "learning_rate": 1.2679075014100395e-05, |
| "loss": 0.43560176849365234, |
| "step": 650 |
| }, |
| { |
| "epoch": 1.1844331641285957, |
| "grad_norm": 9.03114128112793, |
| "learning_rate": 1.2115059221658207e-05, |
| "loss": 0.46458480834960936, |
| "step": 700 |
| }, |
| { |
| "epoch": 1.2690355329949239, |
| "grad_norm": 9.81558895111084, |
| "learning_rate": 1.155104342921602e-05, |
| "loss": 0.40803119659423825, |
| "step": 750 |
| }, |
| { |
| "epoch": 1.353637901861252, |
| "grad_norm": 15.4000825881958, |
| "learning_rate": 1.098702763677383e-05, |
| "loss": 0.42147384643554686, |
| "step": 800 |
| }, |
| { |
| "epoch": 1.4382402707275803, |
| "grad_norm": 10.52159595489502, |
| "learning_rate": 1.0423011844331642e-05, |
| "loss": 0.4100672149658203, |
| "step": 850 |
| }, |
| { |
| "epoch": 1.5228426395939088, |
| "grad_norm": 15.26666259765625, |
| "learning_rate": 9.858996051889454e-06, |
| "loss": 0.3965869903564453, |
| "step": 900 |
| }, |
| { |
| "epoch": 1.6074450084602367, |
| "grad_norm": 9.637870788574219, |
| "learning_rate": 9.294980259447264e-06, |
| "loss": 0.3966701126098633, |
| "step": 950 |
| }, |
| { |
| "epoch": 1.6920473773265652, |
| "grad_norm": 4.112008571624756, |
| "learning_rate": 8.730964467005076e-06, |
| "loss": 0.40687416076660154, |
| "step": 1000 |
| }, |
| { |
| "epoch": 1.7766497461928934, |
| "grad_norm": 11.278714179992676, |
| "learning_rate": 8.16694867456289e-06, |
| "loss": 0.41602436065673826, |
| "step": 1050 |
| }, |
| { |
| "epoch": 1.8612521150592216, |
| "grad_norm": 8.418536186218262, |
| "learning_rate": 7.602932882120701e-06, |
| "loss": 0.40810283660888674, |
| "step": 1100 |
| }, |
| { |
| "epoch": 1.94585448392555, |
| "grad_norm": 4.924833297729492, |
| "learning_rate": 7.038917089678512e-06, |
| "loss": 0.3806829833984375, |
| "step": 1150 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_f1": 0.8019422037747671, |
| "eval_loss": 0.3661089539527893, |
| "eval_precision": 0.8087190017374822, |
| "eval_recall": 0.795278036657347, |
| "eval_runtime": 105.196, |
| "eval_samples_per_second": 2.5, |
| "eval_steps_per_second": 0.627, |
| "step": 1182 |
| }, |
| { |
| "epoch": 2.030456852791878, |
| "grad_norm": 10.482388496398926, |
| "learning_rate": 6.4749012972363234e-06, |
| "loss": 0.36735050201416014, |
| "step": 1200 |
| }, |
| { |
| "epoch": 2.1150592216582065, |
| "grad_norm": 6.7676496505737305, |
| "learning_rate": 5.910885504794135e-06, |
| "loss": 0.3464337158203125, |
| "step": 1250 |
| }, |
| { |
| "epoch": 2.199661590524535, |
| "grad_norm": 8.209813117980957, |
| "learning_rate": 5.346869712351946e-06, |
| "loss": 0.34701999664306643, |
| "step": 1300 |
| }, |
| { |
| "epoch": 2.284263959390863, |
| "grad_norm": 9.558784484863281, |
| "learning_rate": 4.782853919909758e-06, |
| "loss": 0.3395441818237305, |
| "step": 1350 |
| }, |
| { |
| "epoch": 2.3688663282571913, |
| "grad_norm": 6.974896430969238, |
| "learning_rate": 4.218838127467569e-06, |
| "loss": 0.3871475601196289, |
| "step": 1400 |
| }, |
| { |
| "epoch": 2.4534686971235193, |
| "grad_norm": 9.049581527709961, |
| "learning_rate": 3.654822335025381e-06, |
| "loss": 0.3264299774169922, |
| "step": 1450 |
| }, |
| { |
| "epoch": 2.5380710659898478, |
| "grad_norm": 16.217670440673828, |
| "learning_rate": 3.0908065425831923e-06, |
| "loss": 0.3252403259277344, |
| "step": 1500 |
| }, |
| { |
| "epoch": 2.6226734348561758, |
| "grad_norm": 7.654144763946533, |
| "learning_rate": 2.5267907501410045e-06, |
| "loss": 0.3354499816894531, |
| "step": 1550 |
| }, |
| { |
| "epoch": 2.707275803722504, |
| "grad_norm": 8.84153938293457, |
| "learning_rate": 1.9627749576988155e-06, |
| "loss": 0.31287595748901365, |
| "step": 1600 |
| }, |
| { |
| "epoch": 2.7918781725888326, |
| "grad_norm": 8.133597373962402, |
| "learning_rate": 1.3987591652566273e-06, |
| "loss": 0.33677963256835936, |
| "step": 1650 |
| }, |
| { |
| "epoch": 2.8764805414551606, |
| "grad_norm": 5.950267791748047, |
| "learning_rate": 8.347433728144388e-07, |
| "loss": 0.32882442474365237, |
| "step": 1700 |
| }, |
| { |
| "epoch": 2.961082910321489, |
| "grad_norm": 9.175284385681152, |
| "learning_rate": 2.7072758037225044e-07, |
| "loss": 0.3340682220458984, |
| "step": 1750 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_f1": 0.8073293488518403, |
| "eval_loss": 0.3556199371814728, |
| "eval_precision": 0.8176170755017521, |
| "eval_recall": 0.7972972972972973, |
| "eval_runtime": 105.9353, |
| "eval_samples_per_second": 2.483, |
| "eval_steps_per_second": 0.623, |
| "step": 1773 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 1773, |
| "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": 463350353826816.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
