| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0021281878480473877, | |
| "eval_steps": 4, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.093959493491292e-05, | |
| "grad_norm": 10.073624610900879, | |
| "learning_rate": 2.0000000000000003e-06, | |
| "loss": 11.101, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.093959493491292e-05, | |
| "eval_loss": 5.3590240478515625, | |
| "eval_runtime": 571.8056, | |
| "eval_samples_per_second": 10.381, | |
| "eval_steps_per_second": 2.595, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014187918986982584, | |
| "grad_norm": 10.11988639831543, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 8.4331, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00021281878480473875, | |
| "grad_norm": 10.658834457397461, | |
| "learning_rate": 6e-06, | |
| "loss": 11.1969, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002837583797396517, | |
| "grad_norm": 23.196508407592773, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 17.7617, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0002837583797396517, | |
| "eval_loss": 5.353822231292725, | |
| "eval_runtime": 572.5718, | |
| "eval_samples_per_second": 10.367, | |
| "eval_steps_per_second": 2.592, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003546979746745646, | |
| "grad_norm": 16.436473846435547, | |
| "learning_rate": 1e-05, | |
| "loss": 8.2548, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004256375696094775, | |
| "grad_norm": 13.857950210571289, | |
| "learning_rate": 9.960573506572391e-06, | |
| "loss": 10.4373, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004965771645443905, | |
| "grad_norm": 12.2675142288208, | |
| "learning_rate": 9.842915805643156e-06, | |
| "loss": 9.1459, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005675167594793033, | |
| "grad_norm": 8.713933944702148, | |
| "learning_rate": 9.648882429441258e-06, | |
| "loss": 7.2224, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0005675167594793033, | |
| "eval_loss": 5.292234897613525, | |
| "eval_runtime": 572.0789, | |
| "eval_samples_per_second": 10.376, | |
| "eval_steps_per_second": 2.594, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006384563544142163, | |
| "grad_norm": 11.511612892150879, | |
| "learning_rate": 9.381533400219319e-06, | |
| "loss": 9.2579, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007093959493491292, | |
| "grad_norm": 9.224709510803223, | |
| "learning_rate": 9.045084971874738e-06, | |
| "loss": 6.1166, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0007803355442840422, | |
| "grad_norm": 18.363269805908203, | |
| "learning_rate": 8.644843137107058e-06, | |
| "loss": 10.5025, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.000851275139218955, | |
| "grad_norm": 8.955912590026855, | |
| "learning_rate": 8.18711994874345e-06, | |
| "loss": 5.7201, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.000851275139218955, | |
| "eval_loss": 5.211768627166748, | |
| "eval_runtime": 571.6674, | |
| "eval_samples_per_second": 10.384, | |
| "eval_steps_per_second": 2.596, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.000922214734153868, | |
| "grad_norm": 14.641721725463867, | |
| "learning_rate": 7.679133974894984e-06, | |
| "loss": 9.7903, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.000993154329088781, | |
| "grad_norm": 13.248905181884766, | |
| "learning_rate": 7.128896457825364e-06, | |
| "loss": 11.2527, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0010640939240236938, | |
| "grad_norm": 16.2312068939209, | |
| "learning_rate": 6.545084971874738e-06, | |
| "loss": 11.5525, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011350335189586067, | |
| "grad_norm": 10.564983367919922, | |
| "learning_rate": 5.936906572928625e-06, | |
| "loss": 7.3831, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0011350335189586067, | |
| "eval_loss": 5.125219345092773, | |
| "eval_runtime": 571.3846, | |
| "eval_samples_per_second": 10.389, | |
| "eval_steps_per_second": 2.597, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0012059731138935198, | |
| "grad_norm": 13.420829772949219, | |
| "learning_rate": 5.3139525976465675e-06, | |
| "loss": 11.1174, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0012769127088284326, | |
| "grad_norm": 16.875959396362305, | |
| "learning_rate": 4.686047402353433e-06, | |
| "loss": 11.7179, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013478523037633455, | |
| "grad_norm": 15.0596284866333, | |
| "learning_rate": 4.063093427071376e-06, | |
| "loss": 11.2813, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0014187918986982584, | |
| "grad_norm": 17.77897071838379, | |
| "learning_rate": 3.4549150281252635e-06, | |
| "loss": 8.9314, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014187918986982584, | |
| "eval_loss": 5.058083534240723, | |
| "eval_runtime": 571.3734, | |
| "eval_samples_per_second": 10.389, | |
| "eval_steps_per_second": 2.597, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014897314936331714, | |
| "grad_norm": 15.290266036987305, | |
| "learning_rate": 2.871103542174637e-06, | |
| "loss": 12.2422, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0015606710885680843, | |
| "grad_norm": 20.042848587036133, | |
| "learning_rate": 2.320866025105016e-06, | |
| "loss": 12.2315, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0016316106835029972, | |
| "grad_norm": 18.54485511779785, | |
| "learning_rate": 1.8128800512565514e-06, | |
| "loss": 10.9287, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.00170255027843791, | |
| "grad_norm": 13.682432174682617, | |
| "learning_rate": 1.3551568628929434e-06, | |
| "loss": 9.4619, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.00170255027843791, | |
| "eval_loss": 5.023678779602051, | |
| "eval_runtime": 572.14, | |
| "eval_samples_per_second": 10.375, | |
| "eval_steps_per_second": 2.594, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0017734898733728231, | |
| "grad_norm": 18.009124755859375, | |
| "learning_rate": 9.549150281252633e-07, | |
| "loss": 8.3285, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001844429468307736, | |
| "grad_norm": 13.645432472229004, | |
| "learning_rate": 6.184665997806832e-07, | |
| "loss": 10.0566, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0019153690632426488, | |
| "grad_norm": 18.476457595825195, | |
| "learning_rate": 3.511175705587433e-07, | |
| "loss": 12.3408, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.001986308658177562, | |
| "grad_norm": 12.815871238708496, | |
| "learning_rate": 1.5708419435684463e-07, | |
| "loss": 10.3213, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.001986308658177562, | |
| "eval_loss": 5.011484146118164, | |
| "eval_runtime": 571.8616, | |
| "eval_samples_per_second": 10.38, | |
| "eval_steps_per_second": 2.595, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.002057248253112475, | |
| "grad_norm": 13.162454605102539, | |
| "learning_rate": 3.9426493427611177e-08, | |
| "loss": 7.7106, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.0021281878480473877, | |
| "grad_norm": 11.562494277954102, | |
| "learning_rate": 0.0, | |
| "loss": 8.1572, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9801873028546560.0, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |