| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.8849557522123894, | |
| "eval_steps": 9, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008849557522123894, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.7459, | |
| "eval_samples_per_second": 33.067, | |
| "eval_steps_per_second": 4.177, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.02654867256637168, | |
| "grad_norm": NaN, | |
| "learning_rate": 3e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.05309734513274336, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.07964601769911504, | |
| "grad_norm": NaN, | |
| "learning_rate": 9e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.07964601769911504, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2422, | |
| "eval_samples_per_second": 36.244, | |
| "eval_steps_per_second": 4.578, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.10619469026548672, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.13274336283185842, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.1592920353982301, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1592920353982301, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2369, | |
| "eval_samples_per_second": 36.281, | |
| "eval_steps_per_second": 4.583, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.18584070796460178, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.21238938053097345, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.23893805309734514, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.23893805309734514, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2467, | |
| "eval_samples_per_second": 36.213, | |
| "eval_steps_per_second": 4.574, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.26548672566371684, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.2920353982300885, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.3185840707964602, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.3185840707964602, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.252, | |
| "eval_samples_per_second": 36.177, | |
| "eval_steps_per_second": 4.57, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.34513274336283184, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.37168141592920356, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.39823008849557523, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.39823008849557523, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2469, | |
| "eval_samples_per_second": 36.212, | |
| "eval_steps_per_second": 4.574, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4247787610619469, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.45132743362831856, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.4778761061946903, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 0.0, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.4778761061946903, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2495, | |
| "eval_samples_per_second": 36.194, | |
| "eval_steps_per_second": 4.572, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.504424778761062, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 0.0, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.5309734513274337, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5575221238938053, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 0.0, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.5575221238938053, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2548, | |
| "eval_samples_per_second": 36.157, | |
| "eval_steps_per_second": 4.567, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.584070796460177, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 0.0, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.6106194690265486, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 0.0, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.6371681415929203, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 0.0, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6371681415929203, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2459, | |
| "eval_samples_per_second": 36.219, | |
| "eval_steps_per_second": 4.575, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.6637168141592921, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 0.0, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6902654867256637, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 0.0, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.7168141592920354, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 0.0, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7168141592920354, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2465, | |
| "eval_samples_per_second": 36.214, | |
| "eval_steps_per_second": 4.574, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.7433628318584071, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.597595192178702e-06, | |
| "loss": 0.0, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.7699115044247787, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.060297685041659e-06, | |
| "loss": 0.0, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.7964601769911505, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0153689607045845e-06, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.7964601769911505, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2502, | |
| "eval_samples_per_second": 36.189, | |
| "eval_steps_per_second": 4.571, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8230088495575221, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.4852136862001764e-06, | |
| "loss": 0.0, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.8495575221238938, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.865965629214819e-07, | |
| "loss": 0.0, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.8761061946902655, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.04586490452119e-08, | |
| "loss": 0.0, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.8761061946902655, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.2548, | |
| "eval_samples_per_second": 36.158, | |
| "eval_steps_per_second": 4.567, | |
| "step": 99 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7214473068544e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |