| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02297266253158741, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00011486331265793706, | |
| "eval_loss": NaN, | |
| "eval_runtime": 100.3681, | |
| "eval_samples_per_second": 18.263, | |
| "eval_steps_per_second": 9.136, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0011486331265793705, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2264, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.002297266253158741, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 2.002, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0034458993797381117, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 3.2142, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004594532506317482, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.005743165632896853, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6247, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.005743165632896853, | |
| "eval_loss": NaN, | |
| "eval_runtime": 98.6764, | |
| "eval_samples_per_second": 18.576, | |
| "eval_steps_per_second": 9.293, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.006891798759476223, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 3.6482, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.008040431886055594, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.436, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.009189065012634964, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0954, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.010337698139214336, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.011486331265793705, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4721, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.011486331265793705, | |
| "eval_loss": NaN, | |
| "eval_runtime": 98.6813, | |
| "eval_samples_per_second": 18.575, | |
| "eval_steps_per_second": 9.293, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.012634964392373075, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7792, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.013783597518952447, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.014932230645531817, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.3379, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.01608086377211119, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 1.1498, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.01722949689869056, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.499, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.01722949689869056, | |
| "eval_loss": NaN, | |
| "eval_runtime": 98.6846, | |
| "eval_samples_per_second": 18.574, | |
| "eval_steps_per_second": 9.292, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.018378130025269928, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.2116, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.0195267631518493, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1141, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.02067539627842867, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.02182402940500804, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0809, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.02297266253158741, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0745, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.02297266253158741, | |
| "eval_loss": NaN, | |
| "eval_runtime": 98.6665, | |
| "eval_samples_per_second": 18.578, | |
| "eval_steps_per_second": 9.294, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.440939984171827e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |