| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00031196381219778506, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.119638121977851e-05, | |
| "grad_norm": 0.13636963069438934, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9578, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.119638121977851e-05, | |
| "eval_loss": 2.9149186611175537, | |
| "eval_runtime": 294.25, | |
| "eval_samples_per_second": 45.869, | |
| "eval_steps_per_second": 22.936, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.239276243955701e-05, | |
| "grad_norm": 0.16631676256656647, | |
| "learning_rate": 4e-05, | |
| "loss": 2.8283, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.358914365933551e-05, | |
| "grad_norm": 0.1473722755908966, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8448, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.358914365933551e-05, | |
| "eval_loss": 2.9144093990325928, | |
| "eval_runtime": 292.9549, | |
| "eval_samples_per_second": 46.072, | |
| "eval_steps_per_second": 23.038, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012478552487911403, | |
| "grad_norm": 0.14745832979679108, | |
| "learning_rate": 8e-05, | |
| "loss": 2.8856, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00015598190609889253, | |
| "grad_norm": 0.15959642827510834, | |
| "learning_rate": 0.0001, | |
| "loss": 2.8705, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00018717828731867103, | |
| "grad_norm": 0.18836471438407898, | |
| "learning_rate": 0.00012, | |
| "loss": 3.1284, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00018717828731867103, | |
| "eval_loss": 2.908966541290283, | |
| "eval_runtime": 292.7262, | |
| "eval_samples_per_second": 46.108, | |
| "eval_steps_per_second": 23.056, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00021837466853844953, | |
| "grad_norm": 0.16317172348499298, | |
| "learning_rate": 0.00014, | |
| "loss": 3.0666, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00024957104975822806, | |
| "grad_norm": 0.20634764432907104, | |
| "learning_rate": 0.00016, | |
| "loss": 2.9782, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00028076743097800656, | |
| "grad_norm": 0.17137481272220612, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6056, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00028076743097800656, | |
| "eval_loss": 2.884537696838379, | |
| "eval_runtime": 292.8468, | |
| "eval_samples_per_second": 46.089, | |
| "eval_steps_per_second": 23.046, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00031196381219778506, | |
| "grad_norm": 0.22768421471118927, | |
| "learning_rate": 0.0002, | |
| "loss": 2.8706, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 624708449992704.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |