| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.12445550715619166, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002489110143123833, | |
| "eval_loss": 0.8763667345046997, | |
| "eval_runtime": 46.8857, | |
| "eval_samples_per_second": 3.626, | |
| "eval_steps_per_second": 1.813, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.012445550715619166, | |
| "grad_norm": 1.0315775871276855, | |
| "learning_rate": 5e-05, | |
| "loss": 3.4604, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.024891101431238332, | |
| "grad_norm": 1.3416284322738647, | |
| "learning_rate": 0.0001, | |
| "loss": 3.4396, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.024891101431238332, | |
| "eval_loss": 0.8357529640197754, | |
| "eval_runtime": 49.2871, | |
| "eval_samples_per_second": 3.449, | |
| "eval_steps_per_second": 1.725, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.037336652146857496, | |
| "grad_norm": 1.2301503419876099, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.2513, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.049782202862476664, | |
| "grad_norm": 1.227513313293457, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.2492, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.049782202862476664, | |
| "eval_loss": 0.7855488657951355, | |
| "eval_runtime": 49.8653, | |
| "eval_samples_per_second": 3.409, | |
| "eval_steps_per_second": 1.705, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.06222775357809583, | |
| "grad_norm": 1.1817725896835327, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.0351, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.07467330429371499, | |
| "grad_norm": 1.4378055334091187, | |
| "learning_rate": 5e-05, | |
| "loss": 2.9669, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07467330429371499, | |
| "eval_loss": 0.7551403045654297, | |
| "eval_runtime": 49.9813, | |
| "eval_samples_per_second": 3.401, | |
| "eval_steps_per_second": 1.701, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.08711885500933417, | |
| "grad_norm": 1.4035176038742065, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.7865, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.09956440572495333, | |
| "grad_norm": 1.5695966482162476, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.0397, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09956440572495333, | |
| "eval_loss": 0.7450600862503052, | |
| "eval_runtime": 49.9519, | |
| "eval_samples_per_second": 3.403, | |
| "eval_steps_per_second": 1.702, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11200995644057249, | |
| "grad_norm": 1.4493436813354492, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.1448, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.12445550715619166, | |
| "grad_norm": 1.4496955871582031, | |
| "learning_rate": 0.0, | |
| "loss": 3.0665, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.12445550715619166, | |
| "eval_loss": 0.7428323030471802, | |
| "eval_runtime": 50.1265, | |
| "eval_samples_per_second": 3.391, | |
| "eval_steps_per_second": 1.696, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.8528053583872e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |