| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03912363067292645, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000782472613458529, | |
| "eval_loss": 11.766357421875, | |
| "eval_runtime": 14.1981, | |
| "eval_samples_per_second": 37.963, | |
| "eval_steps_per_second": 19.017, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003912363067292645, | |
| "grad_norm": 0.05658465996384621, | |
| "learning_rate": 5e-05, | |
| "loss": 11.764, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00782472613458529, | |
| "grad_norm": 0.03729768842458725, | |
| "learning_rate": 0.0001, | |
| "loss": 11.7637, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00782472613458529, | |
| "eval_loss": 11.766192436218262, | |
| "eval_runtime": 13.477, | |
| "eval_samples_per_second": 39.994, | |
| "eval_steps_per_second": 20.034, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.011737089201877934, | |
| "grad_norm": 0.04390498623251915, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 11.7714, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.01564945226917058, | |
| "grad_norm": 0.04456234350800514, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 11.7622, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01564945226917058, | |
| "eval_loss": 11.765852928161621, | |
| "eval_runtime": 12.723, | |
| "eval_samples_per_second": 42.364, | |
| "eval_steps_per_second": 21.221, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.019561815336463225, | |
| "grad_norm": 0.057392362505197525, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 11.7654, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.023474178403755867, | |
| "grad_norm": 0.05766809731721878, | |
| "learning_rate": 5e-05, | |
| "loss": 11.7613, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023474178403755867, | |
| "eval_loss": 11.76557445526123, | |
| "eval_runtime": 9.2599, | |
| "eval_samples_per_second": 58.208, | |
| "eval_steps_per_second": 29.158, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.027386541471048513, | |
| "grad_norm": 0.04820512235164642, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 11.758, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.03129890453834116, | |
| "grad_norm": 0.051342207938432693, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 11.7617, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03129890453834116, | |
| "eval_loss": 11.765429496765137, | |
| "eval_runtime": 10.0452, | |
| "eval_samples_per_second": 53.658, | |
| "eval_steps_per_second": 26.879, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.035211267605633804, | |
| "grad_norm": 0.06057089567184448, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 11.7664, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03912363067292645, | |
| "grad_norm": 0.042387183755636215, | |
| "learning_rate": 0.0, | |
| "loss": 11.7621, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03912363067292645, | |
| "eval_loss": 11.765402793884277, | |
| "eval_runtime": 9.7518, | |
| "eval_samples_per_second": 55.272, | |
| "eval_steps_per_second": 27.687, | |
| "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": 2539015372800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |